diff --git a/dist/face-api.esm-nobundle.js b/dist/face-api.esm-nobundle.js index c910e2d..49799a2 100644 --- a/dist/face-api.esm-nobundle.js +++ b/dist/face-api.esm-nobundle.js @@ -5,5 +5,5 @@ author: ' */ -var dn=Object.create,Ge=Object.defineProperty,un=Object.getPrototypeOf,fn=Object.prototype.hasOwnProperty,ln=Object.getOwnPropertyNames,hn=Object.getOwnPropertyDescriptor;var lo=o=>Ge(o,"__esModule",{value:!0});var ho=(o,t)=>()=>(t||(t={exports:{}},o(t.exports,t)),t.exports),Er=(o,t)=>{lo(o);for(var e in t)Ge(o,e,{get:t[e],enumerable:!0})},Bt=(o,t,e)=>{if(lo(o),t&&typeof t=="object"||typeof t=="function")for(let r of ln(t))!fn.call(o,r)&&r!=="default"&&Ge(o,r,{get:()=>t[r],enumerable:!(e=hn(t,r))||e.enumerable});return o},b=o=>o&&o.__esModule?o:Bt(Ge(o!=null?dn(un(o)):{},"default",{value:o,enumerable:!0}),o);import*as Ma from"@tensorflow/tfjs/dist/index.js";import*as Ca from"@tensorflow/tfjs-backend-wasm";var g=ho(xn=>{Bt(xn,Ma);Bt(xn,Ca)});var yo=ho((Pn,vo)=>{Er(Pn,{isNodejs:()=>_n});function _n(){return typeof global=="object"&&!0&&typeof vo!="undefined"&&typeof process!="undefined"&&!!process.version}});var va=b(g());var Qr={};Er(Qr,{AnchorPosition:()=>dt,DrawBox:()=>Xe,DrawBoxOptions:()=>Hr,DrawFaceLandmarks:()=>Kr,DrawFaceLandmarksOptions:()=>Zr,DrawTextField:()=>Mt,DrawTextFieldOptions:()=>Ne,drawContour:()=>lt,drawDetections:()=>En,drawFaceExpressions:()=>In,drawFaceLandmarks:()=>Ln});function lt(o,t,e=!1){if(o.beginPath(),t.slice(1).forEach(({x:r,y:n},a)=>{let s=t[a];o.moveTo(s.x,s.y),o.lineTo(r,n)}),e){let r=t[t.length-1],n=t[0];if(!r||!n)return;o.moveTo(r.x,r.y),o.lineTo(n.x,n.y)}o.stroke()}var Mr={};Er(Mr,{computeReshapedDimensions:()=>Ir,getCenterPoint:()=>Ot,isDimensions:()=>Ve,isEven:()=>ze,isFloat:()=>Nr,isTensor:()=>Rt,isTensor1D:()=>bn,isTensor2D:()=>Cr,isTensor3D:()=>ht,isTensor4D:()=>z,isValidNumber:()=>rt,isValidProbablitiy:()=>ee,range:()=>ct,round:()=>$t});var xo=b(g());var A=class{constructor(t,e){if(!rt(t)||!rt(e))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:e})}`);this._width=t,this._height=e}get width(){return this._width}get height(){return this._height}reverse(){return new A(1/this.width,1/this.height)}};function Rt(o,t){return o instanceof xo.Tensor&&o.shape.length===t}function bn(o){return Rt(o,1)}function Cr(o){return Rt(o,2)}function ht(o){return Rt(o,3)}function z(o){return Rt(o,4)}function Nr(o){return o%1!=0}function ze(o){return o%2==0}function $t(o,t=2){let e=10**t;return Math.floor(o*e)/e}function Ve(o){return o&&o.width&&o.height}function Ir({width:o,height:t},e){let r=e/Math.max(t,o);return new A(Math.round(o*r),Math.round(t*r))}function Ot(o){return o.reduce((t,e)=>t.add(e),new x(0,0)).div(new x(o.length,o.length))}function ct(o,t,e){return Array(o).fill(0).map((r,n)=>t+n*e)}function rt(o){return!!o&&o!==Infinity&&o!==-Infinity&&!Number.isNaN(o)||o===0}function ee(o){return rt(o)&&o>=0&&o<=1}var x=class{constructor(t,e){this._x=t,this._y=e}get x(){return this._x}get y(){return this._y}add(t){return new x(this.x+t.x,this.y+t.y)}sub(t){return new x(this.x-t.x,this.y-t.y)}mul(t){return new x(this.x*t.x,this.y*t.y)}div(t){return new x(this.x/t.x,this.y/t.y)}abs(){return new x(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new x(Math.floor(this.x),Math.floor(this.y))}};var D=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(rt)}static assertIsValidBox(t,e,r=!1){if(!D.isRect(t))throw new Error(`${e} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!r&&(t.width<0||t.height<0))throw new Error(`${e} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,e=!0){let r=t||{},n=[r.left,r.top,r.right,r.bottom].every(rt),a=[r.x,r.y,r.width,r.height].every(rt);if(!a&&!n)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(r)}`);let[s,i,c,m]=a?[r.x,r.y,r.width,r.height]:[r.left,r.top,r.right-r.left,r.bottom-r.top];D.assertIsValidBox({x:s,y:i,width:c,height:m},"Box.constructor",e),this._x=s,this._y=i,this._width=c,this._height=m}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new x(this.left,this.top)}get topRight(){return new x(this.right,this.top)}get bottomLeft(){return new x(this.left,this.bottom)}get bottomRight(){return new x(this.right,this.bottom)}round(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.round(a));return new D({x:t,y:e,width:r,height:n})}floor(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.floor(a));return new D({x:t,y:e,width:r,height:n})}toSquare(){let{x:t,y:e,width:r,height:n}=this,a=Math.abs(r-n);return re&&(i=-d+e+r,d=e),u>t&&(c=-u+t+n,u=t),m<1&&(c=2-m,m=1),p<1&&(c=2-p,p=1),{dy:s,edy:c,dx:a,edx:i,y:p,ey:u,x:m,ex:d,w:r,h:n}}calibrate(t){return new D({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var re=class extends D{constructor(t,e,r,n,a=!1){super({left:t,top:e,right:r,bottom:n},a)}};var Dt=class{constructor(t,e,r,n,a){this._imageDims=new A(a.width,a.height),this._score=t,this._classScore=e,this._className=r,this._box=new D(n).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new D(this._box).rescale(this.imageDims.reverse())}forSize(t,e){return new Dt(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:e})}};var M=class extends Dt{constructor(t,e,r){super(t,t,"",e,r)}forSize(t,e){let{score:r,relativeBox:n,imageDims:a}=super.forSize(t,e);return new M(r,n,a)}};function Lr(o,t,e=!0){let r=Math.max(0,Math.min(o.right,t.right)-Math.max(o.left,t.left)),n=Math.max(0,Math.min(o.bottom,t.bottom)-Math.max(o.top,t.top)),a=r*n;return e?a/(o.area+t.area-a):a/Math.min(o.area,t.area)}function kr(o){let t=o.map(i=>i.x),e=o.map(i=>i.y),r=t.reduce((i,c)=>ccii({score:s,boxIndex:i})).sort((s,i)=>s.score-i.score).map(s=>s.boxIndex),a=[];for(;n.length>0;){let s=n.pop();a.push(s);let i=n,c=[];for(let m=0;mc[p]<=e)}return a}var mt=b(g());function ot(o,t){return mt.tidy(()=>{let[e,r,n]=t,a=mt.fill([...o.shape.slice(0,3),1],e,"float32"),s=mt.fill([...o.shape.slice(0,3),1],r,"float32"),i=mt.fill([...o.shape.slice(0,3),1],n,"float32"),c=mt.concat([a,s,i],3);return mt.sub(o,c)})}var Et=b(g());function Ar(o,t=!1){return Et.tidy(()=>{let[e,r]=o.shape.slice(1);if(e===r)return o;let n=Math.abs(e-r),a=Math.round(n*(t?.5:1)),s=e>r?2:1,i=u=>{let f=o.shape.slice();return f[s]=u,Et.fill(f,0,"float32")},c=i(a),m=n-c.shape[s],d=[t&&m?i(m):null,o,c].filter(u=>!!u).map(u=>Et.cast(u,"float32"));return Et.concat(d,s)})}function gn(o){let t=o.slice();for(let e=t.length-1;e>0;e--){let r=Math.floor(Math.random()*(e+1)),n=t[e];t[e]=t[r],t[r]=n}return t}function Ee(o){return 1/(1+Math.exp(-o))}function vn(o){return Math.log(o/(1-o))}var oe=class extends D{constructor(t,e,r,n,a=!1){super({x:t,y:e,width:r,height:n},a)}};var yn=.5,Fn=.43,Tn=.45,V=class{constructor(t,e,r=new x(0,0)){let{width:n,height:a}=e;this._imgDims=new A(n,a),this._shift=r,this._positions=t.map(s=>s.mul(new x(n,a)).add(r))}get shift(){return new x(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new x(this.imageWidth,this.imageHeight)))}forSize(t,e){return new this.constructor(this.relativePositions,{width:t,height:e})}shiftBy(t,e){return new this.constructor(this.relativePositions,this._imgDims,new x(t,e))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,e={}){if(t){let a=t instanceof M?t.box.floor():new D(t);return this.shiftBy(a.x,a.y).align(null,e)}let{useDlibAlignment:r,minBoxPadding:n}={useDlibAlignment:!1,minBoxPadding:.2,...e};return r?this.alignDlib():this.alignMinBbox(n)}alignDlib(){let t=this.getRefPointsForAlignment(),[e,r,n]=t,a=d=>n.sub(d).magnitude(),s=(a(e)+a(r))/2,i=Math.floor(s/Tn),c=Ot(t),m=Math.floor(Math.max(0,c.x-yn*i)),p=Math.floor(Math.max(0,c.y-Fn*i));return new oe(m,p,Math.min(i,this.imageWidth+m),Math.min(i,this.imageHeight+p))}alignMinBbox(t){let e=kr(this.positions);return e.pad(e.width*t,e.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var bo=class extends V{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Ot([t[3],t[4]])]}};var ne=class extends V{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Ot)}};var Me=class{constructor(t,e){this._label=t,this._distance=e}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${$t(this.distance)})`:""}`}};var Ce=class extends D{static assertIsValidLabeledBox(t,e){if(D.assertIsValidBox(t,e),!rt(t.label))throw new Error(`${e} - expected property label (${t.label}) to be a number`)}constructor(t,e){super(t);this._label=e}get label(){return this._label}};var xt=class{constructor(t,e){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(e)||e.some(r=>!(r instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=e}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let e=t.descriptors.map(r=>new Float32Array(r));return new xt(t.label,e)}};var go=class extends Ce{static assertIsValidPredictedBox(t,e){if(Ce.assertIsValidLabeledBox(t,e),!ee(t.score)||!ee(t.classScore))throw new Error(`${e} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,e,r,n){super(t,e);this._score=r,this._classScore=n}get score(){return this._score}get classScore(){return this._classScore}};function pt(o){return o.detection instanceof M}function jt(o,t){return{...o,...{detection:t}}}function Wr(){let o=window.fetch;if(!o)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:o,readFile:t}}function Ue(o){let t="";if(!o)try{o=require("fs")}catch(r){t=r.toString()}return{readFile:o?r=>new Promise((n,a)=>{o.readFile(r,(s,i)=>s?a(s):n(i))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function Br(){let o=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,e=()=>{if(o)return new o;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},r=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},n=global.fetch,a=Ue();return{Canvas:o||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:e,createImageElement:r,fetch:n,...a}}function Rr(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var $r=b(yo()),k;function wn(){if(!k)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return k}function Or(o){k=o}function jr(){return Rr()?Or(Wr()):$r.isNodejs()?Or(Br()):null}function Dn(o){if(k||jr(),!k)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=k.Canvas,Image:e=k.Image}=o;k.Canvas=t,k.Image=e,k.createCanvasElement=o.createCanvasElement||(()=>new t),k.createImageElement=o.createImageElement||(()=>new e),k.ImageData=o.ImageData||k.ImageData,k.Video=o.Video||k.Video,k.fetch=o.fetch||k.fetch,k.readFile=o.readFile||k.readFile}var w={getEnv:wn,setEnv:Or,initialize:jr,createBrowserEnv:Wr,createFileSystem:Ue,createNodejsEnv:Br,monkeyPatch:Dn,isBrowser:Rr,isNodejs:$r.isNodejs};jr();function Ht(o){return!w.isNodejs()&&typeof o=="string"?document.getElementById(o):o}function $(o){let{Canvas:t,CanvasRenderingContext2D:e}=w.getEnv();if(o instanceof e)return o;let r=Ht(o);if(!(r instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let n=r.getContext("2d");if(!n)throw new Error("resolveContext2d - canvas 2d context is null");return n}var dt;(function(o){o.TOP_LEFT="TOP_LEFT",o.TOP_RIGHT="TOP_RIGHT",o.BOTTOM_LEFT="BOTTOM_LEFT",o.BOTTOM_RIGHT="BOTTOM_RIGHT"})(dt||(dt={}));var Ne=class{constructor(t={}){let{anchorPosition:e,backgroundColor:r,fontColor:n,fontSize:a,fontStyle:s,padding:i}=t;this.anchorPosition=e||dt.TOP_LEFT,this.backgroundColor=r||"rgba(0, 0, 0, 0.5)",this.fontColor=n||"rgba(255, 255, 255, 1)",this.fontSize=a||14,this.fontStyle=s||"Georgia",this.padding=i||4}},Mt=class{constructor(t,e,r={}){this.text=typeof t=="string"?[t]:t instanceof Mt?t.text:t,this.anchor=e,this.options=new Ne(r)}measureWidth(t){let{padding:e}=this.options;return this.text.map(r=>t.measureText(r).width).reduce((r,n)=>r{let v=c+d.x,_=c+d.y+(f+1)*s;r.fillText(u,v,_)})}};var Hr=class{constructor(t={}){let{boxColor:e,lineWidth:r,label:n,drawLabelOptions:a}=t;this.boxColor=e||"rgba(0, 0, 255, 1)",this.lineWidth=r||2,this.label=n;let s={anchorPosition:dt.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Ne({...s,...a})}},Xe=class{constructor(t,e={}){this.box=new D(t),this.options=new Hr(e)}draw(t){let e=$(t),{boxColor:r,lineWidth:n}=this.options,{x:a,y:s,width:i,height:c}=this.box;e.strokeStyle=r,e.lineWidth=n,e.strokeRect(a,s,i,c);let{label:m}=this.options;m&&new Mt([m],{x:a-n/2,y:s},this.options.drawLabelOptions).draw(t)}};function En(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof M?r.score:pt(r)?r.detection.score:void 0,a=r instanceof M?r.box:pt(r)?r.detection.box:new D(r),s=n?`${$t(n)}`:void 0;new Xe(a,{label:s}).draw(o)})}var fe=b(g());function Ie(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t&&o.complete||o instanceof e&&o.readyState>=3}function Yr(o){return new Promise((t,e)=>{if(o instanceof w.getEnv().Canvas||Ie(o))return t(null);function r(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),e(a))}function n(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),t(a))}o.addEventListener("load",n),o.addEventListener("error",r)})}function Gr(o){return new Promise((t,e)=>{o instanceof Blob||e(new Error("bufferToImage - expected buf to be of type: Blob"));let r=new FileReader;r.onload=()=>{typeof r.result!="string"&&e(new Error("bufferToImage - expected reader.result to be a string, in onload"));let n=w.getEnv().createImageElement();n.onload=()=>t(n),n.onerror=e,n.src=r.result},r.onerror=e,r.readAsDataURL(o)})}function Yt(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t?new A(o.naturalWidth,o.naturalHeight):o instanceof e?new A(o.videoWidth,o.videoHeight):new A(o.width,o.height)}function ae({width:o,height:t}){let{createCanvasElement:e}=w.getEnv(),r=e();return r.width=o,r.height=t,r}function Le(o,t){let{ImageData:e}=w.getEnv();if(!(o instanceof e)&&!Ie(o))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:r,height:n}=t||Yt(o),a=ae({width:r,height:n});return o instanceof e?$(a).putImageData(o,0,0):$(a).drawImage(o,0,0,r,n),a}var Je=b(g());async function zr(o,t){let e=t||w.getEnv().createCanvasElement(),[r,n,a]=o.shape.slice(z(o)?1:0),s=Je.tidy(()=>o.as3D(r,n,a).toInt());return await Je.browser.toPixels(s,e),s.dispose(),e}function qe(o){let{Image:t,Canvas:e,Video:r}=w.getEnv();return o instanceof t||o instanceof e||o instanceof r}var J=b(g());function Vr(o,t,e=!1){let{Image:r,Canvas:n}=w.getEnv();if(!(o instanceof r||o instanceof n))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let a=Yt(o),s=t/Math.max(a.height,a.width),i=s*a.width,c=s*a.height,m=ae({width:t,height:t}),p=o instanceof n?o:Le(o),d=Math.abs(i-c)/2,u=e&&i{if(ht(r)){this._imageTensors[n]=r,this._inputDimensions[n]=r.shape;return}if(z(r)){let s=r.shape[0];if(s!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${s} passed, but not supported in input array`);this._imageTensors[n]=r,this._inputDimensions[n]=r.shape.slice(1);return}let a=r instanceof w.getEnv().Canvas?r:Le(r);this._canvases[n]=a,this._inputDimensions[n]=[a.height,a.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ct(this.batchSize,0,1).map((t,e)=>this.getReshapedInputDimensions(e))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let e=this.getInputWidth(t),r=this.getInputHeight(t);return Ir({width:e,height:r},this.inputSize)}toBatchTensor(t,e=!0){return this._inputSize=t,J.tidy(()=>{let r=ct(this.batchSize,0,1).map(a=>{let s=this.getInput(a);if(s instanceof J.Tensor){let i=z(s)?s:s.expandDims();return i=Ar(i,e),(i.shape[1]!==t||i.shape[2]!==t)&&(i=J.image.resizeBilinear(i,[t,t])),i.as3D(t,t,3)}if(s instanceof w.getEnv().Canvas)return J.browser.fromPixels(Vr(s,t,e));throw new Error(`toBatchTensor - at batchIdx ${a}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${s}`)});return J.stack(r.map(a=>J.cast(a,"float32"))).as4D(this.batchSize,t,t,3)})}};async function E(o){if(o instanceof bt)return o;let t=Array.isArray(o)?o:[o];if(!t.length)throw new Error("toNetInput - empty array passed as input");let e=n=>Array.isArray(o)?` at input index ${n}:`:"",r=t.map(Ht);return r.forEach((n,a)=>{if(!qe(n)&&!ht(n)&&!z(n))throw typeof t[a]=="string"?new Error(`toNetInput -${e(a)} string passed, but could not resolve HTMLElement for element id ${t[a]}`):new Error(`toNetInput -${e(a)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(z(n)){let s=n.shape[0];if(s!==1)throw new Error(`toNetInput -${e(a)} tf.Tensor4D with batchSize ${s} passed, but not supported in input array`)}}),await Promise.all(r.map(n=>qe(n)&&Yr(n))),new bt(r,Array.isArray(o))}async function se(o,t){let{Canvas:e}=w.getEnv(),r=o;if(!(o instanceof e)){let s=await E(o);if(s.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let i=s.getInput(0);r=i instanceof e?i:await zr(i)}let n=$(r);return t.map(s=>s instanceof M?s.forSize(r.width,r.height).box.floor():s).map(s=>s.clipAtImageBorders(r.width,r.height)).map(({x:s,y:i,width:c,height:m})=>{let p=ae({width:c,height:m});return $(p).putImageData(n.getImageData(s,i,c,m),0,0),p})}var Ze=b(g());async function ie(o,t){if(!ht(o)&&!z(o))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(z(o)&&o.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return Ze.tidy(()=>{let[e,r,n]=o.shape.slice(z(o)?1:0);return t.map(i=>i instanceof M?i.forSize(r,e).box:i).map(i=>i.clipAtImageBorders(r,e)).map(({x:i,y:c,width:m,height:p})=>Ze.slice3d(o.as3D(e,r,n),[c,i,0],[p,m,n]))})}async function Gt(o,t){let{fetch:e}=w.getEnv(),r=await e(o,t);if(!(r.status<400))throw new Error(`failed to fetch: (${r.status}) ${r.statusText}, from url: ${r.url}`);return r}async function Mn(o){let t=await Gt(o),e=await t.blob();if(!e.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${e.type}, for url: ${t.url}`);return Gr(e)}async function Ur(o){return(await Gt(o)).json()}async function Cn(o){return new Float32Array(await(await Gt(o)).arrayBuffer())}var Fo=b(g());function Ke(o,t){let e=`${t}-weights_manifest.json`;if(!o)return{modelBaseUri:"",manifestUri:e};if(o==="/")return{modelBaseUri:"/",manifestUri:`/${e}`};let r=o.startsWith("http://")?"http://":o.startsWith("https://")?"https://":"";o=o.replace(r,"");let n=o.split("/").filter(i=>i),a=o.endsWith(".json")?n[n.length-1]:e,s=r+(o.endsWith(".json")?n.slice(0,n.length-1):n).join("/");return s=o.startsWith("/")?`/${s}`:s,{modelBaseUri:s,manifestUri:s==="/"?`/${a}`:`${s}/${a}`}}async function Xr(o,t){let{manifestUri:e,modelBaseUri:r}=Ke(o,t),n=await Ur(e);return Fo.io.loadWeights(n,r)}function Nn(o,t,e=!1){let{width:r,height:n}=e?Yt(t):t;return o.width=r,o.height=n,{width:r,height:n}}var Nt=b(g());var gt=b(g());var S=class{constructor(){this._params=void 0;this._paramMappings=[]}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:e,objProp:r}=this.traversePropertyPath(t);return e[r]}reassignParamFromPath(t,e){let{obj:r,objProp:n}=this.traversePropertyPath(t);r[n].dispose(),r[n]=e}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof gt.Variable)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof gt.Variable))}variable(){this.getFrozenParams().forEach(({path:t,tensor:e})=>{this.reassignParamFromPath(t,e.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:e})=>{let r=gt.tensor(e.dataSync());e.dispose(),this.reassignParamFromPath(t,r)})}dispose(t=!0){this.getParamList().forEach(e=>{if(t&&e.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${e.path}`);e.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,e)=>t.concat(e)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let e=await Xr(t,this.getDefaultModelName());this.loadFromWeightMap(e)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:e}=w.getEnv(),{manifestUri:r,modelBaseUri:n}=Ke(t,this.getDefaultModelName()),a=m=>Promise.all(m.map(p=>e(p).then(d=>d.buffer))),s=gt.io.weightsLoaderFactory(a),i=JSON.parse((await e(r)).toString()),c=await s(i,n);this.loadFromWeightMap(c)}loadFromWeightMap(t){let{paramMappings:e,params:r}=this.extractParamsFromWeightMap(t);this._paramMappings=e,this._params=r}extractWeights(t){let{paramMappings:e,params:r}=this.extractParams(t);this._paramMappings=e,this._params=r}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let e=t.split("/").reduce((a,s)=>{if(!a.nextObj.hasOwnProperty(s))throw new Error(`traversePropertyPath - object does not have property ${s}, for path ${t}`);return{obj:a.nextObj,objProp:s,nextObj:a.nextObj[s]}},{nextObj:this.params}),{obj:r,objProp:n}=e;if(!r||!n||!(r[n]instanceof gt.Tensor))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:r,objProp:n}}};var C=b(g());var ce=b(g());function O(o,t,e){return ce.tidy(()=>{let r=ce.separableConv2d(o,t.depthwise_filter,t.pointwise_filter,e,"same");return r=ce.add(r,t.bias),r})}function Qe(o,t,e=!1){return C.tidy(()=>{let r=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,[2,2],"same"),t.conv0.bias):O(o,t.conv0,[2,2])),n=O(r,t.conv1,[1,1]),a=C.relu(C.add(r,n)),s=O(a,t.conv2,[1,1]);return C.relu(C.add(r,C.add(n,s)))})}function ke(o,t,e=!1,r=!0){return C.tidy(()=>{let n=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,r?[2,2]:[1,1],"same"),t.conv0.bias):O(o,t.conv0,r?[2,2]:[1,1])),a=O(n,t.conv1,[1,1]),s=C.relu(C.add(n,a)),i=O(s,t.conv2,[1,1]),c=C.relu(C.add(n,C.add(a,i))),m=O(c,t.conv3,[1,1]);return C.relu(C.add(n,C.add(a,C.add(i,m))))})}var Ct=b(g());function zt(o,t,e="same",r=!1){return Ct.tidy(()=>{let n=Ct.add(Ct.conv2d(o,t.filters,[1,1],e),t.bias);return r?Ct.relu(n):n})}function W(o,t){Object.keys(o).forEach(e=>{t.some(r=>r.originalPath===e)||o[e].dispose()})}var tr=b(g());function me(o,t){return(e,r,n,a)=>{let s=tr.tensor4d(o(e*r*n*n),[n,n,e,r]),i=tr.tensor1d(o(r));return t.push({paramPath:`${a}/filters`},{paramPath:`${a}/bias`}),{filters:s,bias:i}}}var er=b(g());function rr(o,t){return(e,r,n)=>{let a=er.tensor2d(o(e*r),[e,r]),s=er.tensor1d(o(r));return t.push({paramPath:`${n}/weights`},{paramPath:`${n}/bias`}),{weights:a,bias:s}}}var Se=b(g());var or=class{constructor(t,e,r){this.depthwise_filter=t;this.pointwise_filter=e;this.bias=r}};function pe(o,t){return(e,r,n)=>{let a=Se.tensor4d(o(3*3*e),[3,3,e,1]),s=Se.tensor4d(o(e*r),[1,1,e,r]),i=Se.tensor1d(o(r));return t.push({paramPath:`${n}/depthwise_filter`},{paramPath:`${n}/pointwise_filter`},{paramPath:`${n}/bias`}),new or(a,s,i)}}function de(o){return t=>{let e=o(`${t}/depthwise_filter`,4),r=o(`${t}/pointwise_filter`,4),n=o(`${t}/bias`,1);return new or(e,r,n)}}function j(o,t){return(e,r,n)=>{let a=o[e];if(!Rt(a,r))throw new Error(`expected weightMap[${e}] to be a Tensor${r}D, instead have ${a}`);return t.push({originalPath:e,paramPath:n||e}),a}}function B(o){let t=o;function e(n){let a=t.slice(0,n);return t=t.slice(n),a}function r(){return t}return{extractWeights:e,getRemainingWeights:r}}function nr(o,t){let e=me(o,t),r=pe(o,t);function n(s,i,c,m=!1){let p=m?e(s,i,3,`${c}/conv0`):r(s,i,`${c}/conv0`),d=r(i,i,`${c}/conv1`),u=r(i,i,`${c}/conv2`);return{conv0:p,conv1:d,conv2:u}}function a(s,i,c,m=!1){let{conv0:p,conv1:d,conv2:u}=n(s,i,c,m),f=r(i,i,`${c}/conv3`);return{conv0:p,conv1:d,conv2:u,conv3:f}}return{extractDenseBlock3Params:n,extractDenseBlock4Params:a}}function To(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock4Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2"),c=n(128,256,"dense3");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i,dense3:c}}}function ar(o){return t=>{let e=o(`${t}/filters`,4),r=o(`${t}/bias`,1);return{filters:e,bias:r}}}function sr(o,t){let e=j(o,t),r=ar(e),n=de(e);function a(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`);return{conv0:m,conv1:p,conv2:d}}function s(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`),u=n(`${i}/conv3`);return{conv0:m,conv1:p,conv2:d,conv3:u}}return{extractDenseBlock3Params:a,extractDenseBlock4Params:s}}function Po(o){let t=[],{extractDenseBlock4Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2"),dense3:e("dense3")};return W(o,t),{params:r,paramMappings:t}}var Ae=class extends S{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceFeatureExtractor - load model before inference");return Nt.tidy(()=>{let r=Nt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Nt.scalar(255)),s=ke(a,e.dense0,!0);return s=ke(s,e.dense1),s=ke(s,e.dense2),s=ke(s,e.dense3),s=Nt.avgPool(s,[7,7],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return Po(t)}extractParams(t){return To(t)}};var Do=b(g());var ue=b(g());function We(o,t){return ue.tidy(()=>ue.add(ue.matMul(o,t.weights),t.bias))}function _o(o,t,e){let r=[],{extractWeights:n,getRemainingWeights:a}=B(o),i=rr(n,r)(t,e,"fc");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:r,params:{fc:i}}}function wo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:r("fc")};return W(o,t),{params:n,paramMappings:t}}function ir(o){let t={},e={};return Object.keys(o).forEach(r=>{let n=r.startsWith("fc")?e:t;n[r]=o[r]}),{featureExtractorMap:t,classifierMap:e}}var Be=class extends S{constructor(t,e){super(t);this._faceFeatureExtractor=e}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return Do.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t;return We(r.as2D(r.shape[0],-1),e.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return _o(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),wo(r)}extractParams(t){let e=this.getClassifierChannelsIn(),r=this.getClassifierChannelsOut(),n=r*e+r,a=t.slice(0,t.length-n),s=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(s)}};var Jr=["neutral","happy","sad","angry","fearful","disgusted","surprised"],It=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Jr.forEach((e,r)=>{this[e]=t[r]})}asSortedArray(){return Jr.map(t=>({expression:t,probability:this[t]})).sort((t,e)=>e.probability-t.probability)}};var cr=class extends Be{constructor(t=new Ae){super("FaceExpressionNet",t)}forwardInput(t){return fe.tidy(()=>fe.softmax(this.runNet(t)))}async forward(t){return this.forwardInput(await E(t))}async predictExpressions(t){let e=await E(t),r=await this.forwardInput(e),n=await Promise.all(fe.unstack(r).map(async s=>{let i=await s.data();return s.dispose(),i}));r.dispose();let a=n.map(s=>new It(s));return e.isBatchInput?a:a[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function qr(o){return o.expressions instanceof It}function mr(o,t){return{...o,...{expressions:t}}}function In(o,t,e=.1,r){(Array.isArray(t)?t:[t]).forEach(a=>{let s=a instanceof It?a:qr(a)?a.expressions:void 0;if(!s)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let c=s.asSortedArray().filter(d=>d.probability>e),m=pt(a)?a.detection.box.bottomLeft:r||new x(0,0);new Mt(c.map(d=>`${d.expression} (${$t(d.probability)})`),m).draw(o)})}function Vt(o){return pt(o)&&o.landmarks instanceof V&&o.unshiftedLandmarks instanceof V&&o.alignedRect instanceof M}function le(o,t){let{box:e}=o.detection,r=t.shiftBy(e.x,e.y),n=r.align(),{imageDims:a}=o.detection,s=new M(o.detection.score,n.rescale(a.reverse()),a);return{...o,...{landmarks:r,unshiftedLandmarks:t,alignedRect:s}}}var Zr=class{constructor(t={}){let{drawLines:e=!0,drawPoints:r=!0,lineWidth:n,lineColor:a,pointSize:s,pointColor:i}=t;this.drawLines=e,this.drawPoints=r,this.lineWidth=n||1,this.pointSize=s||2,this.lineColor=a||"rgba(0, 255, 255, 1)",this.pointColor=i||"rgba(255, 0, 255, 1)"}},Kr=class{constructor(t,e={}){this.faceLandmarks=t,this.options=new Zr(e)}draw(t){let e=$(t),{drawLines:r,drawPoints:n,lineWidth:a,lineColor:s,pointSize:i,pointColor:c}=this.options;if(r&&this.faceLandmarks instanceof ne&&(e.strokeStyle=s,e.lineWidth=a,lt(e,this.faceLandmarks.getJawOutline()),lt(e,this.faceLandmarks.getLeftEyeBrow()),lt(e,this.faceLandmarks.getRightEyeBrow()),lt(e,this.faceLandmarks.getNose()),lt(e,this.faceLandmarks.getLeftEye(),!0),lt(e,this.faceLandmarks.getRightEye(),!0),lt(e,this.faceLandmarks.getMouth(),!0)),n){e.strokeStyle=c,e.fillStyle=c;let m=p=>{e.beginPath(),e.arc(p.x,p.y,i,0,2*Math.PI),e.fill()};this.faceLandmarks.positions.forEach(m)}}};function Ln(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof V?r:Vt(r)?r.landmarks:void 0;if(!n)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new Kr(n).draw(o)})}var Eo="0.11.4";var ut=b(g());var I=b(g());function kn(o,t){let e=me(o,t),r=pe(o,t);function n(s,i,c){let m=r(s,i,`${c}/separable_conv0`),p=r(i,i,`${c}/separable_conv1`),d=e(s,i,1,`${c}/expansion_conv`);return{separable_conv0:m,separable_conv1:p,expansion_conv:d}}function a(s,i){let c=r(s,s,`${i}/separable_conv0`),m=r(s,s,`${i}/separable_conv1`),p=r(s,s,`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:e,extractSeparableConvParams:r,extractReductionBlockParams:n,extractMainBlockParams:a}}function Mo(o,t){let e=[],{extractWeights:r,getRemainingWeights:n}=B(o),{extractConvParams:a,extractSeparableConvParams:s,extractReductionBlockParams:i,extractMainBlockParams:c}=kn(r,e),m=a(3,32,3,"entry_flow/conv_in"),p=i(32,64,"entry_flow/reduction_block_0"),d=i(64,128,"entry_flow/reduction_block_1"),u={conv_in:m,reduction_block_0:p,reduction_block_1:d},f={};ct(t,0,1).forEach(y=>{f[`main_block_${y}`]=c(128,`middle_flow/main_block_${y}`)});let v=i(128,256,"exit_flow/reduction_block"),_=s(256,512,"exit_flow/separable_conv"),h={reduction_block:v,separable_conv:_};if(n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{paramMappings:e,params:{entry_flow:u,middle_flow:f,exit_flow:h}}}function Sn(o,t){let e=j(o,t),r=ar(e),n=de(e);function a(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=r(`${i}/expansion_conv`);return{separable_conv0:c,separable_conv1:m,expansion_conv:p}}function s(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=n(`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}}function Co(o,t){let e=[],{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}=Sn(o,e),i=r("entry_flow/conv_in"),c=a("entry_flow/reduction_block_0"),m=a("entry_flow/reduction_block_1"),p={conv_in:i,reduction_block_0:c,reduction_block_1:m},d={};ct(t,0,1).forEach(_=>{d[`main_block_${_}`]=s(`middle_flow/main_block_${_}`)});let u=a("exit_flow/reduction_block"),f=n("exit_flow/separable_conv"),v={reduction_block:u,separable_conv:f};return W(o,e),{params:{entry_flow:p,middle_flow:d,exit_flow:v},paramMappings:e}}function No(o,t,e){return I.add(I.conv2d(o,t.filters,e,"same"),t.bias)}function to(o,t,e=!0){let r=e?I.relu(o):o;return r=O(r,t.separable_conv0,[1,1]),r=O(I.relu(r),t.separable_conv1,[1,1]),r=I.maxPool(r,[3,3],[2,2],"same"),r=I.add(r,No(o,t.expansion_conv,[2,2])),r}function An(o,t){let e=O(I.relu(o),t.separable_conv0,[1,1]);return e=O(I.relu(e),t.separable_conv1,[1,1]),e=O(I.relu(e),t.separable_conv2,[1,1]),e=I.add(e,o),e}var eo=class extends S{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyXception - load model before inference");return I.tidy(()=>{let r=I.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(I.scalar(256)),s=I.relu(No(a,e.entry_flow.conv_in,[2,2]));return s=to(s,e.entry_flow.reduction_block_0,!1),s=to(s,e.entry_flow.reduction_block_1),ct(this._numMainBlocks,0,1).forEach(i=>{s=An(s,e.middle_flow[`main_block_${i}`])}),s=to(s,e.exit_flow.reduction_block),s=I.relu(O(s,e.exit_flow.separable_conv,[1,1])),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return Co(t,this._numMainBlocks)}extractParams(t){return Mo(t,this._numMainBlocks)}};function Io(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),n=rr(e,t),a=n(512,1,"fc/age"),s=n(512,2,"fc/gender");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{fc:{age:a,gender:s}}}}function Lo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:{age:r("fc/age"),gender:r("fc/gender")}};return W(o,t),{params:n,paramMappings:t}}var vt;(function(o){o.FEMALE="female",o.MALE="male"})(vt||(vt={}));var pr=class extends S{constructor(t=new eo(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return ut.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t,n=ut.avgPool(r,[7,7],[2,2],"valid").as2D(r.shape[0],-1),a=We(n,e.fc.age).as1D(),s=We(n,e.fc.gender);return{age:a,gender:s}})}forwardInput(t){return ut.tidy(()=>{let{age:e,gender:r}=this.runNet(t);return{age:e,gender:ut.softmax(r)}})}async forward(t){return this.forwardInput(await E(t))}async predictAgeAndGender(t){let e=await E(t),r=await this.forwardInput(e),n=ut.unstack(r.age),a=ut.unstack(r.gender),s=n.map((c,m)=>({ageTensor:c,genderTensor:a[m]})),i=await Promise.all(s.map(async({ageTensor:c,genderTensor:m})=>{let p=(await c.data())[0],d=(await m.data())[0],u=d>.5,f=u?vt.MALE:vt.FEMALE,v=u?d:1-d;return c.dispose(),m.dispose(),{age:p,gender:f,genderProbability:v}}));return r.age.dispose(),r.gender.dispose(),e.isBatchInput?i:i[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return Io(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),Lo(r)}extractParams(t){let e=512*1+1+(512*2+2),r=t.slice(0,t.length-e),n=t.slice(t.length-e);return this.faceFeatureExtractor.extractWeights(r),this.extractClassifierParams(n)}};var H=b(g());var Re=class extends Be{postProcess(t,e,r){let n=r.map(({width:s,height:i})=>{let c=e/Math.max(i,s);return{width:s*c,height:i*c}}),a=n.length;return H.tidy(()=>{let s=(d,u)=>H.stack([H.fill([68],d,"float32"),H.fill([68],u,"float32")],1).as2D(1,136).as1D(),i=(d,u)=>{let{width:f,height:v}=n[d];return u(f,v)?Math.abs(f-v)/2:0},c=d=>i(d,(u,f)=>ui(d,(u,f)=>fs(c(u),m(u))))).div(H.stack(Array.from(Array(a),(d,u)=>s(n[u].width,n[u].height))))})}forwardInput(t){return H.tidy(()=>{let e=this.runNet(t);return this.postProcess(e,t.inputSize,t.inputDimensions.map(([r,n])=>({height:r,width:n})))})}async forward(t){return this.forwardInput(await E(t))}async detectLandmarks(t){let e=await E(t),r=H.tidy(()=>H.unstack(this.forwardInput(e))),n=await Promise.all(r.map(async(a,s)=>{let i=Array.from(await a.data()),c=i.filter((p,d)=>ze(d)),m=i.filter((p,d)=>!ze(d));return new ne(Array(68).fill(0).map((p,d)=>new x(c[d],m[d])),{height:e.getInputHeight(s),width:e.getInputWidth(s)})}));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getClassifierChannelsOut(){return 136}};var he=class extends Re{constructor(t=new Ae){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};var Lt=b(g());function ko(o){let t=[],{extractDenseBlock3Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2")};return W(o,t),{params:r,paramMappings:t}}function So(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock3Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i}}}var ro=class extends S{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyFaceFeatureExtractor - load model before inference");return Lt.tidy(()=>{let r=Lt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Lt.scalar(255)),s=Qe(a,e.dense0,!0);return s=Qe(s,e.dense1),s=Qe(s,e.dense2),s=Lt.avgPool(s,[14,14],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return ko(t)}extractParams(t){return So(t)}};var dr=class extends Re{constructor(t=new ro){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Ao=class extends he{};var U=b(g());var xe=b(g());var ur=b(g());function Wo(o,t){return ur.add(ur.mul(o,t.weights),t.biases)}function oo(o,t,e,r,n="same"){let{filters:a,bias:s}=t.conv,i=xe.conv2d(o,a,e,n);return i=xe.add(i,s),i=Wo(i,t.scale),r?xe.relu(i):i}function Bo(o,t){return oo(o,t,[1,1],!0)}function no(o,t){return oo(o,t,[1,1],!1)}function fr(o,t){return oo(o,t,[2,2],!0,"valid")}var Y=b(g());function Wn(o,t){function e(i,c,m){let p=o(i),d=p.length/(c*m*m);if(Nr(d))throw new Error(`depth has to be an integer: ${d}, weights.length: ${p.length}, numFilters: ${c}, filterSize: ${m}`);return Y.tidy(()=>Y.transpose(Y.tensor4d(p,[c,d,m,m]),[2,3,1,0]))}function r(i,c,m,p){let d=e(i,c,m),u=Y.tensor1d(o(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/bias`}),{filters:d,bias:u}}function n(i,c){let m=Y.tensor1d(o(i)),p=Y.tensor1d(o(i));return t.push({paramPath:`${c}/weights`},{paramPath:`${c}/biases`}),{weights:m,biases:p}}function a(i,c,m,p){let d=r(i,c,m,`${p}/conv`),u=n(c,`${p}/scale`);return{conv:d,scale:u}}function s(i,c,m,p,d=!1){let u=a((d?.5:1)*i,c,m,`${p}/conv1`),f=a(i,c,m,`${p}/conv2`);return{conv1:u,conv2:f}}return{extractConvLayerParams:a,extractResidualLayerParams:s}}function Ro(o){let{extractWeights:t,getRemainingWeights:e}=B(o),r=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=Wn(t,r),s=n(4704,32,7,"conv32_down"),i=a(9216,32,3,"conv32_1"),c=a(9216,32,3,"conv32_2"),m=a(9216,32,3,"conv32_3"),p=a(36864,64,3,"conv64_down",!0),d=a(36864,64,3,"conv64_1"),u=a(36864,64,3,"conv64_2"),f=a(36864,64,3,"conv64_3"),v=a(147456,128,3,"conv128_down",!0),_=a(147456,128,3,"conv128_1"),h=a(147456,128,3,"conv128_2"),y=a(589824,256,3,"conv256_down",!0),T=a(589824,256,3,"conv256_1"),F=a(589824,256,3,"conv256_2"),L=a(589824,256,3,"conv256_down_out"),G=Y.tidy(()=>Y.transpose(Y.tensor2d(t(256*128),[128,256]),[1,0]));if(r.push({paramPath:"fc"}),e().length!==0)throw new Error(`weights remaing after extract: ${e().length}`);return{params:{conv32_down:s,conv32_1:i,conv32_2:c,conv32_3:m,conv64_down:p,conv64_1:d,conv64_2:u,conv64_3:f,conv128_down:v,conv128_1:_,conv128_2:h,conv256_down:y,conv256_1:T,conv256_2:F,conv256_down_out:L,fc:G},paramMappings:r}}function Bn(o,t){let e=j(o,t);function r(s){let i=e(`${s}/scale/weights`,1),c=e(`${s}/scale/biases`,1);return{weights:i,biases:c}}function n(s){let i=e(`${s}/conv/filters`,4),c=e(`${s}/conv/bias`,1),m=r(s);return{conv:{filters:i,bias:c},scale:m}}function a(s){return{conv1:n(`${s}/conv1`),conv2:n(`${s}/conv2`)}}return{extractConvLayerParams:n,extractResidualLayerParams:a}}function $o(o){let t=[],{extractConvLayerParams:e,extractResidualLayerParams:r}=Bn(o,t),n=e("conv32_down"),a=r("conv32_1"),s=r("conv32_2"),i=r("conv32_3"),c=r("conv64_down"),m=r("conv64_1"),p=r("conv64_2"),d=r("conv64_3"),u=r("conv128_down"),f=r("conv128_1"),v=r("conv128_2"),_=r("conv256_down"),h=r("conv256_1"),y=r("conv256_2"),T=r("conv256_down_out"),{fc:F}=o;if(t.push({originalPath:"fc",paramPath:"fc"}),!Cr(F))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${F}`);let L={conv32_down:n,conv32_1:a,conv32_2:s,conv32_3:i,conv64_down:c,conv64_1:m,conv64_2:p,conv64_3:d,conv128_down:u,conv128_1:f,conv128_2:v,conv256_down:_,conv256_1:h,conv256_2:y,conv256_down_out:T,fc:F};return W(o,t),{params:L,paramMappings:t}}var R=b(g());function nt(o,t){let e=Bo(o,t.conv1);return e=no(e,t.conv2),e=R.add(e,o),e=R.relu(e),e}function $e(o,t){let e=fr(o,t.conv1);e=no(e,t.conv2);let r=R.avgPool(o,2,2,"valid"),n=R.zeros(r.shape),a=r.shape[3]!==e.shape[3];if(r.shape[1]!==e.shape[1]||r.shape[2]!==e.shape[2]){let i=[...e.shape];i[1]=1;let c=R.zeros(i);e=R.concat([e,c],1);let m=[...e.shape];m[2]=1;let p=R.zeros(m);e=R.concat([e,p],2)}return r=a?R.concat([r,n],3):r,e=R.add(r,e),e=R.relu(e),e}var be=class extends S{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceRecognitionNet - load model before inference");return U.tidy(()=>{let r=U.cast(t.toBatchTensor(150,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(U.scalar(256)),s=fr(a,e.conv32_down);s=U.maxPool(s,3,2,"valid"),s=nt(s,e.conv32_1),s=nt(s,e.conv32_2),s=nt(s,e.conv32_3),s=$e(s,e.conv64_down),s=nt(s,e.conv64_1),s=nt(s,e.conv64_2),s=nt(s,e.conv64_3),s=$e(s,e.conv128_down),s=nt(s,e.conv128_1),s=nt(s,e.conv128_2),s=$e(s,e.conv256_down),s=nt(s,e.conv256_1),s=nt(s,e.conv256_2),s=$e(s,e.conv256_down_out);let i=s.mean([1,2]);return U.matMul(i,e.fc)})}async forward(t){return this.forwardInput(await E(t))}async computeFaceDescriptor(t){let e=await E(t),r=U.tidy(()=>U.unstack(this.forwardInput(e))),n=await Promise.all(r.map(a=>a.data()));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return $o(t)}extractParams(t){return Ro(t)}};function Rn(o){let t=new be;return t.extractWeights(o),t}function lr(o,t){return{...o,...{descriptor:t}}}function $n(o){return typeof o.age=="number"}function hr(o,t){return{...o,...{age:t}}}function On(o){return(o.gender===vt.MALE||o.gender===vt.FEMALE)&&ee(o.genderProbability)}function xr(o,t,e){return{...o,...{gender:t,genderProbability:e}}}var st=b(g());var at=b(g());function jn(o,t){function e(c,m){let p=at.tensor4d(o(3*3*c),[3,3,c,1]),d=at.tensor1d(o(c)),u=at.tensor1d(o(c)),f=at.tensor1d(o(c)),v=at.tensor1d(o(c));return t.push({paramPath:`${m}/filters`},{paramPath:`${m}/batch_norm_scale`},{paramPath:`${m}/batch_norm_offset`},{paramPath:`${m}/batch_norm_mean`},{paramPath:`${m}/batch_norm_variance`}),{filters:p,batch_norm_scale:d,batch_norm_offset:u,batch_norm_mean:f,batch_norm_variance:v}}function r(c,m,p,d,u){let f=at.tensor4d(o(c*m*p*p),[p,p,c,m]),v=at.tensor1d(o(m));return t.push({paramPath:`${d}/filters`},{paramPath:`${d}/${u?"batch_norm_offset":"bias"}`}),{filters:f,bias:v}}function n(c,m,p,d){let{filters:u,bias:f}=r(c,m,p,d,!0);return{filters:u,batch_norm_offset:f}}function a(c,m,p){let d=e(c,`${p}/depthwise_conv`),u=n(c,m,1,`${p}/pointwise_conv`);return{depthwise_conv:d,pointwise_conv:u}}function s(){let c=n(3,32,3,"mobilenetv1/conv_0"),m=a(32,64,"mobilenetv1/conv_1"),p=a(64,128,"mobilenetv1/conv_2"),d=a(128,128,"mobilenetv1/conv_3"),u=a(128,256,"mobilenetv1/conv_4"),f=a(256,256,"mobilenetv1/conv_5"),v=a(256,512,"mobilenetv1/conv_6"),_=a(512,512,"mobilenetv1/conv_7"),h=a(512,512,"mobilenetv1/conv_8"),y=a(512,512,"mobilenetv1/conv_9"),T=a(512,512,"mobilenetv1/conv_10"),F=a(512,512,"mobilenetv1/conv_11"),L=a(512,1024,"mobilenetv1/conv_12"),G=a(1024,1024,"mobilenetv1/conv_13");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:f,conv_6:v,conv_7:_,conv_8:h,conv_9:y,conv_10:T,conv_11:F,conv_12:L,conv_13:G}}function i(){let c=n(1024,256,1,"prediction_layer/conv_0"),m=n(256,512,3,"prediction_layer/conv_1"),p=n(512,128,1,"prediction_layer/conv_2"),d=n(128,256,3,"prediction_layer/conv_3"),u=n(256,128,1,"prediction_layer/conv_4"),f=n(128,256,3,"prediction_layer/conv_5"),v=n(256,64,1,"prediction_layer/conv_6"),_=n(64,128,3,"prediction_layer/conv_7"),h=r(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=r(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),T=r(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),F=r(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),L=r(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),G=r(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),et=r(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),it=r(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),X=r(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),Pt=r(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),_t=r(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),wt=r(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:f,conv_6:v,conv_7:_,box_predictor_0:{box_encoding_predictor:h,class_predictor:y},box_predictor_1:{box_encoding_predictor:T,class_predictor:F},box_predictor_2:{box_encoding_predictor:L,class_predictor:G},box_predictor_3:{box_encoding_predictor:et,class_predictor:it},box_predictor_4:{box_encoding_predictor:X,class_predictor:Pt},box_predictor_5:{box_encoding_predictor:_t,class_predictor:wt}}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:i}}function Oo(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=jn(e,t),s=n(),i=a(),m={extra_dim:at.tensor3d(e(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{params:{mobilenetv1:s,prediction_layer:i,output_layer:m},paramMappings:t}}function Hn(o,t){let e=j(o,t);function r(m,p,d){let u=e(`${m}/Conv2d_${p}_pointwise/weights`,4,`${d}/filters`),f=e(`${m}/Conv2d_${p}_pointwise/convolution_bn_offset`,1,`${d}/batch_norm_offset`);return{filters:u,batch_norm_offset:f}}function n(m){let p=`mobilenetv1/conv_${m}`,d=`MobilenetV1/Conv2d_${m}_depthwise`,u=`${p}/depthwise_conv`,f=`${p}/pointwise_conv`,v=e(`${d}/depthwise_weights`,4,`${u}/filters`),_=e(`${d}/BatchNorm/gamma`,1,`${u}/batch_norm_scale`),h=e(`${d}/BatchNorm/beta`,1,`${u}/batch_norm_offset`),y=e(`${d}/BatchNorm/moving_mean`,1,`${u}/batch_norm_mean`),T=e(`${d}/BatchNorm/moving_variance`,1,`${u}/batch_norm_variance`);return{depthwise_conv:{filters:v,batch_norm_scale:_,batch_norm_offset:h,batch_norm_mean:y,batch_norm_variance:T},pointwise_conv:r("MobilenetV1",m,f)}}function a(){return{conv_0:r("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:n(1),conv_2:n(2),conv_3:n(3),conv_4:n(4),conv_5:n(5),conv_6:n(6),conv_7:n(7),conv_8:n(8),conv_9:n(9),conv_10:n(10),conv_11:n(11),conv_12:n(12),conv_13:n(13)}}function s(m,p){let d=e(`${m}/weights`,4,`${p}/filters`),u=e(`${m}/biases`,1,`${p}/bias`);return{filters:d,bias:u}}function i(m){let p=s(`Prediction/BoxPredictor_${m}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${m}/box_encoding_predictor`),d=s(`Prediction/BoxPredictor_${m}/ClassPredictor`,`prediction_layer/box_predictor_${m}/class_predictor`);return{box_encoding_predictor:p,class_predictor:d}}function c(){return{conv_0:r("Prediction",0,"prediction_layer/conv_0"),conv_1:r("Prediction",1,"prediction_layer/conv_1"),conv_2:r("Prediction",2,"prediction_layer/conv_2"),conv_3:r("Prediction",3,"prediction_layer/conv_3"),conv_4:r("Prediction",4,"prediction_layer/conv_4"),conv_5:r("Prediction",5,"prediction_layer/conv_5"),conv_6:r("Prediction",6,"prediction_layer/conv_6"),conv_7:r("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:i(0),box_predictor_1:i(1),box_predictor_2:i(2),box_predictor_3:i(3),box_predictor_4:i(4),box_predictor_5:i(5)}}return{extractMobilenetV1Params:a,extractPredictionLayerParams:c}}function jo(o){let t=[],{extractMobilenetV1Params:e,extractPredictionLayerParams:r}=Hn(o,t),n=o["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!ht(n))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${n}`);let a={mobilenetv1:e(),prediction_layer:r(),output_layer:{extra_dim:n}};return W(o,t),{params:a,paramMappings:t}}var yt=b(g());var kt=b(g());function q(o,t,e){return kt.tidy(()=>{let r=kt.conv2d(o,t.filters,e,"same");return r=kt.add(r,t.batch_norm_offset),kt.clipByValue(r,0,6)})}var Yn=.0010000000474974513;function Gn(o,t,e){return yt.tidy(()=>{let r=yt.depthwiseConv2d(o,t.filters,e,"same");return r=yt.batchNorm(r,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Yn),yt.clipByValue(r,0,6)})}function zn(o){return[2,4,6,12].some(t=>t===o)?[2,2]:[1,1]}function Ho(o,t){return yt.tidy(()=>{let e,r=q(o,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((a,s)=>{let i=s+1,c=zn(i);r=Gn(r,a.depthwise_conv,c),r=q(r,a.pointwise_conv,[1,1]),i===11&&(e=r)}),e===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:r,conv11:e}})}function Vn(o,t,e){let r=o.arraySync(),n=Math.min(r[t][0],r[t][2]),a=Math.min(r[t][1],r[t][3]),s=Math.max(r[t][0],r[t][2]),i=Math.max(r[t][1],r[t][3]),c=Math.min(r[e][0],r[e][2]),m=Math.min(r[e][1],r[e][3]),p=Math.max(r[e][0],r[e][2]),d=Math.max(r[e][1],r[e][3]),u=(s-n)*(i-a),f=(p-c)*(d-m);if(u<=0||f<=0)return 0;let v=Math.max(n,c),_=Math.max(a,m),h=Math.min(s,p),y=Math.min(i,d),T=Math.max(h-v,0)*Math.max(y-_,0);return T/(u+f-T)}function Yo(o,t,e,r,n){let a=o.shape[0],s=Math.min(e,a),i=t.map((p,d)=>({score:p,boxIndex:d})).filter(p=>p.score>n).sort((p,d)=>d.score-p.score),c=p=>p<=r?1:0,m=[];return i.forEach(p=>{if(m.length>=s)return;let d=p.score;for(let u=m.length-1;u>=0;--u){let f=Vn(o,p.boxIndex,m[u]);if(f!==0&&(p.score*=c(f),p.score<=n))break}d===p.score&&m.push(p.boxIndex)}),m}var l=b(g());function Un(o){let t=l.unstack(l.transpose(o,[1,0])),e=[l.sub(t[2],t[0]),l.sub(t[3],t[1])],r=[l.add(t[0],l.div(e[0],l.scalar(2))),l.add(t[1],l.div(e[1],l.scalar(2)))];return{sizes:e,centers:r}}function Xn(o,t){let{sizes:e,centers:r}=Un(o),n=l.unstack(l.transpose(t,[1,0])),a=l.div(l.mul(l.exp(l.div(n[2],l.scalar(5))),e[0]),l.scalar(2)),s=l.add(l.mul(l.div(n[0],l.scalar(10)),e[0]),r[0]),i=l.div(l.mul(l.exp(l.div(n[3],l.scalar(5))),e[1]),l.scalar(2)),c=l.add(l.mul(l.div(n[1],l.scalar(10)),e[1]),r[1]);return l.transpose(l.stack([l.sub(s,a),l.sub(c,i),l.add(s,a),l.add(c,i)]),[1,0])}function Go(o,t,e){return l.tidy(()=>{let r=o.shape[0],n=Xn(l.reshape(l.tile(e.extra_dim,[r,1,1]),[-1,4]),l.reshape(o,[-1,4]));n=l.reshape(n,[r,n.shape[0]/r,4]);let a=l.sigmoid(l.slice(t,[0,0,1],[-1,-1,-1])),s=l.slice(a,[0,0,0],[-1,-1,1]);s=l.reshape(s,[r,s.shape[1]]);let i=l.unstack(n),c=l.unstack(s);return{boxes:i,scores:c}})}var je=b(g());var Oe=b(g());function Ut(o,t){return Oe.tidy(()=>{let e=o.shape[0],r=Oe.reshape(zt(o,t.box_encoding_predictor),[e,-1,1,4]),n=Oe.reshape(zt(o,t.class_predictor),[e,-1,3]);return{boxPredictionEncoding:r,classPrediction:n}})}function zo(o,t,e){return je.tidy(()=>{let r=q(o,e.conv_0,[1,1]),n=q(r,e.conv_1,[2,2]),a=q(n,e.conv_2,[1,1]),s=q(a,e.conv_3,[2,2]),i=q(s,e.conv_4,[1,1]),c=q(i,e.conv_5,[2,2]),m=q(c,e.conv_6,[1,1]),p=q(m,e.conv_7,[2,2]),d=Ut(t,e.box_predictor_0),u=Ut(o,e.box_predictor_1),f=Ut(n,e.box_predictor_2),v=Ut(s,e.box_predictor_3),_=Ut(c,e.box_predictor_4),h=Ut(p,e.box_predictor_5),y=je.concat([d.boxPredictionEncoding,u.boxPredictionEncoding,f.boxPredictionEncoding,v.boxPredictionEncoding,_.boxPredictionEncoding,h.boxPredictionEncoding],1),T=je.concat([d.classPrediction,u.classPrediction,f.classPrediction,v.classPrediction,_.classPrediction,h.classPrediction],1);return{boxPredictions:y,classPredictions:T}})}var Z=class{constructor({minConfidence:t,maxResults:e}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=e||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Xt=class extends S{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("SsdMobilenetv1 - load model before inference");return st.tidy(()=>{let r=st.cast(t.toBatchTensor(512,!1),"float32"),n=st.sub(st.mul(r,st.scalar(.007843137718737125)),st.scalar(1)),a=Ho(n,e.mobilenetv1),{boxPredictions:s,classPredictions:i}=zo(a.out,a.conv11,e.prediction_layer);return Go(s,i,e.output_layer)})}async forward(t){return this.forwardInput(await E(t))}async locateFaces(t,e={}){let{maxResults:r,minConfidence:n}=new Z(e),a=await E(t),{boxes:s,scores:i}=this.forwardInput(a),c=s[0],m=i[0];for(let F=1;F{let[L,G]=[Math.max(0,y[F][0]),Math.min(1,y[F][2])].map(X=>X*h),[et,it]=[Math.max(0,y[F][1]),Math.min(1,y[F][3])].map(X=>X*_);return new M(p[F],new oe(et,L,it-et,G-L),{height:a.getInputHeight(0),width:a.getInputWidth(0)})});return c.dispose(),m.dispose(),T}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return jo(t)}extractParams(t){return Oo(t)}};function Vo(o){let t=new Xt;return t.extractWeights(o),t}function Jn(o){return Vo(o)}var Uo=class extends Xt{};var Xo=.4,Jo=[new x(.738768,.874946),new x(2.42204,2.65704),new x(4.30971,7.04493),new x(10.246,4.59428),new x(12.6868,11.8741)],qo=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],Zo=[117.001,114.697,97.404],Ko="tiny_yolov2_model",Qo="tiny_yolov2_separable_conv_model";var N=b(g());var br=o=>typeof o=="number";function ao(o){if(!o)throw new Error(`invalid config: ${o}`);if(typeof o.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${o.withSeparableConvs}`);if(!br(o.iouThreshold)||o.iouThreshold<0||o.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${o.iouThreshold}`);if(!Array.isArray(o.classes)||!o.classes.length||!o.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(o.classes)}`);if(!Array.isArray(o.anchors)||!o.anchors.length||!o.anchors.map(t=>t||{}).every(t=>br(t.x)&&br(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(o.anchors)}`);if(o.meanRgb&&(!Array.isArray(o.meanRgb)||o.meanRgb.length!==3||!o.meanRgb.every(br)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(o.meanRgb)}`)}var Q=b(g());var K=b(g());function ge(o){return K.tidy(()=>{let t=K.mul(o,K.scalar(.10000000149011612));return K.add(K.relu(K.sub(o,t)),t)})}function Ft(o,t){return Q.tidy(()=>{let e=Q.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=Q.conv2d(e,t.conv.filters,[1,1],"valid"),e=Q.sub(e,t.bn.sub),e=Q.mul(e,t.bn.truediv),e=Q.add(e,t.conv.bias),ge(e)})}var St=b(g());function Tt(o,t){return St.tidy(()=>{let e=St.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=St.separableConv2d(e,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),e=St.add(e,t.bias),ge(e)})}var so=b(g());function qn(o,t){let e=me(o,t);function r(s,i){let c=so.tensor1d(o(s)),m=so.tensor1d(o(s));return t.push({paramPath:`${i}/sub`},{paramPath:`${i}/truediv`}),{sub:c,truediv:m}}function n(s,i,c){let m=e(s,i,3,`${c}/conv`),p=r(i,`${c}/bn`);return{conv:m,bn:p}}let a=pe(o,t);return{extractConvParams:e,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}}function tn(o,t,e,r){let{extractWeights:n,getRemainingWeights:a}=B(o),s=[],{extractConvParams:i,extractConvWithBatchNormParams:c,extractSeparableConvParams:m}=qn(n,s),p;if(t.withSeparableConvs){let[d,u,f,v,_,h,y,T,F]=r,L=t.isFirstLayerConv2d?i(d,u,3,"conv0"):m(d,u,"conv0"),G=m(u,f,"conv1"),et=m(f,v,"conv2"),it=m(v,_,"conv3"),X=m(_,h,"conv4"),Pt=m(h,y,"conv5"),_t=T?m(y,T,"conv6"):void 0,wt=F?m(T,F,"conv7"):void 0,te=i(F||T||y,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:te}}else{let[d,u,f,v,_,h,y,T,F]=r,L=c(d,u,"conv0"),G=c(u,f,"conv1"),et=c(f,v,"conv2"),it=c(v,_,"conv3"),X=c(_,h,"conv4"),Pt=c(h,y,"conv5"),_t=c(y,T,"conv6"),wt=c(T,F,"conv7"),te=i(F,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:te}}if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:p,paramMappings:s}}function Zn(o,t){let e=j(o,t);function r(i){let c=e(`${i}/sub`,1),m=e(`${i}/truediv`,1);return{sub:c,truediv:m}}function n(i){let c=e(`${i}/filters`,4),m=e(`${i}/bias`,1);return{filters:c,bias:m}}function a(i){let c=n(`${i}/conv`),m=r(`${i}/bn`);return{conv:c,bn:m}}let s=de(e);return{extractConvParams:n,extractConvWithBatchNormParams:a,extractSeparableConvParams:s}}function en(o,t){let e=[],{extractConvParams:r,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}=Zn(o,e),s;if(t.withSeparableConvs){let i=t.filterSizes&&t.filterSizes.length||9;s={conv0:t.isFirstLayerConv2d?r("conv0"):a("conv0"),conv1:a("conv1"),conv2:a("conv2"),conv3:a("conv3"),conv4:a("conv4"),conv5:a("conv5"),conv6:i>7?a("conv6"):void 0,conv7:i>8?a("conv7"):void 0,conv8:r("conv8")}}else s={conv0:n("conv0"),conv1:n("conv1"),conv2:n("conv2"),conv3:n("conv3"),conv4:n("conv4"),conv5:n("conv5"),conv6:n("conv6"),conv7:n("conv7"),conv8:r("conv8")};return W(o,e),{params:s,paramMappings:e}}var ft=class{constructor({inputSize:t,scoreThreshold:e}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=e||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var io=class extends S{constructor(t){super("TinyYolov2");ao(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,e){let r=Ft(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=Ft(r,e.conv6),r=Ft(r,e.conv7),zt(r,e.conv8,"valid",!1)}runMobilenet(t,e){let r=this.config.isFirstLayerConv2d?ge(zt(t,e.conv0,"valid",!1)):Tt(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=e.conv6?Tt(r,e.conv6):r,r=e.conv7?Tt(r,e.conv7):r,zt(r,e.conv8,"valid",!1)}forwardInput(t,e){let{params:r}=this;if(!r)throw new Error("TinyYolov2 - load model before inference");return N.tidy(()=>{let n=N.cast(t.toBatchTensor(e,!1),"float32");return n=this.config.meanRgb?ot(n,this.config.meanRgb):n,n=n.div(N.scalar(256)),this.config.withSeparableConvs?this.runMobilenet(n,r):this.runTinyYolov2(n,r)})}async forward(t,e){return this.forwardInput(await E(t),e)}async detect(t,e={}){let{inputSize:r,scoreThreshold:n}=new ft(e),a=await E(t),s=await this.forwardInput(a,r),i=N.tidy(()=>N.unstack(s)[0].expandDims()),c={width:a.getInputWidth(0),height:a.getInputHeight(0)},m=await this.extractBoxes(i,a.getReshapedInputDimensions(0),n);s.dispose(),i.dispose();let p=m.map(h=>h.box),d=m.map(h=>h.score),u=m.map(h=>h.classScore),f=m.map(h=>this.config.classes[h.label]);return Sr(p.map(h=>h.rescale(r)),d,this.config.iouThreshold,!0).map(h=>new Dt(d[h],u[h],f[h],p[h],c))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return en(t,this.config)}extractParams(t){let e=this.config.filterSizes||io.DEFAULT_FILTER_SIZES,r=e?e.length:void 0;if(r!==7&&r!==8&&r!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${r} filterSizes in config`);return tn(t,this.config,this.boxEncodingSize,e)}async extractBoxes(t,e,r){let{width:n,height:a}=e,s=Math.max(n,a),i=s/n,c=s/a,m=t.shape[1],p=this.config.anchors.length,[d,u,f]=N.tidy(()=>{let y=t.reshape([m,m,p,this.boxEncodingSize]),T=y.slice([0,0,0,0],[m,m,p,4]),F=y.slice([0,0,0,4],[m,m,p,1]),L=this.withClassScores?N.softmax(y.slice([0,0,0,5],[m,m,p,this.config.classes.length]),3):N.scalar(0);return[T,F,L]}),v=[],_=await u.array(),h=await d.array();for(let y=0;yr){let G=(T+Ee(h[y][T][F][0]))/m*i,et=(y+Ee(h[y][T][F][1]))/m*c,it=Math.exp(h[y][T][F][2])*this.config.anchors[F].x/m*i,X=Math.exp(h[y][T][F][3])*this.config.anchors[F].y/m*c,Pt=G-it/2,_t=et-X/2,wt={row:y,col:T,anchor:F},{classScore:te,label:fo}=this.withClassScores?await this.extractPredictedClass(f,wt):{classScore:1,label:0};v.push({box:new re(Pt,_t,Pt+it,_t+X),score:L,classScore:L*te,label:fo,...wt})}}return d.dispose(),u.dispose(),f.dispose(),v}async extractPredictedClass(t,e){let{row:r,col:n,anchor:a}=e,s=await t.array();return Array(this.config.classes.length).fill(0).map((i,c)=>s[r][n][a][c]).map((i,c)=>({classScore:i,label:c})).reduce((i,c)=>i.classScore>c.classScore?i:c)}},ve=io;ve.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var ye=class extends ve{constructor(t=!0){let e={withSeparableConvs:t,iouThreshold:Xo,classes:["face"],...t?{anchors:qo,meanRgb:Zo}:{anchors:Jo,withClassScores:!0}};super(e)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?Qo:Ko}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function Kn(o,t=!0){let e=new ye(t);return e.extractWeights(o),e}var gr=class extends ft{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var tt=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};var He=b(g());var co=b(g());async function Jt(o,t,e,r,n=({alignedRect:a})=>a){let a=o.map(c=>Vt(c)?n(c):c.detection),s=r||(t instanceof co.Tensor?await ie(t,a):await se(t,a)),i=await e(s);return s.forEach(c=>c instanceof co.Tensor&&c.dispose()),i}async function Fe(o,t,e,r,n){return Jt([o],t,async a=>e(a[0]),r,n)}var rn=.4,on=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],nn=[117.001,114.697,97.404];var Te=class extends ve{constructor(){let t={withSeparableConvs:!0,iouThreshold:rn,classes:["face"],anchors:on,meanRgb:nn,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var P={ssdMobilenetv1:new Xt,tinyFaceDetector:new Te,tinyYolov2:new ye,faceLandmark68Net:new he,faceLandmark68TinyNet:new dr,faceRecognitionNet:new be,faceExpressionNet:new cr,ageGenderNet:new pr},an=(o,t)=>P.ssdMobilenetv1.locateFaces(o,t),Qn=(o,t)=>P.tinyFaceDetector.locateFaces(o,t),ta=(o,t)=>P.tinyYolov2.locateFaces(o,t),sn=o=>P.faceLandmark68Net.detectLandmarks(o),ea=o=>P.faceLandmark68TinyNet.detectLandmarks(o),ra=o=>P.faceRecognitionNet.computeFaceDescriptor(o),oa=o=>P.faceExpressionNet.predictExpressions(o),na=o=>P.ageGenderNet.predictAgeAndGender(o),cn=o=>P.ssdMobilenetv1.load(o),aa=o=>P.tinyFaceDetector.load(o),sa=o=>P.tinyYolov2.load(o),ia=o=>P.faceLandmark68Net.load(o),ca=o=>P.faceLandmark68TinyNet.load(o),ma=o=>P.faceRecognitionNet.load(o),pa=o=>P.faceExpressionNet.load(o),da=o=>P.ageGenderNet.load(o),ua=cn,fa=an,la=sn;var mo=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},we=class extends mo{async run(){let t=await this.parentTask,e=await Jt(t,this.input,async r=>Promise.all(r.map(n=>P.faceExpressionNet.predictExpressions(n))),this.extractedFaces);return t.map((r,n)=>mr(r,e[n]))}withAgeAndGender(){return new Pe(this,this.input)}},De=class extends mo{async run(){let t=await this.parentTask;if(!t)return;let e=await Fe(t,this.input,r=>P.faceExpressionNet.predictExpressions(r),this.extractedFaces);return mr(t,e)}withAgeAndGender(){return new _e(this,this.input)}},Kt=class extends we{withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Qt=class extends De{withAgeAndGender(){return new Zt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var po=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},Pe=class extends po{async run(){let t=await this.parentTask,e=await Jt(t,this.input,async r=>Promise.all(r.map(n=>P.ageGenderNet.predictAgeAndGender(n))),this.extractedFaces);return t.map((r,n)=>{let{age:a,gender:s,genderProbability:i}=e[n];return hr(xr(r,s,i),a)})}withFaceExpressions(){return new we(this,this.input)}},_e=class extends po{async run(){let t=await this.parentTask;if(!t)return;let{age:e,gender:r,genderProbability:n}=await Fe(t,this.input,a=>P.ageGenderNet.predictAgeAndGender(a),this.extractedFaces);return hr(xr(t,r,n),e)}withFaceExpressions(){return new De(this,this.input)}},qt=class extends Pe{withFaceExpressions(){return new Kt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Zt=class extends _e{withFaceExpressions(){return new Qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var vr=class extends tt{constructor(t,e){super();this.parentTask=t;this.input=e}},At=class extends vr{async run(){let t=await this.parentTask;return(await Jt(t,this.input,r=>Promise.all(r.map(n=>P.faceRecognitionNet.computeFaceDescriptor(n))),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}))).map((r,n)=>lr(t[n],r))}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}},Wt=class extends vr{async run(){let t=await this.parentTask;if(!t)return;let e=await Fe(t,this.input,r=>P.faceRecognitionNet.computeFaceDescriptor(r),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}));return lr(t,e)}withFaceExpressions(){return new Qt(this,this.input)}withAgeAndGender(){return new Zt(this,this.input)}};var yr=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.useTinyLandmarkNet=r}get landmarkNet(){return this.useTinyLandmarkNet?P.faceLandmark68TinyNet:P.faceLandmark68Net}},Fr=class extends yr{async run(){let t=await this.parentTask,e=t.map(a=>a.detection),r=this.input instanceof He.Tensor?await ie(this.input,e):await se(this.input,e),n=await Promise.all(r.map(a=>this.landmarkNet.detectLandmarks(a)));return r.forEach(a=>a instanceof He.Tensor&&a.dispose()),t.map((a,s)=>le(a,n[s]))}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Tr=class extends yr{async run(){let t=await this.parentTask;if(!t)return;let{detection:e}=t,r=this.input instanceof He.Tensor?await ie(this.input,[e]):await se(this.input,[e]),n=await this.landmarkNet.detectLandmarks(r[0]);return r.forEach(a=>a instanceof He.Tensor&&a.dispose()),le(t,n)}withFaceExpressions(){return new Qt(this,this.input)}withAgeAndGender(){return new Zt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var Pr=class extends tt{constructor(t,e=new Z){super();this.input=t;this.options=e}},Ye=class extends Pr{async run(){let{input:t,options:e}=this,r=e instanceof gr?n=>P.tinyFaceDetector.locateFaces(n,e):e instanceof Z?n=>P.ssdMobilenetv1.locateFaces(n,e):e instanceof ft?n=>P.tinyYolov2.locateFaces(n,e):null;if(!r)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return r(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let e=await this.run();t(e.map(r=>jt({},r)))})}withFaceLandmarks(t=!1){return new Fr(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new we(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Pe(this.runAndExtendWithFaceDetections(),this.input)}},_r=class extends Pr{async run(){let t=await new Ye(this.input,this.options),e=t[0];return t.forEach(r=>{r.score>e.score&&(e=r)}),e}runAndExtendWithFaceDetection(){return new Promise(async t=>{let e=await this.run();t(e?jt({},e):void 0)})}withFaceLandmarks(t=!1){return new Tr(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new De(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new _e(this.runAndExtendWithFaceDetection(),this.input)}};function ha(o,t=new Z){return new _r(o,t)}function wr(o,t=new Z){return new Ye(o,t)}async function mn(o,t){return wr(o,new Z(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function xa(o,t={}){return wr(o,new ft(t)).withFaceLandmarks().withFaceDescriptors()}var ba=mn;function uo(o,t){if(o.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let e=Array.from(o),r=Array.from(t);return Math.sqrt(e.map((n,a)=>n-r[a]).reduce((n,a)=>n+a**2,0))}var Dr=class{constructor(t,e=.6){this._distanceThreshold=e;let r=Array.isArray(t)?t:[t];if(!r.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let n=1,a=()=>`person ${n++}`;this._labeledDescriptors=r.map(s=>{if(s instanceof xt)return s;if(s instanceof Float32Array)return new xt(a(),[s]);if(s.descriptor&&s.descriptor instanceof Float32Array)return new xt(a(),[s.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,e){return e.map(r=>uo(r,t)).reduce((r,n)=>r+n,0)/(e.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:e,label:r})=>new Me(r,this.computeMeanDistance(t,e))).reduce((e,r)=>e.distancet.toJSON())}}static fromJSON(t){let e=t.labeledDescriptors.map(r=>xt.fromJSON(r));return new Dr(e,t.distanceThreshold)}};function ga(o){let t=new Te;return t.extractWeights(o),t}function pn(o,t){let{width:e,height:r}=new A(t.width,t.height);if(e<=0||r<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:e,height:r})}`);if(Array.isArray(o))return o.map(n=>pn(n,{width:e,height:r}));if(Vt(o)){let n=o.detection.forSize(e,r),a=o.unshiftedLandmarks.forSize(n.box.width,n.box.height);return le(jt(o,n),a)}return pt(o)?jt(o,o.detection.forSize(e,r)):o instanceof V||o instanceof M?o.forSize(e,r):o}var ya=typeof process!="undefined",Fa=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Ta={faceapi:Eo,node:ya,browser:Fa};export{pr as AgeGenderNet,re as BoundingBox,D as Box,tt as ComposableTask,At as ComputeAllFaceDescriptorsTask,vr as ComputeFaceDescriptorsTaskBase,Wt as ComputeSingleFaceDescriptorTask,Fr as DetectAllFaceLandmarksTask,Ye as DetectAllFacesTask,yr as DetectFaceLandmarksTaskBase,Pr as DetectFacesTaskBase,Tr as DetectSingleFaceLandmarksTask,_r as DetectSingleFaceTask,A as Dimensions,Jr as FACE_EXPRESSION_LABELS,M as FaceDetection,Uo as FaceDetectionNet,cr as FaceExpressionNet,It as FaceExpressions,he as FaceLandmark68Net,dr as FaceLandmark68TinyNet,Ao as FaceLandmarkNet,V as FaceLandmarks,bo as FaceLandmarks5,ne as FaceLandmarks68,Me as FaceMatch,Dr as FaceMatcher,be as FaceRecognitionNet,vt as Gender,Ce as LabeledBox,xt as LabeledFaceDescriptors,bt as NetInput,S as NeuralNetwork,Dt as ObjectDetection,x as Point,go as PredictedBox,oe as Rect,Xt as SsdMobilenetv1,Z as SsdMobilenetv1Options,Te as TinyFaceDetector,gr as TinyFaceDetectorOptions,ye as TinyYolov2,ft as TinyYolov2Options,ba as allFaces,mn as allFacesSsdMobilenetv1,xa as allFacesTinyYolov2,Yr as awaitMediaLoaded,Gr as bufferToImage,ra as computeFaceDescriptor,ae as createCanvas,Le as createCanvasFromMedia,Jn as createFaceDetectionNet,Rn as createFaceRecognitionNet,Vo as createSsdMobilenetv1,ga as createTinyFaceDetector,Kn as createTinyYolov2,wr as detectAllFaces,sn as detectFaceLandmarks,ea as detectFaceLandmarksTiny,la as detectLandmarks,ha as detectSingleFace,Qr as draw,w as env,uo as euclideanDistance,hr as extendWithAge,lr as extendWithFaceDescriptor,jt as extendWithFaceDetection,mr as extendWithFaceExpressions,le as extendWithFaceLandmarks,xr as extendWithGender,ie as extractFaceTensors,se as extractFaces,Mn as fetchImage,Ur as fetchJson,Cn as fetchNetWeights,Gt as fetchOrThrow,$ as getContext2dOrThrow,Yt as getMediaDimensions,zr as imageTensorToCanvas,Vr as imageToSquare,vn as inverseSigmoid,Lr as iou,qe as isMediaElement,Ie as isMediaLoaded,$n as isWithAge,pt as isWithFaceDetection,qr as isWithFaceExpressions,Vt as isWithFaceLandmarks,On as isWithGender,da as loadAgeGenderModel,ua as loadFaceDetectionModel,pa as loadFaceExpressionModel,ia as loadFaceLandmarkModel,ca as loadFaceLandmarkTinyModel,ma as loadFaceRecognitionModel,cn as loadSsdMobilenetv1Model,aa as loadTinyFaceDetectorModel,sa as loadTinyYolov2Model,Xr as loadWeightMap,fa as locateFaces,Nn as matchDimensions,kr as minBbox,P as nets,Sr as nonMaxSuppression,ot as normalize,Ar as padToSquare,na as predictAgeAndGender,oa as recognizeFaceExpressions,pn as resizeResults,Ht as resolveInput,gn as shuffleArray,Ee as sigmoid,an as ssdMobilenetv1,va as tf,Qn as tinyFaceDetector,ta as tinyYolov2,E as toNetInput,Mr as utils,ao as validateConfig,Ta as version}; +var dn=Object.create,Ge=Object.defineProperty,un=Object.getPrototypeOf,fn=Object.prototype.hasOwnProperty,ln=Object.getOwnPropertyNames,hn=Object.getOwnPropertyDescriptor;var lo=o=>Ge(o,"__esModule",{value:!0});var ho=(o,t)=>()=>(t||(t={exports:{}},o(t.exports,t)),t.exports),Er=(o,t)=>{lo(o);for(var e in t)Ge(o,e,{get:t[e],enumerable:!0})},Bt=(o,t,e)=>{if(lo(o),t&&typeof t=="object"||typeof t=="function")for(let r of ln(t))!fn.call(o,r)&&r!=="default"&&Ge(o,r,{get:()=>t[r],enumerable:!(e=hn(t,r))||e.enumerable});return o},b=o=>o&&o.__esModule?o:Bt(Ge(o!=null?dn(un(o)):{},"default",{value:o,enumerable:!0}),o);import*as Ma from"@tensorflow/tfjs/dist/index.js";import*as Ca from"@tensorflow/tfjs-backend-wasm";var g=ho(xn=>{Bt(xn,Ma);Bt(xn,Ca)});var yo=ho((Pn,vo)=>{Er(Pn,{isNodejs:()=>_n});function _n(){return typeof global=="object"&&!0&&typeof vo!="undefined"&&typeof process!="undefined"&&!!process.version}});var va=b(g());var Qr={};Er(Qr,{AnchorPosition:()=>dt,DrawBox:()=>Xe,DrawBoxOptions:()=>Hr,DrawFaceLandmarks:()=>Kr,DrawFaceLandmarksOptions:()=>Zr,DrawTextField:()=>Mt,DrawTextFieldOptions:()=>Ne,drawContour:()=>lt,drawDetections:()=>En,drawFaceExpressions:()=>In,drawFaceLandmarks:()=>Ln});function lt(o,t,e=!1){if(o.beginPath(),t.slice(1).forEach(({x:r,y:n},a)=>{let s=t[a];o.moveTo(s.x,s.y),o.lineTo(r,n)}),e){let r=t[t.length-1],n=t[0];if(!r||!n)return;o.moveTo(r.x,r.y),o.lineTo(n.x,n.y)}o.stroke()}var Mr={};Er(Mr,{computeReshapedDimensions:()=>Ir,getCenterPoint:()=>Ot,isDimensions:()=>Ve,isEven:()=>ze,isFloat:()=>Nr,isTensor:()=>Rt,isTensor1D:()=>bn,isTensor2D:()=>Cr,isTensor3D:()=>ht,isTensor4D:()=>z,isValidNumber:()=>rt,isValidProbablitiy:()=>ee,range:()=>ct,round:()=>$t});var xo=b(g());var A=class{constructor(t,e){if(!rt(t)||!rt(e))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:e})}`);this._width=t,this._height=e}get width(){return this._width}get height(){return this._height}reverse(){return new A(1/this.width,1/this.height)}};function Rt(o,t){return o instanceof xo.Tensor&&o.shape.length===t}function bn(o){return Rt(o,1)}function Cr(o){return Rt(o,2)}function ht(o){return Rt(o,3)}function z(o){return Rt(o,4)}function Nr(o){return o%1!=0}function ze(o){return o%2==0}function $t(o,t=2){let e=10**t;return Math.floor(o*e)/e}function Ve(o){return o&&o.width&&o.height}function Ir({width:o,height:t},e){let r=e/Math.max(t,o);return new A(Math.round(o*r),Math.round(t*r))}function Ot(o){return o.reduce((t,e)=>t.add(e),new x(0,0)).div(new x(o.length,o.length))}function ct(o,t,e){return Array(o).fill(0).map((r,n)=>t+n*e)}function rt(o){return!!o&&o!==Infinity&&o!==-Infinity&&!Number.isNaN(o)||o===0}function ee(o){return rt(o)&&o>=0&&o<=1}var x=class{constructor(t,e){this._x=t,this._y=e}get x(){return this._x}get y(){return this._y}add(t){return new x(this.x+t.x,this.y+t.y)}sub(t){return new x(this.x-t.x,this.y-t.y)}mul(t){return new x(this.x*t.x,this.y*t.y)}div(t){return new x(this.x/t.x,this.y/t.y)}abs(){return new x(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new x(Math.floor(this.x),Math.floor(this.y))}};var D=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(rt)}static assertIsValidBox(t,e,r=!1){if(!D.isRect(t))throw new Error(`${e} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!r&&(t.width<0||t.height<0))throw new Error(`${e} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,e=!0){let r=t||{},n=[r.left,r.top,r.right,r.bottom].every(rt),a=[r.x,r.y,r.width,r.height].every(rt);if(!a&&!n)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(r)}`);let[s,i,c,m]=a?[r.x,r.y,r.width,r.height]:[r.left,r.top,r.right-r.left,r.bottom-r.top];D.assertIsValidBox({x:s,y:i,width:c,height:m},"Box.constructor",e),this._x=s,this._y=i,this._width=c,this._height=m}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new x(this.left,this.top)}get topRight(){return new x(this.right,this.top)}get bottomLeft(){return new x(this.left,this.bottom)}get bottomRight(){return new x(this.right,this.bottom)}round(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.round(a));return new D({x:t,y:e,width:r,height:n})}floor(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.floor(a));return new D({x:t,y:e,width:r,height:n})}toSquare(){let{x:t,y:e,width:r,height:n}=this,a=Math.abs(r-n);return re&&(i=-d+e+r,d=e),u>t&&(c=-u+t+n,u=t),m<1&&(c=2-m,m=1),p<1&&(c=2-p,p=1),{dy:s,edy:c,dx:a,edx:i,y:p,ey:u,x:m,ex:d,w:r,h:n}}calibrate(t){return new D({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var re=class extends D{constructor(t,e,r,n,a=!1){super({left:t,top:e,right:r,bottom:n},a)}};var Dt=class{constructor(t,e,r,n,a){this._imageDims=new A(a.width,a.height),this._score=t,this._classScore=e,this._className=r,this._box=new D(n).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new D(this._box).rescale(this.imageDims.reverse())}forSize(t,e){return new Dt(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:e})}};var M=class extends Dt{constructor(t,e,r){super(t,t,"",e,r)}forSize(t,e){let{score:r,relativeBox:n,imageDims:a}=super.forSize(t,e);return new M(r,n,a)}};function Lr(o,t,e=!0){let r=Math.max(0,Math.min(o.right,t.right)-Math.max(o.left,t.left)),n=Math.max(0,Math.min(o.bottom,t.bottom)-Math.max(o.top,t.top)),a=r*n;return e?a/(o.area+t.area-a):a/Math.min(o.area,t.area)}function kr(o){let t=o.map(i=>i.x),e=o.map(i=>i.y),r=t.reduce((i,c)=>ccii({score:s,boxIndex:i})).sort((s,i)=>s.score-i.score).map(s=>s.boxIndex),a=[];for(;n.length>0;){let s=n.pop();a.push(s);let i=n,c=[];for(let m=0;mc[p]<=e)}return a}var mt=b(g());function ot(o,t){return mt.tidy(()=>{let[e,r,n]=t,a=mt.fill([...o.shape.slice(0,3),1],e,"float32"),s=mt.fill([...o.shape.slice(0,3),1],r,"float32"),i=mt.fill([...o.shape.slice(0,3),1],n,"float32"),c=mt.concat([a,s,i],3);return mt.sub(o,c)})}var Et=b(g());function Ar(o,t=!1){return Et.tidy(()=>{let[e,r]=o.shape.slice(1);if(e===r)return o;let n=Math.abs(e-r),a=Math.round(n*(t?.5:1)),s=e>r?2:1,i=u=>{let f=o.shape.slice();return f[s]=u,Et.fill(f,0,"float32")},c=i(a),m=n-c.shape[s],d=[t&&m?i(m):null,o,c].filter(u=>!!u).map(u=>Et.cast(u,"float32"));return Et.concat(d,s)})}function gn(o){let t=o.slice();for(let e=t.length-1;e>0;e--){let r=Math.floor(Math.random()*(e+1)),n=t[e];t[e]=t[r],t[r]=n}return t}function Ee(o){return 1/(1+Math.exp(-o))}function vn(o){return Math.log(o/(1-o))}var oe=class extends D{constructor(t,e,r,n,a=!1){super({x:t,y:e,width:r,height:n},a)}};var yn=.5,Fn=.43,Tn=.45,V=class{constructor(t,e,r=new x(0,0)){let{width:n,height:a}=e;this._imgDims=new A(n,a),this._shift=r,this._positions=t.map(s=>s.mul(new x(n,a)).add(r))}get shift(){return new x(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new x(this.imageWidth,this.imageHeight)))}forSize(t,e){return new this.constructor(this.relativePositions,{width:t,height:e})}shiftBy(t,e){return new this.constructor(this.relativePositions,this._imgDims,new x(t,e))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,e={}){if(t){let a=t instanceof M?t.box.floor():new D(t);return this.shiftBy(a.x,a.y).align(null,e)}let{useDlibAlignment:r,minBoxPadding:n}={useDlibAlignment:!1,minBoxPadding:.2,...e};return r?this.alignDlib():this.alignMinBbox(n)}alignDlib(){let t=this.getRefPointsForAlignment(),[e,r,n]=t,a=d=>n.sub(d).magnitude(),s=(a(e)+a(r))/2,i=Math.floor(s/Tn),c=Ot(t),m=Math.floor(Math.max(0,c.x-yn*i)),p=Math.floor(Math.max(0,c.y-Fn*i));return new oe(m,p,Math.min(i,this.imageWidth+m),Math.min(i,this.imageHeight+p))}alignMinBbox(t){let e=kr(this.positions);return e.pad(e.width*t,e.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var bo=class extends V{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Ot([t[3],t[4]])]}};var ne=class extends V{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Ot)}};var Me=class{constructor(t,e){this._label=t,this._distance=e}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${$t(this.distance)})`:""}`}};var Ce=class extends D{static assertIsValidLabeledBox(t,e){if(D.assertIsValidBox(t,e),!rt(t.label))throw new Error(`${e} - expected property label (${t.label}) to be a number`)}constructor(t,e){super(t);this._label=e}get label(){return this._label}};var xt=class{constructor(t,e){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(e)||e.some(r=>!(r instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=e}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let e=t.descriptors.map(r=>new Float32Array(r));return new xt(t.label,e)}};var go=class extends Ce{static assertIsValidPredictedBox(t,e){if(Ce.assertIsValidLabeledBox(t,e),!ee(t.score)||!ee(t.classScore))throw new Error(`${e} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,e,r,n){super(t,e);this._score=r,this._classScore=n}get score(){return this._score}get classScore(){return this._classScore}};function pt(o){return o.detection instanceof M}function jt(o,t){return{...o,...{detection:t}}}function Wr(){let o=window.fetch;if(!o)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:o,readFile:t}}function Ue(o){let t="";if(!o)try{o=require("fs")}catch(r){t=r.toString()}return{readFile:o?r=>new Promise((n,a)=>{o.readFile(r,(s,i)=>s?a(s):n(i))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function Br(){let o=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,e=()=>{if(o)return new o;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},r=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},n=global.fetch,a=Ue();return{Canvas:o||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:e,createImageElement:r,fetch:n,...a}}function Rr(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var $r=b(yo()),k;function wn(){if(!k)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return k}function Or(o){k=o}function jr(){return Rr()?Or(Wr()):$r.isNodejs()?Or(Br()):null}function Dn(o){if(k||jr(),!k)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=k.Canvas,Image:e=k.Image}=o;k.Canvas=t,k.Image=e,k.createCanvasElement=o.createCanvasElement||(()=>new t),k.createImageElement=o.createImageElement||(()=>new e),k.ImageData=o.ImageData||k.ImageData,k.Video=o.Video||k.Video,k.fetch=o.fetch||k.fetch,k.readFile=o.readFile||k.readFile}var w={getEnv:wn,setEnv:Or,initialize:jr,createBrowserEnv:Wr,createFileSystem:Ue,createNodejsEnv:Br,monkeyPatch:Dn,isBrowser:Rr,isNodejs:$r.isNodejs};jr();function Ht(o){return!w.isNodejs()&&typeof o=="string"?document.getElementById(o):o}function $(o){let{Canvas:t,CanvasRenderingContext2D:e}=w.getEnv();if(o instanceof e)return o;let r=Ht(o);if(!(r instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let n=r.getContext("2d");if(!n)throw new Error("resolveContext2d - canvas 2d context is null");return n}var dt;(function(o){o.TOP_LEFT="TOP_LEFT",o.TOP_RIGHT="TOP_RIGHT",o.BOTTOM_LEFT="BOTTOM_LEFT",o.BOTTOM_RIGHT="BOTTOM_RIGHT"})(dt||(dt={}));var Ne=class{constructor(t={}){let{anchorPosition:e,backgroundColor:r,fontColor:n,fontSize:a,fontStyle:s,padding:i}=t;this.anchorPosition=e||dt.TOP_LEFT,this.backgroundColor=r||"rgba(0, 0, 0, 0.5)",this.fontColor=n||"rgba(255, 255, 255, 1)",this.fontSize=a||14,this.fontStyle=s||"Georgia",this.padding=i||4}},Mt=class{constructor(t,e,r={}){this.text=typeof t=="string"?[t]:t instanceof Mt?t.text:t,this.anchor=e,this.options=new Ne(r)}measureWidth(t){let{padding:e}=this.options;return this.text.map(r=>t.measureText(r).width).reduce((r,n)=>r{let v=c+d.x,_=c+d.y+(f+1)*s;r.fillText(u,v,_)})}};var Hr=class{constructor(t={}){let{boxColor:e,lineWidth:r,label:n,drawLabelOptions:a}=t;this.boxColor=e||"rgba(0, 0, 255, 1)",this.lineWidth=r||2,this.label=n;let s={anchorPosition:dt.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Ne({...s,...a})}},Xe=class{constructor(t,e={}){this.box=new D(t),this.options=new Hr(e)}draw(t){let e=$(t),{boxColor:r,lineWidth:n}=this.options,{x:a,y:s,width:i,height:c}=this.box;e.strokeStyle=r,e.lineWidth=n,e.strokeRect(a,s,i,c);let{label:m}=this.options;m&&new Mt([m],{x:a-n/2,y:s},this.options.drawLabelOptions).draw(t)}};function En(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof M?r.score:pt(r)?r.detection.score:void 0,a=r instanceof M?r.box:pt(r)?r.detection.box:new D(r),s=n?`${$t(n)}`:void 0;new Xe(a,{label:s}).draw(o)})}var fe=b(g());function Ie(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t&&o.complete||o instanceof e&&o.readyState>=3}function Yr(o){return new Promise((t,e)=>{if(o instanceof w.getEnv().Canvas||Ie(o))return t(null);function r(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),e(a))}function n(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),t(a))}o.addEventListener("load",n),o.addEventListener("error",r)})}function Gr(o){return new Promise((t,e)=>{o instanceof Blob||e(new Error("bufferToImage - expected buf to be of type: Blob"));let r=new FileReader;r.onload=()=>{typeof r.result!="string"&&e(new Error("bufferToImage - expected reader.result to be a string, in onload"));let n=w.getEnv().createImageElement();n.onload=()=>t(n),n.onerror=e,n.src=r.result},r.onerror=e,r.readAsDataURL(o)})}function Yt(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t?new A(o.naturalWidth,o.naturalHeight):o instanceof e?new A(o.videoWidth,o.videoHeight):new A(o.width,o.height)}function ae({width:o,height:t}){let{createCanvasElement:e}=w.getEnv(),r=e();return r.width=o,r.height=t,r}function Le(o,t){let{ImageData:e}=w.getEnv();if(!(o instanceof e)&&!Ie(o))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:r,height:n}=t||Yt(o),a=ae({width:r,height:n});return o instanceof e?$(a).putImageData(o,0,0):$(a).drawImage(o,0,0,r,n),a}var Je=b(g());async function zr(o,t){let e=t||w.getEnv().createCanvasElement(),[r,n,a]=o.shape.slice(z(o)?1:0),s=Je.tidy(()=>o.as3D(r,n,a).toInt());return await Je.browser.toPixels(s,e),s.dispose(),e}function qe(o){let{Image:t,Canvas:e,Video:r}=w.getEnv();return o instanceof t||o instanceof e||o instanceof r}var J=b(g());function Vr(o,t,e=!1){let{Image:r,Canvas:n}=w.getEnv();if(!(o instanceof r||o instanceof n))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let a=Yt(o),s=t/Math.max(a.height,a.width),i=s*a.width,c=s*a.height,m=ae({width:t,height:t}),p=o instanceof n?o:Le(o),d=Math.abs(i-c)/2,u=e&&i{if(ht(r)){this._imageTensors[n]=r,this._inputDimensions[n]=r.shape;return}if(z(r)){let s=r.shape[0];if(s!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${s} passed, but not supported in input array`);this._imageTensors[n]=r,this._inputDimensions[n]=r.shape.slice(1);return}let a=r instanceof w.getEnv().Canvas?r:Le(r);this._canvases[n]=a,this._inputDimensions[n]=[a.height,a.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ct(this.batchSize,0,1).map((t,e)=>this.getReshapedInputDimensions(e))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let e=this.getInputWidth(t),r=this.getInputHeight(t);return Ir({width:e,height:r},this.inputSize)}toBatchTensor(t,e=!0){return this._inputSize=t,J.tidy(()=>{let r=ct(this.batchSize,0,1).map(a=>{let s=this.getInput(a);if(s instanceof J.Tensor){let i=z(s)?s:s.expandDims();return i=Ar(i,e),(i.shape[1]!==t||i.shape[2]!==t)&&(i=J.image.resizeBilinear(i,[t,t])),i.as3D(t,t,3)}if(s instanceof w.getEnv().Canvas)return J.browser.fromPixels(Vr(s,t,e));throw new Error(`toBatchTensor - at batchIdx ${a}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${s}`)});return J.stack(r.map(a=>J.cast(a,"float32"))).as4D(this.batchSize,t,t,3)})}};async function E(o){if(o instanceof bt)return o;let t=Array.isArray(o)?o:[o];if(!t.length)throw new Error("toNetInput - empty array passed as input");let e=n=>Array.isArray(o)?` at input index ${n}:`:"",r=t.map(Ht);return r.forEach((n,a)=>{if(!qe(n)&&!ht(n)&&!z(n))throw typeof t[a]=="string"?new Error(`toNetInput -${e(a)} string passed, but could not resolve HTMLElement for element id ${t[a]}`):new Error(`toNetInput -${e(a)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(z(n)){let s=n.shape[0];if(s!==1)throw new Error(`toNetInput -${e(a)} tf.Tensor4D with batchSize ${s} passed, but not supported in input array`)}}),await Promise.all(r.map(n=>qe(n)&&Yr(n))),new bt(r,Array.isArray(o))}async function se(o,t){let{Canvas:e}=w.getEnv(),r=o;if(!(o instanceof e)){let s=await E(o);if(s.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let i=s.getInput(0);r=i instanceof e?i:await zr(i)}let n=$(r);return t.map(s=>s instanceof M?s.forSize(r.width,r.height).box.floor():s).map(s=>s.clipAtImageBorders(r.width,r.height)).map(({x:s,y:i,width:c,height:m})=>{let p=ae({width:c,height:m});return $(p).putImageData(n.getImageData(s,i,c,m),0,0),p})}var Ze=b(g());async function ie(o,t){if(!ht(o)&&!z(o))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(z(o)&&o.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return Ze.tidy(()=>{let[e,r,n]=o.shape.slice(z(o)?1:0);return t.map(i=>i instanceof M?i.forSize(r,e).box:i).map(i=>i.clipAtImageBorders(r,e)).map(({x:i,y:c,width:m,height:p})=>Ze.slice3d(o.as3D(e,r,n),[c,i,0],[p,m,n]))})}async function Gt(o,t){let{fetch:e}=w.getEnv(),r=await e(o,t);if(!(r.status<400))throw new Error(`failed to fetch: (${r.status}) ${r.statusText}, from url: ${r.url}`);return r}async function Mn(o){let t=await Gt(o),e=await t.blob();if(!e.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${e.type}, for url: ${t.url}`);return Gr(e)}async function Ur(o){return(await Gt(o)).json()}async function Cn(o){return new Float32Array(await(await Gt(o)).arrayBuffer())}var Fo=b(g());function Ke(o,t){let e=`${t}-weights_manifest.json`;if(!o)return{modelBaseUri:"",manifestUri:e};if(o==="/")return{modelBaseUri:"/",manifestUri:`/${e}`};let r=o.startsWith("http://")?"http://":o.startsWith("https://")?"https://":"";o=o.replace(r,"");let n=o.split("/").filter(i=>i),a=o.endsWith(".json")?n[n.length-1]:e,s=r+(o.endsWith(".json")?n.slice(0,n.length-1):n).join("/");return s=o.startsWith("/")?`/${s}`:s,{modelBaseUri:s,manifestUri:s==="/"?`/${a}`:`${s}/${a}`}}async function Xr(o,t){let{manifestUri:e,modelBaseUri:r}=Ke(o,t),n=await Ur(e);return Fo.io.loadWeights(n,r)}function Nn(o,t,e=!1){let{width:r,height:n}=e?Yt(t):t;return o.width=r,o.height=n,{width:r,height:n}}var Nt=b(g());var gt=b(g());var S=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:e,objProp:r}=this.traversePropertyPath(t);return e[r]}reassignParamFromPath(t,e){let{obj:r,objProp:n}=this.traversePropertyPath(t);r[n].dispose(),r[n]=e}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof gt.Variable)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof gt.Variable))}variable(){this.getFrozenParams().forEach(({path:t,tensor:e})=>{this.reassignParamFromPath(t,e.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:e})=>{let r=gt.tensor(e.dataSync());e.dispose(),this.reassignParamFromPath(t,r)})}dispose(t=!0){this.getParamList().forEach(e=>{if(t&&e.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${e.path}`);e.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,e)=>t.concat(e)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let e=await Xr(t,this.getDefaultModelName());this.loadFromWeightMap(e)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:e}=w.getEnv(),{manifestUri:r,modelBaseUri:n}=Ke(t,this.getDefaultModelName()),a=m=>Promise.all(m.map(p=>e(p).then(d=>d.buffer))),s=gt.io.weightsLoaderFactory(a),i=JSON.parse((await e(r)).toString()),c=await s(i,n);this.loadFromWeightMap(c)}loadFromWeightMap(t){let{paramMappings:e,params:r}=this.extractParamsFromWeightMap(t);this._paramMappings=e,this._params=r}extractWeights(t){let{paramMappings:e,params:r}=this.extractParams(t);this._paramMappings=e,this._params=r}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let e=t.split("/").reduce((a,s)=>{if(!a.nextObj.hasOwnProperty(s))throw new Error(`traversePropertyPath - object does not have property ${s}, for path ${t}`);return{obj:a.nextObj,objProp:s,nextObj:a.nextObj[s]}},{nextObj:this.params}),{obj:r,objProp:n}=e;if(!r||!n||!(r[n]instanceof gt.Tensor))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:r,objProp:n}}};var C=b(g());var ce=b(g());function O(o,t,e){return ce.tidy(()=>{let r=ce.separableConv2d(o,t.depthwise_filter,t.pointwise_filter,e,"same");return r=ce.add(r,t.bias),r})}function Qe(o,t,e=!1){return C.tidy(()=>{let r=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,[2,2],"same"),t.conv0.bias):O(o,t.conv0,[2,2])),n=O(r,t.conv1,[1,1]),a=C.relu(C.add(r,n)),s=O(a,t.conv2,[1,1]);return C.relu(C.add(r,C.add(n,s)))})}function ke(o,t,e=!1,r=!0){return C.tidy(()=>{let n=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,r?[2,2]:[1,1],"same"),t.conv0.bias):O(o,t.conv0,r?[2,2]:[1,1])),a=O(n,t.conv1,[1,1]),s=C.relu(C.add(n,a)),i=O(s,t.conv2,[1,1]),c=C.relu(C.add(n,C.add(a,i))),m=O(c,t.conv3,[1,1]);return C.relu(C.add(n,C.add(a,C.add(i,m))))})}var Ct=b(g());function zt(o,t,e="same",r=!1){return Ct.tidy(()=>{let n=Ct.add(Ct.conv2d(o,t.filters,[1,1],e),t.bias);return r?Ct.relu(n):n})}function W(o,t){Object.keys(o).forEach(e=>{t.some(r=>r.originalPath===e)||o[e].dispose()})}var tr=b(g());function me(o,t){return(e,r,n,a)=>{let s=tr.tensor4d(o(e*r*n*n),[n,n,e,r]),i=tr.tensor1d(o(r));return t.push({paramPath:`${a}/filters`},{paramPath:`${a}/bias`}),{filters:s,bias:i}}}var er=b(g());function rr(o,t){return(e,r,n)=>{let a=er.tensor2d(o(e*r),[e,r]),s=er.tensor1d(o(r));return t.push({paramPath:`${n}/weights`},{paramPath:`${n}/bias`}),{weights:a,bias:s}}}var Se=b(g());var or=class{constructor(t,e,r){this.depthwise_filter=t;this.pointwise_filter=e;this.bias=r}};function pe(o,t){return(e,r,n)=>{let a=Se.tensor4d(o(3*3*e),[3,3,e,1]),s=Se.tensor4d(o(e*r),[1,1,e,r]),i=Se.tensor1d(o(r));return t.push({paramPath:`${n}/depthwise_filter`},{paramPath:`${n}/pointwise_filter`},{paramPath:`${n}/bias`}),new or(a,s,i)}}function de(o){return t=>{let e=o(`${t}/depthwise_filter`,4),r=o(`${t}/pointwise_filter`,4),n=o(`${t}/bias`,1);return new or(e,r,n)}}function j(o,t){return(e,r,n)=>{let a=o[e];if(!Rt(a,r))throw new Error(`expected weightMap[${e}] to be a Tensor${r}D, instead have ${a}`);return t.push({originalPath:e,paramPath:n||e}),a}}function B(o){let t=o;function e(n){let a=t.slice(0,n);return t=t.slice(n),a}function r(){return t}return{extractWeights:e,getRemainingWeights:r}}function nr(o,t){let e=me(o,t),r=pe(o,t);function n(s,i,c,m=!1){let p=m?e(s,i,3,`${c}/conv0`):r(s,i,`${c}/conv0`),d=r(i,i,`${c}/conv1`),u=r(i,i,`${c}/conv2`);return{conv0:p,conv1:d,conv2:u}}function a(s,i,c,m=!1){let{conv0:p,conv1:d,conv2:u}=n(s,i,c,m),f=r(i,i,`${c}/conv3`);return{conv0:p,conv1:d,conv2:u,conv3:f}}return{extractDenseBlock3Params:n,extractDenseBlock4Params:a}}function To(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock4Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2"),c=n(128,256,"dense3");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i,dense3:c}}}function ar(o){return t=>{let e=o(`${t}/filters`,4),r=o(`${t}/bias`,1);return{filters:e,bias:r}}}function sr(o,t){let e=j(o,t),r=ar(e),n=de(e);function a(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`);return{conv0:m,conv1:p,conv2:d}}function s(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`),u=n(`${i}/conv3`);return{conv0:m,conv1:p,conv2:d,conv3:u}}return{extractDenseBlock3Params:a,extractDenseBlock4Params:s}}function Po(o){let t=[],{extractDenseBlock4Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2"),dense3:e("dense3")};return W(o,t),{params:r,paramMappings:t}}var Ae=class extends S{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceFeatureExtractor - load model before inference");return Nt.tidy(()=>{let r=Nt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Nt.scalar(255)),s=ke(a,e.dense0,!0);return s=ke(s,e.dense1),s=ke(s,e.dense2),s=ke(s,e.dense3),s=Nt.avgPool(s,[7,7],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return Po(t)}extractParams(t){return To(t)}};var Do=b(g());var ue=b(g());function We(o,t){return ue.tidy(()=>ue.add(ue.matMul(o,t.weights),t.bias))}function _o(o,t,e){let r=[],{extractWeights:n,getRemainingWeights:a}=B(o),i=rr(n,r)(t,e,"fc");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:r,params:{fc:i}}}function wo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:r("fc")};return W(o,t),{params:n,paramMappings:t}}function ir(o){let t={},e={};return Object.keys(o).forEach(r=>{let n=r.startsWith("fc")?e:t;n[r]=o[r]}),{featureExtractorMap:t,classifierMap:e}}var Be=class extends S{constructor(t,e){super(t);this._faceFeatureExtractor=e}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return Do.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t;return We(r.as2D(r.shape[0],-1),e.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return _o(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),wo(r)}extractParams(t){let e=this.getClassifierChannelsIn(),r=this.getClassifierChannelsOut(),n=r*e+r,a=t.slice(0,t.length-n),s=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(s)}};var Jr=["neutral","happy","sad","angry","fearful","disgusted","surprised"],It=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Jr.forEach((e,r)=>{this[e]=t[r]})}asSortedArray(){return Jr.map(t=>({expression:t,probability:this[t]})).sort((t,e)=>e.probability-t.probability)}};var cr=class extends Be{constructor(t=new Ae){super("FaceExpressionNet",t)}forwardInput(t){return fe.tidy(()=>fe.softmax(this.runNet(t)))}async forward(t){return this.forwardInput(await E(t))}async predictExpressions(t){let e=await E(t),r=await this.forwardInput(e),n=await Promise.all(fe.unstack(r).map(async s=>{let i=await s.data();return s.dispose(),i}));r.dispose();let a=n.map(s=>new It(s));return e.isBatchInput?a:a[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function qr(o){return o.expressions instanceof It}function mr(o,t){return{...o,...{expressions:t}}}function In(o,t,e=.1,r){(Array.isArray(t)?t:[t]).forEach(a=>{let s=a instanceof It?a:qr(a)?a.expressions:void 0;if(!s)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let c=s.asSortedArray().filter(d=>d.probability>e),m=pt(a)?a.detection.box.bottomLeft:r||new x(0,0);new Mt(c.map(d=>`${d.expression} (${$t(d.probability)})`),m).draw(o)})}function Vt(o){return pt(o)&&o.landmarks instanceof V&&o.unshiftedLandmarks instanceof V&&o.alignedRect instanceof M}function le(o,t){let{box:e}=o.detection,r=t.shiftBy(e.x,e.y),n=r.align(),{imageDims:a}=o.detection,s=new M(o.detection.score,n.rescale(a.reverse()),a);return{...o,...{landmarks:r,unshiftedLandmarks:t,alignedRect:s}}}var Zr=class{constructor(t={}){let{drawLines:e=!0,drawPoints:r=!0,lineWidth:n,lineColor:a,pointSize:s,pointColor:i}=t;this.drawLines=e,this.drawPoints=r,this.lineWidth=n||1,this.pointSize=s||2,this.lineColor=a||"rgba(0, 255, 255, 1)",this.pointColor=i||"rgba(255, 0, 255, 1)"}},Kr=class{constructor(t,e={}){this.faceLandmarks=t,this.options=new Zr(e)}draw(t){let e=$(t),{drawLines:r,drawPoints:n,lineWidth:a,lineColor:s,pointSize:i,pointColor:c}=this.options;if(r&&this.faceLandmarks instanceof ne&&(e.strokeStyle=s,e.lineWidth=a,lt(e,this.faceLandmarks.getJawOutline()),lt(e,this.faceLandmarks.getLeftEyeBrow()),lt(e,this.faceLandmarks.getRightEyeBrow()),lt(e,this.faceLandmarks.getNose()),lt(e,this.faceLandmarks.getLeftEye(),!0),lt(e,this.faceLandmarks.getRightEye(),!0),lt(e,this.faceLandmarks.getMouth(),!0)),n){e.strokeStyle=c,e.fillStyle=c;let m=p=>{e.beginPath(),e.arc(p.x,p.y,i,0,2*Math.PI),e.fill()};this.faceLandmarks.positions.forEach(m)}}};function Ln(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof V?r:Vt(r)?r.landmarks:void 0;if(!n)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new Kr(n).draw(o)})}var Eo="0.11.6";var ut=b(g());var I=b(g());function kn(o,t){let e=me(o,t),r=pe(o,t);function n(s,i,c){let m=r(s,i,`${c}/separable_conv0`),p=r(i,i,`${c}/separable_conv1`),d=e(s,i,1,`${c}/expansion_conv`);return{separable_conv0:m,separable_conv1:p,expansion_conv:d}}function a(s,i){let c=r(s,s,`${i}/separable_conv0`),m=r(s,s,`${i}/separable_conv1`),p=r(s,s,`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:e,extractSeparableConvParams:r,extractReductionBlockParams:n,extractMainBlockParams:a}}function Mo(o,t){let e=[],{extractWeights:r,getRemainingWeights:n}=B(o),{extractConvParams:a,extractSeparableConvParams:s,extractReductionBlockParams:i,extractMainBlockParams:c}=kn(r,e),m=a(3,32,3,"entry_flow/conv_in"),p=i(32,64,"entry_flow/reduction_block_0"),d=i(64,128,"entry_flow/reduction_block_1"),u={conv_in:m,reduction_block_0:p,reduction_block_1:d},f={};ct(t,0,1).forEach(y=>{f[`main_block_${y}`]=c(128,`middle_flow/main_block_${y}`)});let v=i(128,256,"exit_flow/reduction_block"),_=s(256,512,"exit_flow/separable_conv"),h={reduction_block:v,separable_conv:_};if(n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{paramMappings:e,params:{entry_flow:u,middle_flow:f,exit_flow:h}}}function Sn(o,t){let e=j(o,t),r=ar(e),n=de(e);function a(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=r(`${i}/expansion_conv`);return{separable_conv0:c,separable_conv1:m,expansion_conv:p}}function s(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=n(`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}}function Co(o,t){let e=[],{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}=Sn(o,e),i=r("entry_flow/conv_in"),c=a("entry_flow/reduction_block_0"),m=a("entry_flow/reduction_block_1"),p={conv_in:i,reduction_block_0:c,reduction_block_1:m},d={};ct(t,0,1).forEach(_=>{d[`main_block_${_}`]=s(`middle_flow/main_block_${_}`)});let u=a("exit_flow/reduction_block"),f=n("exit_flow/separable_conv"),v={reduction_block:u,separable_conv:f};return W(o,e),{params:{entry_flow:p,middle_flow:d,exit_flow:v},paramMappings:e}}function No(o,t,e){return I.add(I.conv2d(o,t.filters,e,"same"),t.bias)}function to(o,t,e=!0){let r=e?I.relu(o):o;return r=O(r,t.separable_conv0,[1,1]),r=O(I.relu(r),t.separable_conv1,[1,1]),r=I.maxPool(r,[3,3],[2,2],"same"),r=I.add(r,No(o,t.expansion_conv,[2,2])),r}function An(o,t){let e=O(I.relu(o),t.separable_conv0,[1,1]);return e=O(I.relu(e),t.separable_conv1,[1,1]),e=O(I.relu(e),t.separable_conv2,[1,1]),e=I.add(e,o),e}var eo=class extends S{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyXception - load model before inference");return I.tidy(()=>{let r=I.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(I.scalar(256)),s=I.relu(No(a,e.entry_flow.conv_in,[2,2]));return s=to(s,e.entry_flow.reduction_block_0,!1),s=to(s,e.entry_flow.reduction_block_1),ct(this._numMainBlocks,0,1).forEach(i=>{s=An(s,e.middle_flow[`main_block_${i}`])}),s=to(s,e.exit_flow.reduction_block),s=I.relu(O(s,e.exit_flow.separable_conv,[1,1])),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return Co(t,this._numMainBlocks)}extractParams(t){return Mo(t,this._numMainBlocks)}};function Io(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),n=rr(e,t),a=n(512,1,"fc/age"),s=n(512,2,"fc/gender");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{fc:{age:a,gender:s}}}}function Lo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:{age:r("fc/age"),gender:r("fc/gender")}};return W(o,t),{params:n,paramMappings:t}}var vt;(function(o){o.FEMALE="female",o.MALE="male"})(vt||(vt={}));var pr=class extends S{constructor(t=new eo(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return ut.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t,n=ut.avgPool(r,[7,7],[2,2],"valid").as2D(r.shape[0],-1),a=We(n,e.fc.age).as1D(),s=We(n,e.fc.gender);return{age:a,gender:s}})}forwardInput(t){return ut.tidy(()=>{let{age:e,gender:r}=this.runNet(t);return{age:e,gender:ut.softmax(r)}})}async forward(t){return this.forwardInput(await E(t))}async predictAgeAndGender(t){let e=await E(t),r=await this.forwardInput(e),n=ut.unstack(r.age),a=ut.unstack(r.gender),s=n.map((c,m)=>({ageTensor:c,genderTensor:a[m]})),i=await Promise.all(s.map(async({ageTensor:c,genderTensor:m})=>{let p=(await c.data())[0],d=(await m.data())[0],u=d>.5,f=u?vt.MALE:vt.FEMALE,v=u?d:1-d;return c.dispose(),m.dispose(),{age:p,gender:f,genderProbability:v}}));return r.age.dispose(),r.gender.dispose(),e.isBatchInput?i:i[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return Io(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),Lo(r)}extractParams(t){let e=512*1+1+(512*2+2),r=t.slice(0,t.length-e),n=t.slice(t.length-e);return this.faceFeatureExtractor.extractWeights(r),this.extractClassifierParams(n)}};var H=b(g());var Re=class extends Be{postProcess(t,e,r){let n=r.map(({width:s,height:i})=>{let c=e/Math.max(i,s);return{width:s*c,height:i*c}}),a=n.length;return H.tidy(()=>{let s=(d,u)=>H.stack([H.fill([68],d,"float32"),H.fill([68],u,"float32")],1).as2D(1,136).as1D(),i=(d,u)=>{let{width:f,height:v}=n[d];return u(f,v)?Math.abs(f-v)/2:0},c=d=>i(d,(u,f)=>ui(d,(u,f)=>fs(c(u),m(u))))).div(H.stack(Array.from(Array(a),(d,u)=>s(n[u].width,n[u].height))))})}forwardInput(t){return H.tidy(()=>{let e=this.runNet(t);return this.postProcess(e,t.inputSize,t.inputDimensions.map(([r,n])=>({height:r,width:n})))})}async forward(t){return this.forwardInput(await E(t))}async detectLandmarks(t){let e=await E(t),r=H.tidy(()=>H.unstack(this.forwardInput(e))),n=await Promise.all(r.map(async(a,s)=>{let i=Array.from(await a.data()),c=i.filter((p,d)=>ze(d)),m=i.filter((p,d)=>!ze(d));return new ne(Array(68).fill(0).map((p,d)=>new x(c[d],m[d])),{height:e.getInputHeight(s),width:e.getInputWidth(s)})}));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getClassifierChannelsOut(){return 136}};var he=class extends Re{constructor(t=new Ae){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};var Lt=b(g());function ko(o){let t=[],{extractDenseBlock3Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2")};return W(o,t),{params:r,paramMappings:t}}function So(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock3Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i}}}var ro=class extends S{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyFaceFeatureExtractor - load model before inference");return Lt.tidy(()=>{let r=Lt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Lt.scalar(255)),s=Qe(a,e.dense0,!0);return s=Qe(s,e.dense1),s=Qe(s,e.dense2),s=Lt.avgPool(s,[14,14],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return ko(t)}extractParams(t){return So(t)}};var dr=class extends Re{constructor(t=new ro){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Ao=class extends he{};var U=b(g());var xe=b(g());var ur=b(g());function Wo(o,t){return ur.add(ur.mul(o,t.weights),t.biases)}function oo(o,t,e,r,n="same"){let{filters:a,bias:s}=t.conv,i=xe.conv2d(o,a,e,n);return i=xe.add(i,s),i=Wo(i,t.scale),r?xe.relu(i):i}function Bo(o,t){return oo(o,t,[1,1],!0)}function no(o,t){return oo(o,t,[1,1],!1)}function fr(o,t){return oo(o,t,[2,2],!0,"valid")}var Y=b(g());function Wn(o,t){function e(i,c,m){let p=o(i),d=p.length/(c*m*m);if(Nr(d))throw new Error(`depth has to be an integer: ${d}, weights.length: ${p.length}, numFilters: ${c}, filterSize: ${m}`);return Y.tidy(()=>Y.transpose(Y.tensor4d(p,[c,d,m,m]),[2,3,1,0]))}function r(i,c,m,p){let d=e(i,c,m),u=Y.tensor1d(o(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/bias`}),{filters:d,bias:u}}function n(i,c){let m=Y.tensor1d(o(i)),p=Y.tensor1d(o(i));return t.push({paramPath:`${c}/weights`},{paramPath:`${c}/biases`}),{weights:m,biases:p}}function a(i,c,m,p){let d=r(i,c,m,`${p}/conv`),u=n(c,`${p}/scale`);return{conv:d,scale:u}}function s(i,c,m,p,d=!1){let u=a((d?.5:1)*i,c,m,`${p}/conv1`),f=a(i,c,m,`${p}/conv2`);return{conv1:u,conv2:f}}return{extractConvLayerParams:a,extractResidualLayerParams:s}}function Ro(o){let{extractWeights:t,getRemainingWeights:e}=B(o),r=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=Wn(t,r),s=n(4704,32,7,"conv32_down"),i=a(9216,32,3,"conv32_1"),c=a(9216,32,3,"conv32_2"),m=a(9216,32,3,"conv32_3"),p=a(36864,64,3,"conv64_down",!0),d=a(36864,64,3,"conv64_1"),u=a(36864,64,3,"conv64_2"),f=a(36864,64,3,"conv64_3"),v=a(147456,128,3,"conv128_down",!0),_=a(147456,128,3,"conv128_1"),h=a(147456,128,3,"conv128_2"),y=a(589824,256,3,"conv256_down",!0),T=a(589824,256,3,"conv256_1"),F=a(589824,256,3,"conv256_2"),L=a(589824,256,3,"conv256_down_out"),G=Y.tidy(()=>Y.transpose(Y.tensor2d(t(256*128),[128,256]),[1,0]));if(r.push({paramPath:"fc"}),e().length!==0)throw new Error(`weights remaing after extract: ${e().length}`);return{params:{conv32_down:s,conv32_1:i,conv32_2:c,conv32_3:m,conv64_down:p,conv64_1:d,conv64_2:u,conv64_3:f,conv128_down:v,conv128_1:_,conv128_2:h,conv256_down:y,conv256_1:T,conv256_2:F,conv256_down_out:L,fc:G},paramMappings:r}}function Bn(o,t){let e=j(o,t);function r(s){let i=e(`${s}/scale/weights`,1),c=e(`${s}/scale/biases`,1);return{weights:i,biases:c}}function n(s){let i=e(`${s}/conv/filters`,4),c=e(`${s}/conv/bias`,1),m=r(s);return{conv:{filters:i,bias:c},scale:m}}function a(s){return{conv1:n(`${s}/conv1`),conv2:n(`${s}/conv2`)}}return{extractConvLayerParams:n,extractResidualLayerParams:a}}function $o(o){let t=[],{extractConvLayerParams:e,extractResidualLayerParams:r}=Bn(o,t),n=e("conv32_down"),a=r("conv32_1"),s=r("conv32_2"),i=r("conv32_3"),c=r("conv64_down"),m=r("conv64_1"),p=r("conv64_2"),d=r("conv64_3"),u=r("conv128_down"),f=r("conv128_1"),v=r("conv128_2"),_=r("conv256_down"),h=r("conv256_1"),y=r("conv256_2"),T=r("conv256_down_out"),{fc:F}=o;if(t.push({originalPath:"fc",paramPath:"fc"}),!Cr(F))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${F}`);let L={conv32_down:n,conv32_1:a,conv32_2:s,conv32_3:i,conv64_down:c,conv64_1:m,conv64_2:p,conv64_3:d,conv128_down:u,conv128_1:f,conv128_2:v,conv256_down:_,conv256_1:h,conv256_2:y,conv256_down_out:T,fc:F};return W(o,t),{params:L,paramMappings:t}}var R=b(g());function nt(o,t){let e=Bo(o,t.conv1);return e=no(e,t.conv2),e=R.add(e,o),e=R.relu(e),e}function $e(o,t){let e=fr(o,t.conv1);e=no(e,t.conv2);let r=R.avgPool(o,2,2,"valid"),n=R.zeros(r.shape),a=r.shape[3]!==e.shape[3];if(r.shape[1]!==e.shape[1]||r.shape[2]!==e.shape[2]){let i=[...e.shape];i[1]=1;let c=R.zeros(i);e=R.concat([e,c],1);let m=[...e.shape];m[2]=1;let p=R.zeros(m);e=R.concat([e,p],2)}return r=a?R.concat([r,n],3):r,e=R.add(r,e),e=R.relu(e),e}var be=class extends S{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceRecognitionNet - load model before inference");return U.tidy(()=>{let r=U.cast(t.toBatchTensor(150,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(U.scalar(256)),s=fr(a,e.conv32_down);s=U.maxPool(s,3,2,"valid"),s=nt(s,e.conv32_1),s=nt(s,e.conv32_2),s=nt(s,e.conv32_3),s=$e(s,e.conv64_down),s=nt(s,e.conv64_1),s=nt(s,e.conv64_2),s=nt(s,e.conv64_3),s=$e(s,e.conv128_down),s=nt(s,e.conv128_1),s=nt(s,e.conv128_2),s=$e(s,e.conv256_down),s=nt(s,e.conv256_1),s=nt(s,e.conv256_2),s=$e(s,e.conv256_down_out);let i=s.mean([1,2]);return U.matMul(i,e.fc)})}async forward(t){return this.forwardInput(await E(t))}async computeFaceDescriptor(t){var a;if((a=t==null?void 0:t.shape)==null?void 0:a.some(s=>s<=0))return new Float32Array(128);let e=await E(t),r=U.tidy(()=>U.unstack(this.forwardInput(e))),n=await Promise.all(r.map(s=>s.data()));return r.forEach(s=>s.dispose()),e.isBatchInput?n:n[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return $o(t)}extractParams(t){return Ro(t)}};function Rn(o){let t=new be;return t.extractWeights(o),t}function lr(o,t){return{...o,...{descriptor:t}}}function $n(o){return typeof o.age=="number"}function hr(o,t){return{...o,...{age:t}}}function On(o){return(o.gender===vt.MALE||o.gender===vt.FEMALE)&&ee(o.genderProbability)}function xr(o,t,e){return{...o,...{gender:t,genderProbability:e}}}var st=b(g());var at=b(g());function jn(o,t){function e(c,m){let p=at.tensor4d(o(3*3*c),[3,3,c,1]),d=at.tensor1d(o(c)),u=at.tensor1d(o(c)),f=at.tensor1d(o(c)),v=at.tensor1d(o(c));return t.push({paramPath:`${m}/filters`},{paramPath:`${m}/batch_norm_scale`},{paramPath:`${m}/batch_norm_offset`},{paramPath:`${m}/batch_norm_mean`},{paramPath:`${m}/batch_norm_variance`}),{filters:p,batch_norm_scale:d,batch_norm_offset:u,batch_norm_mean:f,batch_norm_variance:v}}function r(c,m,p,d,u){let f=at.tensor4d(o(c*m*p*p),[p,p,c,m]),v=at.tensor1d(o(m));return t.push({paramPath:`${d}/filters`},{paramPath:`${d}/${u?"batch_norm_offset":"bias"}`}),{filters:f,bias:v}}function n(c,m,p,d){let{filters:u,bias:f}=r(c,m,p,d,!0);return{filters:u,batch_norm_offset:f}}function a(c,m,p){let d=e(c,`${p}/depthwise_conv`),u=n(c,m,1,`${p}/pointwise_conv`);return{depthwise_conv:d,pointwise_conv:u}}function s(){let c=n(3,32,3,"mobilenetv1/conv_0"),m=a(32,64,"mobilenetv1/conv_1"),p=a(64,128,"mobilenetv1/conv_2"),d=a(128,128,"mobilenetv1/conv_3"),u=a(128,256,"mobilenetv1/conv_4"),f=a(256,256,"mobilenetv1/conv_5"),v=a(256,512,"mobilenetv1/conv_6"),_=a(512,512,"mobilenetv1/conv_7"),h=a(512,512,"mobilenetv1/conv_8"),y=a(512,512,"mobilenetv1/conv_9"),T=a(512,512,"mobilenetv1/conv_10"),F=a(512,512,"mobilenetv1/conv_11"),L=a(512,1024,"mobilenetv1/conv_12"),G=a(1024,1024,"mobilenetv1/conv_13");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:f,conv_6:v,conv_7:_,conv_8:h,conv_9:y,conv_10:T,conv_11:F,conv_12:L,conv_13:G}}function i(){let c=n(1024,256,1,"prediction_layer/conv_0"),m=n(256,512,3,"prediction_layer/conv_1"),p=n(512,128,1,"prediction_layer/conv_2"),d=n(128,256,3,"prediction_layer/conv_3"),u=n(256,128,1,"prediction_layer/conv_4"),f=n(128,256,3,"prediction_layer/conv_5"),v=n(256,64,1,"prediction_layer/conv_6"),_=n(64,128,3,"prediction_layer/conv_7"),h=r(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=r(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),T=r(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),F=r(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),L=r(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),G=r(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),et=r(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),it=r(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),X=r(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),Pt=r(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),_t=r(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),wt=r(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:f,conv_6:v,conv_7:_,box_predictor_0:{box_encoding_predictor:h,class_predictor:y},box_predictor_1:{box_encoding_predictor:T,class_predictor:F},box_predictor_2:{box_encoding_predictor:L,class_predictor:G},box_predictor_3:{box_encoding_predictor:et,class_predictor:it},box_predictor_4:{box_encoding_predictor:X,class_predictor:Pt},box_predictor_5:{box_encoding_predictor:_t,class_predictor:wt}}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:i}}function Oo(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=jn(e,t),s=n(),i=a(),m={extra_dim:at.tensor3d(e(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{params:{mobilenetv1:s,prediction_layer:i,output_layer:m},paramMappings:t}}function Hn(o,t){let e=j(o,t);function r(m,p,d){let u=e(`${m}/Conv2d_${p}_pointwise/weights`,4,`${d}/filters`),f=e(`${m}/Conv2d_${p}_pointwise/convolution_bn_offset`,1,`${d}/batch_norm_offset`);return{filters:u,batch_norm_offset:f}}function n(m){let p=`mobilenetv1/conv_${m}`,d=`MobilenetV1/Conv2d_${m}_depthwise`,u=`${p}/depthwise_conv`,f=`${p}/pointwise_conv`,v=e(`${d}/depthwise_weights`,4,`${u}/filters`),_=e(`${d}/BatchNorm/gamma`,1,`${u}/batch_norm_scale`),h=e(`${d}/BatchNorm/beta`,1,`${u}/batch_norm_offset`),y=e(`${d}/BatchNorm/moving_mean`,1,`${u}/batch_norm_mean`),T=e(`${d}/BatchNorm/moving_variance`,1,`${u}/batch_norm_variance`);return{depthwise_conv:{filters:v,batch_norm_scale:_,batch_norm_offset:h,batch_norm_mean:y,batch_norm_variance:T},pointwise_conv:r("MobilenetV1",m,f)}}function a(){return{conv_0:r("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:n(1),conv_2:n(2),conv_3:n(3),conv_4:n(4),conv_5:n(5),conv_6:n(6),conv_7:n(7),conv_8:n(8),conv_9:n(9),conv_10:n(10),conv_11:n(11),conv_12:n(12),conv_13:n(13)}}function s(m,p){let d=e(`${m}/weights`,4,`${p}/filters`),u=e(`${m}/biases`,1,`${p}/bias`);return{filters:d,bias:u}}function i(m){let p=s(`Prediction/BoxPredictor_${m}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${m}/box_encoding_predictor`),d=s(`Prediction/BoxPredictor_${m}/ClassPredictor`,`prediction_layer/box_predictor_${m}/class_predictor`);return{box_encoding_predictor:p,class_predictor:d}}function c(){return{conv_0:r("Prediction",0,"prediction_layer/conv_0"),conv_1:r("Prediction",1,"prediction_layer/conv_1"),conv_2:r("Prediction",2,"prediction_layer/conv_2"),conv_3:r("Prediction",3,"prediction_layer/conv_3"),conv_4:r("Prediction",4,"prediction_layer/conv_4"),conv_5:r("Prediction",5,"prediction_layer/conv_5"),conv_6:r("Prediction",6,"prediction_layer/conv_6"),conv_7:r("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:i(0),box_predictor_1:i(1),box_predictor_2:i(2),box_predictor_3:i(3),box_predictor_4:i(4),box_predictor_5:i(5)}}return{extractMobilenetV1Params:a,extractPredictionLayerParams:c}}function jo(o){let t=[],{extractMobilenetV1Params:e,extractPredictionLayerParams:r}=Hn(o,t),n=o["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!ht(n))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${n}`);let a={mobilenetv1:e(),prediction_layer:r(),output_layer:{extra_dim:n}};return W(o,t),{params:a,paramMappings:t}}var yt=b(g());var kt=b(g());function q(o,t,e){return kt.tidy(()=>{let r=kt.conv2d(o,t.filters,e,"same");return r=kt.add(r,t.batch_norm_offset),kt.clipByValue(r,0,6)})}var Yn=.0010000000474974513;function Gn(o,t,e){return yt.tidy(()=>{let r=yt.depthwiseConv2d(o,t.filters,e,"same");return r=yt.batchNorm(r,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Yn),yt.clipByValue(r,0,6)})}function zn(o){return[2,4,6,12].some(t=>t===o)?[2,2]:[1,1]}function Ho(o,t){return yt.tidy(()=>{let e,r=q(o,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((a,s)=>{let i=s+1,c=zn(i);r=Gn(r,a.depthwise_conv,c),r=q(r,a.pointwise_conv,[1,1]),i===11&&(e=r)}),e===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:r,conv11:e}})}function Vn(o,t,e){let r=o.arraySync(),n=Math.min(r[t][0],r[t][2]),a=Math.min(r[t][1],r[t][3]),s=Math.max(r[t][0],r[t][2]),i=Math.max(r[t][1],r[t][3]),c=Math.min(r[e][0],r[e][2]),m=Math.min(r[e][1],r[e][3]),p=Math.max(r[e][0],r[e][2]),d=Math.max(r[e][1],r[e][3]),u=(s-n)*(i-a),f=(p-c)*(d-m);if(u<=0||f<=0)return 0;let v=Math.max(n,c),_=Math.max(a,m),h=Math.min(s,p),y=Math.min(i,d),T=Math.max(h-v,0)*Math.max(y-_,0);return T/(u+f-T)}function Yo(o,t,e,r,n){let a=o.shape[0],s=Math.min(e,a),i=t.map((p,d)=>({score:p,boxIndex:d})).filter(p=>p.score>n).sort((p,d)=>d.score-p.score),c=p=>p<=r?1:0,m=[];return i.forEach(p=>{if(m.length>=s)return;let d=p.score;for(let u=m.length-1;u>=0;--u){let f=Vn(o,p.boxIndex,m[u]);if(f!==0&&(p.score*=c(f),p.score<=n))break}d===p.score&&m.push(p.boxIndex)}),m}var l=b(g());function Un(o){let t=l.unstack(l.transpose(o,[1,0])),e=[l.sub(t[2],t[0]),l.sub(t[3],t[1])],r=[l.add(t[0],l.div(e[0],l.scalar(2))),l.add(t[1],l.div(e[1],l.scalar(2)))];return{sizes:e,centers:r}}function Xn(o,t){let{sizes:e,centers:r}=Un(o),n=l.unstack(l.transpose(t,[1,0])),a=l.div(l.mul(l.exp(l.div(n[2],l.scalar(5))),e[0]),l.scalar(2)),s=l.add(l.mul(l.div(n[0],l.scalar(10)),e[0]),r[0]),i=l.div(l.mul(l.exp(l.div(n[3],l.scalar(5))),e[1]),l.scalar(2)),c=l.add(l.mul(l.div(n[1],l.scalar(10)),e[1]),r[1]);return l.transpose(l.stack([l.sub(s,a),l.sub(c,i),l.add(s,a),l.add(c,i)]),[1,0])}function Go(o,t,e){return l.tidy(()=>{let r=o.shape[0],n=Xn(l.reshape(l.tile(e.extra_dim,[r,1,1]),[-1,4]),l.reshape(o,[-1,4]));n=l.reshape(n,[r,n.shape[0]/r,4]);let a=l.sigmoid(l.slice(t,[0,0,1],[-1,-1,-1])),s=l.slice(a,[0,0,0],[-1,-1,1]);s=l.reshape(s,[r,s.shape[1]]);let i=l.unstack(n),c=l.unstack(s);return{boxes:i,scores:c}})}var je=b(g());var Oe=b(g());function Ut(o,t){return Oe.tidy(()=>{let e=o.shape[0],r=Oe.reshape(zt(o,t.box_encoding_predictor),[e,-1,1,4]),n=Oe.reshape(zt(o,t.class_predictor),[e,-1,3]);return{boxPredictionEncoding:r,classPrediction:n}})}function zo(o,t,e){return je.tidy(()=>{let r=q(o,e.conv_0,[1,1]),n=q(r,e.conv_1,[2,2]),a=q(n,e.conv_2,[1,1]),s=q(a,e.conv_3,[2,2]),i=q(s,e.conv_4,[1,1]),c=q(i,e.conv_5,[2,2]),m=q(c,e.conv_6,[1,1]),p=q(m,e.conv_7,[2,2]),d=Ut(t,e.box_predictor_0),u=Ut(o,e.box_predictor_1),f=Ut(n,e.box_predictor_2),v=Ut(s,e.box_predictor_3),_=Ut(c,e.box_predictor_4),h=Ut(p,e.box_predictor_5),y=je.concat([d.boxPredictionEncoding,u.boxPredictionEncoding,f.boxPredictionEncoding,v.boxPredictionEncoding,_.boxPredictionEncoding,h.boxPredictionEncoding],1),T=je.concat([d.classPrediction,u.classPrediction,f.classPrediction,v.classPrediction,_.classPrediction,h.classPrediction],1);return{boxPredictions:y,classPredictions:T}})}var Z=class{constructor({minConfidence:t,maxResults:e}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=e||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Xt=class extends S{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("SsdMobilenetv1 - load model before inference");return st.tidy(()=>{let r=st.cast(t.toBatchTensor(512,!1),"float32"),n=st.sub(st.mul(r,st.scalar(.007843137718737125)),st.scalar(1)),a=Ho(n,e.mobilenetv1),{boxPredictions:s,classPredictions:i}=zo(a.out,a.conv11,e.prediction_layer);return Go(s,i,e.output_layer)})}async forward(t){return this.forwardInput(await E(t))}async locateFaces(t,e={}){let{maxResults:r,minConfidence:n}=new Z(e),a=await E(t),{boxes:s,scores:i}=this.forwardInput(a),c=s[0],m=i[0];for(let F=1;F{let[L,G]=[Math.max(0,y[F][0]),Math.min(1,y[F][2])].map(X=>X*h),[et,it]=[Math.max(0,y[F][1]),Math.min(1,y[F][3])].map(X=>X*_);return new M(p[F],new oe(et,L,it-et,G-L),{height:a.getInputHeight(0),width:a.getInputWidth(0)})});return c.dispose(),m.dispose(),T}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return jo(t)}extractParams(t){return Oo(t)}};function Vo(o){let t=new Xt;return t.extractWeights(o),t}function Jn(o){return Vo(o)}var Uo=class extends Xt{};var Xo=.4,Jo=[new x(.738768,.874946),new x(2.42204,2.65704),new x(4.30971,7.04493),new x(10.246,4.59428),new x(12.6868,11.8741)],qo=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],Zo=[117.001,114.697,97.404],Ko="tiny_yolov2_model",Qo="tiny_yolov2_separable_conv_model";var N=b(g());var br=o=>typeof o=="number";function ao(o){if(!o)throw new Error(`invalid config: ${o}`);if(typeof o.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${o.withSeparableConvs}`);if(!br(o.iouThreshold)||o.iouThreshold<0||o.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${o.iouThreshold}`);if(!Array.isArray(o.classes)||!o.classes.length||!o.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(o.classes)}`);if(!Array.isArray(o.anchors)||!o.anchors.length||!o.anchors.map(t=>t||{}).every(t=>br(t.x)&&br(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(o.anchors)}`);if(o.meanRgb&&(!Array.isArray(o.meanRgb)||o.meanRgb.length!==3||!o.meanRgb.every(br)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(o.meanRgb)}`)}var Q=b(g());var K=b(g());function ge(o){return K.tidy(()=>{let t=K.mul(o,K.scalar(.10000000149011612));return K.add(K.relu(K.sub(o,t)),t)})}function Ft(o,t){return Q.tidy(()=>{let e=Q.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=Q.conv2d(e,t.conv.filters,[1,1],"valid"),e=Q.sub(e,t.bn.sub),e=Q.mul(e,t.bn.truediv),e=Q.add(e,t.conv.bias),ge(e)})}var St=b(g());function Tt(o,t){return St.tidy(()=>{let e=St.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=St.separableConv2d(e,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),e=St.add(e,t.bias),ge(e)})}var so=b(g());function qn(o,t){let e=me(o,t);function r(s,i){let c=so.tensor1d(o(s)),m=so.tensor1d(o(s));return t.push({paramPath:`${i}/sub`},{paramPath:`${i}/truediv`}),{sub:c,truediv:m}}function n(s,i,c){let m=e(s,i,3,`${c}/conv`),p=r(i,`${c}/bn`);return{conv:m,bn:p}}let a=pe(o,t);return{extractConvParams:e,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}}function tn(o,t,e,r){let{extractWeights:n,getRemainingWeights:a}=B(o),s=[],{extractConvParams:i,extractConvWithBatchNormParams:c,extractSeparableConvParams:m}=qn(n,s),p;if(t.withSeparableConvs){let[d,u,f,v,_,h,y,T,F]=r,L=t.isFirstLayerConv2d?i(d,u,3,"conv0"):m(d,u,"conv0"),G=m(u,f,"conv1"),et=m(f,v,"conv2"),it=m(v,_,"conv3"),X=m(_,h,"conv4"),Pt=m(h,y,"conv5"),_t=T?m(y,T,"conv6"):void 0,wt=F?m(T,F,"conv7"):void 0,te=i(F||T||y,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:te}}else{let[d,u,f,v,_,h,y,T,F]=r,L=c(d,u,"conv0"),G=c(u,f,"conv1"),et=c(f,v,"conv2"),it=c(v,_,"conv3"),X=c(_,h,"conv4"),Pt=c(h,y,"conv5"),_t=c(y,T,"conv6"),wt=c(T,F,"conv7"),te=i(F,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:te}}if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:p,paramMappings:s}}function Zn(o,t){let e=j(o,t);function r(i){let c=e(`${i}/sub`,1),m=e(`${i}/truediv`,1);return{sub:c,truediv:m}}function n(i){let c=e(`${i}/filters`,4),m=e(`${i}/bias`,1);return{filters:c,bias:m}}function a(i){let c=n(`${i}/conv`),m=r(`${i}/bn`);return{conv:c,bn:m}}let s=de(e);return{extractConvParams:n,extractConvWithBatchNormParams:a,extractSeparableConvParams:s}}function en(o,t){let e=[],{extractConvParams:r,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}=Zn(o,e),s;if(t.withSeparableConvs){let i=t.filterSizes&&t.filterSizes.length||9;s={conv0:t.isFirstLayerConv2d?r("conv0"):a("conv0"),conv1:a("conv1"),conv2:a("conv2"),conv3:a("conv3"),conv4:a("conv4"),conv5:a("conv5"),conv6:i>7?a("conv6"):void 0,conv7:i>8?a("conv7"):void 0,conv8:r("conv8")}}else s={conv0:n("conv0"),conv1:n("conv1"),conv2:n("conv2"),conv3:n("conv3"),conv4:n("conv4"),conv5:n("conv5"),conv6:n("conv6"),conv7:n("conv7"),conv8:r("conv8")};return W(o,e),{params:s,paramMappings:e}}var ft=class{constructor({inputSize:t,scoreThreshold:e}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=e||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var io=class extends S{constructor(t){super("TinyYolov2");ao(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,e){let r=Ft(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=Ft(r,e.conv6),r=Ft(r,e.conv7),zt(r,e.conv8,"valid",!1)}runMobilenet(t,e){let r=this.config.isFirstLayerConv2d?ge(zt(t,e.conv0,"valid",!1)):Tt(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=e.conv6?Tt(r,e.conv6):r,r=e.conv7?Tt(r,e.conv7):r,zt(r,e.conv8,"valid",!1)}forwardInput(t,e){let{params:r}=this;if(!r)throw new Error("TinyYolov2 - load model before inference");return N.tidy(()=>{let n=N.cast(t.toBatchTensor(e,!1),"float32");return n=this.config.meanRgb?ot(n,this.config.meanRgb):n,n=n.div(N.scalar(256)),this.config.withSeparableConvs?this.runMobilenet(n,r):this.runTinyYolov2(n,r)})}async forward(t,e){return this.forwardInput(await E(t),e)}async detect(t,e={}){let{inputSize:r,scoreThreshold:n}=new ft(e),a=await E(t),s=await this.forwardInput(a,r),i=N.tidy(()=>N.unstack(s)[0].expandDims()),c={width:a.getInputWidth(0),height:a.getInputHeight(0)},m=await this.extractBoxes(i,a.getReshapedInputDimensions(0),n);s.dispose(),i.dispose();let p=m.map(h=>h.box),d=m.map(h=>h.score),u=m.map(h=>h.classScore),f=m.map(h=>this.config.classes[h.label]);return Sr(p.map(h=>h.rescale(r)),d,this.config.iouThreshold,!0).map(h=>new Dt(d[h],u[h],f[h],p[h],c))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return en(t,this.config)}extractParams(t){let e=this.config.filterSizes||io.DEFAULT_FILTER_SIZES,r=e?e.length:void 0;if(r!==7&&r!==8&&r!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${r} filterSizes in config`);return tn(t,this.config,this.boxEncodingSize,e)}async extractBoxes(t,e,r){let{width:n,height:a}=e,s=Math.max(n,a),i=s/n,c=s/a,m=t.shape[1],p=this.config.anchors.length,[d,u,f]=N.tidy(()=>{let y=t.reshape([m,m,p,this.boxEncodingSize]),T=y.slice([0,0,0,0],[m,m,p,4]),F=y.slice([0,0,0,4],[m,m,p,1]),L=this.withClassScores?N.softmax(y.slice([0,0,0,5],[m,m,p,this.config.classes.length]),3):N.scalar(0);return[T,F,L]}),v=[],_=await u.array(),h=await d.array();for(let y=0;yr){let G=(T+Ee(h[y][T][F][0]))/m*i,et=(y+Ee(h[y][T][F][1]))/m*c,it=Math.exp(h[y][T][F][2])*this.config.anchors[F].x/m*i,X=Math.exp(h[y][T][F][3])*this.config.anchors[F].y/m*c,Pt=G-it/2,_t=et-X/2,wt={row:y,col:T,anchor:F},{classScore:te,label:fo}=this.withClassScores?await this.extractPredictedClass(f,wt):{classScore:1,label:0};v.push({box:new re(Pt,_t,Pt+it,_t+X),score:L,classScore:L*te,label:fo,...wt})}}return d.dispose(),u.dispose(),f.dispose(),v}async extractPredictedClass(t,e){let{row:r,col:n,anchor:a}=e,s=await t.array();return Array(this.config.classes.length).fill(0).map((i,c)=>s[r][n][a][c]).map((i,c)=>({classScore:i,label:c})).reduce((i,c)=>i.classScore>c.classScore?i:c)}},ve=io;ve.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var ye=class extends ve{constructor(t=!0){let e={withSeparableConvs:t,iouThreshold:Xo,classes:["face"],...t?{anchors:qo,meanRgb:Zo}:{anchors:Jo,withClassScores:!0}};super(e)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?Qo:Ko}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function Kn(o,t=!0){let e=new ye(t);return e.extractWeights(o),e}var gr=class extends ft{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var tt=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};var He=b(g());var co=b(g());async function Jt(o,t,e,r,n=({alignedRect:a})=>a){let a=o.map(c=>Vt(c)?n(c):c.detection),s=r||(t instanceof co.Tensor?await ie(t,a):await se(t,a)),i=await e(s);return s.forEach(c=>c instanceof co.Tensor&&c.dispose()),i}async function Fe(o,t,e,r,n){return Jt([o],t,async a=>e(a[0]),r,n)}var rn=.4,on=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],nn=[117.001,114.697,97.404];var Te=class extends ve{constructor(){let t={withSeparableConvs:!0,iouThreshold:rn,classes:["face"],anchors:on,meanRgb:nn,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var P={ssdMobilenetv1:new Xt,tinyFaceDetector:new Te,tinyYolov2:new ye,faceLandmark68Net:new he,faceLandmark68TinyNet:new dr,faceRecognitionNet:new be,faceExpressionNet:new cr,ageGenderNet:new pr},an=(o,t)=>P.ssdMobilenetv1.locateFaces(o,t),Qn=(o,t)=>P.tinyFaceDetector.locateFaces(o,t),ta=(o,t)=>P.tinyYolov2.locateFaces(o,t),sn=o=>P.faceLandmark68Net.detectLandmarks(o),ea=o=>P.faceLandmark68TinyNet.detectLandmarks(o),ra=o=>P.faceRecognitionNet.computeFaceDescriptor(o),oa=o=>P.faceExpressionNet.predictExpressions(o),na=o=>P.ageGenderNet.predictAgeAndGender(o),cn=o=>P.ssdMobilenetv1.load(o),aa=o=>P.tinyFaceDetector.load(o),sa=o=>P.tinyYolov2.load(o),ia=o=>P.faceLandmark68Net.load(o),ca=o=>P.faceLandmark68TinyNet.load(o),ma=o=>P.faceRecognitionNet.load(o),pa=o=>P.faceExpressionNet.load(o),da=o=>P.ageGenderNet.load(o),ua=cn,fa=an,la=sn;var mo=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},we=class extends mo{async run(){let t=await this.parentTask,e=await Jt(t,this.input,async r=>Promise.all(r.map(n=>P.faceExpressionNet.predictExpressions(n))),this.extractedFaces);return t.map((r,n)=>mr(r,e[n]))}withAgeAndGender(){return new Pe(this,this.input)}},De=class extends mo{async run(){let t=await this.parentTask;if(!t)return;let e=await Fe(t,this.input,r=>P.faceExpressionNet.predictExpressions(r),this.extractedFaces);return mr(t,e)}withAgeAndGender(){return new _e(this,this.input)}},Kt=class extends we{withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Qt=class extends De{withAgeAndGender(){return new Zt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var po=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},Pe=class extends po{async run(){let t=await this.parentTask,e=await Jt(t,this.input,async r=>Promise.all(r.map(n=>P.ageGenderNet.predictAgeAndGender(n))),this.extractedFaces);return t.map((r,n)=>{let{age:a,gender:s,genderProbability:i}=e[n];return hr(xr(r,s,i),a)})}withFaceExpressions(){return new we(this,this.input)}},_e=class extends po{async run(){let t=await this.parentTask;if(!t)return;let{age:e,gender:r,genderProbability:n}=await Fe(t,this.input,a=>P.ageGenderNet.predictAgeAndGender(a),this.extractedFaces);return hr(xr(t,r,n),e)}withFaceExpressions(){return new De(this,this.input)}},qt=class extends Pe{withFaceExpressions(){return new Kt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Zt=class extends _e{withFaceExpressions(){return new Qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var vr=class extends tt{constructor(t,e){super();this.parentTask=t;this.input=e}},At=class extends vr{async run(){let t=await this.parentTask;return(await Jt(t,this.input,r=>Promise.all(r.map(n=>P.faceRecognitionNet.computeFaceDescriptor(n))),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}))).map((r,n)=>lr(t[n],r))}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}},Wt=class extends vr{async run(){let t=await this.parentTask;if(!t)return;let e=await Fe(t,this.input,r=>P.faceRecognitionNet.computeFaceDescriptor(r),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}));return lr(t,e)}withFaceExpressions(){return new Qt(this,this.input)}withAgeAndGender(){return new Zt(this,this.input)}};var yr=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.useTinyLandmarkNet=r}get landmarkNet(){return this.useTinyLandmarkNet?P.faceLandmark68TinyNet:P.faceLandmark68Net}},Fr=class extends yr{async run(){let t=await this.parentTask,e=t.map(a=>a.detection),r=this.input instanceof He.Tensor?await ie(this.input,e):await se(this.input,e),n=await Promise.all(r.map(a=>this.landmarkNet.detectLandmarks(a)));return r.forEach(a=>a instanceof He.Tensor&&a.dispose()),t.map((a,s)=>le(a,n[s]))}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Tr=class extends yr{async run(){let t=await this.parentTask;if(!t)return;let{detection:e}=t,r=this.input instanceof He.Tensor?await ie(this.input,[e]):await se(this.input,[e]),n=await this.landmarkNet.detectLandmarks(r[0]);return r.forEach(a=>a instanceof He.Tensor&&a.dispose()),le(t,n)}withFaceExpressions(){return new Qt(this,this.input)}withAgeAndGender(){return new Zt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var Pr=class extends tt{constructor(t,e=new Z){super();this.input=t;this.options=e}},Ye=class extends Pr{async run(){let{input:t,options:e}=this,r=e instanceof gr?n=>P.tinyFaceDetector.locateFaces(n,e):e instanceof Z?n=>P.ssdMobilenetv1.locateFaces(n,e):e instanceof ft?n=>P.tinyYolov2.locateFaces(n,e):null;if(!r)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return r(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let e=await this.run();t(e.map(r=>jt({},r)))})}withFaceLandmarks(t=!1){return new Fr(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new we(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Pe(this.runAndExtendWithFaceDetections(),this.input)}},_r=class extends Pr{async run(){let t=await new Ye(this.input,this.options),e=t[0];return t.forEach(r=>{r.score>e.score&&(e=r)}),e}runAndExtendWithFaceDetection(){return new Promise(async t=>{let e=await this.run();t(e?jt({},e):void 0)})}withFaceLandmarks(t=!1){return new Tr(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new De(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new _e(this.runAndExtendWithFaceDetection(),this.input)}};function ha(o,t=new Z){return new _r(o,t)}function wr(o,t=new Z){return new Ye(o,t)}async function mn(o,t){return wr(o,new Z(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function xa(o,t={}){return wr(o,new ft(t)).withFaceLandmarks().withFaceDescriptors()}var ba=mn;function uo(o,t){if(o.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let e=Array.from(o),r=Array.from(t);return Math.sqrt(e.map((n,a)=>n-r[a]).reduce((n,a)=>n+a**2,0))}var Dr=class{constructor(t,e=.6){this._distanceThreshold=e;let r=Array.isArray(t)?t:[t];if(!r.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let n=1,a=()=>`person ${n++}`;this._labeledDescriptors=r.map(s=>{if(s instanceof xt)return s;if(s instanceof Float32Array)return new xt(a(),[s]);if(s.descriptor&&s.descriptor instanceof Float32Array)return new xt(a(),[s.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,e){return e.map(r=>uo(r,t)).reduce((r,n)=>r+n,0)/(e.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:e,label:r})=>new Me(r,this.computeMeanDistance(t,e))).reduce((e,r)=>e.distancet.toJSON())}}static fromJSON(t){let e=t.labeledDescriptors.map(r=>xt.fromJSON(r));return new Dr(e,t.distanceThreshold)}};function ga(o){let t=new Te;return t.extractWeights(o),t}function pn(o,t){let{width:e,height:r}=new A(t.width,t.height);if(e<=0||r<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:e,height:r})}`);if(Array.isArray(o))return o.map(n=>pn(n,{width:e,height:r}));if(Vt(o)){let n=o.detection.forSize(e,r),a=o.unshiftedLandmarks.forSize(n.box.width,n.box.height);return le(jt(o,n),a)}return pt(o)?jt(o,o.detection.forSize(e,r)):o instanceof V||o instanceof M?o.forSize(e,r):o}var ya=typeof process!="undefined",Fa=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Ta={faceapi:Eo,node:ya,browser:Fa};export{pr as AgeGenderNet,re as BoundingBox,D as Box,tt as ComposableTask,At as ComputeAllFaceDescriptorsTask,vr as ComputeFaceDescriptorsTaskBase,Wt as ComputeSingleFaceDescriptorTask,Fr as DetectAllFaceLandmarksTask,Ye as DetectAllFacesTask,yr as DetectFaceLandmarksTaskBase,Pr as DetectFacesTaskBase,Tr as DetectSingleFaceLandmarksTask,_r as DetectSingleFaceTask,A as Dimensions,Jr as FACE_EXPRESSION_LABELS,M as FaceDetection,Uo as FaceDetectionNet,cr as FaceExpressionNet,It as FaceExpressions,he as FaceLandmark68Net,dr as FaceLandmark68TinyNet,Ao as FaceLandmarkNet,V as FaceLandmarks,bo as FaceLandmarks5,ne as FaceLandmarks68,Me as FaceMatch,Dr as FaceMatcher,be as FaceRecognitionNet,vt as Gender,Ce as LabeledBox,xt as LabeledFaceDescriptors,bt as NetInput,S as NeuralNetwork,Dt as ObjectDetection,x as Point,go as PredictedBox,oe as Rect,Xt as SsdMobilenetv1,Z as SsdMobilenetv1Options,Te as TinyFaceDetector,gr as TinyFaceDetectorOptions,ye as TinyYolov2,ft as TinyYolov2Options,ba as allFaces,mn as allFacesSsdMobilenetv1,xa as allFacesTinyYolov2,Yr as awaitMediaLoaded,Gr as bufferToImage,ra as computeFaceDescriptor,ae as createCanvas,Le as createCanvasFromMedia,Jn as createFaceDetectionNet,Rn as createFaceRecognitionNet,Vo as createSsdMobilenetv1,ga as createTinyFaceDetector,Kn as createTinyYolov2,wr as detectAllFaces,sn as detectFaceLandmarks,ea as detectFaceLandmarksTiny,la as detectLandmarks,ha as detectSingleFace,Qr as draw,w as env,uo as euclideanDistance,hr as extendWithAge,lr as extendWithFaceDescriptor,jt as extendWithFaceDetection,mr as extendWithFaceExpressions,le as extendWithFaceLandmarks,xr as extendWithGender,ie as extractFaceTensors,se as extractFaces,Mn as fetchImage,Ur as fetchJson,Cn as fetchNetWeights,Gt as fetchOrThrow,$ as getContext2dOrThrow,Yt as getMediaDimensions,zr as imageTensorToCanvas,Vr as imageToSquare,vn as inverseSigmoid,Lr as iou,qe as isMediaElement,Ie as isMediaLoaded,$n as isWithAge,pt as isWithFaceDetection,qr as isWithFaceExpressions,Vt as isWithFaceLandmarks,On as isWithGender,da as loadAgeGenderModel,ua as loadFaceDetectionModel,pa as loadFaceExpressionModel,ia as loadFaceLandmarkModel,ca as loadFaceLandmarkTinyModel,ma as loadFaceRecognitionModel,cn as loadSsdMobilenetv1Model,aa as loadTinyFaceDetectorModel,sa as loadTinyYolov2Model,Xr as loadWeightMap,fa as locateFaces,Nn as matchDimensions,kr as minBbox,P as nets,Sr as nonMaxSuppression,ot as normalize,Ar as padToSquare,na as predictAgeAndGender,oa as recognizeFaceExpressions,pn as resizeResults,Ht as resolveInput,gn as shuffleArray,Ee as sigmoid,an as ssdMobilenetv1,va as tf,Qn as tinyFaceDetector,ta as tinyYolov2,E as toNetInput,Mr as utils,ao as validateConfig,Ta as version}; //# sourceMappingURL=face-api.esm-nobundle.js.map diff --git a/dist/face-api.esm-nobundle.js.map b/dist/face-api.esm-nobundle.js.map index cadcc64..c485195 100644 --- a/dist/face-api.esm-nobundle.js.map +++ b/dist/face-api.esm-nobundle.js.map @@ -1,7 +1,7 @@ { "version": 3, "sources": ["../src/tfjs/tf-browser.ts", "../src/env/isNodejs.ts", "../src/index.ts", "../src/draw/index.ts", "../src/draw/drawContour.ts", "../src/utils/index.ts", "../src/classes/Dimensions.ts", "../src/classes/Point.ts", "../src/classes/Box.ts", "../src/classes/BoundingBox.ts", "../src/classes/ObjectDetection.ts", "../src/classes/FaceDetection.ts", "../src/ops/iou.ts", "../src/ops/minBbox.ts", "../src/ops/nonMaxSuppression.ts", "../src/ops/normalize.ts", "../src/ops/padToSquare.ts", "../src/ops/shuffleArray.ts", "../src/ops/index.ts", "../src/classes/Rect.ts", "../src/classes/FaceLandmarks.ts", "../src/classes/FaceLandmarks5.ts", "../src/classes/FaceLandmarks68.ts", "../src/classes/FaceMatch.ts", "../src/classes/LabeledBox.ts", "../src/classes/LabeledFaceDescriptors.ts", "../src/classes/PredictedBox.ts", "../src/factories/WithFaceDetection.ts", "../src/env/createBrowserEnv.ts", "../src/env/createFileSystem.ts", "../src/env/createNodejsEnv.ts", "../src/env/isBrowser.ts", "../src/env/index.ts", "../src/dom/resolveInput.ts", "../src/dom/getContext2dOrThrow.ts", "../src/draw/DrawTextField.ts", "../src/draw/DrawBox.ts", "../src/draw/drawDetections.ts", "../src/faceExpressionNet/FaceExpressionNet.ts", "../src/dom/isMediaLoaded.ts", "../src/dom/awaitMediaLoaded.ts", "../src/dom/bufferToImage.ts", "../src/dom/getMediaDimensions.ts", "../src/dom/createCanvas.ts", "../src/dom/imageTensorToCanvas.ts", "../src/dom/isMediaElement.ts", "../src/dom/NetInput.ts", "../src/dom/imageToSquare.ts", "../src/dom/toNetInput.ts", "../src/dom/extractFaces.ts", "../src/dom/extractFaceTensors.ts", "../src/dom/fetchOrThrow.ts", "../src/dom/fetchImage.ts", "../src/dom/fetchJson.ts", "../src/dom/fetchNetWeights.ts", "../src/dom/loadWeightMap.ts", "../src/common/getModelUris.ts", "../src/dom/matchDimensions.ts", "../src/faceFeatureExtractor/FaceFeatureExtractor.ts", "../src/NeuralNetwork.ts", "../src/faceFeatureExtractor/denseBlock.ts", "../src/common/depthwiseSeparableConv.ts", "../src/common/convLayer.ts", "../src/common/disposeUnusedWeightTensors.ts", "../src/common/extractConvParamsFactory.ts", "../src/common/extractFCParamsFactory.ts", "../src/common/extractSeparableConvParamsFactory.ts", "../src/common/types.ts", "../src/common/extractWeightEntryFactory.ts", "../src/common/extractWeightsFactory.ts", "../src/faceFeatureExtractor/extractorsFactory.ts", "../src/faceFeatureExtractor/extractParams.ts", "../src/common/loadConvParamsFactory.ts", "../src/faceFeatureExtractor/loadParamsFactory.ts", "../src/faceFeatureExtractor/extractParamsFromWeightMap.ts", "../src/faceProcessor/FaceProcessor.ts", "../src/common/fullyConnectedLayer.ts", "../src/faceProcessor/extractParams.ts", "../src/faceProcessor/extractParamsFromWeightMap.ts", "../src/faceProcessor/util.ts", "../src/faceExpressionNet/FaceExpressions.ts", "../src/factories/WithFaceExpressions.ts", "../src/draw/drawFaceExpressions.ts", "../src/factories/WithFaceLandmarks.ts", "../src/draw/DrawFaceLandmarks.ts", "../src/ageGenderNet/AgeGenderNet.ts", "../src/xception/TinyXception.ts", "../src/xception/extractParams.ts", "../src/xception/extractParamsFromWeightMap.ts", "../src/ageGenderNet/extractParams.ts", "../src/ageGenderNet/extractParamsFromWeightMap.ts", "../src/ageGenderNet/types.ts", "../src/faceLandmarkNet/FaceLandmark68NetBase.ts", "../src/faceLandmarkNet/FaceLandmark68Net.ts", "../src/faceFeatureExtractor/TinyFaceFeatureExtractor.ts", "../src/faceFeatureExtractor/extractParamsFromWeightMapTiny.ts", "../src/faceFeatureExtractor/extractParamsTiny.ts", "../src/faceLandmarkNet/FaceLandmark68TinyNet.ts", "../src/faceLandmarkNet/index.ts", "../src/faceRecognitionNet/FaceRecognitionNet.ts", "../src/faceRecognitionNet/convLayer.ts", "../src/faceRecognitionNet/scaleLayer.ts", "../src/faceRecognitionNet/extractParams.ts", "../src/faceRecognitionNet/extractParamsFromWeightMap.ts", "../src/faceRecognitionNet/residualLayer.ts", "../src/faceRecognitionNet/index.ts", "../src/factories/WithFaceDescriptor.ts", "../src/factories/WithAge.ts", "../src/factories/WithGender.ts", "../src/ssdMobilenetv1/SsdMobilenetv1.ts", "../src/ssdMobilenetv1/extractParams.ts", "../src/ssdMobilenetv1/extractParamsFromWeightMap.ts", "../src/ssdMobilenetv1/mobileNetV1.ts", "../src/ssdMobilenetv1/pointwiseConvLayer.ts", "../src/ssdMobilenetv1/nonMaxSuppression.ts", "../src/ssdMobilenetv1/outputLayer.ts", "../src/ssdMobilenetv1/predictionLayer.ts", "../src/ssdMobilenetv1/boxPredictionLayer.ts", "../src/ssdMobilenetv1/SsdMobilenetv1Options.ts", "../src/ssdMobilenetv1/index.ts", "../src/tinyYolov2/const.ts", "../src/tinyYolov2/TinyYolov2Base.ts", "../src/tinyYolov2/config.ts", "../src/tinyYolov2/convWithBatchNorm.ts", "../src/tinyYolov2/leaky.ts", "../src/tinyYolov2/depthwiseSeparableConv.ts", "../src/tinyYolov2/extractParams.ts", "../src/tinyYolov2/extractParamsFromWeightMap.ts", "../src/tinyYolov2/TinyYolov2Options.ts", "../src/tinyYolov2/TinyYolov2.ts", "../src/tinyYolov2/index.ts", "../src/tinyFaceDetector/TinyFaceDetectorOptions.ts", "../src/globalApi/ComposableTask.ts", "../src/globalApi/DetectFaceLandmarksTasks.ts", "../src/globalApi/extractFacesAndComputeResults.ts", "../src/tinyFaceDetector/const.ts", "../src/tinyFaceDetector/TinyFaceDetector.ts", "../src/globalApi/nets.ts", "../src/globalApi/PredictFaceExpressionsTask.ts", "../src/globalApi/PredictAgeAndGenderTask.ts", "../src/globalApi/ComputeFaceDescriptorsTasks.ts", "../src/globalApi/DetectFacesTasks.ts", "../src/globalApi/detectFaces.ts", "../src/globalApi/allFaces.ts", "../src/euclideanDistance.ts", "../src/globalApi/FaceMatcher.ts", "../src/tinyFaceDetector/index.ts", "../src/resizeResults.ts"], - "sourcesContent": ["/* eslint-disable import/no-extraneous-dependencies */\n/* eslint-disable node/no-unpublished-import */\n\n// wrapper to load tfjs in a single place so version can be changed quickly\n\nexport * from '@tensorflow/tfjs/dist/index.js';\nexport * from '@tensorflow/tfjs-backend-wasm';\n", "export function isNodejs(): boolean {\n return typeof global === 'object'\n && typeof require === 'function'\n && typeof module !== 'undefined'\n // issues with gatsby.js: module.exports is undefined\n // && !!module.exports\n && typeof process !== 'undefined' && !!process.version;\n}\n", "import * as tf from '../dist/tfjs.esm';\nimport * as draw from './draw/index';\nimport * as utils from './utils/index';\nimport * as pkg from '../package.json';\n\nexport { tf, draw, utils };\n\nexport * from './ageGenderNet/index';\nexport * from './classes/index';\nexport * from './dom/index';\nexport * from './env/index';\nexport * from './faceExpressionNet/index';\nexport * from './faceLandmarkNet/index';\nexport * from './faceRecognitionNet/index';\nexport * from './factories/index';\nexport * from './globalApi/index';\nexport * from './ops/index';\nexport * from './ssdMobilenetv1/index';\nexport * from './tinyFaceDetector/index';\nexport * from './tinyYolov2/index';\nexport * from './euclideanDistance';\nexport * from './NeuralNetwork';\nexport * from './resizeResults';\n\nconst node = (typeof process !== 'undefined');\n// eslint-disable-next-line no-undef\nconst browser = (typeof navigator !== 'undefined') && (typeof navigator.userAgent !== 'undefined');\nexport const version = { faceapi: pkg.version as string, node, browser };\n", "export * from './drawContour';\nexport * from './drawDetections';\nexport * from './drawFaceExpressions';\nexport * from './DrawBox';\nexport * from './DrawFaceLandmarks';\nexport * from './DrawTextField';\n", "import { Point } from '../classes/index';\n\nexport function drawContour(\n ctx: CanvasRenderingContext2D,\n points: Point[],\n isClosed: boolean = false,\n) {\n ctx.beginPath();\n\n points.slice(1).forEach(({ x, y }, prevIdx) => {\n const from = points[prevIdx];\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(x, y);\n });\n\n if (isClosed) {\n const from = points[points.length - 1];\n const to = points[0];\n if (!from || !to) {\n return;\n }\n\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(to.x, to.y);\n }\n\n ctx.stroke();\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Point } from '../classes/index';\nimport { Dimensions, IDimensions } from '../classes/Dimensions';\n\nexport function isTensor(tensor: any, dim: number) {\n return tensor instanceof tf.Tensor && tensor.shape.length === dim;\n}\n\nexport function isTensor1D(tensor: any): tensor is tf.Tensor1D {\n return isTensor(tensor, 1);\n}\n\nexport function isTensor2D(tensor: any): tensor is tf.Tensor2D {\n return isTensor(tensor, 2);\n}\n\nexport function isTensor3D(tensor: any): tensor is tf.Tensor3D {\n return isTensor(tensor, 3);\n}\n\nexport function isTensor4D(tensor: any): tensor is tf.Tensor4D {\n return isTensor(tensor, 4);\n}\n\nexport function isFloat(num: number) {\n return num % 1 !== 0;\n}\n\nexport function isEven(num: number) {\n return num % 2 === 0;\n}\n\nexport function round(num: number, prec: number = 2) {\n const f = 10 ** prec;\n return Math.floor(num * f) / f;\n}\n\nexport function isDimensions(obj: any): boolean {\n return obj && obj.width && obj.height;\n}\n\nexport function computeReshapedDimensions({ width, height }: IDimensions, inputSize: number) {\n const scale = inputSize / Math.max(height, width);\n return new Dimensions(Math.round(width * scale), Math.round(height * scale));\n}\n\nexport function getCenterPoint(pts: Point[]): Point {\n return pts.reduce((sum, pt) => sum.add(pt), new Point(0, 0))\n .div(new Point(pts.length, pts.length));\n}\n\nexport function range(num: number, start: number, step: number): number[] {\n return Array(num).fill(0).map((_, i) => start + (i * step));\n}\n\nexport function isValidNumber(num: any) {\n // eslint-disable-next-line no-mixed-operators\n return !!num && (num !== Infinity) && (num !== -Infinity) && !Number.isNaN(num) || num === 0;\n}\n\nexport function isValidProbablitiy(num: any) {\n return isValidNumber(num) && num >= 0 && num <= 1.0;\n}\n", "import { isValidNumber } from '../utils/index';\n\nexport interface IDimensions {\n width: number\n height: number\n}\n\nexport class Dimensions implements IDimensions {\n private _width: number\n\n private _height: number\n\n constructor(width: number, height: number) {\n if (!isValidNumber(width) || !isValidNumber(height)) {\n throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({ width, height })}`);\n }\n\n this._width = width;\n this._height = height;\n }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public reverse(): Dimensions {\n return new Dimensions(1 / this.width, 1 / this.height);\n }\n}\n", "export interface IPoint {\n x: number\n y: number\n}\n\nexport class Point implements IPoint {\n private _x: number\n\n private _y: number\n\n constructor(x: number, y: number) {\n this._x = x;\n this._y = y;\n }\n\n get x(): number { return this._x; }\n\n get y(): number { return this._y; }\n\n public add(pt: IPoint): Point {\n return new Point(this.x + pt.x, this.y + pt.y);\n }\n\n public sub(pt: IPoint): Point {\n return new Point(this.x - pt.x, this.y - pt.y);\n }\n\n public mul(pt: IPoint): Point {\n return new Point(this.x * pt.x, this.y * pt.y);\n }\n\n public div(pt: IPoint): Point {\n return new Point(this.x / pt.x, this.y / pt.y);\n }\n\n public abs(): Point {\n return new Point(Math.abs(this.x), Math.abs(this.y));\n }\n\n public magnitude(): number {\n return Math.sqrt((this.x ** 2) + (this.y ** 2));\n }\n\n public floor(): Point {\n return new Point(Math.floor(this.x), Math.floor(this.y));\n }\n}\n", "import { isDimensions, isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { IDimensions } from './Dimensions';\nimport { Point } from './Point';\nimport { IRect } from './Rect';\n\nexport class Box implements IBoundingBox, IRect {\n public static isRect(rect: any): boolean {\n return !!rect && [rect.x, rect.y, rect.width, rect.height].every(isValidNumber);\n }\n\n public static assertIsValidBox(box: any, callee: string, allowNegativeDimensions: boolean = false) {\n if (!Box.isRect(box)) {\n throw new Error(`${callee} - invalid box: ${JSON.stringify(box)}, expected object with properties x, y, width, height`);\n }\n\n if (!allowNegativeDimensions && (box.width < 0 || box.height < 0)) {\n throw new Error(`${callee} - width (${box.width}) and height (${box.height}) must be positive numbers`);\n }\n }\n\n private _x: number\n\n private _y: number\n\n private _width: number\n\n private _height: number\n\n constructor(_box: IBoundingBox | IRect, allowNegativeDimensions: boolean = true) {\n const box = (_box || {}) as any;\n\n const isBbox = [box.left, box.top, box.right, box.bottom].every(isValidNumber);\n const isRect = [box.x, box.y, box.width, box.height].every(isValidNumber);\n\n if (!isRect && !isBbox) {\n throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(box)}`);\n }\n\n const [x, y, width, height] = isRect\n ? [box.x, box.y, box.width, box.height]\n : [box.left, box.top, box.right - box.left, box.bottom - box.top];\n\n Box.assertIsValidBox({\n x, y, width, height,\n }, 'Box.constructor', allowNegativeDimensions);\n\n this._x = x;\n this._y = y;\n this._width = width;\n this._height = height;\n }\n\n public get x(): number { return this._x; }\n\n public get y(): number { return this._y; }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public get left(): number { return this.x; }\n\n public get top(): number { return this.y; }\n\n public get right(): number { return this.x + this.width; }\n\n public get bottom(): number { return this.y + this.height; }\n\n public get area(): number { return this.width * this.height; }\n\n public get topLeft(): Point { return new Point(this.left, this.top); }\n\n public get topRight(): Point { return new Point(this.right, this.top); }\n\n public get bottomLeft(): Point { return new Point(this.left, this.bottom); }\n\n public get bottomRight(): Point { return new Point(this.right, this.bottom); }\n\n public round(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.round(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public floor(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.floor(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public toSquare(): Box {\n let {\n x, y, width, height,\n } = this;\n const diff = Math.abs(width - height);\n if (width < height) {\n x -= (diff / 2);\n width += diff;\n }\n if (height < width) {\n y -= (diff / 2);\n height += diff;\n }\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public rescale(s: IDimensions | number): Box {\n const scaleX = isDimensions(s) ? (s as IDimensions).width : s as number;\n const scaleY = isDimensions(s) ? (s as IDimensions).height : s as number;\n return new Box({\n x: this.x * scaleX,\n y: this.y * scaleY,\n width: this.width * scaleX,\n height: this.height * scaleY,\n });\n }\n\n public pad(padX: number, padY: number): Box {\n const [x, y, width, height] = [\n this.x - (padX / 2),\n this.y - (padY / 2),\n this.width + padX,\n this.height + padY,\n ];\n return new Box({\n x, y, width, height,\n });\n }\n\n public clipAtImageBorders(imgWidth: number, imgHeight: number): Box {\n const {\n x, y, right, bottom,\n } = this;\n const clippedX = Math.max(x, 0);\n const clippedY = Math.max(y, 0);\n\n const newWidth = right - clippedX;\n const newHeight = bottom - clippedY;\n const clippedWidth = Math.min(newWidth, imgWidth - clippedX);\n const clippedHeight = Math.min(newHeight, imgHeight - clippedY);\n\n return (new Box({\n x: clippedX, y: clippedY, width: clippedWidth, height: clippedHeight,\n })).floor();\n }\n\n public shift(sx: number, sy: number): Box {\n const { width, height } = this;\n const x = this.x + sx;\n const y = this.y + sy;\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public padAtBorders(imageHeight: number, imageWidth: number) {\n const w = this.width + 1;\n const h = this.height + 1;\n\n const dx = 1;\n const dy = 1;\n let edx = w;\n let edy = h;\n\n let x = this.left;\n let y = this.top;\n let ex = this.right;\n let ey = this.bottom;\n\n if (ex > imageWidth) {\n edx = -ex + imageWidth + w;\n ex = imageWidth;\n }\n if (ey > imageHeight) {\n edy = -ey + imageHeight + h;\n ey = imageHeight;\n }\n if (x < 1) {\n edy = 2 - x;\n x = 1;\n }\n if (y < 1) {\n edy = 2 - y;\n y = 1;\n }\n\n return {\n dy, edy, dx, edx, y, ey, x, ex, w, h,\n };\n }\n\n public calibrate(region: Box) {\n return new Box({\n left: this.left + (region.left * this.width),\n top: this.top + (region.top * this.height),\n right: this.right + (region.right * this.width),\n bottom: this.bottom + (region.bottom * this.height),\n }).toSquare().round();\n }\n}\n", "import { Box } from './Box';\n\nexport interface IBoundingBox {\n left: number\n top: number\n right: number\n bottom: number\n}\n\nexport class BoundingBox extends Box implements IBoundingBox {\n constructor(left: number, top: number, right: number, bottom: number, allowNegativeDimensions: boolean = false) {\n super({\n left, top, right, bottom,\n }, allowNegativeDimensions);\n }\n}\n", "import { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { IRect, Rect } from './Rect';\n\nexport class ObjectDetection {\n private _score: number\n\n private _classScore: number\n\n private _className: string\n\n private _box: Rect\n\n private _imageDims: Dimensions\n\n constructor(\n score: number,\n classScore: number,\n className: string,\n relativeBox: IRect,\n imageDims: IDimensions,\n ) {\n this._imageDims = new Dimensions(imageDims.width, imageDims.height);\n this._score = score;\n this._classScore = classScore;\n this._className = className;\n this._box = new Box(relativeBox).rescale(this._imageDims);\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n\n public get className(): string { return this._className; }\n\n public get box(): Box { return this._box; }\n\n public get imageDims(): Dimensions { return this._imageDims; }\n\n public get imageWidth(): number { return this.imageDims.width; }\n\n public get imageHeight(): number { return this.imageDims.height; }\n\n public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()); }\n\n public forSize(width: number, height: number): ObjectDetection {\n return new ObjectDetection(\n this.score,\n this.classScore,\n this.className,\n this.relativeBox,\n { width, height },\n );\n }\n}\n", "import { Box } from './Box';\nimport { IDimensions } from './Dimensions';\nimport { ObjectDetection } from './ObjectDetection';\nimport { Rect } from './Rect';\n\nexport interface IFaceDetecion {\n score: number\n box: Box\n}\n\nexport class FaceDetection extends ObjectDetection implements IFaceDetecion {\n constructor(\n score: number,\n relativeBox: Rect,\n imageDims: IDimensions,\n ) {\n super(score, score, '', relativeBox, imageDims);\n }\n\n public forSize(width: number, height: number): FaceDetection {\n const { score, relativeBox, imageDims } = super.forSize(width, height);\n return new FaceDetection(score, relativeBox, imageDims);\n }\n}\n", "import { Box } from '../classes/Box';\n\nexport function iou(box1: Box, box2: Box, isIOU: boolean = true) {\n const width = Math.max(0.0, Math.min(box1.right, box2.right) - Math.max(box1.left, box2.left));\n const height = Math.max(0.0, Math.min(box1.bottom, box2.bottom) - Math.max(box1.top, box2.top));\n const interSection = width * height;\n\n return isIOU\n ? interSection / (box1.area + box2.area - interSection)\n : interSection / Math.min(box1.area, box2.area);\n}\n", "import { BoundingBox, IPoint } from '../classes/index';\n\nexport function minBbox(pts: IPoint[]): BoundingBox {\n const xs = pts.map((pt) => pt.x);\n const ys = pts.map((pt) => pt.y);\n const minX = xs.reduce((min, x) => (x < min ? x : min), Infinity);\n const minY = ys.reduce((min, y) => (y < min ? y : min), Infinity);\n const maxX = xs.reduce((max, x) => (max < x ? x : max), 0);\n const maxY = ys.reduce((max, y) => (max < y ? y : max), 0);\n\n return new BoundingBox(minX, minY, maxX, maxY);\n}\n", "import { Box } from '../classes/Box';\nimport { iou } from './iou';\n\nexport function nonMaxSuppression(\n boxes: Box[],\n scores: number[],\n iouThreshold: number,\n isIOU: boolean = true,\n): number[] {\n let indicesSortedByScore = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .sort((c1, c2) => c1.score - c2.score)\n .map((c) => c.boxIndex);\n\n const pick: number[] = [];\n\n while (indicesSortedByScore.length > 0) {\n const curr = indicesSortedByScore.pop() as number;\n pick.push(curr);\n\n const indices = indicesSortedByScore;\n\n const outputs: number[] = [];\n for (let i = 0; i < indices.length; i++) {\n const idx = indices[i];\n\n const currBox = boxes[curr];\n const idxBox = boxes[idx];\n\n outputs.push(iou(currBox, idxBox, isIOU));\n }\n\n indicesSortedByScore = indicesSortedByScore.filter(\n (_, j) => outputs[j] <= iouThreshold,\n );\n }\n\n return pick;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function normalize(x: tf.Tensor4D, meanRgb: number[]): tf.Tensor4D {\n return tf.tidy(() => {\n const [r, g, b] = meanRgb;\n const avg_r = tf.fill([...x.shape.slice(0, 3), 1], r, 'float32');\n const avg_g = tf.fill([...x.shape.slice(0, 3), 1], g, 'float32');\n const avg_b = tf.fill([...x.shape.slice(0, 3), 1], b, 'float32');\n const avg_rgb = tf.concat([avg_r, avg_g, avg_b], 3);\n\n return tf.sub(x, avg_rgb);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n/**\n * Pads the smaller dimension of an image tensor with zeros, such that width === height.\n *\n * @param imgTensor The image tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The padded tensor with width === height.\n */\nexport function padToSquare(\n imgTensor: tf.Tensor4D,\n isCenterImage: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const [height, width] = imgTensor.shape.slice(1);\n if (height === width) {\n return imgTensor;\n }\n\n const dimDiff = Math.abs(height - width);\n const paddingAmount = Math.round(dimDiff * (isCenterImage ? 0.5 : 1));\n const paddingAxis = height > width ? 2 : 1;\n\n const createPaddingTensor = (paddingAmountLocal: number): tf.Tensor => {\n const paddingTensorShape = imgTensor.shape.slice();\n paddingTensorShape[paddingAxis] = paddingAmountLocal;\n return tf.fill(paddingTensorShape, 0, 'float32');\n };\n\n const paddingTensorAppend = createPaddingTensor(paddingAmount);\n const remainingPaddingAmount = dimDiff - (paddingTensorAppend.shape[paddingAxis] as number);\n\n const paddingTensorPrepend = isCenterImage && remainingPaddingAmount\n ? createPaddingTensor(remainingPaddingAmount)\n : null;\n\n const tensorsToStack = [\n paddingTensorPrepend,\n imgTensor,\n paddingTensorAppend,\n ]\n .filter((t) => !!t)\n // .map((t: tf.Tensor) => t.toFloat()) as tf.Tensor4D[]\n .map((t: tf.Tensor) => tf.cast(t, 'float32')) as tf.Tensor4D[];\n return tf.concat(tensorsToStack, paddingAxis);\n });\n}\n", "export function shuffleArray(inputArray: any[]) {\n const array = inputArray.slice();\n for (let i = array.length - 1; i > 0; i--) {\n const j = Math.floor(Math.random() * (i + 1));\n const x = array[i];\n array[i] = array[j];\n array[j] = x;\n }\n return array;\n}\n", "export * from './iou';\nexport * from './minBbox';\nexport * from './nonMaxSuppression';\nexport * from './normalize';\nexport * from './padToSquare';\nexport * from './shuffleArray';\n\nexport function sigmoid(x: number) {\n return 1 / (1 + Math.exp(-x));\n}\n\nexport function inverseSigmoid(x: number) {\n return Math.log(x / (1 - x));\n}\n", "import { Box } from './Box';\n\nexport interface IRect {\n x: number\n y: number\n width: number\n height: number\n}\n\nexport class Rect extends Box implements IRect {\n constructor(x: number, y: number, width: number, height: number, allowNegativeDimensions: boolean = false) {\n super({\n x, y, width, height,\n }, allowNegativeDimensions);\n }\n}\n", "import { minBbox } from '../ops/index';\nimport { getCenterPoint } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { FaceDetection } from './FaceDetection';\nimport { Point } from './Point';\nimport { IRect, Rect } from './Rect';\n\n// face alignment constants\nconst relX = 0.5;\nconst relY = 0.43;\nconst relScale = 0.45;\n\nexport interface IFaceLandmarks {\n positions: Point[]\n shift: Point\n}\n\nexport class FaceLandmarks implements IFaceLandmarks {\n protected _shift: Point\n\n protected _positions: Point[]\n\n protected _imgDims: Dimensions\n\n constructor(\n relativeFaceLandmarkPositions: Point[],\n imgDims: IDimensions,\n shift: Point = new Point(0, 0),\n ) {\n const { width, height } = imgDims;\n this._imgDims = new Dimensions(width, height);\n this._shift = shift;\n this._positions = relativeFaceLandmarkPositions.map(\n (pt) => pt.mul(new Point(width, height)).add(shift),\n );\n }\n\n public get shift(): Point { return new Point(this._shift.x, this._shift.y); }\n\n public get imageWidth(): number { return this._imgDims.width; }\n\n public get imageHeight(): number { return this._imgDims.height; }\n\n public get positions(): Point[] { return this._positions; }\n\n public get relativePositions(): Point[] {\n return this._positions.map(\n (pt) => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight)),\n );\n }\n\n public forSize(width: number, height: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n { width, height },\n );\n }\n\n public shiftBy(x: number, y: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n this._imgDims,\n new Point(x, y),\n );\n }\n\n public shiftByPoint(pt: Point): T {\n return this.shiftBy(pt.x, pt.y);\n }\n\n /**\n * Aligns the face landmarks after face detection from the relative positions of the faces\n * bounding box, or it's current shift. This function should be used to align the face images\n * after face detection has been performed, before they are passed to the face recognition net.\n * This will make the computed face descriptor more accurate.\n *\n * @param detection (optional) The bounding box of the face or the face detection result. If\n * no argument was passed the position of the face landmarks are assumed to be relative to\n * it's current shift.\n * @returns The bounding box of the aligned face.\n */\n public align(\n detection?: FaceDetection | IRect | IBoundingBox | null,\n options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { },\n ): Box {\n if (detection) {\n const box = detection instanceof FaceDetection\n ? detection.box.floor()\n : new Box(detection);\n\n return this.shiftBy(box.x, box.y).align(null, options);\n }\n\n const { useDlibAlignment, minBoxPadding } = { useDlibAlignment: false, minBoxPadding: 0.2, ...options };\n\n if (useDlibAlignment) {\n return this.alignDlib();\n }\n\n return this.alignMinBbox(minBoxPadding);\n }\n\n private alignDlib(): Box {\n const centers = this.getRefPointsForAlignment();\n\n const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers;\n const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude();\n const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;\n\n const size = Math.floor(eyeToMouthDist / relScale);\n\n const refPoint = getCenterPoint(centers);\n // TODO: pad in case rectangle is out of image bounds\n const x = Math.floor(Math.max(0, refPoint.x - (relX * size)));\n const y = Math.floor(Math.max(0, refPoint.y - (relY * size)));\n\n return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y));\n }\n\n private alignMinBbox(padding: number): Box {\n const box = minBbox(this.positions);\n return box.pad(box.width * padding, box.height * padding);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n throw new Error('getRefPointsForAlignment not implemented by base class');\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks5 extends FaceLandmarks {\n protected getRefPointsForAlignment(): Point[] {\n const pts = this.positions;\n return [\n pts[0],\n pts[1],\n getCenterPoint([pts[3], pts[4]]),\n ];\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks68 extends FaceLandmarks {\n public getJawOutline(): Point[] {\n return this.positions.slice(0, 17);\n }\n\n public getLeftEyeBrow(): Point[] {\n return this.positions.slice(17, 22);\n }\n\n public getRightEyeBrow(): Point[] {\n return this.positions.slice(22, 27);\n }\n\n public getNose(): Point[] {\n return this.positions.slice(27, 36);\n }\n\n public getLeftEye(): Point[] {\n return this.positions.slice(36, 42);\n }\n\n public getRightEye(): Point[] {\n return this.positions.slice(42, 48);\n }\n\n public getMouth(): Point[] {\n return this.positions.slice(48, 68);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n return [\n this.getLeftEye(),\n this.getRightEye(),\n this.getMouth(),\n ].map(getCenterPoint);\n }\n}\n", "import { round } from '../utils/index';\n\nexport interface IFaceMatch {\n label: string\n distance: number\n}\n\nexport class FaceMatch implements IFaceMatch {\n private _label: string\n\n private _distance: number\n\n constructor(label: string, distance: number) {\n this._label = label;\n this._distance = distance;\n }\n\n public get label(): string { return this._label; }\n\n public get distance(): number { return this._distance; }\n\n public toString(withDistance: boolean = true): string {\n return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`;\n }\n}\n", "import { isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { IRect } from './Rect';\n\nexport class LabeledBox extends Box {\n public static assertIsValidLabeledBox(box: any, callee: string) {\n Box.assertIsValidBox(box, callee);\n\n if (!isValidNumber(box.label)) {\n throw new Error(`${callee} - expected property label (${box.label}) to be a number`);\n }\n }\n\n private _label: number\n\n constructor(box: IBoundingBox | IRect | any, label: number) {\n super(box);\n this._label = label;\n }\n\n public get label(): number { return this._label; }\n}\n", "export class LabeledFaceDescriptors {\n private _label: string\n\n private _descriptors: Float32Array[]\n\n constructor(label: string, descriptors: Float32Array[]) {\n if (!(typeof label === 'string')) {\n throw new Error('LabeledFaceDescriptors - constructor expected label to be a string');\n }\n\n if (!Array.isArray(descriptors) || descriptors.some((desc) => !(desc instanceof Float32Array))) {\n throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array');\n }\n\n this._label = label;\n this._descriptors = descriptors;\n }\n\n public get label(): string { return this._label; }\n\n public get descriptors(): Float32Array[] { return this._descriptors; }\n\n public toJSON(): any {\n return {\n label: this.label,\n descriptors: this.descriptors.map((d) => Array.from(d)),\n };\n }\n\n public static fromJSON(json: any): LabeledFaceDescriptors {\n const descriptors = json.descriptors.map((d: any) => new Float32Array(d));\n return new LabeledFaceDescriptors(json.label, descriptors);\n }\n}\n", "import { isValidProbablitiy } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { LabeledBox } from './LabeledBox';\nimport { IRect } from './Rect';\n\nexport class PredictedBox extends LabeledBox {\n public static assertIsValidPredictedBox(box: any, callee: string) {\n LabeledBox.assertIsValidLabeledBox(box, callee);\n\n if (\n !isValidProbablitiy(box.score)\n || !isValidProbablitiy(box.classScore)\n ) {\n throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`);\n }\n }\n\n private _score: number\n\n private _classScore: number\n\n constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {\n super(box, label);\n this._score = score;\n this._classScore = classScore;\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\n\nexport type WithFaceDetection = TSource & {\n detection: FaceDetection\n}\n\nexport function isWithFaceDetection(obj: any): obj is WithFaceDetection<{}> {\n return obj.detection instanceof FaceDetection;\n}\n\nexport function extendWithFaceDetection<\n TSource\n>(\n sourceObj: TSource,\n detection: FaceDetection,\n): WithFaceDetection {\n const extension = { detection };\n return { ...sourceObj, ...extension };\n}\n", "import { Environment } from './types';\n\nexport function createBrowserEnv(): Environment {\n const fetch = window.fetch;\n if (!fetch) throw new Error('fetch - missing fetch implementation for browser environment');\n\n const readFile = () => {\n throw new Error('readFile - filesystem not available for browser environment');\n };\n\n return {\n Canvas: HTMLCanvasElement,\n CanvasRenderingContext2D,\n Image: HTMLImageElement,\n ImageData,\n Video: HTMLVideoElement,\n createCanvasElement: () => document.createElement('canvas'),\n createImageElement: () => document.createElement('img'),\n fetch,\n readFile,\n };\n}\n", "import { FileSystem } from './types';\n\nexport function createFileSystem(fs?: any): FileSystem {\n let requireFsError = '';\n\n if (!fs) {\n try {\n // eslint-disable-next-line global-require\n fs = require('fs');\n } catch (err) {\n requireFsError = err.toString();\n }\n }\n\n const readFile = fs\n ? (filePath: string) => new Promise((resolve, reject) => {\n fs.readFile(filePath, (err: any, buffer: Buffer) => (err ? reject(err) : resolve(buffer)));\n })\n : () => {\n throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`);\n };\n\n return {\n readFile,\n };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { createFileSystem } from './createFileSystem';\nimport { Environment } from './types';\n\nexport function createNodejsEnv(): Environment {\n // eslint-disable-next-line dot-notation\n const Canvas = global['Canvas'] || global.HTMLCanvasElement;\n const Image = global.Image || global.HTMLImageElement;\n\n const createCanvasElement = () => {\n if (Canvas) return new Canvas();\n throw new Error('createCanvasElement - missing Canvas implementation for nodejs environment');\n };\n\n const createImageElement = () => {\n if (Image) return new Image();\n throw new Error('createImageElement - missing Image implementation for nodejs environment');\n };\n\n const fetch = global.fetch;\n // if (!fetch) throw new Error('fetch - missing fetch implementation for nodejs environment');\n\n const fileSystem = createFileSystem();\n\n return {\n Canvas: Canvas || class {},\n CanvasRenderingContext2D: global.CanvasRenderingContext2D || class {},\n Image: Image || class {},\n ImageData: global.ImageData || class {},\n Video: global.HTMLVideoElement || class {},\n createCanvasElement,\n createImageElement,\n fetch,\n ...fileSystem,\n };\n}\n", "export function isBrowser(): boolean {\n return typeof window === 'object'\n && typeof document !== 'undefined'\n && typeof HTMLImageElement !== 'undefined'\n && typeof HTMLCanvasElement !== 'undefined'\n && typeof HTMLVideoElement !== 'undefined'\n && typeof ImageData !== 'undefined'\n && typeof CanvasRenderingContext2D !== 'undefined';\n}\n", "import { createBrowserEnv } from './createBrowserEnv';\nimport { createFileSystem } from './createFileSystem';\nimport { createNodejsEnv } from './createNodejsEnv';\nimport { isBrowser } from './isBrowser';\nimport { isNodejs } from './isNodejs';\nimport { Environment } from './types';\n\nlet environment: Environment | null;\n\nfunction getEnv(): Environment {\n if (!environment) {\n throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()');\n }\n return environment;\n}\n\nfunction setEnv(env: Environment) {\n environment = env;\n}\n\nfunction initialize() {\n // check for isBrowser() first to prevent electron renderer process\n // to be initialized with wrong environment due to isNodejs() returning true\n if (isBrowser()) return setEnv(createBrowserEnv());\n if (isNodejs()) return setEnv(createNodejsEnv());\n return null;\n}\n\nfunction monkeyPatch(env: Partial) {\n if (!environment) {\n initialize();\n }\n\n if (!environment) {\n throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()');\n }\n\n const { Canvas = environment.Canvas, Image = environment.Image } = env;\n environment.Canvas = Canvas;\n environment.Image = Image;\n environment.createCanvasElement = env.createCanvasElement || (() => new Canvas());\n environment.createImageElement = env.createImageElement || (() => new Image());\n\n environment.ImageData = env.ImageData || environment.ImageData;\n environment.Video = env.Video || environment.Video;\n environment.fetch = env.fetch || environment.fetch;\n environment.readFile = env.readFile || environment.readFile;\n}\n\nexport const env = {\n getEnv,\n setEnv,\n initialize,\n createBrowserEnv,\n createFileSystem,\n createNodejsEnv,\n monkeyPatch,\n isBrowser,\n isNodejs,\n};\n\ninitialize();\n\nexport * from './types';\n", "import { env } from '../env/index';\n\nexport function resolveInput(arg: string | any) {\n if (!env.isNodejs() && typeof arg === 'string') {\n return document.getElementById(arg);\n }\n return arg;\n}\n", "import { env } from '../env/index';\nimport { resolveInput } from './resolveInput';\n\nexport function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {\n const { Canvas, CanvasRenderingContext2D } = env.getEnv();\n\n if (canvasArg instanceof CanvasRenderingContext2D) {\n return canvasArg;\n }\n\n const canvas = resolveInput(canvasArg);\n\n if (!(canvas instanceof Canvas)) {\n throw new Error('resolveContext2d - expected canvas to be of instance of Canvas');\n }\n\n const ctx = canvas.getContext('2d');\n if (!ctx) {\n throw new Error('resolveContext2d - canvas 2d context is null');\n }\n\n return ctx;\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IDimensions, IPoint } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { resolveInput } from '../dom/resolveInput';\n\n// eslint-disable-next-line no-shadow\nexport enum AnchorPosition {\n // eslint-disable-next-line no-unused-vars\n TOP_LEFT = 'TOP_LEFT',\n // eslint-disable-next-line no-unused-vars\n TOP_RIGHT = 'TOP_RIGHT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_LEFT = 'BOTTOM_LEFT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_RIGHT = 'BOTTOM_RIGHT'\n}\n\nexport interface IDrawTextFieldOptions {\n anchorPosition?: AnchorPosition\n backgroundColor?: string\n fontColor?: string\n fontSize?: number\n fontStyle?: string\n padding?: number\n}\n\nexport class DrawTextFieldOptions implements IDrawTextFieldOptions {\n public anchorPosition: AnchorPosition\n\n public backgroundColor: string\n\n public fontColor: string\n\n public fontSize: number\n\n public fontStyle: string\n\n public padding: number\n\n constructor(options: IDrawTextFieldOptions = {}) {\n const {\n anchorPosition, backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = options;\n this.anchorPosition = anchorPosition || AnchorPosition.TOP_LEFT;\n this.backgroundColor = backgroundColor || 'rgba(0, 0, 0, 0.5)';\n this.fontColor = fontColor || 'rgba(255, 255, 255, 1)';\n this.fontSize = fontSize || 14;\n this.fontStyle = fontStyle || 'Georgia';\n this.padding = padding || 4;\n }\n}\n\nexport class DrawTextField {\n public text: string[]\n\n public anchor : IPoint\n\n public options: DrawTextFieldOptions\n\n constructor(\n text: string | string[] | DrawTextField,\n anchor: IPoint,\n options: IDrawTextFieldOptions = {},\n ) {\n // eslint-disable-next-line no-nested-ternary\n this.text = typeof text === 'string'\n ? [text]\n : (text instanceof DrawTextField ? text.text : text);\n this.anchor = anchor;\n this.options = new DrawTextFieldOptions(options);\n }\n\n measureWidth(ctx: CanvasRenderingContext2D): number {\n const { padding } = this.options;\n return this.text.map((l) => ctx.measureText(l).width).reduce((w0, w1) => (w0 < w1 ? w1 : w0), 0) + (2 * padding);\n }\n\n measureHeight(): number {\n const { fontSize, padding } = this.options;\n return this.text.length * fontSize + (2 * padding);\n }\n\n getUpperLeft(ctx: CanvasRenderingContext2D, canvasDims?: IDimensions): IPoint {\n const { anchorPosition } = this.options;\n const isShiftLeft = anchorPosition === AnchorPosition.BOTTOM_RIGHT || anchorPosition === AnchorPosition.TOP_RIGHT;\n const isShiftTop = anchorPosition === AnchorPosition.BOTTOM_LEFT || anchorPosition === AnchorPosition.BOTTOM_RIGHT;\n\n const textFieldWidth = this.measureWidth(ctx);\n const textFieldHeight = this.measureHeight();\n const x = (isShiftLeft ? this.anchor.x - textFieldWidth : this.anchor.x);\n const y = isShiftTop ? this.anchor.y - textFieldHeight : this.anchor.y;\n\n // adjust anchor if text box exceeds canvas borders\n if (canvasDims) {\n const { width, height } = canvasDims;\n const newX = Math.max(Math.min(x, width - textFieldWidth), 0);\n const newY = Math.max(Math.min(y, height - textFieldHeight), 0);\n return { x: newX, y: newY };\n }\n return { x, y };\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const canvas = resolveInput(canvasArg);\n const ctx = getContext2dOrThrow(canvas);\n\n const {\n backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = this.options;\n\n ctx.font = `${fontSize}px ${fontStyle}`;\n const maxTextWidth = this.measureWidth(ctx);\n const textHeight = this.measureHeight();\n\n ctx.fillStyle = backgroundColor;\n const upperLeft = this.getUpperLeft(ctx, canvas);\n ctx.fillRect(upperLeft.x, upperLeft.y, maxTextWidth, textHeight);\n\n ctx.fillStyle = fontColor;\n this.text.forEach((textLine, i) => {\n const x = padding + upperLeft.x;\n const y = padding + upperLeft.y + ((i + 1) * fontSize);\n ctx.fillText(textLine, x, y);\n });\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { Box, IBoundingBox, IRect } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport {\n AnchorPosition, DrawTextField, DrawTextFieldOptions, IDrawTextFieldOptions,\n} from './DrawTextField';\n\nexport interface IDrawBoxOptions {\n boxColor?: string\n lineWidth?: number\n drawLabelOptions?: IDrawTextFieldOptions\n label?: string\n}\n\nexport class DrawBoxOptions {\n public boxColor: string\n\n public lineWidth: number\n\n public drawLabelOptions: DrawTextFieldOptions\n\n public label?: string\n\n constructor(options: IDrawBoxOptions = {}) {\n const {\n boxColor, lineWidth, label, drawLabelOptions,\n } = options;\n this.boxColor = boxColor || 'rgba(0, 0, 255, 1)';\n this.lineWidth = lineWidth || 2;\n this.label = label;\n\n const defaultDrawLabelOptions = {\n anchorPosition: AnchorPosition.BOTTOM_LEFT,\n backgroundColor: this.boxColor,\n };\n this.drawLabelOptions = new DrawTextFieldOptions({ ...defaultDrawLabelOptions, ...drawLabelOptions });\n }\n}\n\nexport class DrawBox {\n public box: Box\n\n public options: DrawBoxOptions\n\n constructor(\n box: IBoundingBox | IRect,\n options: IDrawBoxOptions = {},\n ) {\n this.box = new Box(box);\n this.options = new DrawBoxOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const { boxColor, lineWidth } = this.options;\n\n const {\n x, y, width, height,\n } = this.box;\n ctx.strokeStyle = boxColor;\n ctx.lineWidth = lineWidth;\n ctx.strokeRect(x, y, width, height);\n\n const { label } = this.options;\n if (label) {\n new DrawTextField([label], { x: x - (lineWidth / 2), y }, this.options.drawLabelOptions).draw(canvasArg);\n }\n }\n}\n", "import { Box, IBoundingBox, IRect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { round } from '../utils/index';\nimport { DrawBox } from './DrawBox';\n\nexport type TDrawDetectionsInput = IRect | IBoundingBox | FaceDetection | WithFaceDetection<{}>\n\nexport function drawDetections(\n canvasArg: string | HTMLCanvasElement,\n detections: TDrawDetectionsInput | Array,\n) {\n const detectionsArray = Array.isArray(detections) ? detections : [detections];\n\n detectionsArray.forEach((det) => {\n // eslint-disable-next-line no-nested-ternary\n const score = det instanceof FaceDetection\n ? det.score\n : (isWithFaceDetection(det) ? det.detection.score : undefined);\n\n // eslint-disable-next-line no-nested-ternary\n const box = det instanceof FaceDetection\n ? det.box\n : (isWithFaceDetection(det) ? det.detection.box : new Box(det));\n\n const label = score ? `${round(score)}` : undefined;\n new DrawBox(box, { label }).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { FaceExpressions } from './FaceExpressions';\n\nexport class FaceExpressionNet extends FaceProcessor {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceExpressionNet', faceFeatureExtractor);\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n return tf.tidy(() => tf.softmax(this.runNet(input)));\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictExpressions(input: TNetInput) {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n const probabilitesByBatch = await Promise.all(tf.unstack(out).map(async (t) => {\n const data = await t.data();\n t.dispose();\n return data;\n }));\n out.dispose();\n\n const predictionsByBatch = probabilitesByBatch\n .map((probabilites) => new FaceExpressions(probabilites as Float32Array));\n\n return netInput.isBatchInput\n ? predictionsByBatch\n : predictionsByBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_expression_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n\n protected getClassifierChannelsOut(): number {\n return 7;\n }\n}\n", "import { env } from '../env/index';\n\nexport function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {\n const { Image, Video } = env.getEnv();\n\n return (media instanceof Image && media.complete)\n || (media instanceof Video && media.readyState >= 3);\n}\n", "import { env } from '../env/index';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {\n // eslint-disable-next-line consistent-return\n return new Promise((resolve, reject) => {\n if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {\n return resolve(null);\n }\n\n function onError(e: Event) {\n if (!e.currentTarget) return;\n // eslint-disable-next-line no-use-before-define\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n reject(e);\n }\n\n function onLoad(e: Event) {\n if (!e.currentTarget) return;\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n resolve(e);\n }\n\n media.addEventListener('load', onLoad);\n media.addEventListener('error', onError);\n });\n}\n", "import { env } from '../env/index';\n\nexport function bufferToImage(buf: Blob): Promise {\n return new Promise((resolve, reject) => {\n if (!(buf instanceof Blob)) reject(new Error('bufferToImage - expected buf to be of type: Blob'));\n const reader = new FileReader();\n reader.onload = () => {\n if (typeof reader.result !== 'string') reject(new Error('bufferToImage - expected reader.result to be a string, in onload'));\n const img = env.getEnv().createImageElement();\n img.onload = () => resolve(img);\n img.onerror = reject;\n img.src = reader.result as string;\n };\n reader.onerror = reject;\n reader.readAsDataURL(buf);\n });\n}\n", "import { Dimensions, IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\n\nexport function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {\n const { Image, Video } = env.getEnv();\n\n if (input instanceof Image) {\n return new Dimensions(input.naturalWidth, input.naturalHeight);\n }\n if (input instanceof Video) {\n return new Dimensions(input.videoWidth, input.videoHeight);\n }\n return new Dimensions(input.width, input.height);\n}\n", "import { IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {\n const { createCanvasElement } = env.getEnv();\n const canvas = createCanvasElement();\n canvas.width = width;\n canvas.height = height;\n return canvas;\n}\n\nexport function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {\n const { ImageData } = env.getEnv();\n\n if (!(media instanceof ImageData) && !isMediaLoaded(media)) {\n throw new Error('createCanvasFromMedia - media has not finished loading yet');\n }\n\n const { width, height } = dims || getMediaDimensions(media);\n const canvas = createCanvas({ width, height });\n\n if (media instanceof ImageData) {\n getContext2dOrThrow(canvas).putImageData(media, 0, 0);\n } else {\n getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height);\n }\n return canvas;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { env } from '../env/index';\nimport { isTensor4D } from '../utils/index';\n\nexport async function imageTensorToCanvas(\n imgTensor: tf.Tensor,\n canvas?: HTMLCanvasElement,\n): Promise {\n const targetCanvas = canvas || env.getEnv().createCanvasElement();\n\n const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0);\n const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt());\n await tf.browser.toPixels(imgTensor3D, targetCanvas);\n\n imgTensor3D.dispose();\n\n return targetCanvas;\n}\n", "import { env } from '../env/index';\n\nexport function isMediaElement(input: any) {\n const { Image, Canvas, Video } = env.getEnv();\n\n return input instanceof Image\n || input instanceof Canvas\n || input instanceof Video;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Dimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { padToSquare } from '../ops/padToSquare';\nimport {\n computeReshapedDimensions, isTensor3D, isTensor4D, range,\n} from '../utils/index';\nimport { createCanvasFromMedia } from './createCanvas';\nimport { imageToSquare } from './imageToSquare';\nimport { TResolvedNetInput } from './types';\n\nexport class NetInput {\n private _imageTensors: Array = []\n\n private _canvases: HTMLCanvasElement[] = []\n\n private _batchSize: number\n\n private _treatAsBatchInput: boolean = false\n\n private _inputDimensions: number[][] = []\n\n private _inputSize: number\n\n constructor(\n inputs: Array,\n treatAsBatchInput: boolean = false,\n ) {\n if (!Array.isArray(inputs)) {\n throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`);\n }\n\n this._treatAsBatchInput = treatAsBatchInput;\n this._batchSize = inputs.length;\n\n inputs.forEach((input, idx) => {\n if (isTensor3D(input)) {\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = input.shape;\n return;\n }\n\n if (isTensor4D(input)) {\n const batchSize = (input as any).shape[0];\n if (batchSize !== 1) {\n throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = (input as any).shape.slice(1);\n return;\n }\n\n const canvas = (input as any) instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input);\n this._canvases[idx] = canvas;\n this._inputDimensions[idx] = [canvas.height, canvas.width, 3];\n });\n }\n\n public get imageTensors(): Array {\n return this._imageTensors;\n }\n\n public get canvases(): HTMLCanvasElement[] {\n return this._canvases;\n }\n\n public get isBatchInput(): boolean {\n return this.batchSize > 1 || this._treatAsBatchInput;\n }\n\n public get batchSize(): number {\n return this._batchSize;\n }\n\n public get inputDimensions(): number[][] {\n return this._inputDimensions;\n }\n\n public get inputSize(): number | undefined {\n return this._inputSize;\n }\n\n public get reshapedInputDimensions(): Dimensions[] {\n return range(this.batchSize, 0, 1).map(\n (_, batchIdx) => this.getReshapedInputDimensions(batchIdx),\n );\n }\n\n public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {\n return this.canvases[batchIdx] || this.imageTensors[batchIdx];\n }\n\n public getInputDimensions(batchIdx: number): number[] {\n return this._inputDimensions[batchIdx];\n }\n\n public getInputHeight(batchIdx: number): number {\n return this._inputDimensions[batchIdx][0];\n }\n\n public getInputWidth(batchIdx: number): number {\n return this._inputDimensions[batchIdx][1];\n }\n\n public getReshapedInputDimensions(batchIdx: number): Dimensions {\n if (typeof this.inputSize !== 'number') {\n throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet');\n }\n\n const width = this.getInputWidth(batchIdx);\n const height = this.getInputHeight(batchIdx);\n return computeReshapedDimensions({ width, height }, this.inputSize);\n }\n\n /**\n * Create a batch tensor from all input canvases and tensors\n * with size [batchSize, inputSize, inputSize, 3].\n *\n * @param inputSize Height and width of the tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The batch tensor.\n */\n public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {\n this._inputSize = inputSize;\n\n return tf.tidy(() => {\n const inputTensors = range(this.batchSize, 0, 1).map((batchIdx) => {\n const input = this.getInput(batchIdx);\n\n if (input instanceof tf.Tensor) {\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n let imgTensor = isTensor4D(input) ? input : input.expandDims();\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n imgTensor = padToSquare(imgTensor, isCenterInputs);\n\n if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {\n imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize]);\n }\n\n return imgTensor.as3D(inputSize, inputSize, 3);\n }\n\n if (input instanceof env.getEnv().Canvas) {\n return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs));\n }\n\n throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`);\n });\n\n // const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)\n const batchTensor = tf.stack(inputTensors.map((t) => tf.cast(t, 'float32'))).as4D(this.batchSize, inputSize, inputSize, 3);\n // const batchTensor = tf.stack(inputTensors.map(t => tf.Tensor.as4D(tf.cast(t, 'float32'))), this.batchSize, inputSize, inputSize, 3);\n\n return batchTensor;\n });\n }\n}\n", "import { env } from '../env/index';\nimport { createCanvas, createCanvasFromMedia } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {\n const { Image, Canvas } = env.getEnv();\n\n if (!(input instanceof Image || input instanceof Canvas)) {\n throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement');\n }\n\n const dims = getMediaDimensions(input);\n const scale = inputSize / Math.max(dims.height, dims.width);\n const width = scale * dims.width;\n const height = scale * dims.height;\n\n const targetCanvas = createCanvas({ width: inputSize, height: inputSize });\n const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input);\n\n const offset = Math.abs(width - height) / 2;\n const dx = centerImage && width < height ? offset : 0;\n const dy = centerImage && height < width ? offset : 0;\n getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height);\n\n return targetCanvas;\n}\n", "import { isTensor3D, isTensor4D } from '../utils/index';\nimport { awaitMediaLoaded } from './awaitMediaLoaded';\nimport { isMediaElement } from './isMediaElement';\nimport { NetInput } from './NetInput';\nimport { resolveInput } from './resolveInput';\nimport { TNetInput } from './types';\n\n/**\n * Validates the input to make sure, they are valid net inputs and awaits all media elements\n * to be finished loading.\n *\n * @param input The input, which can be a media element or an array of different media elements.\n * @returns A NetInput instance, which can be passed into one of the neural networks.\n */\nexport async function toNetInput(inputs: TNetInput): Promise {\n if (inputs instanceof NetInput) {\n return inputs;\n }\n\n const inputArgArray = Array.isArray(inputs)\n ? inputs\n : [inputs];\n\n if (!inputArgArray.length) {\n throw new Error('toNetInput - empty array passed as input');\n }\n\n const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');\n\n const inputArray = inputArgArray.map(resolveInput);\n\n inputArray.forEach((input, i) => {\n if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {\n if (typeof inputArgArray[i] === 'string') {\n throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);\n }\n\n throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);\n }\n\n if (isTensor4D(input)) {\n // if tf.Tensor4D is passed in the input array, the batch size has to be 1\n const batchSize = input.shape[0];\n if (batchSize !== 1) {\n throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n }\n });\n\n // wait for all media elements being loaded\n await Promise.all(\n inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),\n );\n\n return new NetInput(inputArray, Array.isArray(inputs));\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { Rect } from '../classes/Rect';\nimport { env } from '../env/index';\nimport { createCanvas } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { imageTensorToCanvas } from './imageTensorToCanvas';\nimport { toNetInput } from './toNetInput';\nimport { TNetInput } from './types';\n\n/**\n * Extracts the image regions containing the detected faces.\n *\n * @param input The image that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns The Canvases of the corresponding image region for each detected face.\n */\nexport async function extractFaces(\n input: TNetInput,\n detections: Array,\n): Promise {\n const { Canvas } = env.getEnv();\n\n let canvas = input as HTMLCanvasElement;\n\n if (!(input instanceof Canvas)) {\n const netInput = await toNetInput(input);\n\n if (netInput.batchSize > 1) {\n throw new Error('extractFaces - batchSize > 1 not supported');\n }\n\n const tensorOrCanvas = netInput.getInput(0);\n canvas = tensorOrCanvas instanceof Canvas\n ? tensorOrCanvas\n : await imageTensorToCanvas(tensorOrCanvas);\n }\n\n const ctx = getContext2dOrThrow(canvas);\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(canvas.width, canvas.height).box.floor()\n : det),\n )\n .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));\n\n return boxes.map(({\n x, y, width, height,\n }) => {\n const faceImg = createCanvas({ width, height });\n getContext2dOrThrow(faceImg)\n .putImageData(ctx.getImageData(x, y, width, height), 0, 0);\n return faceImg;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isTensor3D, isTensor4D } from '../utils/index';\n\n/**\n * Extracts the tensors of the image regions containing the detected faces.\n * Useful if you want to compute the face descriptors for the face images.\n * Using this method is faster then extracting a canvas for each face and\n * converting them to tensors individually.\n *\n * @param imageTensor The image tensor that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns Tensors of the corresponding image region for each detected face.\n */\nexport async function extractFaceTensors(\n imageTensor: tf.Tensor3D | tf.Tensor4D,\n detections: Array,\n): Promise {\n if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {\n throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D');\n }\n\n if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {\n throw new Error('extractFaceTensors - batchSize > 1 not supported');\n }\n\n return tf.tidy(() => {\n const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0);\n\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(imgWidth, imgHeight).box\n : det),\n )\n .map((box) => box.clipAtImageBorders(imgWidth, imgHeight));\n\n const faceTensors = boxes.map(({\n x, y, width, height,\n }) => tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels]));\n\n return faceTensors;\n });\n}\n", "import { env } from '../env/index';\n\nexport async function fetchOrThrow(\n url: string,\n // eslint-disable-next-line no-undef\n init?: RequestInit,\n): Promise {\n const { fetch } = env.getEnv();\n const res = await fetch(url, init);\n if (!(res.status < 400)) {\n throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`);\n }\n return res;\n}\n", "import { bufferToImage } from './bufferToImage';\nimport { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchImage(uri: string): Promise {\n const res = await fetchOrThrow(uri);\n const blob = await (res).blob();\n\n if (!blob.type.startsWith('image/')) {\n throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`);\n }\n return bufferToImage(blob);\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchJson(uri: string): Promise {\n return (await fetchOrThrow(uri)).json();\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchNetWeights(uri: string): Promise {\n return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer());\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { getModelUris } from '../common/getModelUris';\nimport { fetchJson } from './fetchJson';\n\nexport async function loadWeightMap(\n uri: string | undefined,\n defaultModelName: string,\n): Promise {\n const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName);\n const manifest = await fetchJson(manifestUri);\n // if (manifest['weightsManifest']) manifest = manifest['weightsManifest'];\n return tf.io.loadWeights(manifest, modelBaseUri);\n}\n", "export function getModelUris(uri: string | undefined, defaultModelName: string) {\n const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`;\n\n if (!uri) {\n return {\n modelBaseUri: '',\n manifestUri: defaultManifestFilename,\n };\n }\n\n if (uri === '/') {\n return {\n modelBaseUri: '/',\n manifestUri: `/${defaultManifestFilename}`,\n };\n }\n // eslint-disable-next-line no-nested-ternary\n const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';\n uri = uri.replace(protocol, '');\n\n const parts = uri.split('/').filter((s) => s);\n\n const manifestFile = uri.endsWith('.json')\n ? parts[parts.length - 1]\n : defaultManifestFilename;\n\n let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/');\n modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri;\n\n return {\n modelBaseUri,\n manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`,\n };\n}\n", "import { IDimensions } from '../classes/index';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {\n const { width, height } = useMediaDimensions\n ? getMediaDimensions(reference)\n : reference;\n input.width = width;\n input.height = height;\n return { width, height };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock4 } from './denseBlock';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';\n\nexport class FaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('FaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock4(normalized, params.dense0, true);\n out = denseBlock4(out, params.dense1);\n out = denseBlock4(out, params.dense2);\n out = denseBlock4(out, params.dense3);\n out = tf.avgPool(out, [7, 7], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../dist/tfjs.esm';\n\nimport { ParamMapping } from './common/index';\nimport { getModelUris } from './common/getModelUris';\nimport { loadWeightMap } from './dom/index';\nimport { env } from './env/index';\n\nexport abstract class NeuralNetwork {\n protected _params: TNetParams | undefined = undefined\n\n protected _paramMappings: ParamMapping[] = []\n\n public _name: any;\n\n public get params(): TNetParams | undefined { return this._params; }\n\n public get paramMappings(): ParamMapping[] { return this._paramMappings; }\n\n public get isLoaded(): boolean { return !!this.params; }\n\n public getParamFromPath(paramPath: string): tf.Tensor {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n return obj[objProp];\n }\n\n public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n obj[objProp].dispose();\n obj[objProp] = tensor;\n }\n\n public getParamList() {\n return this._paramMappings.map(({ paramPath }) => ({\n path: paramPath,\n tensor: this.getParamFromPath(paramPath),\n }));\n }\n\n public getTrainableParams() {\n return this.getParamList().filter((param) => param.tensor instanceof tf.Variable);\n }\n\n public getFrozenParams() {\n return this.getParamList().filter((param) => !(param.tensor instanceof tf.Variable));\n }\n\n public variable() {\n this.getFrozenParams().forEach(({ path, tensor }) => {\n this.reassignParamFromPath(path, tensor.variable());\n });\n }\n\n public freeze() {\n this.getTrainableParams().forEach(({ path, tensor: variable }) => {\n const tensor = tf.tensor(variable.dataSync());\n variable.dispose();\n this.reassignParamFromPath(path, tensor);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.getParamList().forEach((param) => {\n if (throwOnRedispose && param.tensor.isDisposed) {\n throw new Error(`param tensor has already been disposed for path ${param.path}`);\n }\n param.tensor.dispose();\n });\n this._params = undefined;\n }\n\n public serializeParams(): Float32Array {\n return new Float32Array(\n this.getParamList()\n .map(({ tensor }) => Array.from(tensor.dataSync()) as number[])\n .reduce((flat, arr) => flat.concat(arr)),\n );\n }\n\n public async load(weightsOrUrl: Float32Array | string | undefined): Promise {\n if (weightsOrUrl instanceof Float32Array) {\n this.extractWeights(weightsOrUrl);\n return;\n }\n\n await this.loadFromUri(weightsOrUrl);\n }\n\n public async loadFromUri(uri: string | undefined) {\n if (uri && typeof uri !== 'string') {\n throw new Error(`${this._name}.loadFromUri - expected model uri`);\n }\n\n const weightMap = await loadWeightMap(uri, this.getDefaultModelName());\n this.loadFromWeightMap(weightMap);\n }\n\n public async loadFromDisk(filePath: string | undefined) {\n if (filePath && typeof filePath !== 'string') {\n throw new Error(`${this._name}.loadFromDisk - expected model file path`);\n }\n\n const { readFile } = env.getEnv();\n\n const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName());\n\n const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(\n filePaths.map((fp) => readFile(fp).then((buf) => buf.buffer)),\n );\n const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk);\n const manifest = JSON.parse((await readFile(manifestUri)).toString());\n const weightMap = await loadWeights(manifest, modelBaseUri);\n\n this.loadFromWeightMap(weightMap);\n }\n\n public loadFromWeightMap(weightMap: tf.NamedTensorMap) {\n const {\n paramMappings,\n params,\n } = this.extractParamsFromWeightMap(weightMap);\n\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n public extractWeights(weights: Float32Array) {\n const {\n paramMappings,\n params,\n } = this.extractParams(weights);\n\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n private traversePropertyPath(paramPath: string) {\n if (!this.params) {\n throw new Error('traversePropertyPath - model has no loaded params');\n }\n\n const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {\n // eslint-disable-next-line no-prototype-builtins\n if (!res.nextObj.hasOwnProperty(objProp)) {\n throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`);\n }\n\n return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] };\n }, { nextObj: this.params });\n\n const { obj, objProp } = result;\n if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {\n throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`);\n }\n\n return { obj, objProp };\n }\n\n protected abstract getDefaultModelName(): string\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, SeparableConvParams } from '../common/index';\nimport { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function denseBlock3(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock3Params,\n isFirstLayer: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n });\n}\n\nexport function denseBlock4(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock4Params,\n isFirstLayer: boolean = false,\n isScaleDown: boolean = true,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from './types';\n\nexport function depthwiseSeparableConv(\n x: tf.Tensor4D,\n params: SeparableConvParams,\n stride: [number, number],\n): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same');\n out = tf.add(out, params.bias);\n return out;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\nexport function convLayer(\n x: tf.Tensor4D,\n params: ConvParams,\n padding: 'valid' | 'same' = 'same',\n withRelu: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out = tf.add(\n tf.conv2d(x, params.filters, [1, 1], padding),\n params.bias,\n ) as tf.Tensor4D;\n\n return withRelu ? tf.relu(out) : out;\n });\n}\n", "import { ParamMapping } from './types';\n\nexport function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {\n Object.keys(weightMap).forEach((path) => {\n if (!paramMappings.some((pm) => pm.originalPath === path)) {\n weightMap[path].dispose();\n }\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';\n\nexport function extractConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams => {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, FCParams, ParamMapping } from './types';\n\nexport function extractFCParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): FCParams => {\n const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);\n const fc_bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return {\n weights: fc_weights,\n bias: fc_bias,\n };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';\n\nexport function extractSeparableConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams => {\n const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1]);\n const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut]);\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/depthwise_filter` },\n { paramPath: `${mappedPrefix}/pointwise_filter` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n\nexport function loadSeparableConvParamsFactory(\n // eslint-disable-next-line no-unused-vars\n extractWeightEntry: (originalPath: string, paramRank: number) => T,\n) {\n return (prefix: string): SeparableConvParams => {\n const depthwise_filter = extractWeightEntry(`${prefix}/depthwise_filter`, 4);\n const pointwise_filter = extractWeightEntry(`${prefix}/pointwise_filter`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n// eslint-disable-next-line no-unused-vars\nexport type ExtractWeightsFunction = (numWeights: number) => Float32Array\n\nexport type ParamMapping = {\n originalPath?: string\n paramPath: string\n}\n\nexport type ConvParams = {\n filters: tf.Tensor4D\n bias: tf.Tensor1D\n}\n\nexport type FCParams = {\n weights: tf.Tensor2D\n bias: tf.Tensor1D\n}\n\nexport class SeparableConvParams {\n // eslint-disable-next-line no-useless-constructor\n constructor(\n // eslint-disable-next-line no-unused-vars\n public depthwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public pointwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public bias: tf.Tensor1D,\n // eslint-disable-next-line no-empty-function\n ) {}\n}\n", "import { isTensor } from '../utils/index';\nimport { ParamMapping } from './types';\n\nexport function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {\n return (originalPath: string, paramRank: number, mappedPath?: string) => {\n const tensor = weightMap[originalPath];\n\n if (!isTensor(tensor, paramRank)) {\n throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`);\n }\n\n paramMappings.push(\n { originalPath, paramPath: mappedPath || originalPath },\n );\n\n return tensor;\n };\n}\n", "export function extractWeightsFactory(weights: Float32Array) {\n let remainingWeights = weights;\n\n function extractWeights(numWeights: number): Float32Array {\n const ret = remainingWeights.slice(0, numWeights);\n remainingWeights = remainingWeights.slice(numWeights);\n return ret;\n }\n\n function getRemainingWeights(): Float32Array {\n return remainingWeights;\n }\n\n return {\n extractWeights,\n getRemainingWeights,\n };\n}\n", "import {\n extractConvParamsFactory,\n extractSeparableConvParamsFactory,\n ExtractWeightsFunction,\n ParamMapping,\n} from '../common/index';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)\n : extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`);\n const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`);\n const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer);\n const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock4Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock4Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock4Params(64, 128, 'dense2');\n const dense3 = extractDenseBlock4Params(128, 256, 'dense3');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: {\n dense0, dense1, dense2, dense3,\n },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\n// eslint-disable-next-line no-unused-vars\nexport function loadConvParamsFactory(extractWeightEntry: (originalPath: string, paramRank: number) => T) {\n return (prefix: string): ConvParams => {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return { filters, bias };\n };\n}\n", "import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n const conv3 = extractSeparableConvParams(`${prefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock4Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock4Params('dense0', true),\n dense1: extractDenseBlock4Params('dense1'),\n dense2: extractDenseBlock4Params('dense2'),\n dense3: extractDenseBlock4Params('dense3'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { NetInput } from '../dom/index';\nimport {\n FaceFeatureExtractorParams,\n IFaceFeatureExtractor,\n TinyFaceFeatureExtractorParams,\n} from '../faceFeatureExtractor/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { NetParams } from './types';\nimport { seperateWeightMaps } from './util';\n\nexport abstract class FaceProcessor<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends NeuralNetwork {\n protected _faceFeatureExtractor: IFaceFeatureExtractor\n\n constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor) {\n super(_name);\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): IFaceFeatureExtractor {\n return this._faceFeatureExtractor;\n }\n\n protected abstract getDefaultModelName(): string\n\n protected abstract getClassifierChannelsIn(): number\n\n protected abstract getClassifierChannelsOut(): number\n\n public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut());\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const cIn = this.getClassifierChannelsIn();\n const cOut = this.getClassifierChannelsOut();\n const classifierWeightSize = (cOut * cIn) + cOut;\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from './types';\n\nexport function fullyConnectedLayer(\n x: tf.Tensor2D,\n params: FCParams,\n): tf.Tensor2D {\n return tf.tidy(() => tf.add(\n tf.matMul(x, params.weights),\n params.bias,\n ));\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const fc = extractFCParams(channelsIn, channelsOut, 'fc');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: extractFcParams('fc'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function seperateWeightMaps(weightMap: tf.NamedTensorMap) {\n const featureExtractorMap: tf.NamedTensorMap = {};\n const classifierMap: tf.NamedTensorMap = {};\n\n Object.keys(weightMap).forEach((key) => {\n const map = key.startsWith('fc') ? classifierMap : featureExtractorMap;\n map[key] = weightMap[key];\n });\n\n return { featureExtractorMap, classifierMap };\n}\n", "export const FACE_EXPRESSION_LABELS = ['neutral', 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised'];\n\nexport class FaceExpressions {\n public neutral: number\n\n public happy: number\n\n public sad: number\n\n public angry: number\n\n public fearful: number\n\n public disgusted: number\n\n public surprised: number\n\n constructor(probabilities: number[] | Float32Array) {\n if (probabilities.length !== 7) {\n throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${probabilities.length}`);\n }\n\n FACE_EXPRESSION_LABELS.forEach((expression, idx) => {\n this[expression] = probabilities[idx];\n });\n }\n\n asSortedArray() {\n return FACE_EXPRESSION_LABELS\n .map((expression) => ({ expression, probability: this[expression] as number }))\n .sort((e0, e1) => e1.probability - e0.probability);\n }\n}\n", "import { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\n\nexport type WithFaceExpressions = TSource & {\n expressions: FaceExpressions\n}\n\nexport function isWithFaceExpressions(obj: any): obj is WithFaceExpressions<{}> {\n return obj.expressions instanceof FaceExpressions;\n}\n\nexport function extendWithFaceExpressions<\n TSource\n>(\n sourceObj: TSource,\n expressions: FaceExpressions,\n): WithFaceExpressions {\n const extension = { expressions };\n return { ...sourceObj, ...extension };\n}\n", "import { IPoint, Point } from '../classes/index';\nimport { FaceExpressions } from '../faceExpressionNet/index';\nimport { isWithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { round } from '../utils/index';\nimport { DrawTextField } from './DrawTextField';\n\nexport type DrawFaceExpressionsInput = FaceExpressions | WithFaceExpressions<{}>\n\nexport function drawFaceExpressions(\n canvasArg: string | HTMLCanvasElement,\n faceExpressions: DrawFaceExpressionsInput | Array,\n minConfidence = 0.1,\n textFieldAnchor?: IPoint,\n) {\n const faceExpressionsArray = Array.isArray(faceExpressions) ? faceExpressions : [faceExpressions];\n\n faceExpressionsArray.forEach((e) => {\n // eslint-disable-next-line no-nested-ternary\n const expr = e instanceof FaceExpressions\n ? e\n : (isWithFaceExpressions(e) ? e.expressions : undefined);\n if (!expr) {\n throw new Error('drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof');\n }\n\n const sorted = expr.asSortedArray();\n const resultsToDisplay = sorted.filter((exprLocal) => exprLocal.probability > minConfidence);\n\n const anchor = isWithFaceDetection(e)\n ? e.detection.box.bottomLeft\n : (textFieldAnchor || new Point(0, 0));\n\n const drawTextField = new DrawTextField(\n resultsToDisplay.map((exprLocal) => `${exprLocal.expression} (${round(exprLocal.probability)})`),\n anchor,\n );\n drawTextField.draw(canvasArg);\n });\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { isWithFaceDetection, WithFaceDetection } from './WithFaceDetection';\n\nexport type WithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 > = TSource & {\n landmarks: TFaceLandmarks\n unshiftedLandmarks: TFaceLandmarks\n alignedRect: FaceDetection\n }\n\nexport function isWithFaceLandmarks(obj: any): obj is WithFaceLandmarks, FaceLandmarks> {\n return isWithFaceDetection(obj)\n // eslint-disable-next-line dot-notation\n && obj['landmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['unshiftedLandmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['alignedRect'] instanceof FaceDetection;\n}\n\nexport function extendWithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 >(sourceObj: TSource, unshiftedLandmarks: TFaceLandmarks): WithFaceLandmarks {\n const { box: shift } = sourceObj.detection;\n const landmarks = unshiftedLandmarks.shiftBy(shift.x, shift.y);\n\n const rect = landmarks.align();\n const { imageDims } = sourceObj.detection;\n const alignedRect = new FaceDetection(sourceObj.detection.score, rect.rescale(imageDims.reverse()), imageDims);\n\n const extension = {\n landmarks,\n unshiftedLandmarks,\n alignedRect,\n };\n\n return { ...sourceObj, ...extension };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IPoint } from '../classes/index';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { drawContour } from './drawContour';\n\nexport interface IDrawFaceLandmarksOptions {\n drawLines?: boolean\n drawPoints?: boolean\n lineWidth?: number\n pointSize?: number\n lineColor?: string\n pointColor?: string\n}\n\nexport class DrawFaceLandmarksOptions {\n public drawLines: boolean\n\n public drawPoints: boolean\n\n public lineWidth: number\n\n public pointSize: number\n\n public lineColor: string\n\n public pointColor: string\n\n constructor(options: IDrawFaceLandmarksOptions = {}) {\n const {\n drawLines = true, drawPoints = true, lineWidth, lineColor, pointSize, pointColor,\n } = options;\n this.drawLines = drawLines;\n this.drawPoints = drawPoints;\n this.lineWidth = lineWidth || 1;\n this.pointSize = pointSize || 2;\n this.lineColor = lineColor || 'rgba(0, 255, 255, 1)';\n this.pointColor = pointColor || 'rgba(255, 0, 255, 1)';\n }\n}\n\nexport class DrawFaceLandmarks {\n public faceLandmarks: FaceLandmarks\n\n public options: DrawFaceLandmarksOptions\n\n constructor(\n faceLandmarks: FaceLandmarks,\n options: IDrawFaceLandmarksOptions = {},\n ) {\n this.faceLandmarks = faceLandmarks;\n this.options = new DrawFaceLandmarksOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const {\n drawLines, drawPoints, lineWidth, lineColor, pointSize, pointColor,\n } = this.options;\n\n if (drawLines && this.faceLandmarks instanceof FaceLandmarks68) {\n ctx.strokeStyle = lineColor;\n ctx.lineWidth = lineWidth;\n drawContour(ctx, this.faceLandmarks.getJawOutline());\n drawContour(ctx, this.faceLandmarks.getLeftEyeBrow());\n drawContour(ctx, this.faceLandmarks.getRightEyeBrow());\n drawContour(ctx, this.faceLandmarks.getNose());\n drawContour(ctx, this.faceLandmarks.getLeftEye(), true);\n drawContour(ctx, this.faceLandmarks.getRightEye(), true);\n drawContour(ctx, this.faceLandmarks.getMouth(), true);\n }\n\n if (drawPoints) {\n ctx.strokeStyle = pointColor;\n ctx.fillStyle = pointColor;\n\n const drawPoint = (pt: IPoint) => {\n ctx.beginPath();\n ctx.arc(pt.x, pt.y, pointSize, 0, 2 * Math.PI);\n ctx.fill();\n };\n this.faceLandmarks.positions.forEach(drawPoint);\n }\n }\n}\n\nexport type DrawFaceLandmarksInput = FaceLandmarks | WithFaceLandmarks>\n\nexport function drawFaceLandmarks(\n canvasArg: string | HTMLCanvasElement,\n faceLandmarks: DrawFaceLandmarksInput | Array,\n) {\n const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];\n faceLandmarksArray.forEach((f) => {\n // eslint-disable-next-line no-nested-ternary\n const landmarks = f instanceof FaceLandmarks\n ? f\n : (isWithFaceLandmarks(f) ? f.landmarks : undefined);\n if (!landmarks) {\n throw new Error('drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof');\n }\n\n new DrawFaceLandmarks(landmarks).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { seperateWeightMaps } from '../faceProcessor/util';\nimport { TinyXception } from '../xception/TinyXception';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport {\n AgeAndGenderPrediction, Gender, NetOutput, NetParams,\n} from './types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\n\nexport class AgeGenderNet extends NeuralNetwork {\n private _faceFeatureExtractor: TinyXception\n\n constructor(faceFeatureExtractor: TinyXception = new TinyXception(2)) {\n super('AgeGenderNet');\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): TinyXception {\n return this._faceFeatureExtractor;\n }\n\n public runNet(input: NetInput | tf.Tensor4D): NetOutput {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n\n const pooled = tf.avgPool(bottleneckFeatures, [7, 7], [2, 2], 'valid').as2D(bottleneckFeatures.shape[0], -1);\n const age = fullyConnectedLayer(pooled, params.fc.age).as1D();\n const gender = fullyConnectedLayer(pooled, params.fc.gender);\n return { age, gender };\n });\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): NetOutput {\n return tf.tidy(() => {\n const { age, gender } = this.runNet(input);\n return { age, gender: tf.softmax(gender) };\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictAgeAndGender(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n\n const ages = tf.unstack(out.age);\n const genders = tf.unstack(out.gender);\n const ageAndGenderTensors = ages.map((ageTensor, i) => ({\n ageTensor,\n genderTensor: genders[i],\n }));\n\n const predictionsByBatch = await Promise.all(\n ageAndGenderTensors.map(async ({ ageTensor, genderTensor }) => {\n const age = (await ageTensor.data())[0];\n const probMale = (await genderTensor.data())[0];\n const isMale = probMale > 0.5;\n const gender = isMale ? Gender.MALE : Gender.FEMALE;\n const genderProbability = isMale ? probMale : (1 - probMale);\n\n ageTensor.dispose();\n genderTensor.dispose();\n return { age, gender, genderProbability };\n }),\n );\n out.age.dispose();\n out.gender.dispose();\n\n return netInput.isBatchInput ? predictionsByBatch as AgeAndGenderPrediction[] : predictionsByBatch[0] as AgeAndGenderPrediction;\n }\n\n protected getDefaultModelName(): string {\n return 'age_gender_model';\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights);\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const classifierWeightSize = (512 * 1 + 1) + (512 * 2 + 2);\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, depthwiseSeparableConv } from '../common/index';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { range } from '../utils/index';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction conv(x: tf.Tensor4D, params: ConvParams, stride: [number, number]): tf.Tensor4D {\n return tf.add(tf.conv2d(x, params.filters, stride, 'same'), params.bias);\n}\n\nfunction reductionBlock(x: tf.Tensor4D, params: ReductionBlockParams, isActivateInput: boolean = true): tf.Tensor4D {\n let out = isActivateInput ? tf.relu(x) : x;\n out = depthwiseSeparableConv(out, params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = tf.maxPool(out, [3, 3], [2, 2], 'same');\n out = tf.add(out, conv(x, params.expansion_conv, [2, 2]));\n return out;\n}\n\nfunction mainBlock(x: tf.Tensor4D, params: MainBlockParams): tf.Tensor4D {\n let out = depthwiseSeparableConv(tf.relu(x), params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv2, [1, 1]);\n out = tf.add(out, x);\n return out;\n}\n\nexport class TinyXception extends NeuralNetwork {\n private _numMainBlocks: number\n\n constructor(numMainBlocks: number) {\n super('TinyXception');\n this._numMainBlocks = numMainBlocks;\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyXception - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = tf.relu(conv(normalized, params.entry_flow.conv_in, [2, 2]));\n out = reductionBlock(out, params.entry_flow.reduction_block_0, false);\n out = reductionBlock(out, params.entry_flow.reduction_block_1);\n\n range(this._numMainBlocks, 0, 1).forEach((idx) => {\n out = mainBlock(out, params.middle_flow[`main_block_${idx}`]);\n });\n\n out = reductionBlock(out, params.exit_flow.reduction_block);\n out = tf.relu(depthwiseSeparableConv(out, params.exit_flow.separable_conv, [1, 1]));\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_xception_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this._numMainBlocks);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights, this._numMainBlocks);\n }\n}\n", "import { extractConvParamsFactory, extractSeparableConvParamsFactory, extractWeightsFactory } from '../common/index';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractReductionBlockParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(channels: number, mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParams(weights: Float32Array, numMainBlocks: number): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const entry_flow_conv_in = extractConvParams(3, 32, 3, 'entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams(32, 64, 'entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams(64, 128, 'entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(128, `middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams(128, 256, 'exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams(256, 512, 'exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { entry_flow, middle_flow, exit_flow },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors,\n extractWeightEntryFactory,\n loadSeparableConvParamsFactory,\n ParamMapping,\n} from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractReductionBlockParams(mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(`${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(`${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n numMainBlocks: number,\n): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const entry_flow_conv_in = extractConvParams('entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams('entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams('entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(`middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams('exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams('exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params: { entry_flow, middle_flow, exit_flow }, paramMappings };\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const age = extractFCParams(512, 1, 'fc/age');\n const gender = extractFCParams(512, 2, 'fc/gender');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc: { age, gender } },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: {\n age: extractFcParams('fc/age'),\n gender: extractFcParams('fc/gender'),\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from '../common/index';\n\n// eslint-disable-next-line no-shadow\nexport enum Gender {\n // eslint-disable-next-line no-unused-vars\n FEMALE = 'female',\n // eslint-disable-next-line no-unused-vars\n MALE = 'male'\n}\n\nexport type AgeAndGenderPrediction = {\n age: number\n gender: Gender\n genderProbability: number\n}\n\nexport type NetOutput = { age: tf.Tensor1D, gender: tf.Tensor2D }\n\nexport type NetParams = {\n fc: {\n age: FCParams\n gender: FCParams\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { IDimensions, Point } from '../classes/index';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { isEven } from '../utils/index';\n\nexport abstract class FaceLandmark68NetBase<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends FaceProcessor {\n public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {\n const inputDimensions = originalDimensions.map(({ width, height }) => {\n const scale = inputSize / Math.max(height, width);\n return {\n width: width * scale,\n height: height * scale,\n };\n });\n\n const batchSize = inputDimensions.length;\n\n return tf.tidy(() => {\n const createInterleavedTensor = (fillX: number, fillY: number) => tf.stack([tf.fill([68], fillX, 'float32'), tf.fill([68], fillY, 'float32')], 1).as2D(1, 136).as1D();\n\n // eslint-disable-next-line no-unused-vars\n const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {\n const { width, height } = inputDimensions[batchIdx];\n return cond(width, height) ? Math.abs(width - height) / 2 : 0;\n };\n\n const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h);\n const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w);\n\n const landmarkTensors = output\n .mul(tf.fill([batchSize, 136], inputSize, 'float32'))\n .sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n getPaddingX(batchIdx),\n getPaddingY(batchIdx),\n ))))\n .div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n inputDimensions[batchIdx].width,\n inputDimensions[batchIdx].height,\n ))));\n\n return landmarkTensors as tf.Tensor2D;\n });\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n return tf.tidy(() => {\n const out = this.runNet(input);\n return this.postProcess(\n out,\n input.inputSize as number,\n input.inputDimensions.map(([height, width]) => ({ height, width })),\n );\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async detectLandmarks(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const landmarkTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const landmarksForBatch = await Promise.all(landmarkTensors.map(\n async (landmarkTensor, batchIdx) => {\n const landmarksArray = Array.from(await landmarkTensor.data());\n const xCoords = landmarksArray.filter((_, i) => isEven(i));\n const yCoords = landmarksArray.filter((_, i) => !isEven(i));\n\n return new FaceLandmarks68(\n Array(68).fill(0).map((_, i) => new Point(xCoords[i] as number, yCoords[i] as number)),\n {\n height: netInput.getInputHeight(batchIdx),\n width: netInput.getInputWidth(batchIdx),\n },\n );\n },\n ));\n\n landmarkTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput ? landmarksForBatch as FaceLandmarks68[] : landmarksForBatch[0] as FaceLandmarks68;\n }\n\n protected getClassifierChannelsOut(): number {\n return 136;\n }\n}\n", "import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68Net extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceLandmark68Net', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock3 } from './denseBlock';\nimport { extractParamsFromWeightMapTiny } from './extractParamsFromWeightMapTiny';\nimport { extractParamsTiny } from './extractParamsTiny';\nimport { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';\n\nexport class TinyFaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('TinyFaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyFaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock3(normalized, params.dense0, true);\n out = denseBlock3(out, params.dense1);\n out = denseBlock3(out, params.dense2);\n out = tf.avgPool(out, [14, 14], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_tiny_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMapTiny(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParamsTiny(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMapTiny(\n weightMap: tf.NamedTensorMap,\n): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock3Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock3Params('dense0', true),\n dense1: extractDenseBlock3Params('dense1'),\n dense2: extractDenseBlock3Params('dense2'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock3Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock3Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock3Params(64, 128, 'dense2');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { dense0, dense1, dense2 },\n };\n}\n", "import { TinyFaceFeatureExtractor } from '../faceFeatureExtractor/TinyFaceFeatureExtractor';\nimport { TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68TinyNet extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: TinyFaceFeatureExtractor = new TinyFaceFeatureExtractor()) {\n super('FaceLandmark68TinyNet', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_tiny_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 128;\n }\n}\n", "import { FaceLandmark68Net } from './FaceLandmark68Net';\n\nexport * from './FaceLandmark68Net';\nexport * from './FaceLandmark68TinyNet';\n\nexport class FaceLandmarkNet extends FaceLandmark68Net {}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { convDown } from './convLayer';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { residual, residualDown } from './residualLayer';\nimport { NetParams } from './types';\n\nexport class FaceRecognitionNet extends NeuralNetwork {\n constructor() {\n super('FaceRecognitionNet');\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceRecognitionNet - load model before inference');\n }\n\n return tf.tidy(() => {\n // const batchTensor = input.toBatchTensor(150, true).toFloat()\n const batchTensor = tf.cast(input.toBatchTensor(150, true), 'float32');\n\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = convDown(normalized, params.conv32_down);\n out = tf.maxPool(out, 3, 2, 'valid');\n\n out = residual(out, params.conv32_1);\n out = residual(out, params.conv32_2);\n out = residual(out, params.conv32_3);\n\n out = residualDown(out, params.conv64_down);\n out = residual(out, params.conv64_1);\n out = residual(out, params.conv64_2);\n out = residual(out, params.conv64_3);\n\n out = residualDown(out, params.conv128_down);\n out = residual(out, params.conv128_1);\n out = residual(out, params.conv128_2);\n\n out = residualDown(out, params.conv256_down);\n out = residual(out, params.conv256_1);\n out = residual(out, params.conv256_2);\n out = residualDown(out, params.conv256_down_out);\n\n const globalAvg = out.mean([1, 2]) as tf.Tensor2D;\n const fullyConnected = tf.matMul(globalAvg, params.fc);\n\n return fullyConnected;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async computeFaceDescriptor(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n\n const faceDescriptorTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map(\n (t) => t.data(),\n )) as Float32Array[];\n\n faceDescriptorTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput\n ? faceDescriptorsForBatch\n : faceDescriptorsForBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_recognition_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { scale } from './scaleLayer';\nimport { ConvLayerParams } from './types';\n\nfunction convLayer(\n x: tf.Tensor4D,\n params: ConvLayerParams,\n strides: [number, number],\n withRelu: boolean,\n padding: 'valid' | 'same' = 'same',\n): tf.Tensor4D {\n const { filters, bias } = params.conv;\n\n let out = tf.conv2d(x, filters, strides, padding);\n out = tf.add(out, bias);\n out = scale(out, params.scale);\n return withRelu ? tf.relu(out) : out;\n}\n\nexport function conv(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], true);\n}\n\nexport function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], false);\n}\n\nexport function convDown(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [2, 2], true, 'valid');\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ScaleLayerParams } from './types';\n\nexport function scale(x: tf.Tensor4D, params: ScaleLayerParams): tf.Tensor4D {\n return tf.add(tf.mul(x, params.weights), params.biases);\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping,\n} from '../common/index';\nimport { isFloat } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {\n const weights = extractWeights(numFilterValues);\n const depth = weights.length / (numFilters * filterSize * filterSize);\n\n if (isFloat(depth)) {\n throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`);\n }\n\n return tf.tidy(\n () => tf.transpose(\n tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),\n [2, 3, 1, 0],\n ),\n );\n }\n\n function extractConvParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams {\n const filters = extractFilterValues(numFilterValues, numFilters, filterSize);\n const bias = tf.tensor1d(extractWeights(numFilters));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n }\n\n function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {\n const weights = tf.tensor1d(extractWeights(numWeights));\n const biases = tf.tensor1d(extractWeights(numWeights));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/biases` },\n );\n\n return {\n weights,\n biases,\n };\n }\n\n function extractConvLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvLayerParams {\n const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`);\n const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`);\n\n return { conv, scale };\n }\n\n function extractResidualLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n isDown: boolean = false,\n ): ResidualLayerParams {\n const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`);\n const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`);\n\n return { conv1, conv2 };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down');\n const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1');\n const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2');\n const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3');\n\n const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true);\n const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1');\n const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2');\n const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3');\n\n const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true);\n const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1');\n const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2');\n\n const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true);\n const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1');\n const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2');\n const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out');\n\n const fc = tf.tidy(\n () => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0]),\n );\n paramMappings.push({ paramPath: 'fc' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common/index';\nimport { isTensor2D } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractScaleLayerParams(prefix: string): ScaleLayerParams {\n const weights = extractWeightEntry(`${prefix}/scale/weights`, 1);\n const biases = extractWeightEntry(`${prefix}/scale/biases`, 1);\n\n return { weights, biases };\n }\n\n function extractConvLayerParams(prefix: string): ConvLayerParams {\n const filters = extractWeightEntry(`${prefix}/conv/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/conv/bias`, 1);\n const scale = extractScaleLayerParams(prefix);\n\n return { conv: { filters, bias }, scale };\n }\n\n function extractResidualLayerParams(prefix: string): ResidualLayerParams {\n return {\n conv1: extractConvLayerParams(`${prefix}/conv1`),\n conv2: extractConvLayerParams(`${prefix}/conv2`),\n };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const conv32_down = extractConvLayerParams('conv32_down');\n const conv32_1 = extractResidualLayerParams('conv32_1');\n const conv32_2 = extractResidualLayerParams('conv32_2');\n const conv32_3 = extractResidualLayerParams('conv32_3');\n\n const conv64_down = extractResidualLayerParams('conv64_down');\n const conv64_1 = extractResidualLayerParams('conv64_1');\n const conv64_2 = extractResidualLayerParams('conv64_2');\n const conv64_3 = extractResidualLayerParams('conv64_3');\n\n const conv128_down = extractResidualLayerParams('conv128_down');\n const conv128_1 = extractResidualLayerParams('conv128_1');\n const conv128_2 = extractResidualLayerParams('conv128_2');\n\n const conv256_down = extractResidualLayerParams('conv256_down');\n const conv256_1 = extractResidualLayerParams('conv256_1');\n const conv256_2 = extractResidualLayerParams('conv256_2');\n const conv256_down_out = extractResidualLayerParams('conv256_down_out');\n\n const { fc } = weightMap;\n paramMappings.push({ originalPath: 'fc', paramPath: 'fc' });\n\n if (!isTensor2D(fc)) {\n throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { conv, convDown, convNoRelu } from './convLayer';\nimport { ResidualLayerParams } from './types';\n\nexport function residual(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = conv(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n out = tf.add(out, x);\n out = tf.relu(out);\n return out;\n}\n\nexport function residualDown(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = convDown(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n\n let pooled = tf.avgPool(x, 2, 2, 'valid') as tf.Tensor4D;\n const zeros = tf.zeros(pooled.shape);\n const isPad = pooled.shape[3] !== out.shape[3];\n const isAdjustShape = pooled.shape[1] !== out.shape[1] || pooled.shape[2] !== out.shape[2];\n\n if (isAdjustShape) {\n const padShapeX = [...out.shape] as [number, number, number, number];\n padShapeX[1] = 1;\n const zerosW = tf.zeros(padShapeX);\n out = tf.concat([out, zerosW], 1);\n\n const padShapeY = [...out.shape] as [number, number, number, number];\n padShapeY[2] = 1;\n const zerosH = tf.zeros(padShapeY);\n out = tf.concat([out, zerosH], 2);\n }\n\n pooled = isPad ? tf.concat([pooled, zeros], 3) : pooled;\n out = tf.add(pooled, out) as tf.Tensor4D;\n\n out = tf.relu(out);\n return out;\n}\n", "import { FaceRecognitionNet } from './FaceRecognitionNet';\n\nexport * from './FaceRecognitionNet';\n\nexport function createFaceRecognitionNet(weights: Float32Array) {\n const net = new FaceRecognitionNet();\n net.extractWeights(weights);\n return net;\n}\n", "export type WithFaceDescriptor = TSource & {\n descriptor: Float32Array\n}\n\nexport function extendWithFaceDescriptor<\n TSource\n>(\n sourceObj: TSource,\n descriptor: Float32Array,\n): WithFaceDescriptor {\n const extension = { descriptor };\n return { ...sourceObj, ...extension };\n}\n", "export type WithAge = TSource & {\n age: number\n}\n\nexport function isWithAge(obj: any): obj is WithAge<{}> {\n return typeof obj.age === 'number';\n}\n\nexport function extendWithAge<\n TSource\n>(\n sourceObj: TSource,\n age: number,\n): WithAge {\n const extension = { age };\n return { ...sourceObj, ...extension };\n}\n", "import { Gender } from '../ageGenderNet/types';\nimport { isValidProbablitiy } from '../utils/index';\n\nexport type WithGender = TSource & {\n gender: Gender\n genderProbability: number\n}\n\nexport function isWithGender(obj: any): obj is WithGender<{}> {\n return (obj.gender === Gender.MALE || obj.gender === Gender.FEMALE)\n && isValidProbablitiy(obj.genderProbability);\n}\n\nexport function extendWithGender<\n TSource\n>(\n sourceObj: TSource,\n gender: Gender,\n genderProbability: number,\n): WithGender {\n const extension = { gender, genderProbability };\n return { ...sourceObj, ...extension };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { mobileNetV1 } from './mobileNetV1';\nimport { nonMaxSuppression } from './nonMaxSuppression';\nimport { outputLayer } from './outputLayer';\nimport { predictionLayer } from './predictionLayer';\nimport { ISsdMobilenetv1Options, SsdMobilenetv1Options } from './SsdMobilenetv1Options';\nimport { NetParams } from './types';\n\nexport class SsdMobilenetv1 extends NeuralNetwork {\n constructor() {\n super('SsdMobilenetv1');\n }\n\n public forwardInput(input: NetInput) {\n const { params } = this;\n\n if (!params) {\n throw new Error('SsdMobilenetv1 - load model before inference');\n }\n\n return tf.tidy(() => {\n // const batchTensor = input.toBatchTensor(512, false).toFloat()\n const batchTensor = tf.cast(input.toBatchTensor(512, false), 'float32');\n\n const x = tf.sub(tf.mul(batchTensor, tf.scalar(0.007843137718737125)), tf.scalar(1)) as tf.Tensor4D;\n const features = mobileNetV1(x, params.mobilenetv1);\n\n const {\n boxPredictions,\n classPredictions,\n } = predictionLayer(features.out, features.conv11, params.prediction_layer);\n\n return outputLayer(boxPredictions, classPredictions, params.output_layer);\n });\n }\n\n public async forward(input: TNetInput) {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async locateFaces(\n input: TNetInput,\n options: ISsdMobilenetv1Options = {},\n ): Promise {\n const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);\n\n const netInput = await toNetInput(input);\n\n const {\n boxes: _boxes,\n scores: _scores,\n } = this.forwardInput(netInput);\n\n // TODO batches\n const boxes = _boxes[0];\n const scores = _scores[0];\n for (let i = 1; i < _boxes.length; i++) {\n _boxes[i].dispose();\n _scores[i].dispose();\n }\n\n // TODO find a better way to filter by minConfidence\n const scoresData = Array.from(await scores.data());\n\n const iouThreshold = 0.5;\n const indices = nonMaxSuppression(\n boxes,\n scoresData as number[],\n maxResults,\n iouThreshold,\n minConfidence,\n );\n\n const reshapedDims = netInput.getReshapedInputDimensions(0);\n const inputSize = netInput.inputSize as number;\n const padX = inputSize / reshapedDims.width;\n const padY = inputSize / reshapedDims.height;\n\n const boxesData = boxes.arraySync();\n const results = indices\n .map((idx) => {\n const [top, bottom] = [\n Math.max(0, boxesData[idx][0]),\n Math.min(1.0, boxesData[idx][2]),\n ].map((val) => val * padY);\n const [left, right] = [\n Math.max(0, boxesData[idx][1]),\n Math.min(1.0, boxesData[idx][3]),\n ].map((val) => val * padX);\n return new FaceDetection(\n scoresData[idx] as number,\n new Rect(\n left,\n top,\n right - left,\n bottom - top,\n ),\n {\n height: netInput.getInputHeight(0),\n width: netInput.getInputWidth(0),\n },\n );\n });\n\n boxes.dispose();\n scores.dispose();\n\n return results;\n }\n\n protected getDefaultModelName(): string {\n return 'ssd_mobilenetv1_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ExtractWeightsFunction, ParamMapping, ConvParams, extractWeightsFactory,\n} from '../common/index';\nimport {\n MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractDepthwiseConvParams(numChannels: number, mappedPrefix: string): MobileNetV1.DepthwiseConvParams {\n const filters = tf.tensor4d(extractWeights(3 * 3 * numChannels), [3, 3, numChannels, 1]);\n const batch_norm_scale = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_offset = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_mean = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_variance = tf.tensor1d(extractWeights(numChannels));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/batch_norm_scale` },\n { paramPath: `${mappedPrefix}/batch_norm_offset` },\n { paramPath: `${mappedPrefix}/batch_norm_mean` },\n { paramPath: `${mappedPrefix}/batch_norm_variance` },\n );\n\n return {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n };\n }\n\n function extractConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n isPointwiseConv?: boolean,\n ): ConvParams {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/${isPointwiseConv ? 'batch_norm_offset' : 'bias'}` },\n );\n\n return { filters, bias };\n }\n\n function extractPointwiseConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): PointwiseConvParams {\n const {\n filters,\n bias,\n } = extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix, true);\n\n return {\n filters,\n batch_norm_offset: bias,\n };\n }\n\n function extractConvPairParams(\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): MobileNetV1.ConvPairParams {\n const depthwise_conv = extractDepthwiseConvParams(channelsIn, `${mappedPrefix}/depthwise_conv`);\n const pointwise_conv = extractPointwiseConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/pointwise_conv`);\n\n return { depthwise_conv, pointwise_conv };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n const conv_0 = extractPointwiseConvParams(3, 32, 3, 'mobilenetv1/conv_0');\n\n const conv_1 = extractConvPairParams(32, 64, 'mobilenetv1/conv_1');\n const conv_2 = extractConvPairParams(64, 128, 'mobilenetv1/conv_2');\n const conv_3 = extractConvPairParams(128, 128, 'mobilenetv1/conv_3');\n const conv_4 = extractConvPairParams(128, 256, 'mobilenetv1/conv_4');\n const conv_5 = extractConvPairParams(256, 256, 'mobilenetv1/conv_5');\n const conv_6 = extractConvPairParams(256, 512, 'mobilenetv1/conv_6');\n const conv_7 = extractConvPairParams(512, 512, 'mobilenetv1/conv_7');\n const conv_8 = extractConvPairParams(512, 512, 'mobilenetv1/conv_8');\n const conv_9 = extractConvPairParams(512, 512, 'mobilenetv1/conv_9');\n const conv_10 = extractConvPairParams(512, 512, 'mobilenetv1/conv_10');\n const conv_11 = extractConvPairParams(512, 512, 'mobilenetv1/conv_11');\n const conv_12 = extractConvPairParams(512, 1024, 'mobilenetv1/conv_12');\n const conv_13 = extractConvPairParams(1024, 1024, 'mobilenetv1/conv_13');\n\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n conv_8,\n conv_9,\n conv_10,\n conv_11,\n conv_12,\n conv_13,\n };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n const conv_0 = extractPointwiseConvParams(1024, 256, 1, 'prediction_layer/conv_0');\n const conv_1 = extractPointwiseConvParams(256, 512, 3, 'prediction_layer/conv_1');\n const conv_2 = extractPointwiseConvParams(512, 128, 1, 'prediction_layer/conv_2');\n const conv_3 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_3');\n const conv_4 = extractPointwiseConvParams(256, 128, 1, 'prediction_layer/conv_4');\n const conv_5 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_5');\n const conv_6 = extractPointwiseConvParams(256, 64, 1, 'prediction_layer/conv_6');\n const conv_7 = extractPointwiseConvParams(64, 128, 3, 'prediction_layer/conv_7');\n\n const box_encoding_0_predictor = extractConvParams(512, 12, 1, 'prediction_layer/box_predictor_0/box_encoding_predictor');\n const class_predictor_0 = extractConvParams(512, 9, 1, 'prediction_layer/box_predictor_0/class_predictor');\n const box_encoding_1_predictor = extractConvParams(1024, 24, 1, 'prediction_layer/box_predictor_1/box_encoding_predictor');\n const class_predictor_1 = extractConvParams(1024, 18, 1, 'prediction_layer/box_predictor_1/class_predictor');\n const box_encoding_2_predictor = extractConvParams(512, 24, 1, 'prediction_layer/box_predictor_2/box_encoding_predictor');\n const class_predictor_2 = extractConvParams(512, 18, 1, 'prediction_layer/box_predictor_2/class_predictor');\n const box_encoding_3_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_3/box_encoding_predictor');\n const class_predictor_3 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_3/class_predictor');\n const box_encoding_4_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_4/box_encoding_predictor');\n const class_predictor_4 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_4/class_predictor');\n const box_encoding_5_predictor = extractConvParams(128, 24, 1, 'prediction_layer/box_predictor_5/box_encoding_predictor');\n const class_predictor_5 = extractConvParams(128, 18, 1, 'prediction_layer/box_predictor_5/class_predictor');\n\n const box_predictor_0 = {\n box_encoding_predictor: box_encoding_0_predictor,\n class_predictor: class_predictor_0,\n };\n const box_predictor_1 = {\n box_encoding_predictor: box_encoding_1_predictor,\n class_predictor: class_predictor_1,\n };\n const box_predictor_2 = {\n box_encoding_predictor: box_encoding_2_predictor,\n class_predictor: class_predictor_2,\n };\n const box_predictor_3 = {\n box_encoding_predictor: box_encoding_3_predictor,\n class_predictor: class_predictor_3,\n };\n const box_predictor_4 = {\n box_encoding_predictor: box_encoding_4_predictor,\n class_predictor: class_predictor_4,\n };\n const box_predictor_5 = {\n box_encoding_predictor: box_encoding_5_predictor,\n class_predictor: class_predictor_5,\n };\n\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n box_predictor_0,\n box_predictor_1,\n box_predictor_2,\n box_predictor_3,\n box_predictor_4,\n box_predictor_5,\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const mobilenetv1 = extractMobilenetV1Params();\n const prediction_layer = extractPredictionLayerParams();\n const extra_dim = tf.tensor3d(\n extractWeights(5118 * 4),\n [1, 5118, 4],\n );\n const output_layer = {\n extra_dim,\n };\n\n paramMappings.push({ paramPath: 'output_layer/extra_dim' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n params: {\n mobilenetv1,\n prediction_layer,\n output_layer,\n },\n paramMappings,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping,\n} from '../common/index';\nimport { isTensor3D } from '../utils/index';\nimport {\n BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractPointwiseConvParams(prefix: string, idx: number, mappedPrefix: string): PointwiseConvParams {\n const filters = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/weights`, 4, `${mappedPrefix}/filters`);\n const batch_norm_offset = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/convolution_bn_offset`, 1, `${mappedPrefix}/batch_norm_offset`);\n\n return { filters, batch_norm_offset };\n }\n\n function extractConvPairParams(idx: number): MobileNetV1.ConvPairParams {\n const mappedPrefix = `mobilenetv1/conv_${idx}`;\n const prefixDepthwiseConv = `MobilenetV1/Conv2d_${idx}_depthwise`;\n const mappedPrefixDepthwiseConv = `${mappedPrefix}/depthwise_conv`;\n const mappedPrefixPointwiseConv = `${mappedPrefix}/pointwise_conv`;\n\n const filters = extractWeightEntry(`${prefixDepthwiseConv}/depthwise_weights`, 4, `${mappedPrefixDepthwiseConv}/filters`);\n const batch_norm_scale = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/gamma`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_scale`);\n const batch_norm_offset = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/beta`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_offset`);\n const batch_norm_mean = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_mean`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_mean`);\n const batch_norm_variance = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_variance`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_variance`);\n\n return {\n depthwise_conv: {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n },\n pointwise_conv: extractPointwiseConvParams('MobilenetV1', idx, mappedPrefixPointwiseConv),\n };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n return {\n conv_0: extractPointwiseConvParams('MobilenetV1', 0, 'mobilenetv1/conv_0'),\n conv_1: extractConvPairParams(1),\n conv_2: extractConvPairParams(2),\n conv_3: extractConvPairParams(3),\n conv_4: extractConvPairParams(4),\n conv_5: extractConvPairParams(5),\n conv_6: extractConvPairParams(6),\n conv_7: extractConvPairParams(7),\n conv_8: extractConvPairParams(8),\n conv_9: extractConvPairParams(9),\n conv_10: extractConvPairParams(10),\n conv_11: extractConvPairParams(11),\n conv_12: extractConvPairParams(12),\n conv_13: extractConvPairParams(13),\n };\n }\n\n function extractConvParams(prefix: string, mappedPrefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/weights`, 4, `${mappedPrefix}/filters`);\n const bias = extractWeightEntry(`${prefix}/biases`, 1, `${mappedPrefix}/bias`);\n\n return { filters, bias };\n }\n\n function extractBoxPredictorParams(idx: number): BoxPredictionParams {\n const box_encoding_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/BoxEncodingPredictor`,\n `prediction_layer/box_predictor_${idx}/box_encoding_predictor`,\n );\n const class_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/ClassPredictor`,\n `prediction_layer/box_predictor_${idx}/class_predictor`,\n );\n\n return { box_encoding_predictor, class_predictor };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n return {\n conv_0: extractPointwiseConvParams('Prediction', 0, 'prediction_layer/conv_0'),\n conv_1: extractPointwiseConvParams('Prediction', 1, 'prediction_layer/conv_1'),\n conv_2: extractPointwiseConvParams('Prediction', 2, 'prediction_layer/conv_2'),\n conv_3: extractPointwiseConvParams('Prediction', 3, 'prediction_layer/conv_3'),\n conv_4: extractPointwiseConvParams('Prediction', 4, 'prediction_layer/conv_4'),\n conv_5: extractPointwiseConvParams('Prediction', 5, 'prediction_layer/conv_5'),\n conv_6: extractPointwiseConvParams('Prediction', 6, 'prediction_layer/conv_6'),\n conv_7: extractPointwiseConvParams('Prediction', 7, 'prediction_layer/conv_7'),\n box_predictor_0: extractBoxPredictorParams(0),\n box_predictor_1: extractBoxPredictorParams(1),\n box_predictor_2: extractBoxPredictorParams(2),\n box_predictor_3: extractBoxPredictorParams(3),\n box_predictor_4: extractBoxPredictorParams(4),\n box_predictor_5: extractBoxPredictorParams(5),\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const extra_dim = weightMap['Output/extra_dim'];\n paramMappings.push({ originalPath: 'Output/extra_dim', paramPath: 'output_layer/extra_dim' });\n\n if (!isTensor3D(extra_dim)) {\n throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${extra_dim}`);\n }\n\n const params = {\n mobilenetv1: extractMobilenetV1Params(),\n prediction_layer: extractPredictionLayerParams(),\n output_layer: {\n extra_dim,\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { MobileNetV1 } from './types';\n\nconst epsilon = 0.0010000000474974513;\n\nfunction depthwiseConvLayer(\n x: tf.Tensor4D,\n params: MobileNetV1.DepthwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.depthwiseConv2d(x, params.filters, strides, 'same');\n out = tf.batchNorm(\n out,\n params.batch_norm_mean,\n params.batch_norm_variance,\n params.batch_norm_offset,\n params.batch_norm_scale,\n epsilon,\n );\n return tf.clipByValue(out, 0, 6);\n });\n}\n\nfunction getStridesForLayerIdx(layerIdx: number): [number, number] {\n return [2, 4, 6, 12].some((idx) => idx === layerIdx) ? [2, 2] : [1, 1];\n}\n\nexport function mobileNetV1(x: tf.Tensor4D, params: MobileNetV1.Params) {\n return tf.tidy(() => {\n let conv11;\n let out = pointwiseConvLayer(x, params.conv_0, [2, 2]);\n\n const convPairParams = [\n params.conv_1,\n params.conv_2,\n params.conv_3,\n params.conv_4,\n params.conv_5,\n params.conv_6,\n params.conv_7,\n params.conv_8,\n params.conv_9,\n params.conv_10,\n params.conv_11,\n params.conv_12,\n params.conv_13,\n ];\n\n convPairParams.forEach((param, i) => {\n const layerIdx = i + 1;\n const depthwiseConvStrides = getStridesForLayerIdx(layerIdx);\n out = depthwiseConvLayer(out, param.depthwise_conv, depthwiseConvStrides);\n out = pointwiseConvLayer(out, param.pointwise_conv, [1, 1]);\n if (layerIdx === 11) {\n conv11 = out;\n }\n });\n\n if (conv11 === null) {\n throw new Error('mobileNetV1 - output of conv layer 11 is null');\n }\n\n return {\n out,\n conv11: conv11 as any,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { PointwiseConvParams } from './types';\n\nexport function pointwiseConvLayer(\n x: tf.Tensor4D,\n params: PointwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.conv2d(x, params.filters, strides, 'same');\n out = tf.add(out, params.batch_norm_offset);\n return tf.clipByValue(out, 0, 6);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nfunction IOU(boxes: tf.Tensor2D, i: number, j: number) {\n const boxesData = boxes.arraySync();\n const yminI = Math.min(boxesData[i][0], boxesData[i][2]);\n const xminI = Math.min(boxesData[i][1], boxesData[i][3]);\n const ymaxI = Math.max(boxesData[i][0], boxesData[i][2]);\n const xmaxI = Math.max(boxesData[i][1], boxesData[i][3]);\n const yminJ = Math.min(boxesData[j][0], boxesData[j][2]);\n const xminJ = Math.min(boxesData[j][1], boxesData[j][3]);\n const ymaxJ = Math.max(boxesData[j][0], boxesData[j][2]);\n const xmaxJ = Math.max(boxesData[j][1], boxesData[j][3]);\n const areaI = (ymaxI - yminI) * (xmaxI - xminI);\n const areaJ = (ymaxJ - yminJ) * (xmaxJ - xminJ);\n if (areaI <= 0 || areaJ <= 0) {\n return 0.0;\n }\n const intersectionYmin = Math.max(yminI, yminJ);\n const intersectionXmin = Math.max(xminI, xminJ);\n const intersectionYmax = Math.min(ymaxI, ymaxJ);\n const intersectionXmax = Math.min(xmaxI, xmaxJ);\n const intersectionArea = Math.max(intersectionYmax - intersectionYmin, 0.0)\n * Math.max(intersectionXmax - intersectionXmin, 0.0);\n return intersectionArea / (areaI + areaJ - intersectionArea);\n}\n\nexport function nonMaxSuppression(\n boxes: tf.Tensor2D,\n scores: number[],\n maxOutputSize: number,\n iouThreshold: number,\n scoreThreshold: number,\n): number[] {\n const numBoxes = boxes.shape[0];\n const outputSize = Math.min(\n maxOutputSize,\n numBoxes,\n );\n\n const candidates = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .filter((c) => c.score > scoreThreshold)\n .sort((c1, c2) => c2.score - c1.score);\n\n const suppressFunc = (x: number) => (x <= iouThreshold ? 1 : 0);\n\n const selected: number[] = [];\n\n candidates.forEach((c) => {\n if (selected.length >= outputSize) {\n return;\n }\n const originalScore = c.score;\n\n for (let j = selected.length - 1; j >= 0; --j) {\n const iou = IOU(boxes, c.boxIndex, selected[j]);\n if (iou === 0.0) continue;\n c.score *= suppressFunc(iou);\n if (c.score <= scoreThreshold) break;\n }\n if (originalScore === c.score) {\n selected.push(c.boxIndex);\n }\n });\n\n return selected;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { OutputLayerParams } from './types';\n\nfunction getCenterCoordinatesAndSizesLayer(x: tf.Tensor2D) {\n const vec = tf.unstack(tf.transpose(x, [1, 0]));\n\n const sizes = [\n tf.sub(vec[2], vec[0]),\n tf.sub(vec[3], vec[1]),\n ];\n\n const centers = [\n tf.add(vec[0], tf.div(sizes[0], tf.scalar(2))),\n tf.add(vec[1], tf.div(sizes[1], tf.scalar(2))),\n ];\n\n return {\n sizes,\n centers,\n };\n}\n\nfunction decodeBoxesLayer(x0: tf.Tensor2D, x1: tf.Tensor2D) {\n const {\n sizes,\n centers,\n } = getCenterCoordinatesAndSizesLayer(x0);\n\n const vec = tf.unstack(tf.transpose(x1, [1, 0]));\n\n const div0_out = tf.div(tf.mul(tf.exp(tf.div(vec[2], tf.scalar(5))), sizes[0]), tf.scalar(2));\n const add0_out = tf.add(tf.mul(tf.div(vec[0], tf.scalar(10)), sizes[0]), centers[0]);\n\n const div1_out = tf.div(tf.mul(tf.exp(tf.div(vec[3], tf.scalar(5))), sizes[1]), tf.scalar(2));\n const add1_out = tf.add(tf.mul(tf.div(vec[1], tf.scalar(10)), sizes[1]), centers[1]);\n\n return tf.transpose(\n tf.stack([\n tf.sub(add0_out, div0_out),\n tf.sub(add1_out, div1_out),\n tf.add(add0_out, div0_out),\n tf.add(add1_out, div1_out),\n ]),\n [1, 0],\n );\n}\n\nexport function outputLayer(\n boxPredictions: tf.Tensor4D,\n classPredictions: tf.Tensor4D,\n params: OutputLayerParams,\n) {\n return tf.tidy(() => {\n const batchSize = boxPredictions.shape[0];\n\n let boxes = decodeBoxesLayer(\n tf.reshape(tf.tile(params.extra_dim, [batchSize, 1, 1]), [-1, 4]) as tf.Tensor2D,\n tf.reshape(boxPredictions, [-1, 4]) as tf.Tensor2D,\n );\n boxes = tf.reshape(\n boxes,\n [batchSize, (boxes.shape[0] / batchSize), 4],\n );\n\n const scoresAndClasses = tf.sigmoid(tf.slice(classPredictions, [0, 0, 1], [-1, -1, -1]));\n let scores = tf.slice(scoresAndClasses, [0, 0, 0], [-1, -1, 1]) as tf.Tensor;\n\n scores = tf.reshape(\n scores,\n [batchSize, scores.shape[1] as number],\n );\n\n const boxesByBatch = tf.unstack(boxes) as tf.Tensor2D[];\n const scoresByBatch = tf.unstack(scores) as tf.Tensor1D[];\n\n return {\n boxes: boxesByBatch,\n scores: scoresByBatch,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { boxPredictionLayer } from './boxPredictionLayer';\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { PredictionLayerParams } from './types';\n\nexport function predictionLayer(\n x: tf.Tensor4D,\n conv11: tf.Tensor4D,\n params: PredictionLayerParams,\n) {\n return tf.tidy(() => {\n const conv0 = pointwiseConvLayer(x, params.conv_0, [1, 1]);\n const conv1 = pointwiseConvLayer(conv0, params.conv_1, [2, 2]);\n const conv2 = pointwiseConvLayer(conv1, params.conv_2, [1, 1]);\n const conv3 = pointwiseConvLayer(conv2, params.conv_3, [2, 2]);\n const conv4 = pointwiseConvLayer(conv3, params.conv_4, [1, 1]);\n const conv5 = pointwiseConvLayer(conv4, params.conv_5, [2, 2]);\n const conv6 = pointwiseConvLayer(conv5, params.conv_6, [1, 1]);\n const conv7 = pointwiseConvLayer(conv6, params.conv_7, [2, 2]);\n\n const boxPrediction0 = boxPredictionLayer(conv11, params.box_predictor_0);\n const boxPrediction1 = boxPredictionLayer(x, params.box_predictor_1);\n const boxPrediction2 = boxPredictionLayer(conv1, params.box_predictor_2);\n const boxPrediction3 = boxPredictionLayer(conv3, params.box_predictor_3);\n const boxPrediction4 = boxPredictionLayer(conv5, params.box_predictor_4);\n const boxPrediction5 = boxPredictionLayer(conv7, params.box_predictor_5);\n\n const boxPredictions = tf.concat([\n boxPrediction0.boxPredictionEncoding,\n boxPrediction1.boxPredictionEncoding,\n boxPrediction2.boxPredictionEncoding,\n boxPrediction3.boxPredictionEncoding,\n boxPrediction4.boxPredictionEncoding,\n boxPrediction5.boxPredictionEncoding,\n ], 1) as tf.Tensor4D;\n\n const classPredictions = tf.concat([\n boxPrediction0.classPrediction,\n boxPrediction1.classPrediction,\n boxPrediction2.classPrediction,\n boxPrediction3.classPrediction,\n boxPrediction4.classPrediction,\n boxPrediction5.classPrediction,\n ], 1) as tf.Tensor4D;\n\n return {\n boxPredictions,\n classPredictions,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { convLayer } from '../common/index';\nimport { BoxPredictionParams } from './types';\n\nexport function boxPredictionLayer(\n x: tf.Tensor4D,\n params: BoxPredictionParams,\n) {\n return tf.tidy(() => {\n const batchSize = x.shape[0];\n\n const boxPredictionEncoding = tf.reshape(\n convLayer(x, params.box_encoding_predictor),\n [batchSize, -1, 1, 4],\n );\n const classPrediction = tf.reshape(\n convLayer(x, params.class_predictor),\n [batchSize, -1, 3],\n );\n\n return {\n boxPredictionEncoding,\n classPrediction,\n };\n });\n}\n", "export interface ISsdMobilenetv1Options {\n minConfidence?: number\n maxResults?: number\n}\n\nexport class SsdMobilenetv1Options {\n protected _name: string = 'SsdMobilenetv1Options'\n\n private _minConfidence: number\n\n private _maxResults: number\n\n constructor({ minConfidence, maxResults }: ISsdMobilenetv1Options = {}) {\n this._minConfidence = minConfidence || 0.5;\n this._maxResults = maxResults || 100;\n\n if (typeof this._minConfidence !== 'number' || this._minConfidence <= 0 || this._minConfidence >= 1) {\n throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);\n }\n\n if (typeof this._maxResults !== 'number') {\n throw new Error(`${this._name} - expected maxResults to be a number`);\n }\n }\n\n get minConfidence(): number { return this._minConfidence; }\n\n get maxResults(): number { return this._maxResults; }\n}\n", "import { SsdMobilenetv1 } from './SsdMobilenetv1';\n\nexport * from './SsdMobilenetv1';\nexport * from './SsdMobilenetv1Options';\n\nexport function createSsdMobilenetv1(weights: Float32Array) {\n const net = new SsdMobilenetv1();\n net.extractWeights(weights);\n return net;\n}\n\nexport function createFaceDetectionNet(weights: Float32Array) {\n return createSsdMobilenetv1(weights);\n}\n\n// alias for backward compatibily\nexport class FaceDetectionNet extends SsdMobilenetv1 {}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(0.738768, 0.874946),\n new Point(2.42204, 2.65704),\n new Point(4.30971, 7.04493),\n new Point(10.246, 4.59428),\n new Point(12.6868, 11.8741),\n];\n\nexport const BOX_ANCHORS_SEPARABLE = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB_SEPARABLE: [number, number, number] = [117.001, 114.697, 97.404];\n\nexport const DEFAULT_MODEL_NAME = 'tiny_yolov2_model';\nexport const DEFAULT_MODEL_NAME_SEPARABLE_CONV = 'tiny_yolov2_separable_conv_model';\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { BoundingBox } from '../classes/BoundingBox';\nimport { Dimensions } from '../classes/Dimensions';\nimport { ObjectDetection } from '../classes/ObjectDetection';\nimport { convLayer } from '../common/index';\nimport { ConvParams, SeparableConvParams } from '../common/types';\nimport { toNetInput } from '../dom/index';\nimport { NetInput } from '../dom/NetInput';\nimport { TNetInput } from '../dom/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { sigmoid } from '../ops/index';\nimport { nonMaxSuppression } from '../ops/nonMaxSuppression';\nimport { normalize } from '../ops/normalize';\nimport { TinyYolov2Config, validateConfig } from './config';\nimport { convWithBatchNorm } from './convWithBatchNorm';\nimport { depthwiseSeparableConv } from './depthwiseSeparableConv';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { leaky } from './leaky';\nimport { ITinyYolov2Options, TinyYolov2Options } from './TinyYolov2Options';\nimport { DefaultTinyYolov2NetParams, MobilenetParams, TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2Base extends NeuralNetwork {\n public static DEFAULT_FILTER_SIZES = [\n 3, 16, 32, 64, 128, 256, 512, 1024, 1024,\n ]\n\n private _config: TinyYolov2Config\n\n constructor(config: TinyYolov2Config) {\n super('TinyYolov2');\n validateConfig(config);\n this._config = config;\n }\n\n public get config(): TinyYolov2Config {\n return this._config;\n }\n\n public get withClassScores(): boolean {\n return this.config.withClassScores || this.config.classes.length > 1;\n }\n\n public get boxEncodingSize(): number {\n return 5 + (this.withClassScores ? this.config.classes.length : 0);\n }\n\n public runTinyYolov2(x: tf.Tensor4D, params: DefaultTinyYolov2NetParams): tf.Tensor4D {\n let out = convWithBatchNorm(x, params.conv0);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = convWithBatchNorm(out, params.conv6);\n out = convWithBatchNorm(out, params.conv7);\n\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public runMobilenet(x: tf.Tensor4D, params: MobilenetParams): tf.Tensor4D {\n let out = this.config.isFirstLayerConv2d\n ? leaky(convLayer(x, params.conv0 as ConvParams, 'valid', false))\n : depthwiseSeparableConv(x, params.conv0 as SeparableConvParams);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = params.conv6 ? depthwiseSeparableConv(out, params.conv6) : out;\n out = params.conv7 ? depthwiseSeparableConv(out, params.conv7) : out;\n\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public forwardInput(input: NetInput, inputSize: number): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyYolov2 - load model before inference');\n }\n\n return tf.tidy(() => {\n // let batchTensor = input.toBatchTensor(inputSize, false).toFloat()\n let batchTensor = tf.cast(input.toBatchTensor(inputSize, false), 'float32');\n batchTensor = this.config.meanRgb\n ? normalize(batchTensor, this.config.meanRgb)\n : batchTensor;\n batchTensor = batchTensor.div(tf.scalar(256)) as tf.Tensor4D;\n\n return this.config.withSeparableConvs\n ? this.runMobilenet(batchTensor, params as MobilenetParams)\n : this.runTinyYolov2(batchTensor, params as DefaultTinyYolov2NetParams);\n });\n }\n\n public async forward(input: TNetInput, inputSize: number): Promise {\n return this.forwardInput(await toNetInput(input), inputSize);\n }\n\n public async detect(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise {\n const { inputSize, scoreThreshold } = new TinyYolov2Options(forwardParams);\n\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput, inputSize);\n const out0 = tf.tidy(() => tf.unstack(out)[0].expandDims()) as tf.Tensor4D;\n\n const inputDimensions = {\n width: netInput.getInputWidth(0),\n height: netInput.getInputHeight(0),\n };\n\n const results = await this.extractBoxes(out0, netInput.getReshapedInputDimensions(0), scoreThreshold);\n out.dispose();\n out0.dispose();\n\n const boxes = results.map((res) => res.box);\n const scores = results.map((res) => res.score);\n const classScores = results.map((res) => res.classScore);\n const classNames = results.map((res) => this.config.classes[res.label]);\n\n const indices = nonMaxSuppression(\n boxes.map((box) => box.rescale(inputSize)),\n scores,\n this.config.iouThreshold,\n true,\n );\n\n const detections = indices.map((idx) => new ObjectDetection(\n scores[idx],\n classScores[idx],\n classNames[idx],\n boxes[idx],\n inputDimensions,\n ));\n\n return detections;\n }\n\n protected getDefaultModelName(): string {\n return '';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this.config);\n }\n\n protected extractParams(weights: Float32Array) {\n const filterSizes = this.config.filterSizes || TinyYolov2Base.DEFAULT_FILTER_SIZES;\n\n const numFilters = filterSizes ? filterSizes.length : undefined;\n if (numFilters !== 7 && numFilters !== 8 && numFilters !== 9) {\n throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${numFilters} filterSizes in config`);\n }\n return extractParams(weights, this.config, this.boxEncodingSize, filterSizes);\n }\n\n protected async extractBoxes(\n outputTensor: tf.Tensor4D,\n inputBlobDimensions: Dimensions,\n scoreThreshold?: number,\n ) {\n const { width, height } = inputBlobDimensions;\n const inputSize = Math.max(width, height);\n const correctionFactorX = inputSize / width;\n const correctionFactorY = inputSize / height;\n\n const numCells = outputTensor.shape[1];\n const numBoxes = this.config.anchors.length;\n\n const [boxesTensor, scoresTensor, classScoresTensor] = tf.tidy(() => {\n const reshaped = outputTensor.reshape([numCells, numCells, numBoxes, this.boxEncodingSize]);\n\n const boxes = reshaped.slice([0, 0, 0, 0], [numCells, numCells, numBoxes, 4]);\n const scores = reshaped.slice([0, 0, 0, 4], [numCells, numCells, numBoxes, 1]);\n const classScores = this.withClassScores\n ? tf.softmax(reshaped.slice([0, 0, 0, 5], [numCells, numCells, numBoxes, this.config.classes.length]), 3)\n : tf.scalar(0);\n return [boxes, scores, classScores];\n });\n\n const results = [] as any;\n\n const scoresData = await scoresTensor.array();\n const boxesData = await boxesTensor.array();\n for (let row = 0; row < numCells; row++) {\n for (let col = 0; col < numCells; col++) {\n for (let anchor = 0; anchor < numBoxes; anchor++) {\n const score = sigmoid(scoresData[row][col][anchor][0]);\n if (!scoreThreshold || score > scoreThreshold) {\n const ctX = ((col + sigmoid(boxesData[row][col][anchor][0])) / numCells) * correctionFactorX;\n const ctY = ((row + sigmoid(boxesData[row][col][anchor][1])) / numCells) * correctionFactorY;\n const widthLocal = ((Math.exp(boxesData[row][col][anchor][2]) * this.config.anchors[anchor].x) / numCells) * correctionFactorX;\n const heightLocal = ((Math.exp(boxesData[row][col][anchor][3]) * this.config.anchors[anchor].y) / numCells) * correctionFactorY;\n\n const x = (ctX - (widthLocal / 2));\n const y = (ctY - (heightLocal / 2));\n\n const pos = { row, col, anchor };\n const { classScore, label } = this.withClassScores\n ? await this.extractPredictedClass(classScoresTensor as tf.Tensor4D, pos)\n : { classScore: 1, label: 0 };\n\n results.push({\n box: new BoundingBox(x, y, x + widthLocal, y + heightLocal),\n score,\n classScore: score * classScore,\n label,\n ...pos,\n });\n }\n }\n }\n }\n\n boxesTensor.dispose();\n scoresTensor.dispose();\n classScoresTensor.dispose();\n\n return results;\n }\n\n private async extractPredictedClass(classesTensor: tf.Tensor4D, pos: { row: number, col: number, anchor: number }) {\n const { row, col, anchor } = pos;\n const classesData = await classesTensor.array();\n return Array(this.config.classes.length).fill(0)\n .map((_, i) => classesData[row][col][anchor][i])\n .map((classScore, label) => ({\n classScore,\n label,\n }))\n .reduce((max, curr) => (max.classScore > curr.classScore ? max : curr));\n }\n}\n", "import { Point } from '../classes/Point';\n\nexport type TinyYolov2Config = {\n withSeparableConvs: boolean\n iouThreshold: number\n anchors: Point[]\n classes: string[]\n meanRgb?: [number, number, number]\n withClassScores?: boolean,\n filterSizes?: number[]\n isFirstLayerConv2d?: boolean\n}\n\nconst isNumber = (arg: any) => typeof arg === 'number';\n\nexport function validateConfig(config: any) {\n if (!config) {\n throw new Error(`invalid config: ${config}`);\n }\n\n if (typeof config.withSeparableConvs !== 'boolean') {\n throw new Error(`config.withSeparableConvs has to be a boolean, have: ${config.withSeparableConvs}`);\n }\n\n if (!isNumber(config.iouThreshold) || config.iouThreshold < 0 || config.iouThreshold > 1.0) {\n throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${config.iouThreshold}`);\n }\n\n if (\n !Array.isArray(config.classes)\n || !config.classes.length\n || !config.classes.every((c: any) => typeof c === 'string')\n ) {\n throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(config.classes)}`);\n }\n\n if (\n !Array.isArray(config.anchors)\n || !config.anchors.length\n || !config.anchors.map((a: any) => a || {}).every((a: any) => isNumber(a.x) && isNumber(a.y))\n ) {\n throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(config.anchors)}`);\n }\n\n if (config.meanRgb && (\n !Array.isArray(config.meanRgb)\n || config.meanRgb.length !== 3\n || !config.meanRgb.every(isNumber)\n )) {\n throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(config.meanRgb)}`);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { leaky } from './leaky';\nimport { ConvWithBatchNorm } from './types';\n\nexport function convWithBatchNorm(x: tf.Tensor4D, params: ConvWithBatchNorm): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n\n out = tf.conv2d(out, params.conv.filters, [1, 1], 'valid');\n out = tf.sub(out, params.bn.sub);\n out = tf.mul(out, params.bn.truediv);\n out = tf.add(out, params.conv.bias);\n\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function leaky(x: tf.Tensor4D): tf.Tensor4D {\n return tf.tidy(() => {\n const min = tf.mul(x, tf.scalar(0.10000000149011612));\n return tf.add(tf.relu(tf.sub(x, min)), min);\n // return tf.maximum(x, min)\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from '../common/types';\nimport { leaky } from './leaky';\n\nexport function depthwiseSeparableConv(x: tf.Tensor4D, params: SeparableConvParams): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n\n out = tf.separableConv2d(out, params.depthwise_filter, params.pointwise_filter, [1, 1], 'valid');\n out = tf.add(out, params.bias);\n\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { extractConvParamsFactory } from '../common/index';\nimport { extractSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightsFactory } from '../common/extractWeightsFactory';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n\n function extractBatchNormParams(size: number, mappedPrefix: string): BatchNorm {\n const sub = tf.tensor1d(extractWeights(size));\n const truediv = tf.tensor1d(extractWeights(size));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/sub` },\n { paramPath: `${mappedPrefix}/truediv` },\n );\n\n return { sub, truediv };\n }\n\n function extractConvWithBatchNormParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv`);\n const bn = extractBatchNormParams(channelsOut, `${mappedPrefix}/bn`);\n\n return { conv, bn };\n }\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParams(\n weights: Float32Array,\n config: TinyYolov2Config,\n boxEncodingSize: number,\n filterSizes: number[],\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n\n const conv0 = config.isFirstLayerConv2d\n ? extractConvParams(s0, s1, 3, 'conv0')\n : extractSeparableConvParams(s0, s1, 'conv0');\n const conv1 = extractSeparableConvParams(s1, s2, 'conv1');\n const conv2 = extractSeparableConvParams(s2, s3, 'conv2');\n const conv3 = extractSeparableConvParams(s3, s4, 'conv3');\n const conv4 = extractSeparableConvParams(s4, s5, 'conv4');\n const conv5 = extractSeparableConvParams(s5, s6, 'conv5');\n const conv6 = s7 ? extractSeparableConvParams(s6, s7, 'conv6') : undefined;\n const conv7 = s8 ? extractSeparableConvParams(s7, s8, 'conv7') : undefined;\n const conv8 = extractConvParams(s8 || s7 || s6, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n } else {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = extractConvWithBatchNormParams(s0, s1, 'conv0');\n const conv1 = extractConvWithBatchNormParams(s1, s2, 'conv1');\n const conv2 = extractConvWithBatchNormParams(s2, s3, 'conv2');\n const conv3 = extractConvWithBatchNormParams(s3, s4, 'conv3');\n const conv4 = extractConvWithBatchNormParams(s4, s5, 'conv4');\n const conv5 = extractConvWithBatchNormParams(s5, s6, 'conv5');\n const conv6 = extractConvWithBatchNormParams(s6, s7, 'conv6');\n const conv7 = extractConvWithBatchNormParams(s7, s8, 'conv7');\n const conv8 = extractConvParams(s8, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n }\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from '../common/index';\nimport { disposeUnusedWeightTensors } from '../common/disposeUnusedWeightTensors';\nimport { loadSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightEntryFactory } from '../common/extractWeightEntryFactory';\nimport { ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractBatchNormParams(prefix: string): BatchNorm {\n const sub = extractWeightEntry(`${prefix}/sub`, 1);\n const truediv = extractWeightEntry(`${prefix}/truediv`, 1);\n return { sub, truediv };\n }\n\n function extractConvParams(prefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { filters, bias };\n }\n\n function extractConvWithBatchNormParams(prefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(`${prefix}/conv`);\n const bn = extractBatchNormParams(`${prefix}/bn`);\n return { conv, bn };\n }\n\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n config: TinyYolov2Config,\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n // eslint-disable-next-line no-mixed-operators\n const numFilters = (config.filterSizes && config.filterSizes.length || 9);\n params = {\n conv0: config.isFirstLayerConv2d ? extractConvParams('conv0') : extractSeparableConvParams('conv0'),\n conv1: extractSeparableConvParams('conv1'),\n conv2: extractSeparableConvParams('conv2'),\n conv3: extractSeparableConvParams('conv3'),\n conv4: extractSeparableConvParams('conv4'),\n conv5: extractSeparableConvParams('conv5'),\n conv6: numFilters > 7 ? extractSeparableConvParams('conv6') : undefined,\n conv7: numFilters > 8 ? extractSeparableConvParams('conv7') : undefined,\n conv8: extractConvParams('conv8'),\n };\n } else {\n params = {\n conv0: extractConvWithBatchNormParams('conv0'),\n conv1: extractConvWithBatchNormParams('conv1'),\n conv2: extractConvWithBatchNormParams('conv2'),\n conv3: extractConvWithBatchNormParams('conv3'),\n conv4: extractConvWithBatchNormParams('conv4'),\n conv5: extractConvWithBatchNormParams('conv5'),\n conv6: extractConvWithBatchNormParams('conv6'),\n conv7: extractConvWithBatchNormParams('conv7'),\n conv8: extractConvParams('conv8'),\n };\n }\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "export interface ITinyYolov2Options {\n inputSize?: number\n scoreThreshold?: number\n}\n\nexport class TinyYolov2Options {\n protected _name: string = 'TinyYolov2Options'\n\n private _inputSize: number\n\n private _scoreThreshold: number\n\n constructor({ inputSize, scoreThreshold }: ITinyYolov2Options = {}) {\n this._inputSize = inputSize || 416;\n this._scoreThreshold = scoreThreshold || 0.5;\n\n if (typeof this._inputSize !== 'number' || this._inputSize % 32 !== 0) {\n throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);\n }\n\n if (typeof this._scoreThreshold !== 'number' || this._scoreThreshold <= 0 || this._scoreThreshold >= 1) {\n throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`);\n }\n }\n\n get inputSize(): number { return this._inputSize; }\n\n get scoreThreshold(): number { return this._scoreThreshold; }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/types';\nimport { TNetInput } from '../dom/types';\nimport {\n BOX_ANCHORS,\n BOX_ANCHORS_SEPARABLE,\n DEFAULT_MODEL_NAME,\n DEFAULT_MODEL_NAME_SEPARABLE_CONV,\n IOU_THRESHOLD,\n MEAN_RGB_SEPARABLE,\n} from './const';\nimport { TinyYolov2Base } from './TinyYolov2Base';\nimport { ITinyYolov2Options } from './TinyYolov2Options';\nimport { TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2 extends TinyYolov2Base {\n constructor(withSeparableConvs: boolean = true) {\n const config = {\n withSeparableConvs,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n ...(withSeparableConvs\n ? {\n anchors: BOX_ANCHORS_SEPARABLE,\n meanRgb: MEAN_RGB_SEPARABLE,\n }\n : {\n anchors: BOX_ANCHORS,\n withClassScores: true,\n }),\n };\n\n super(config);\n }\n\n public get withSeparableConvs(): boolean {\n return this.config.withSeparableConvs;\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return this.withSeparableConvs ? DEFAULT_MODEL_NAME_SEPARABLE_CONV : DEFAULT_MODEL_NAME;\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { TinyYolov2 } from './TinyYolov2';\n\nexport * from './TinyYolov2Options';\n\nexport * from './config';\nexport * from './types';\n\nexport { TinyYolov2 };\n\nexport function createTinyYolov2(weights: Float32Array, withSeparableConvs: boolean = true) {\n const net = new TinyYolov2(withSeparableConvs);\n net.extractWeights(weights);\n return net;\n}\n", "import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\n\nexport interface ITinyFaceDetectorOptions extends ITinyYolov2Options {}\n\nexport class TinyFaceDetectorOptions extends TinyYolov2Options {\n protected _name: string = 'TinyFaceDetectorOptions'\n}\n", "export class ComposableTask {\n public async then(\n // eslint-disable-next-line no-unused-vars\n onfulfilled: (value: T) => T | PromiseLike,\n ): Promise {\n return onfulfilled(await this.run());\n }\n\n public async run(): Promise {\n throw new Error('ComposableTask - run is not implemented');\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class DetectFaceLandmarksTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected useTinyLandmarkNet: boolean,\n ) {\n super();\n }\n\n protected get landmarkNet(): FaceLandmark68Net | FaceLandmark68TinyNet {\n return this.useTinyLandmarkNet\n ? nets.faceLandmark68TinyNet\n : nets.faceLandmark68Net;\n }\n}\n\nexport class DetectAllFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n const detections = parentResults.map((res) => res.detection);\n\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, detections)\n : await extractFaces(this.input, detections);\n\n const faceLandmarksByFace = await Promise.all(faces.map(\n (face) => this.landmarkNet.detectLandmarks(face),\n )) as FaceLandmarks68[];\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return parentResults.map((parentResult, i) => extendWithFaceLandmarks(parentResult, faceLandmarksByFace[i]));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class DetectSingleFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { detection } = parentResult;\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, [detection])\n : await extractFaces(this.input, [detection]);\n\n const landmarks = await this.landmarkNet.detectLandmarks(faces[0]) as FaceLandmarks68;\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return extendWithFaceLandmarks(parentResult, landmarks);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\n\nexport async function extractAllFacesAndComputeResults, TResult>(\n parentResults: TSource[],\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResults: (faces: Array) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment: (parentResult: WithFaceLandmarks) => FaceDetection = ({ alignedRect }) => alignedRect,\n) {\n const faceBoxes = parentResults.map((parentResult) => (isWithFaceLandmarks(parentResult)\n ? getRectForAlignment(parentResult)\n : parentResult.detection));\n const faces: Array = extractedFaces || (\n input instanceof tf.Tensor\n ? await extractFaceTensors(input, faceBoxes)\n : await extractFaces(input, faceBoxes)\n );\n\n const results = await computeResults(faces);\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return results;\n}\n\nexport async function extractSingleFaceAndComputeResult, TResult>(\n parentResult: TSource,\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResult: (face: HTMLCanvasElement | tf.Tensor3D) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment?: (parentResultLocal: WithFaceLandmarks) => FaceDetection,\n) {\n return extractAllFacesAndComputeResults(\n [parentResult],\n input,\n async (faces) => computeResult(faces[0]),\n extractedFaces,\n getRectForAlignment,\n );\n}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB: [number, number, number] = [117.001, 114.697, 97.404];\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/index';\nimport { TNetInput } from '../dom/index';\nimport { ITinyYolov2Options } from '../tinyYolov2/index';\nimport { TinyYolov2Base } from '../tinyYolov2/TinyYolov2Base';\nimport { TinyYolov2NetParams } from '../tinyYolov2/types';\nimport { BOX_ANCHORS, IOU_THRESHOLD, MEAN_RGB } from './const';\n\nexport class TinyFaceDetector extends TinyYolov2Base {\n constructor() {\n const config = {\n withSeparableConvs: true,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n anchors: BOX_ANCHORS,\n meanRgb: MEAN_RGB,\n isFirstLayerConv2d: true,\n filterSizes: [3, 16, 32, 64, 128, 256, 512],\n };\n\n super(config);\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_face_detector_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { AgeGenderNet } from '../ageGenderNet/AgeGenderNet';\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressionNet } from '../faceExpressionNet/FaceExpressionNet';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { FaceRecognitionNet } from '../faceRecognitionNet/FaceRecognitionNet';\nimport { SsdMobilenetv1 } from '../ssdMobilenetv1/SsdMobilenetv1';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetector } from '../tinyFaceDetector/TinyFaceDetector';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { ITinyYolov2Options, TinyYolov2 } from '../tinyYolov2/index';\n\nexport const nets = {\n ssdMobilenetv1: new SsdMobilenetv1(),\n tinyFaceDetector: new TinyFaceDetector(),\n tinyYolov2: new TinyYolov2(),\n faceLandmark68Net: new FaceLandmark68Net(),\n faceLandmark68TinyNet: new FaceLandmark68TinyNet(),\n faceRecognitionNet: new FaceRecognitionNet(),\n faceExpressionNet: new FaceExpressionNet(),\n ageGenderNet: new AgeGenderNet(),\n};\n\n/**\n * Attempts to detect all faces in an image using SSD Mobilenetv1 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see SsdMobilenetv1Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const ssdMobilenetv1 = (input: TNetInput, options: SsdMobilenetv1Options): Promise => nets.ssdMobilenetv1.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Face Detector.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyFaceDetectorOptions constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyFaceDetector = (input: TNetInput, options: TinyFaceDetectorOptions): Promise => nets.tinyFaceDetector.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Yolov2 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyYolov2Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyYolov2 = (input: TNetInput, options: ITinyYolov2Options): Promise => nets.tinyYolov2.locateFaces(input, options);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarks = (input: TNetInput): Promise => nets.faceLandmark68Net.detectLandmarks(input);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image\n * using a tinier version of the 68 point face landmark model, which is slightly\n * faster at inference, but also slightly less accurate.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarksTiny = (input: TNetInput): Promise => nets.faceLandmark68TinyNet.detectLandmarks(input);\n\n/**\n * Computes a 128 entry vector (face descriptor / face embeddings) from the face shown in an image,\n * which uniquely represents the features of that persons face. The computed face descriptor can\n * be used to measure the similarity between faces, by computing the euclidean distance of two\n * face descriptors.\n *\n * @param inputs The face image extracted from the aligned bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Face descriptor with 128 entries or array thereof in case of batch input.\n */\nexport const computeFaceDescriptor = (input: TNetInput): Promise => nets.faceRecognitionNet.computeFaceDescriptor(input);\n\n/**\n * Recognizes the facial expressions from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Facial expressions with corresponding probabilities or array thereof in case of batch input.\n */\nexport const recognizeFaceExpressions = (input: TNetInput): Promise => nets.faceExpressionNet.predictExpressions(input);\n\n/**\n * Predicts age and gender from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Predictions with age, gender and gender probability or array thereof in case of batch input.\n */\nexport const predictAgeAndGender = (input: TNetInput): Promise => nets.ageGenderNet.predictAgeAndGender(input);\n\nexport const loadSsdMobilenetv1Model = (url: string) => nets.ssdMobilenetv1.load(url);\nexport const loadTinyFaceDetectorModel = (url: string) => nets.tinyFaceDetector.load(url);\nexport const loadTinyYolov2Model = (url: string) => nets.tinyYolov2.load(url);\nexport const loadFaceLandmarkModel = (url: string) => nets.faceLandmark68Net.load(url);\nexport const loadFaceLandmarkTinyModel = (url: string) => nets.faceLandmark68TinyNet.load(url);\nexport const loadFaceRecognitionModel = (url: string) => nets.faceRecognitionNet.load(url);\nexport const loadFaceExpressionModel = (url: string) => nets.faceExpressionNet.load(url);\nexport const loadAgeGenderModel = (url: string) => nets.ageGenderNet.load(url);\n\n// backward compatibility\nexport const loadFaceDetectionModel = loadSsdMobilenetv1Model;\nexport const locateFaces = ssdMobilenetv1;\nexport const detectLandmarks = detectFaceLandmarks;\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderTask,\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\n\nexport class PredictFaceExpressionsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const faceExpressionsByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map(\n (parentResult, i) => extendWithFaceExpressions(parentResult, faceExpressionsByFace[i]),\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const faceExpressions = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithFaceExpressions(parentResult, faceExpressions);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictAllFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { TNetInput } from '../dom/index';\nimport { extendWithAge, WithAge } from '../factories/WithAge';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { extendWithGender, WithGender } from '../factories/WithGender';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllFaceExpressionsTask,\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class PredictAgeAndGenderTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase>[], TSource[]> {\n public async run(): Promise>[]> {\n const parentResults = await this.parentTask;\n\n const ageAndGenderByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map((parentResult, i) => {\n const { age, gender, genderProbability } = ageAndGenderByFace[i];\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n });\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase> | undefined, TSource | undefined> {\n public async run(): Promise> | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { age, gender, genderProbability } = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictAllAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDescriptor, WithFaceDescriptor } from '../factories/WithFaceDescriptor';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class ComputeFaceDescriptorsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n ) {\n super();\n }\n}\n\nexport class ComputeAllFaceDescriptorsTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const descriptors = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n (faces) => Promise.all(faces.map((face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise)),\n null,\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return descriptors.map((descriptor, i) => extendWithFaceDescriptor(parentResults[i], descriptor));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n\nexport class ComputeSingleFaceDescriptorTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n const descriptor = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise,\n null,\n // eslint-disable-next-line no-shadow\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return extendWithFaceDescriptor(parentResult, descriptor);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { TinyYolov2Options } from '../tinyYolov2/index';\nimport { ComposableTask } from './ComposableTask';\nimport { DetectAllFaceLandmarksTask, DetectSingleFaceLandmarksTask } from './DetectFaceLandmarksTasks';\nimport { nets } from './nets';\nimport { PredictAllAgeAndGenderTask, PredictSingleAgeAndGenderTask } from './PredictAgeAndGenderTask';\nimport { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from './PredictFaceExpressionsTask';\nimport { FaceDetectionOptions } from './types';\n\nexport class DetectFacesTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n ) {\n super();\n }\n}\n\nexport class DetectAllFacesTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const { input, options } = this;\n\n // eslint-disable-next-line no-nested-ternary\n const faceDetectionFunction = options instanceof TinyFaceDetectorOptions\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyFaceDetector.locateFaces(input, options)\n : (\n // eslint-disable-next-line no-nested-ternary\n options instanceof SsdMobilenetv1Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.ssdMobilenetv1.locateFaces(input, options)\n : (\n options instanceof TinyYolov2Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyYolov2.locateFaces(input, options)\n : null\n )\n );\n\n if (!faceDetectionFunction) {\n throw new Error('detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options');\n }\n\n return faceDetectionFunction(input);\n }\n\n private runAndExtendWithFaceDetections(): Promise[]> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise[]>(async (resolve) => {\n const detections = await this.run();\n resolve(detections.map((detection) => extendWithFaceDetection({}, detection)));\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectAllFaceLandmarksTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n}\n\nexport class DetectSingleFaceTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const faceDetections = await new DetectAllFacesTask(this.input, this.options);\n let faceDetectionWithHighestScore = faceDetections[0];\n faceDetections.forEach((faceDetection) => {\n if (faceDetection.score > faceDetectionWithHighestScore.score) {\n faceDetectionWithHighestScore = faceDetection;\n }\n });\n return faceDetectionWithHighestScore;\n }\n\n private runAndExtendWithFaceDetection(): Promise | undefined> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise | undefined>(async (resolve) => {\n const detection = await this.run();\n resolve(detection ? extendWithFaceDetection<{}>({}, detection) : undefined);\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectSingleFaceLandmarksTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n}\n", "import { TNetInput } from '../dom/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { DetectAllFacesTask, DetectSingleFaceTask } from './DetectFacesTasks';\nimport { FaceDetectionOptions } from './types';\n\nexport function detectSingleFace(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectSingleFaceTask {\n return new DetectSingleFaceTask(input, options);\n}\n\nexport function detectAllFaces(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectAllFacesTask {\n return new DetectAllFacesTask(input, options);\n}\n", "import { TNetInput } from '../dom/index';\nimport { WithFaceDescriptor, WithFaceDetection, WithFaceLandmarks } from '../factories/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';\nimport { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\nimport { detectAllFaces } from './detectFaces';\n\n// export allFaces API for backward compatibility\n\nexport async function allFacesSsdMobilenetv1(\n input: TNetInput,\n minConfidence?: number,\n): Promise>>[]> {\n return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport async function allFacesTinyYolov2(\n input: TNetInput,\n forwardParams: ITinyYolov2Options = {},\n): Promise>>[]> {\n return detectAllFaces(input, new TinyYolov2Options(forwardParams))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport const allFaces = allFacesSsdMobilenetv1;\n", "export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {\n if (arr1.length !== arr2.length) throw new Error('euclideanDistance: arr1.length !== arr2.length');\n\n const desc1 = Array.from(arr1);\n const desc2 = Array.from(arr2);\n\n return Math.sqrt(\n desc1\n .map((val, i) => val - desc2[i])\n .reduce((res, diff) => res + (diff ** 2), 0),\n );\n}\n", "import { FaceMatch } from '../classes/FaceMatch';\nimport { LabeledFaceDescriptors } from '../classes/LabeledFaceDescriptors';\nimport { euclideanDistance } from '../euclideanDistance';\nimport { WithFaceDescriptor } from '../factories/index';\n\nexport class FaceMatcher {\n private _labeledDescriptors: LabeledFaceDescriptors[]\n\n private _distanceThreshold: number\n\n constructor(\n inputs: LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>,\n distanceThreshold: number = 0.6,\n ) {\n this._distanceThreshold = distanceThreshold;\n\n const inputArray = Array.isArray(inputs) ? inputs : [inputs];\n\n if (!inputArray.length) {\n throw new Error('FaceRecognizer.constructor - expected atleast one input');\n }\n\n let count = 1;\n const createUniqueLabel = () => `person ${count++}`;\n\n this._labeledDescriptors = inputArray.map((desc) => {\n if (desc instanceof LabeledFaceDescriptors) {\n return desc;\n }\n\n if (desc instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc]);\n }\n\n if (desc.descriptor && desc.descriptor instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc.descriptor]);\n }\n\n throw new Error('FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>');\n });\n }\n\n public get labeledDescriptors(): LabeledFaceDescriptors[] { return this._labeledDescriptors; }\n\n public get distanceThreshold(): number { return this._distanceThreshold; }\n\n public computeMeanDistance(queryDescriptor: Float32Array, descriptors: Float32Array[]): number {\n return descriptors\n .map((d) => euclideanDistance(d, queryDescriptor))\n .reduce((d1, d2) => d1 + d2, 0)\n / (descriptors.length || 1);\n }\n\n public matchDescriptor(queryDescriptor: Float32Array): FaceMatch {\n return this.labeledDescriptors\n .map(({ descriptors, label }) => new FaceMatch(\n label,\n this.computeMeanDistance(queryDescriptor, descriptors),\n ))\n .reduce((best, curr) => (best.distance < curr.distance ? best : curr));\n }\n\n public findBestMatch(queryDescriptor: Float32Array): FaceMatch {\n const bestMatch = this.matchDescriptor(queryDescriptor);\n return bestMatch.distance < this.distanceThreshold\n ? bestMatch\n : new FaceMatch('unknown', bestMatch.distance);\n }\n\n public toJSON(): any {\n return {\n distanceThreshold: this.distanceThreshold,\n labeledDescriptors: this.labeledDescriptors.map((ld) => ld.toJSON()),\n };\n }\n\n public static fromJSON(json: any): FaceMatcher {\n const labeledDescriptors = json.labeledDescriptors\n .map((ld: any) => LabeledFaceDescriptors.fromJSON(ld));\n return new FaceMatcher(labeledDescriptors, json.distanceThreshold);\n }\n}\n", "import { TinyFaceDetector } from './TinyFaceDetector';\n\nexport * from './TinyFaceDetector';\nexport * from './TinyFaceDetectorOptions';\n\nexport function createTinyFaceDetector(weights: Float32Array) {\n const net = new TinyFaceDetector();\n net.extractWeights(weights);\n return net;\n}\n", "import { Dimensions, IDimensions } from './classes/index';\nimport { FaceDetection } from './classes/FaceDetection';\nimport { FaceLandmarks } from './classes/FaceLandmarks';\nimport { extendWithFaceDetection, isWithFaceDetection } from './factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, isWithFaceLandmarks } from './factories/WithFaceLandmarks';\n\nexport function resizeResults(results: T, dimensions: IDimensions): T {\n const { width, height } = new Dimensions(dimensions.width, dimensions.height);\n\n if (width <= 0 || height <= 0) {\n throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({ width, height })}`);\n }\n\n if (Array.isArray(results)) {\n // return results.map(obj => resizeResults(obj, { width, height })) as any as T\n return (results as Array).map((obj) => resizeResults(obj, { width, height } as IDimensions)) as any as T;\n }\n\n if (isWithFaceLandmarks(results)) {\n const resizedDetection = results.detection.forSize(width, height);\n const resizedLandmarks = results.unshiftedLandmarks.forSize(resizedDetection.box.width, resizedDetection.box.height);\n return extendWithFaceLandmarks(extendWithFaceDetection(results, resizedDetection), resizedLandmarks);\n }\n\n if (isWithFaceDetection(results)) {\n return extendWithFaceDetection(results, results.detection.forSize(width, height));\n }\n\n if (results instanceof FaceLandmarks || results instanceof FaceDetection) {\n return (results as any).forSize(width, height);\n }\n\n return results;\n}\n"], - "mappings": ";;;;;;;wmBAKA,kDACA,+DADA,UACA,YCNA,6CAAO,cACL,MAAO,OAAO,SAAW,UACpB,IACA,MAAO,KAAW,aAGlB,MAAO,UAAY,aAAe,CAAC,CAAC,QAAQ,WCNnD,OAAoB,OCApB,qRCEO,YACL,EACA,EACA,EAAoB,IAUpB,GARA,EAAI,YAEJ,EAAO,MAAM,GAAG,QAAQ,CAAC,CAAE,IAAG,KAAK,KACjC,GAAM,GAAO,EAAO,GACpB,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,KAGZ,GACF,GAAM,GAAO,EAAO,EAAO,OAAS,GAC9B,EAAK,EAAO,GAClB,GAAI,CAAC,GAAQ,CAAC,EACZ,OAGF,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,EAAG,EAAG,GAGtB,EAAI,SC1BN,2RAAA,OAAoB,OCApB,YAYE,YAAY,EAAe,GACzB,GAAI,CAAC,GAAc,IAAU,CAAC,GAAc,GAC1C,KAAM,IAAI,OAAM,wFAAwF,KAAK,UAAU,CAAE,QAAO,cAGlI,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,QAEnC,UACL,MAAO,IAAI,GAAW,EAAI,KAAK,MAAO,EAAI,KAAK,UDrB5C,YAAkB,EAAa,GACpC,MAAO,aAAqB,YAAU,EAAO,MAAM,SAAW,EAGzD,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,WAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAiB,GACtB,MAAO,GAAM,GAAM,EAGd,YAAgB,GACrB,MAAO,GAAM,GAAM,EAGd,YAAe,EAAa,EAAe,GAChD,GAAM,GAAI,IAAM,EAChB,MAAO,MAAK,MAAM,EAAM,GAAK,EAGxB,YAAsB,GAC3B,MAAO,IAAO,EAAI,OAAS,EAAI,OAG1B,YAAmC,CAAE,QAAO,UAAuB,GACxE,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,IAAI,GAAW,KAAK,MAAM,EAAQ,GAAQ,KAAK,MAAM,EAAS,IAGhE,YAAwB,GAC7B,MAAO,GAAI,OAAO,CAAC,EAAK,IAAO,EAAI,IAAI,GAAK,GAAI,GAAM,EAAG,IACtD,IAAI,GAAI,GAAM,EAAI,OAAQ,EAAI,SAG5B,YAAe,EAAa,EAAe,GAChD,MAAO,OAAM,GAAK,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,EAAS,EAAI,GAGhD,YAAuB,GAE5B,MAAO,CAAC,CAAC,GAAQ,IAAQ,UAAc,IAAQ,WAAc,CAAC,OAAO,MAAM,IAAQ,IAAQ,EAGtF,YAA4B,GACjC,MAAO,IAAc,IAAQ,GAAO,GAAK,GAAO,EE9DlD,YAUE,YAAY,EAAW,GACrB,KAAK,GAAK,EACV,KAAK,GAAK,KAGR,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,GAEvB,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,MACL,MAAO,IAAI,GAAM,KAAK,IAAI,KAAK,GAAI,KAAK,IAAI,KAAK,IAG5C,YACL,MAAO,MAAK,KAAM,KAAK,GAAK,EAAM,KAAK,GAAK,GAGvC,QACL,MAAO,IAAI,GAAM,KAAK,MAAM,KAAK,GAAI,KAAK,MAAM,KAAK,MC5CzD,kBAOgB,QAAO,GACnB,MAAO,CAAC,CAAC,GAAQ,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,MAAO,EAAK,QAAQ,MAAM,UAGrD,kBAAiB,EAAU,EAAgB,EAAmC,IAC1F,GAAI,CAAC,EAAI,OAAO,GACd,KAAM,IAAI,OAAM,GAAG,oBAAyB,KAAK,UAAU,2DAG7D,GAAI,CAAC,GAA4B,GAAI,MAAQ,GAAK,EAAI,OAAS,GAC7D,KAAM,IAAI,OAAM,GAAG,cAAmB,EAAI,sBAAsB,EAAI,oCAYxE,YAAY,EAA4B,EAAmC,IACzE,GAAM,GAAO,GAAQ,GAEf,EAAS,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAO,EAAI,QAAQ,MAAM,IAC1D,EAAS,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAAQ,MAAM,IAE3D,GAAI,CAAC,GAAU,CAAC,EACd,KAAM,IAAI,OAAM,2EAA2E,KAAK,UAAU,MAG5G,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,EAC1B,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAC9B,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAQ,EAAI,KAAM,EAAI,OAAS,EAAI,KAE/D,EAAI,iBAAiB,CACnB,IAAG,IAAG,QAAO,UACZ,kBAAmB,GAEtB,KAAK,GAAK,EACV,KAAK,GAAK,EACV,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,MAE1B,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,WAE/B,QAAiB,MAAO,MAAK,KAE7B,OAAgB,MAAO,MAAK,KAE5B,SAAkB,MAAO,MAAK,EAAI,KAAK,SAEvC,UAAmB,MAAO,MAAK,EAAI,KAAK,UAExC,QAAiB,MAAO,MAAK,MAAQ,KAAK,UAE1C,WAAmB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,QAEpD,YAAoB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAEtD,cAAsB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,WAEvD,eAAuB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAE7D,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,WACL,GAAI,CACF,IAAG,IAAG,QAAO,UACX,KACE,EAAO,KAAK,IAAI,EAAQ,GAC9B,MAAI,GAAQ,GACV,IAAM,EAAO,EACb,GAAS,GAEP,EAAS,GACX,IAAM,EAAO,EACb,GAAU,GAGL,GAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QAAQ,GACb,GAAM,GAAS,GAAa,GAAM,EAAkB,MAAQ,EACtD,EAAS,GAAa,GAAM,EAAkB,OAAS,EAC7D,MAAO,IAAI,GAAI,CACb,EAAG,KAAK,EAAI,EACZ,EAAG,KAAK,EAAI,EACZ,MAAO,KAAK,MAAQ,EACpB,OAAQ,KAAK,OAAS,IAInB,IAAI,EAAc,GACvB,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAC5B,KAAK,EAAK,EAAO,EACjB,KAAK,EAAK,EAAO,EACjB,KAAK,MAAQ,EACb,KAAK,OAAS,GAEhB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,mBAAmB,EAAkB,GAC1C,GAAM,CACJ,IAAG,IAAG,QAAO,UACX,KACE,EAAW,KAAK,IAAI,EAAG,GACvB,EAAW,KAAK,IAAI,EAAG,GAEvB,EAAW,EAAQ,EACnB,EAAY,EAAS,EACrB,EAAe,KAAK,IAAI,EAAU,EAAW,GAC7C,EAAgB,KAAK,IAAI,EAAW,EAAY,GAEtD,MAAQ,IAAI,GAAI,CACd,EAAG,EAAU,EAAG,EAAU,MAAO,EAAc,OAAQ,IACrD,QAGC,MAAM,EAAY,GACvB,GAAM,CAAE,QAAO,UAAW,KACpB,EAAI,KAAK,EAAI,EACb,EAAI,KAAK,EAAI,EAEnB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,aAAa,EAAqB,GACvC,GAAM,GAAI,KAAK,MAAQ,EACjB,EAAI,KAAK,OAAS,EAElB,EAAK,EACL,EAAK,EACP,EAAM,EACN,EAAM,EAEN,EAAI,KAAK,KACT,EAAI,KAAK,IACT,EAAK,KAAK,MACV,EAAK,KAAK,OAEd,MAAI,GAAK,GACP,GAAM,CAAC,EAAK,EAAa,EACzB,EAAK,GAEH,EAAK,GACP,GAAM,CAAC,EAAK,EAAc,EAC1B,EAAK,GAEH,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAEF,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAGC,CACL,KAAI,MAAK,KAAI,MAAK,IAAG,KAAI,IAAG,KAAI,IAAG,KAIhC,UAAU,GACf,MAAO,IAAI,GAAI,CACb,KAAM,KAAK,KAAQ,EAAO,KAAO,KAAK,MACtC,IAAK,KAAK,IAAO,EAAO,IAAM,KAAK,OACnC,MAAO,KAAK,MAAS,EAAO,MAAQ,KAAK,MACzC,OAAQ,KAAK,OAAU,EAAO,OAAS,KAAK,SAC3C,WAAW,UC9MlB,oBASiC,GAC/B,YAAY,EAAc,EAAa,EAAe,EAAgB,EAAmC,IACvG,MAAM,CACJ,OAAM,MAAK,QAAO,UACjB,KCbP,aAeE,YACE,EACA,EACA,EACA,EACA,GAEA,KAAK,WAAa,GAAI,GAAW,EAAU,MAAO,EAAU,QAC5D,KAAK,OAAS,EACd,KAAK,YAAc,EACnB,KAAK,WAAa,EAClB,KAAK,KAAO,GAAI,GAAI,GAAa,QAAQ,KAAK,eAGrC,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,eAEnC,aAAsB,MAAO,MAAK,cAElC,OAAa,MAAO,MAAK,QAEzB,aAA0B,MAAO,MAAK,cAEtC,cAAuB,MAAO,MAAK,UAAU,SAE7C,eAAwB,MAAO,MAAK,UAAU,UAE9C,eAAqB,MAAO,IAAI,GAAI,KAAK,MAAM,QAAQ,KAAK,UAAU,WAE1E,QAAQ,EAAe,GAC5B,MAAO,IAAI,IACT,KAAK,MACL,KAAK,WACL,KAAK,UACL,KAAK,YACL,CAAE,QAAO,aCnDf,mBAUmC,IACjC,YACE,EACA,EACA,GAEA,MAAM,EAAO,EAAO,GAAI,EAAa,GAGhC,QAAQ,EAAe,GAC5B,GAAM,CAAE,QAAO,cAAa,aAAc,MAAM,QAAQ,EAAO,GAC/D,MAAO,IAAI,GAAc,EAAO,EAAa,KCnB1C,YAAa,EAAW,EAAW,EAAiB,IACzD,GAAM,GAAQ,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,MAAO,EAAK,OAAS,KAAK,IAAI,EAAK,KAAM,EAAK,OAClF,EAAS,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,OAAQ,EAAK,QAAU,KAAK,IAAI,EAAK,IAAK,EAAK,MACpF,EAAe,EAAQ,EAE7B,MAAO,GACH,EAAgB,GAAK,KAAO,EAAK,KAAO,GACxC,EAAe,KAAK,IAAI,EAAK,KAAM,EAAK,MCPvC,YAAiB,GACtB,GAAM,GAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAExD,MAAO,IAAI,IAAY,EAAM,EAAM,EAAM,GCPpC,YACL,EACA,EACA,EACA,EAAiB,IAEjB,GAAI,GAAuB,EACxB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAC/B,IAAI,AAAC,GAAM,EAAE,UAEV,EAAiB,GAEvB,KAAO,EAAqB,OAAS,IACnC,GAAM,GAAO,EAAqB,MAClC,EAAK,KAAK,GAEV,GAAM,GAAU,EAEV,EAAoB,GAC1B,OAAS,GAAI,EAAG,EAAI,EAAQ,OAAQ,KAClC,GAAM,GAAM,EAAQ,GAEd,EAAU,EAAM,GAChB,EAAS,EAAM,GAErB,EAAQ,KAAK,GAAI,EAAS,EAAQ,IAGpC,EAAuB,EAAqB,OAC1C,CAAC,EAAG,IAAM,EAAQ,IAAM,GAI5B,MAAO,GCrCT,OAAoB,OAEb,YAAmB,EAAgB,GACxC,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAG,EAAG,GAAK,EACZ,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAU,AAAG,UAAO,CAAC,EAAO,EAAO,GAAQ,GAEjD,MAAO,AAAG,QAAI,EAAG,KCVrB,OAAoB,OAUb,YACL,EACA,EAAyB,IAEzB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAQ,GAAS,EAAU,MAAM,MAAM,GAC9C,GAAI,IAAW,EACb,MAAO,GAGT,GAAM,GAAU,KAAK,IAAI,EAAS,GAC5B,EAAgB,KAAK,MAAM,EAAW,GAAgB,GAAM,IAC5D,EAAc,EAAS,EAAQ,EAAI,EAEnC,EAAsB,AAAC,IAC3B,GAAM,GAAqB,EAAU,MAAM,QAC3C,SAAmB,GAAe,EAC3B,AAAG,QAAK,EAAoB,EAAG,YAGlC,EAAsB,EAAoB,GAC1C,EAAyB,EAAW,EAAoB,MAAM,GAM9D,EAAiB,CAJM,GAAiB,EAC1C,EAAoB,GACpB,KAIF,EACA,GAEC,OAAO,AAAC,GAAM,CAAC,CAAC,GAEhB,IAAI,AAAC,GAAiB,AAAG,QAAK,EAAG,YACpC,MAAO,AAAG,WAAO,EAAgB,KC7C9B,YAAsB,GAC3B,GAAM,GAAQ,EAAW,QACzB,OAAS,GAAI,EAAM,OAAS,EAAG,EAAI,EAAG,KACpC,GAAM,GAAI,KAAK,MAAM,KAAK,SAAY,GAAI,IACpC,EAAI,EAAM,GAChB,EAAM,GAAK,EAAM,GACjB,EAAM,GAAK,EAEb,MAAO,GCDF,YAAiB,GACtB,MAAO,GAAK,GAAI,KAAK,IAAI,CAAC,IAGrB,YAAwB,GAC7B,MAAO,MAAK,IAAI,EAAK,GAAI,ICZ3B,oBAS0B,GACxB,YAAY,EAAW,EAAW,EAAe,EAAgB,EAAmC,IAClG,MAAM,CACJ,IAAG,IAAG,QAAO,UACZ,KCHP,GAAM,IAAO,GACP,GAAO,IACP,GAAW,IAZjB,QA0BE,YACE,EACA,EACA,EAAe,GAAI,GAAM,EAAG,IAE5B,GAAM,CAAE,QAAO,UAAW,EAC1B,KAAK,SAAW,GAAI,GAAW,EAAO,GACtC,KAAK,OAAS,EACd,KAAK,WAAa,EAA8B,IAC9C,AAAC,GAAO,EAAG,IAAI,GAAI,GAAM,EAAO,IAAS,IAAI,OAItC,SAAiB,MAAO,IAAI,GAAM,KAAK,OAAO,EAAG,KAAK,OAAO,MAE7D,cAAuB,MAAO,MAAK,SAAS,SAE5C,eAAwB,MAAO,MAAK,SAAS,UAE7C,aAAuB,MAAO,MAAK,cAEnC,qBACT,MAAO,MAAK,WAAW,IACrB,AAAC,GAAO,EAAG,IAAI,KAAK,QAAQ,IAAI,GAAI,GAAM,KAAK,WAAY,KAAK,eAI7D,QAAiC,EAAe,GACrD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,CAAE,QAAO,WAIN,QAAiC,EAAW,GACjD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,KAAK,SACL,GAAI,GAAM,EAAG,IAIV,aAAsC,GAC3C,MAAO,MAAK,QAAQ,EAAG,EAAG,EAAG,GAcxB,MACL,EACA,EAAkE,IAElE,GAAI,GACF,GAAM,GAAM,YAAqB,GAC7B,EAAU,IAAI,QACd,GAAI,GAAI,GAEZ,MAAO,MAAK,QAAQ,EAAI,EAAG,EAAI,GAAG,MAAM,KAAM,GAGhD,GAAM,CAAE,mBAAkB,iBAAkB,CAAE,iBAAkB,GAAO,cAAe,MAAQ,GAE9F,MAAI,GACK,KAAK,YAGP,KAAK,aAAa,GAGnB,YACN,GAAM,GAAU,KAAK,2BAEf,CAAC,EAAe,EAAgB,GAAe,EAC/C,EAAc,AAAC,GAAc,EAAY,IAAI,GAAI,YACjD,EAAkB,GAAY,GAAiB,EAAY,IAAmB,EAE9E,EAAO,KAAK,MAAM,EAAiB,IAEnC,EAAW,GAAe,GAE1B,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAChD,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAEtD,MAAO,IAAI,IAAK,EAAG,EAAG,KAAK,IAAI,EAAM,KAAK,WAAa,GAAI,KAAK,IAAI,EAAM,KAAK,YAAc,IAGvF,aAAa,GACnB,GAAM,GAAM,GAAQ,KAAK,WACzB,MAAO,GAAI,IAAI,EAAI,MAAQ,EAAS,EAAI,OAAS,GAGzC,2BACR,KAAM,IAAI,OAAM,4DC/HpB,oBAIoC,GACxB,2BACR,GAAM,GAAM,KAAK,UACjB,MAAO,CACL,EAAI,GACJ,EAAI,GACJ,GAAe,CAAC,EAAI,GAAI,EAAI,QCVlC,oBAIqC,GAC5B,gBACL,MAAO,MAAK,UAAU,MAAM,EAAG,IAG1B,iBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,kBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,UACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,aACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,cACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,WACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAGxB,2BACR,MAAO,CACL,KAAK,aACL,KAAK,cACL,KAAK,YACL,IAAI,MCtCV,aAYE,YAAY,EAAe,GACzB,KAAK,OAAS,EACd,KAAK,UAAY,KAGR,SAAkB,MAAO,MAAK,UAE9B,YAAqB,MAAO,MAAK,UAErC,SAAS,EAAwB,IACtC,MAAO,GAAG,KAAK,QAAQ,EAAe,KAAK,GAAM,KAAK,aAAe,OCtBzE,oBAKgC,SAChB,yBAAwB,EAAU,GAG9C,GAFA,EAAI,iBAAiB,EAAK,GAEtB,CAAC,GAAc,EAAI,OACrB,KAAM,IAAI,OAAM,GAAG,gCAAqC,EAAI,yBAMhE,YAAY,EAAiC,GAC3C,MAAM,GACN,KAAK,OAAS,KAGL,SAAkB,MAAO,MAAK,SCrB3C,aAKE,YAAY,EAAe,GACzB,GAAM,MAAO,IAAU,SACrB,KAAM,IAAI,OAAM,sEAGlB,GAAI,CAAC,MAAM,QAAQ,IAAgB,EAAY,KAAK,AAAC,GAAS,CAAE,aAAgB,gBAC9E,KAAM,IAAI,OAAM,4FAGlB,KAAK,OAAS,EACd,KAAK,aAAe,KAGX,SAAkB,MAAO,MAAK,UAE9B,eAAgC,MAAO,MAAK,aAEhD,SACL,MAAO,CACL,MAAO,KAAK,MACZ,YAAa,KAAK,YAAY,IAAI,AAAC,GAAM,MAAM,KAAK,WAI1C,UAAS,GACrB,GAAM,GAAc,EAAK,YAAY,IAAI,AAAC,GAAW,GAAI,cAAa,IACtE,MAAO,IAAI,IAAuB,EAAK,MAAO,KC/BlD,oBAKkC,UAClB,2BAA0B,EAAU,GAGhD,GAFA,GAAW,wBAAwB,EAAK,GAGtC,CAAC,GAAmB,EAAI,QACrB,CAAC,GAAmB,EAAI,YAE3B,KAAM,IAAI,OAAM,GAAG,kCAAuC,EAAI,eAAe,EAAI,6CAQrF,YAAY,EAAiC,EAAe,EAAe,GACzE,MAAM,EAAK,GACX,KAAK,OAAS,EACd,KAAK,YAAc,KAGV,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,cCvBzC,YAA6B,GAClC,MAAO,GAAI,oBAAqB,GAG3B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,cCdf,cACL,GAAM,GAAQ,OAAO,MACrB,GAAI,CAAC,EAAO,KAAM,IAAI,OAAM,gEAE5B,GAAM,GAAW,KACf,KAAM,IAAI,OAAM,gEAGlB,MAAO,CACL,OAAQ,kBACR,yBACA,MAAO,iBACP,UACA,MAAO,iBACP,oBAAqB,IAAM,SAAS,cAAc,UAClD,mBAAoB,IAAM,SAAS,cAAc,OACjD,QACA,YCjBG,YAA0B,GAC/B,GAAI,GAAiB,GAErB,GAAI,CAAC,EACH,IAEE,EAAa,oBACN,GACP,EAAiB,EAAI,WAYzB,MAAO,CACL,SATe,EACb,AAAC,GAAqB,GAAI,SAAgB,CAAC,EAAS,KACpD,EAAG,SAAS,EAAU,CAAC,EAAU,IAAoB,EAAM,EAAO,GAAO,EAAQ,MAEjF,KACA,KAAM,IAAI,OAAM,qEAAqE,OCfpF,cAEL,GAAM,GAAS,OAAO,QAAa,OAAO,kBACpC,EAAQ,OAAO,OAAS,OAAO,iBAE/B,EAAsB,KAC1B,GAAI,EAAQ,MAAO,IAAI,GACvB,KAAM,IAAI,OAAM,+EAGZ,EAAqB,KACzB,GAAI,EAAO,MAAO,IAAI,GACtB,KAAM,IAAI,OAAM,6EAGZ,EAAQ,OAAO,MAGf,EAAa,KAEnB,MAAO,CACL,OAAQ,GAAU,QAClB,yBAA0B,OAAO,0BAA4B,QAC7D,MAAO,GAAS,QAChB,UAAW,OAAO,WAAa,QAC/B,MAAO,OAAO,kBAAoB,QAClC,sBACA,qBACA,WACG,GCjCA,cACL,MAAO,OAAO,SAAW,UACpB,MAAO,WAAa,aACpB,MAAO,mBAAqB,aAC5B,MAAO,oBAAsB,aAC7B,MAAO,mBAAqB,aAC5B,MAAO,YAAc,aACrB,MAAO,2BAA6B,YCH3C,OAAyB,QAGrB,EAEJ,cACE,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,yEAElB,MAAO,GAGT,YAAgB,GACd,EAAc,EAGhB,cAGE,MAAI,MAAoB,GAAO,MAC3B,cAAmB,GAAO,MACvB,KAGT,YAAqB,GAKnB,GAJK,GACH,KAGE,CAAC,EACH,KAAM,IAAI,OAAM,8EAGlB,GAAM,CAAE,SAAS,EAAY,OAAQ,QAAQ,EAAY,OAAU,EACnE,EAAY,OAAS,EACrB,EAAY,MAAQ,EACpB,EAAY,oBAAsB,EAAI,qBAAwB,KAAM,GAAI,IACxE,EAAY,mBAAqB,EAAI,oBAAuB,KAAM,GAAI,IAEtE,EAAY,UAAY,EAAI,WAAa,EAAY,UACrD,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,SAAW,EAAI,UAAY,EAAY,SAG9C,GAAM,GAAM,CACjB,UACA,UACA,cACA,oBACA,oBACA,mBACA,eACA,aACA,sBAGF,KC3DO,YAAsB,GAC3B,MAAI,CAAC,EAAI,YAAc,MAAO,IAAQ,SAC7B,SAAS,eAAe,GAE1B,ECHF,WAA6B,GAClC,GAAM,CAAE,SAAQ,4BAA6B,EAAI,SAEjD,GAAI,YAAqB,GACvB,MAAO,GAGT,GAAM,GAAS,GAAa,GAE5B,GAAI,CAAE,aAAkB,IACtB,KAAM,IAAI,OAAM,kEAGlB,GAAM,GAAM,EAAO,WAAW,MAC9B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,GCfF,GAAK,IAAL,UAAK,GAEV,WAAW,WAEX,YAAY,YAEZ,cAAc,cAEd,eAAe,iBARL,aANZ,aAuCE,YAAY,EAAiC,IAC3C,GAAM,CACJ,iBAAgB,kBAAiB,YAAW,WAAU,YAAW,WAC/D,EACJ,KAAK,eAAiB,GAAkB,GAAe,SACvD,KAAK,gBAAkB,GAAmB,qBAC1C,KAAK,UAAY,GAAa,yBAC9B,KAAK,SAAW,GAAY,GAC5B,KAAK,UAAY,GAAa,UAC9B,KAAK,QAAU,GAAW,IAhD9B,SA2DE,YACE,EACA,EACA,EAAiC,IAGjC,KAAK,KAAO,MAAO,IAAS,SACxB,CAAC,GACA,YAAgB,IAAgB,EAAK,KAAO,EACjD,KAAK,OAAS,EACd,KAAK,QAAU,GAAI,IAAqB,GAG1C,aAAa,GACX,GAAM,CAAE,WAAY,KAAK,QACzB,MAAO,MAAK,KAAK,IAAI,AAAC,GAAM,EAAI,YAAY,GAAG,OAAO,OAAO,CAAC,EAAI,IAAQ,EAAK,EAAK,EAAK,EAAK,GAAM,EAAI,EAG1G,gBACE,GAAM,CAAE,WAAU,WAAY,KAAK,QACnC,MAAO,MAAK,KAAK,OAAS,EAAY,EAAI,EAG5C,aAAa,EAA+B,GAC1C,GAAM,CAAE,kBAAmB,KAAK,QAC1B,EAAc,IAAmB,GAAe,cAAgB,IAAmB,GAAe,UAClG,EAAa,IAAmB,GAAe,aAAe,IAAmB,GAAe,aAEhG,EAAiB,KAAK,aAAa,GACnC,EAAkB,KAAK,gBACvB,EAAK,EAAc,KAAK,OAAO,EAAI,EAAiB,KAAK,OAAO,EAChE,EAAI,EAAa,KAAK,OAAO,EAAI,EAAkB,KAAK,OAAO,EAGrE,GAAI,GACF,GAAM,CAAE,QAAO,UAAW,EACpB,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAQ,GAAiB,GACrD,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAS,GAAkB,GAC7D,MAAO,CAAE,EAAG,EAAM,EAAG,GAEvB,MAAO,CAAE,IAAG,KAGd,KAAK,GACH,GAAM,GAAS,GAAa,GACtB,EAAM,EAAoB,GAE1B,CACJ,kBAAiB,YAAW,WAAU,YAAW,WAC/C,KAAK,QAET,EAAI,KAAO,GAAG,OAAc,IAC5B,GAAM,GAAe,KAAK,aAAa,GACjC,EAAa,KAAK,gBAExB,EAAI,UAAY,EAChB,GAAM,GAAY,KAAK,aAAa,EAAK,GACzC,EAAI,SAAS,EAAU,EAAG,EAAU,EAAG,EAAc,GAErD,EAAI,UAAY,EAChB,KAAK,KAAK,QAAQ,CAAC,EAAU,KAC3B,GAAM,GAAI,EAAU,EAAU,EACxB,EAAI,EAAU,EAAU,EAAM,GAAI,GAAK,EAC7C,EAAI,SAAS,EAAU,EAAG,OC1HhC,aAuBE,YAAY,EAA2B,IACrC,GAAM,CACJ,WAAU,YAAW,QAAO,oBAC1B,EACJ,KAAK,SAAW,GAAY,qBAC5B,KAAK,UAAY,GAAa,EAC9B,KAAK,MAAQ,EAEb,GAAM,GAA0B,CAC9B,eAAgB,GAAe,YAC/B,gBAAiB,KAAK,UAExB,KAAK,iBAAmB,GAAI,IAAqB,IAAK,KAA4B,MAnCtF,SA4CE,YACE,EACA,EAA2B,IAE3B,KAAK,IAAM,GAAI,GAAI,GACnB,KAAK,QAAU,GAAI,IAAe,GAGpC,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CAAE,WAAU,aAAc,KAAK,QAE/B,CACJ,IAAG,IAAG,QAAO,UACX,KAAK,IACT,EAAI,YAAc,EAClB,EAAI,UAAY,EAChB,EAAI,WAAW,EAAG,EAAG,EAAO,GAE5B,GAAM,CAAE,SAAU,KAAK,QACvB,AAAI,GACF,GAAI,IAAc,CAAC,GAAQ,CAAE,EAAG,EAAK,EAAY,EAAI,KAAK,KAAK,QAAQ,kBAAkB,KAAK,KC1D7F,YACL,EACA,GAIA,AAFwB,OAAM,QAAQ,GAAc,EAAa,CAAC,IAElD,QAAQ,AAAC,IAEvB,GAAM,GAAQ,YAAe,GACzB,EAAI,MACH,GAAoB,GAAO,EAAI,UAAU,MAAQ,OAGhD,EAAM,YAAe,GACvB,EAAI,IACH,GAAoB,GAAO,EAAI,UAAU,IAAM,GAAI,GAAI,GAEtD,EAAQ,EAAQ,GAAG,GAAM,KAAW,OAC1C,GAAI,IAAQ,EAAK,CAAE,UAAS,KAAK,KC1BrC,OAAoB,OCEb,YAAuB,GAC5B,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAQ,aAAiB,IAAS,EAAM,UAClC,YAAiB,IAAS,EAAM,YAAc,ECH/C,YAA0B,GAE/B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,GAAI,YAAiB,GAAI,SAAS,QAAU,GAAc,GACxD,MAAO,GAAQ,MAGjB,WAAiB,GACf,AAAI,CAAC,EAAE,eAEP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAO,IAGT,WAAgB,GACd,AAAI,CAAC,EAAE,eACP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAQ,IAGV,EAAM,iBAAiB,OAAQ,GAC/B,EAAM,iBAAiB,QAAS,KCxB7B,YAAuB,GAC5B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,AAAM,YAAe,OAAO,EAAO,GAAI,OAAM,qDAC7C,GAAM,GAAS,GAAI,YACnB,EAAO,OAAS,KACd,AAAI,MAAO,GAAO,QAAW,UAAU,EAAO,GAAI,OAAM,qEACxD,GAAM,GAAM,EAAI,SAAS,qBACzB,EAAI,OAAS,IAAM,EAAQ,GAC3B,EAAI,QAAU,EACd,EAAI,IAAM,EAAO,QAEnB,EAAO,QAAU,EACjB,EAAO,cAAc,KCXlB,YAA4B,GACjC,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAI,aAAiB,GACZ,GAAI,GAAW,EAAM,aAAc,EAAM,eAE9C,YAAiB,GACZ,GAAI,GAAW,EAAM,WAAY,EAAM,aAEzC,GAAI,GAAW,EAAM,MAAO,EAAM,QCNpC,YAAsB,CAAE,QAAO,WACpC,GAAM,CAAE,uBAAwB,EAAI,SAC9B,EAAS,IACf,SAAO,MAAQ,EACf,EAAO,OAAS,EACT,EAGF,YAA+B,EAAwD,GAC5F,GAAM,CAAE,aAAc,EAAI,SAE1B,GAAI,CAAE,aAAiB,KAAc,CAAC,GAAc,GAClD,KAAM,IAAI,OAAM,8DAGlB,GAAM,CAAE,QAAO,UAAW,GAAQ,GAAmB,GAC/C,EAAS,GAAa,CAAE,QAAO,WAErC,MAAI,aAAiB,GACnB,EAAoB,GAAQ,aAAa,EAAO,EAAG,GAEnD,EAAoB,GAAQ,UAAU,EAAO,EAAG,EAAG,EAAO,GAErD,EC7BT,OAAoB,OAKpB,kBACE,EACA,GAEA,GAAM,GAAe,GAAU,EAAI,SAAS,sBAEtC,CAAC,EAAQ,EAAO,GAAe,EAAU,MAAM,MAAM,EAAW,GAAa,EAAI,GACjF,EAAc,AAAG,QAAK,IAAM,EAAU,KAAK,EAAQ,EAAO,GAAa,SAC7E,YAAM,AAAG,YAAQ,SAAS,EAAa,GAEvC,EAAY,UAEL,ECfF,YAAwB,GAC7B,GAAM,CAAE,QAAO,SAAQ,SAAU,EAAI,SAErC,MAAO,aAAiB,IACnB,YAAiB,IACjB,YAAiB,GCPxB,MAAoB,OCKb,YAAuB,EAA6C,EAAmB,EAAuB,IACnH,GAAM,CAAE,QAAO,UAAW,EAAI,SAE9B,GAAI,CAAE,aAAiB,IAAS,YAAiB,IAC/C,KAAM,IAAI,OAAM,4EAGlB,GAAM,GAAO,GAAmB,GAC1B,EAAQ,EAAY,KAAK,IAAI,EAAK,OAAQ,EAAK,OAC/C,EAAQ,EAAQ,EAAK,MACrB,EAAS,EAAQ,EAAK,OAEtB,EAAe,GAAa,CAAE,MAAO,EAAW,OAAQ,IACxD,EAAc,YAAiB,GAAS,EAAQ,GAAsB,GAEtE,EAAS,KAAK,IAAI,EAAQ,GAAU,EACpC,EAAK,GAAe,EAAQ,EAAS,EAAS,EAC9C,EAAK,GAAe,EAAS,EAAQ,EAAS,EACpD,SAAoB,GAAc,UAAU,EAAa,EAAI,EAAI,EAAO,GAEjE,EDzBT,aAyBE,YACE,EACA,EAA6B,IAdvB,mBAAkD,GAElD,eAAiC,GAIjC,wBAA8B,GAE9B,sBAA+B,GAQrC,GAAI,CAAC,MAAM,QAAQ,GACjB,KAAM,IAAI,OAAM,4HAA4H,KAG9I,KAAK,mBAAqB,EAC1B,KAAK,WAAa,EAAO,OAEzB,EAAO,QAAQ,CAAC,EAAO,KACrB,GAAI,GAAW,IACb,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAO,EAAM,MACnC,OAGF,GAAI,EAAW,IACb,GAAM,GAAa,EAAc,MAAM,GACvC,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,yCAAyC,8CAG3D,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAQ,EAAc,MAAM,MAAM,GACxD,OAGF,GAAM,GAAU,YAAyB,GAAI,SAAS,OAAS,EAAQ,GAAsB,GAC7F,KAAK,UAAU,GAAO,EACtB,KAAK,iBAAiB,GAAO,CAAC,EAAO,OAAQ,EAAO,MAAO,QAIpD,gBACT,MAAO,MAAK,iBAGH,YACT,MAAO,MAAK,aAGH,gBACT,MAAO,MAAK,UAAY,GAAK,KAAK,sBAGzB,aACT,MAAO,MAAK,cAGH,mBACT,MAAO,MAAK,oBAGH,aACT,MAAO,MAAK,cAGH,2BACT,MAAO,IAAM,KAAK,UAAW,EAAG,GAAG,IACjC,CAAC,EAAG,IAAa,KAAK,2BAA2B,IAI9C,SAAS,GACd,MAAO,MAAK,SAAS,IAAa,KAAK,aAAa,GAG/C,mBAAmB,GACxB,MAAO,MAAK,iBAAiB,GAGxB,eAAe,GACpB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,cAAc,GACnB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,2BAA2B,GAChC,GAAI,MAAO,MAAK,WAAc,SAC5B,KAAM,IAAI,OAAM,yFAGlB,GAAM,GAAQ,KAAK,cAAc,GAC3B,EAAS,KAAK,eAAe,GACnC,MAAO,IAA0B,CAAE,QAAO,UAAU,KAAK,WAYpD,cAAc,EAAmB,EAA0B,IAChE,YAAK,WAAa,EAEX,AAAG,OAAK,KACb,GAAM,GAAe,GAAM,KAAK,UAAW,EAAG,GAAG,IAAI,AAAC,IACpD,GAAM,GAAQ,KAAK,SAAS,GAE5B,GAAI,YAAoB,WAEtB,GAAI,GAAY,EAAW,GAAS,EAAQ,EAAM,aAElD,SAAY,GAAY,EAAW,GAE/B,GAAU,MAAM,KAAO,GAAa,EAAU,MAAM,KAAO,IAC7D,GAAY,AAAG,QAAM,eAAe,EAAW,CAAC,EAAW,KAGtD,EAAU,KAAK,EAAW,EAAW,GAG9C,GAAI,YAAiB,GAAI,SAAS,OAChC,MAAO,AAAG,WAAQ,WAAW,GAAc,EAAO,EAAW,IAG/D,KAAM,IAAI,OAAM,+BAA+B,8FAAqG,OAOtJ,MAHoB,AAAG,SAAM,EAAa,IAAI,AAAC,GAAM,AAAG,OAAK,EAAG,aAAa,KAAK,KAAK,UAAW,EAAW,EAAW,OE3I9H,iBAAiC,GAC/B,GAAI,YAAkB,IACpB,MAAO,GAGT,GAAM,GAAgB,MAAM,QAAQ,GAChC,EACA,CAAC,GAEL,GAAI,CAAC,EAAc,OACjB,KAAM,IAAI,OAAM,4CAGlB,GAAM,GAAa,AAAC,GAAiB,MAAM,QAAQ,GAAU,mBAAmB,KAAS,GAEnF,EAAa,EAAc,IAAI,IAErC,SAAW,QAAQ,CAAC,EAAO,KACzB,GAAI,CAAC,GAAe,IAAU,CAAC,GAAW,IAAU,CAAC,EAAW,GAC9D,KAAI,OAAO,GAAc,IAAO,SACxB,GAAI,OAAM,eAAe,EAAW,sEAAsE,EAAc,MAG1H,GAAI,OAAM,eAAe,EAAW,iIAG5C,GAAI,EAAW,IAEb,GAAM,GAAY,EAAM,MAAM,GAC9B,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,eAAe,EAAW,iCAAiC,iDAMjF,KAAM,SAAQ,IACZ,EAAW,IAAI,AAAC,GAAU,GAAe,IAAU,GAAiB,KAG/D,GAAI,IAAS,EAAY,MAAM,QAAQ,ICtChD,kBACE,EACA,GAEA,GAAM,CAAE,UAAW,EAAI,SAEnB,EAAS,EAEb,GAAI,CAAE,aAAiB,KACrB,GAAM,GAAW,KAAM,GAAW,GAElC,GAAI,EAAS,UAAY,EACvB,KAAM,IAAI,OAAM,8CAGlB,GAAM,GAAiB,EAAS,SAAS,GACzC,EAAS,YAA0B,GAC/B,EACA,KAAM,IAAoB,GAGhC,GAAM,GAAM,EAAoB,GAQhC,MAAO,AAPO,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAO,MAAO,EAAO,QAAQ,IAAI,QAC7C,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAO,MAAO,EAAO,SAE/C,IAAI,CAAC,CAChB,IAAG,IAAG,QAAO,aAEb,GAAM,GAAU,GAAa,CAAE,QAAO,WACtC,SAAoB,GACjB,aAAa,EAAI,aAAa,EAAG,EAAG,EAAO,GAAS,EAAG,GACnD,ICnDX,OAAoB,OAgBpB,kBACE,EACA,GAEA,GAAI,CAAC,GAAW,IAAgB,CAAC,EAAW,GAC1C,KAAM,IAAI,OAAM,6DAGlB,GAAI,EAAW,IAAgB,EAAY,MAAM,GAAK,EACpD,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAW,EAAU,GAAe,EAAY,MAAM,MAAM,EAAW,GAAe,EAAI,GAajG,MAJoB,AAPN,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAU,GAAW,IACjC,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAU,IAEvB,IAAI,CAAC,CAC7B,IAAG,IAAG,QAAO,YACT,AAAG,WAAQ,EAAY,KAAK,EAAW,EAAU,GAAc,CAAC,EAAG,EAAG,GAAI,CAAC,EAAQ,EAAO,OCtCpG,kBACE,EAEA,GAEA,GAAM,CAAE,SAAU,EAAI,SAChB,EAAM,KAAM,GAAM,EAAK,GAC7B,GAAI,CAAE,GAAI,OAAS,KACjB,KAAM,IAAI,OAAM,qBAAqB,EAAI,WAAW,EAAI,yBAAyB,EAAI,OAEvF,MAAO,GCTT,kBAAiC,GAC/B,GAAM,GAAM,KAAM,IAAa,GACzB,EAAO,KAAO,GAAK,OAEzB,GAAI,CAAC,EAAK,KAAK,WAAW,UACxB,KAAM,IAAI,OAAM,wEAAwE,EAAK,kBAAkB,EAAI,OAErH,MAAO,IAAc,GCRvB,kBAAmC,GACjC,MAAQ,MAAM,IAAa,IAAM,OCDnC,kBAAsC,GACpC,MAAO,IAAI,cAAa,KAAO,MAAM,IAAa,IAAM,eCH1D,OAAoB,OCAb,YAAsB,EAAyB,GACpD,GAAM,GAA0B,GAAG,0BAEnC,GAAI,CAAC,EACH,MAAO,CACL,aAAc,GACd,YAAa,GAIjB,GAAI,IAAQ,IACV,MAAO,CACL,aAAc,IACd,YAAa,IAAI,KAIrB,GAAM,GAAW,EAAI,WAAW,WAAa,UAAY,EAAI,WAAW,YAAc,WAAa,GACnG,EAAM,EAAI,QAAQ,EAAU,IAE5B,GAAM,GAAQ,EAAI,MAAM,KAAK,OAAO,AAAC,GAAM,GAErC,EAAe,EAAI,SAAS,SAC9B,EAAM,EAAM,OAAS,GACrB,EAEA,EAAe,EAAY,GAAI,SAAS,SAAW,EAAM,MAAM,EAAG,EAAM,OAAS,GAAK,GAAO,KAAK,KACtG,SAAe,EAAI,WAAW,KAAO,IAAI,IAAiB,EAEnD,CACL,eACA,YAAa,IAAiB,IAAM,IAAI,IAAiB,GAAG,KAAgB,KD1BhF,kBACE,EACA,GAEA,GAAM,CAAE,cAAa,gBAAiB,GAAa,EAAK,GAClD,EAAW,KAAM,IAAuC,GAE9D,MAAO,AAAG,OAAG,YAAY,EAAU,GET9B,YAAyB,EAAoB,EAAwB,EAA8B,IACxG,GAAM,CAAE,QAAO,UAAW,EACtB,GAAmB,GACnB,EACJ,SAAM,MAAQ,EACd,EAAM,OAAS,EACR,CAAE,QAAO,UCTlB,OAAoB,OCApB,OAAoB,OAApB,0BAQY,aAAkC,OAElC,oBAAiC,MAIhC,UAAmC,MAAO,MAAK,WAE/C,iBAAkC,MAAO,MAAK,kBAE9C,YAAsB,MAAO,CAAC,CAAC,KAAK,OAExC,iBAAiB,GACtB,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,MAAO,GAAI,GAGN,sBAAsB,EAAmB,GAC9C,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,EAAI,GAAS,UACb,EAAI,GAAW,EAGV,eACL,MAAO,MAAK,eAAe,IAAI,CAAC,CAAE,eAAiB,EACjD,KAAM,EACN,OAAQ,KAAK,iBAAiB,MAI3B,qBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,EAAM,iBAAqB,cAGnE,kBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,CAAE,GAAM,iBAAqB,eAGrE,WACL,KAAK,kBAAkB,QAAQ,CAAC,CAAE,OAAM,aACtC,KAAK,sBAAsB,EAAM,EAAO,cAIrC,SACL,KAAK,qBAAqB,QAAQ,CAAC,CAAE,OAAM,OAAQ,MACjD,GAAM,GAAS,AAAG,UAAO,EAAS,YAClC,EAAS,UACT,KAAK,sBAAsB,EAAM,KAI9B,QAAQ,EAA4B,IACzC,KAAK,eAAe,QAAQ,AAAC,IAC3B,GAAI,GAAoB,EAAM,OAAO,WACnC,KAAM,IAAI,OAAM,mDAAmD,EAAM,QAE3E,EAAM,OAAO,YAEf,KAAK,QAAU,OAGV,kBACL,MAAO,IAAI,cACT,KAAK,eACF,IAAI,CAAC,CAAE,YAAa,MAAM,KAAK,EAAO,aACtC,OAAO,CAAC,EAAM,IAAQ,EAAK,OAAO,UAI5B,MAAK,GAChB,GAAI,YAAwB,eAC1B,KAAK,eAAe,GACpB,OAGF,KAAM,MAAK,YAAY,QAGZ,aAAY,GACvB,GAAI,GAAO,MAAO,IAAQ,SACxB,KAAM,IAAI,OAAM,GAAG,KAAK,0CAG1B,GAAM,GAAY,KAAM,IAAc,EAAK,KAAK,uBAChD,KAAK,kBAAkB,QAGZ,cAAa,GACxB,GAAI,GAAY,MAAO,IAAa,SAClC,KAAM,IAAI,OAAM,GAAG,KAAK,iDAG1B,GAAM,CAAE,YAAa,EAAI,SAEnB,CAAE,cAAa,gBAAiB,GAAa,EAAU,KAAK,uBAE5D,EAAuB,AAAC,GAAwB,QAAQ,IAC5D,EAAU,IAAI,AAAC,GAAO,EAAS,GAAI,KAAK,AAAC,GAAQ,EAAI,UAEjD,EAAc,AAAG,MAAG,qBAAqB,GACzC,EAAW,KAAK,MAAO,MAAM,GAAS,IAAc,YACpD,EAAY,KAAM,GAAY,EAAU,GAE9C,KAAK,kBAAkB,GAGlB,kBAAkB,GACvB,GAAM,CACJ,gBACA,UACE,KAAK,2BAA2B,GAEpC,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGV,eAAe,GACpB,GAAM,CACJ,gBACA,UACE,KAAK,cAAc,GAEvB,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGT,qBAAqB,GAC3B,GAAI,CAAC,KAAK,OACR,KAAM,IAAI,OAAM,qDAGlB,GAAM,GAAS,EAAU,MAAM,KAAK,OAAO,CAAC,EAAoD,KAE9F,GAAI,CAAC,EAAI,QAAQ,eAAe,GAC9B,KAAM,IAAI,OAAM,wDAAwD,eAAqB,KAG/F,MAAO,CAAE,IAAK,EAAI,QAAS,UAAS,QAAS,EAAI,QAAQ,KACxD,CAAE,QAAS,KAAK,SAEb,CAAE,MAAK,WAAY,EACzB,GAAI,CAAC,GAAO,CAAC,GAAW,CAAE,GAAI,YAAuB,YACnD,KAAM,IAAI,OAAM,8DAA8D,KAGhF,MAAO,CAAE,MAAK,aC1JlB,MAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,iBAAkB,EAAO,iBAAkB,EAAQ,QAC1F,SAAM,AAAG,OAAI,EAAK,EAAO,MAClB,IDNJ,YACL,EACA,EACA,EAAwB,IAExB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,CAAC,EAAG,GAAI,QACrE,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,CAAC,EAAG,KAE7E,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,OAItC,YACL,EACA,EACA,EAAwB,GACxB,EAAuB,IAEvB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,GAAI,QAC5F,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,KAEpG,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAE/D,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,KACxC,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,QEpD1D,OAAoB,OAIb,YACL,EACA,EACA,EAA4B,OAC5B,EAAoB,IAEpB,MAAO,AAAG,SAAK,KACb,GAAM,GAAM,AAAG,OACb,AAAG,UAAO,EAAG,EAAO,QAAS,CAAC,EAAG,GAAI,GACrC,EAAO,MAGT,MAAO,GAAW,AAAG,QAAK,GAAO,ICd9B,WAAoC,EAAgB,GACzD,OAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,AAAK,EAAc,KAAK,AAAC,GAAO,EAAG,eAAiB,IAClD,EAAU,GAAM,YCLtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,EACA,KAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,SCzBtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,KAEA,GAAM,GAAa,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAY,IAChF,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CACL,QAAS,EACT,KAAM,ICvBZ,OAAoB,OCApB,aAsBE,YAES,EAEA,EAEA,GAJA,wBAEA,wBAEA,cDxBJ,YACL,EACA,GAEA,MAAO,CAAC,EAAoB,EAAqB,KAC/C,GAAM,GAAmB,AAAG,YAAS,EAAe,EAAI,EAAI,GAAa,CAAC,EAAG,EAAG,EAAY,IACtF,EAAmB,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAG,EAAG,EAAY,IAC5F,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,WAGX,GAAI,IACT,EACA,EACA,IAKC,YAEL,GAEA,MAAO,AAAC,KACN,GAAM,GAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,IAAI,IACT,EACA,EACA,IEpCC,WAAmC,EAAgB,GACxD,MAAO,CAAC,EAAsB,EAAmB,KAC/C,GAAM,GAAS,EAAU,GAEzB,GAAI,CAAC,GAAS,EAAQ,GACpB,KAAM,IAAI,OAAM,sBAAsB,oBAA+B,oBAA4B,KAGnG,SAAc,KACZ,CAAE,eAAc,UAAW,GAAc,IAGpC,GCfJ,WAA+B,GACpC,GAAI,GAAmB,EAEvB,WAAwB,GACtB,GAAM,GAAM,EAAiB,MAAM,EAAG,GACtC,SAAmB,EAAiB,MAAM,GACnC,EAGT,aACE,MAAO,GAGT,MAAO,CACL,iBACA,uBCPG,YAA2B,EAAwC,GACxE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,GAAQ,EACV,EAAkB,EAAY,EAAa,EAAG,GAAG,WACjD,EAA2B,EAAY,EAAa,GAAG,WACrD,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAChE,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,CAAE,QAAO,QAAO,SAAU,EAAyB,EAAY,EAAa,EAAc,GAC1F,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAC3C,EAAS,EAAyB,IAAK,IAAK,UAElD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CACN,SAAQ,SAAQ,SAAQ,WCvBvB,YAA+B,GACpC,MAAO,AAAC,KACN,GAAM,GAAU,EAAgC,GAAG,YAAkB,GAC/D,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,CAAE,UAAS,SCNf,YAA2B,EAAgB,GAChD,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBhBxBnB,oBAU0C,GACxC,cACE,MAAM,wBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,sDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAE/B,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,+BAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KiBlDzB,OAAoB,OCApB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,IAAM,AAAG,OACtB,AAAG,UAAO,EAAG,EAAO,SACpB,EAAO,OCPJ,YAAuB,EAAuB,EAAoB,GACvE,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAIpB,EAAK,AAFa,GAAuB,EAAgB,GAEpC,EAAY,EAAa,MAEpD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,OCdP,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,EAAgB,OAGtB,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,YAA4B,GACjC,GAAM,GAAyC,GACzC,EAAmC,GAEzC,cAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,GAAM,GAAM,EAAI,WAAW,MAAQ,EAAgB,EACnD,EAAI,GAAO,EAAU,KAGhB,CAAE,sBAAqB,iBJXhC,oBAkBU,GAGR,YAAY,EAAe,GACzB,MAAM,GACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBASP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EACJ,MAAO,IAAoB,EAAmB,KAAK,EAAmB,MAAM,GAAI,IAAK,EAAO,MAIzF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,EAAS,KAAK,0BAA2B,KAAK,4BAG3D,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAM,KAAK,0BACX,EAAO,KAAK,2BACZ,EAAwB,EAAO,EAAO,EAEtC,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KKnFjC,GAAM,IAAyB,CAAC,UAAW,QAAS,MAAO,QAAS,UAAW,YAAa,aAAnG,SAiBE,YAAY,GACV,GAAI,EAAc,SAAW,EAC3B,KAAM,IAAI,OAAM,8EAA8E,EAAc,UAG9G,GAAuB,QAAQ,CAAC,EAAY,KAC1C,KAAK,GAAc,EAAc,KAIrC,gBACE,MAAO,IACJ,IAAI,AAAC,GAAgB,EAAE,aAAY,YAAa,KAAK,MACrD,KAAK,CAAC,EAAI,IAAO,EAAG,YAAc,EAAG,e1C9B5C,oBAQuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGtB,aAAa,GAClB,MAAO,AAAG,SAAK,IAAM,AAAG,WAAQ,KAAK,OAAO,UAGjC,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,oBAAmB,GAC9B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAC9B,EAAsB,KAAM,SAAQ,IAAI,AAAG,WAAQ,GAAK,IAAI,KAAO,KACvE,GAAM,GAAO,KAAM,GAAE,OACrB,SAAE,UACK,KAET,EAAI,UAEJ,GAAM,GAAqB,EACxB,IAAI,AAAC,GAAiB,GAAI,IAAgB,IAE7C,MAAO,GAAS,aACZ,EACA,EAAmB,GAGf,sBACR,MAAO,wBAGC,0BACR,MAAO,KAGC,2BACR,MAAO,K2C1CJ,YAA+B,GACpC,MAAO,GAAI,sBAAuB,IAG7B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,gBCPf,YACL,EACA,EACA,EAAgB,GAChB,GAIA,AAF6B,OAAM,QAAQ,GAAmB,EAAkB,CAAC,IAE5D,QAAQ,AAAC,IAE5B,GAAM,GAAO,YAAa,IACtB,EACC,GAAsB,GAAK,EAAE,YAAc,OAChD,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mHAIlB,GAAM,GAAmB,AADV,EAAK,gBACY,OAAO,AAAC,GAAc,EAAU,YAAc,GAExE,EAAS,GAAoB,GAC/B,EAAE,UAAU,IAAI,WACf,GAAmB,GAAI,GAAM,EAAG,GAMrC,AAJsB,GAAI,IACxB,EAAiB,IAAI,AAAC,GAAc,GAAG,EAAU,eAAe,GAAM,EAAU,iBAChF,GAEY,KAAK,KCxBhB,YAA6B,GAClC,MAAO,IAAoB,IAEtB,EAAI,oBAAwB,IAE5B,EAAI,6BAAiC,IAErC,EAAI,sBAA0B,GAG9B,YAEoD,EAAoB,GAC7E,GAAM,CAAE,IAAK,GAAU,EAAU,UAC3B,EAAY,EAAmB,QAAwB,EAAM,EAAG,EAAM,GAEtE,EAAO,EAAU,QACjB,CAAE,aAAc,EAAU,UAC1B,EAAc,GAAI,GAAc,EAAU,UAAU,MAAO,EAAK,QAAQ,EAAU,WAAY,GAQpG,MAAO,IAAK,KANM,CAChB,YACA,qBACA,gBCpCJ,aA+BE,YAAY,EAAqC,IAC/C,GAAM,CACJ,YAAY,GAAM,aAAa,GAAM,YAAW,YAAW,YAAW,cACpE,EACJ,KAAK,UAAY,EACjB,KAAK,WAAa,EAClB,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,uBAC9B,KAAK,WAAa,GAAc,yBAxCpC,SAiDE,YACE,EACA,EAAqC,IAErC,KAAK,cAAgB,EACrB,KAAK,QAAU,GAAI,IAAyB,GAG9C,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CACJ,YAAW,aAAY,YAAW,YAAW,YAAW,cACtD,KAAK,QAcT,GAZI,GAAa,KAAK,wBAAyB,KAC7C,GAAI,YAAc,EAClB,EAAI,UAAY,EAChB,GAAY,EAAK,KAAK,cAAc,iBACpC,GAAY,EAAK,KAAK,cAAc,kBACpC,GAAY,EAAK,KAAK,cAAc,mBACpC,GAAY,EAAK,KAAK,cAAc,WACpC,GAAY,EAAK,KAAK,cAAc,aAAc,IAClD,GAAY,EAAK,KAAK,cAAc,cAAe,IACnD,GAAY,EAAK,KAAK,cAAc,WAAY,KAG9C,GACF,EAAI,YAAc,EAClB,EAAI,UAAY,EAEhB,GAAM,GAAY,AAAC,IACjB,EAAI,YACJ,EAAI,IAAI,EAAG,EAAG,EAAG,EAAG,EAAW,EAAG,EAAI,KAAK,IAC3C,EAAI,QAEN,KAAK,cAAc,UAAU,QAAQ,MAOpC,YACL,EACA,GAGA,AAD2B,OAAM,QAAQ,GAAiB,EAAgB,CAAC,IACxD,QAAQ,AAAC,IAE1B,GAAM,GAAY,YAAa,GAC3B,EACC,GAAoB,GAAK,EAAE,UAAY,OAC5C,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gIAGlB,GAAI,IAAkB,GAAW,KAAK,qBC1G1C,OAAoB,OCApB,MAAoB,OCKpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAqC,EAAoB,EAAqB,GAC5E,GAAM,GAAkB,EAA2B,EAAY,EAAa,GAAG,qBACzE,EAAkB,EAA2B,EAAa,EAAa,GAAG,qBAC1E,EAAiB,EAAkB,EAAY,EAAa,EAAG,GAAG,oBAExE,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,EAAkB,GAChD,GAAM,GAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBAE1E,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YAAuB,EAAuB,GACnD,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAgB,GAEhC,EAAqB,EAAkB,EAAG,GAAI,EAAG,sBACjD,EAA+B,EAA4B,GAAI,GAAI,gCACnE,EAA+B,EAA4B,GAAI,IAAK,gCAEpE,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,IAAK,0BAA0B,OAG3F,GAAM,GAA4B,EAA4B,IAAK,IAAK,6BAClE,EAA2B,EAA2B,IAAK,IAAK,4BAEhE,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,aAAY,cAAa,cCjEvC,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAqC,GACnC,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAiB,EAAkB,GAAG,oBAE5C,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,GAC9B,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAEtD,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAW,GAE3B,EAAqB,EAAkB,sBACvC,EAA+B,EAA4B,gCAC3D,EAA+B,EAA4B,gCAE3D,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,0BAA0B,OAGtF,GAAM,GAA4B,EAA4B,6BACxD,EAA2B,EAA2B,4BAEtD,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,SAA2B,EAAW,GAE/B,CAAE,OAAQ,CAAE,aAAY,cAAa,aAAa,iBFrE3D,YAAc,EAAgB,EAAoB,GAChD,MAAO,AAAG,OAAI,AAAG,SAAO,EAAG,EAAO,QAAS,EAAQ,QAAS,EAAO,MAGrE,YAAwB,EAAgB,EAA8B,EAA2B,IAC/F,GAAI,GAAM,EAAkB,AAAG,OAAK,GAAK,EACzC,SAAM,EAAuB,EAAK,EAAO,gBAAiB,CAAC,EAAG,IAC9D,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,AAAG,MAAI,EAAK,GAAK,EAAG,EAAO,eAAgB,CAAC,EAAG,KAC9C,EAGT,YAAmB,EAAgB,GACjC,GAAI,GAAM,EAAuB,AAAG,OAAK,GAAI,EAAO,gBAAiB,CAAC,EAAG,IACzE,SAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,MAAI,EAAK,GACX,EA7BT,oBAgCkC,GAGhC,YAAY,GACV,MAAM,gBACN,KAAK,eAAiB,EAGjB,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,8CAGlB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,AAAG,OAAK,GAAK,EAAY,EAAO,WAAW,QAAS,CAAC,EAAG,KAClE,SAAM,GAAe,EAAK,EAAO,WAAW,kBAAmB,IAC/D,EAAM,GAAe,EAAK,EAAO,WAAW,mBAE5C,GAAM,KAAK,eAAgB,EAAG,GAAG,QAAQ,AAAC,IACxC,EAAM,GAAU,EAAK,EAAO,YAAY,cAAc,QAGxD,EAAM,GAAe,EAAK,EAAO,UAAU,iBAC3C,EAAM,AAAG,OAAK,EAAuB,EAAK,EAAO,UAAU,eAAgB,CAAC,EAAG,KACxE,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,sBAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,gBAG1C,cAAc,GACtB,MAAO,IAAc,EAAS,KAAK,kBG5EhC,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAkB,GAAuB,EAAgB,GAEzD,EAAM,EAAgB,IAAK,EAAG,UAC9B,EAAS,EAAgB,IAAK,EAAG,aAEvC,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,GAAI,CAAE,MAAK,YCflB,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,CACF,IAAK,EAAgB,UACrB,OAAQ,EAAgB,eAI5B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,GAAK,IAAL,UAAK,GAEV,SAAS,SAET,OAAO,SAJG,aNLZ,oBAakC,GAGhC,YAAY,EAAqC,GAAI,IAAa,IAChE,MAAM,gBACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBAGP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EAEE,EAAS,AAAG,WAAQ,EAAoB,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAAS,KAAK,EAAmB,MAAM,GAAI,IACnG,EAAM,GAAoB,EAAQ,EAAO,GAAG,KAAK,OACjD,EAAS,GAAoB,EAAQ,EAAO,GAAG,QACrD,MAAO,CAAE,MAAK,YAIX,aAAa,GAClB,MAAO,AAAG,SAAK,KACb,GAAM,CAAE,MAAK,UAAW,KAAK,OAAO,GACpC,MAAO,CAAE,MAAK,OAAQ,AAAG,WAAQ,WAIxB,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,qBAAoB,GAC/B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAE9B,EAAO,AAAG,WAAQ,EAAI,KACtB,EAAU,AAAG,WAAQ,EAAI,QACzB,EAAsB,EAAK,IAAI,CAAC,EAAW,IAAO,EACtD,YACA,aAAc,EAAQ,MAGlB,EAAqB,KAAM,SAAQ,IACvC,EAAoB,IAAI,MAAO,CAAE,YAAW,mBAC1C,GAAM,GAAO,MAAM,GAAU,QAAQ,GAC/B,EAAY,MAAM,GAAa,QAAQ,GACvC,EAAS,EAAW,GACpB,EAAS,EAAS,GAAO,KAAO,GAAO,OACvC,EAAoB,EAAS,EAAY,EAAI,EAEnD,SAAU,UACV,EAAa,UACN,CAAE,MAAK,SAAQ,wBAG1B,SAAI,IAAI,UACR,EAAI,OAAO,UAEJ,EAAS,aAAe,EAAiD,EAAmB,GAG3F,sBACR,MAAO,mBAGF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,GAGb,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAwB,IAAM,EAAI,EAAM,KAAM,EAAI,GAElD,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KOvHxC,MAAoB,OAApB,oBAYU,IACD,YAAY,EAAqB,EAAmB,GACzD,GAAM,GAAkB,EAAmB,IAAI,CAAC,CAAE,QAAO,aACvD,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,CACL,MAAO,EAAQ,EACf,OAAQ,EAAS,KAIf,EAAY,EAAgB,OAElC,MAAO,AAAG,QAAK,KACb,GAAM,GAA0B,CAAC,EAAe,IAAkB,AAAG,QAAM,CAAC,AAAG,OAAK,CAAC,IAAK,EAAO,WAAY,AAAG,OAAK,CAAC,IAAK,EAAO,YAAa,GAAG,KAAK,EAAG,KAAK,OAGzJ,EAAa,CAAC,EAAkB,KACpC,GAAM,CAAE,QAAO,UAAW,EAAgB,GAC1C,MAAO,GAAK,EAAO,GAAU,KAAK,IAAI,EAAQ,GAAU,EAAI,GAGxD,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GACvE,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GAa7E,MAXwB,GACrB,IAAI,AAAG,OAAK,CAAC,EAAW,KAAM,EAAW,YACzC,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAY,GACZ,EAAY,OAEb,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAgB,GAAU,MAC1B,EAAgB,GAAU,aAO3B,aAAa,GAClB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,KAAK,OAAO,GACxB,MAAO,MAAK,YACV,EACA,EAAM,UACN,EAAM,gBAAgB,IAAI,CAAC,CAAC,EAAQ,KAAY,EAAE,SAAQ,mBAKnD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,iBAAgB,GAC3B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAkB,AAAG,OACzB,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAAoB,KAAM,SAAQ,IAAI,EAAgB,IAC1D,MAAO,EAAgB,KACrB,GAAM,GAAiB,MAAM,KAAK,KAAM,GAAe,QACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,GAAO,IACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,CAAC,GAAO,IAExD,MAAO,IAAI,IACT,MAAM,IAAI,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,GAAI,GAAM,EAAQ,GAAc,EAAQ,KACxE,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,QAMtC,SAAgB,QAAQ,AAAC,GAAM,EAAE,WAE1B,EAAS,aAAe,EAAyC,EAAkB,GAGlF,2BACR,MAAO,OC9FX,oBAIuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGnB,sBACR,MAAO,yBAGC,0BACR,MAAO,OCdX,OAAoB,OCMb,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCnBZ,YAA2B,GAChC,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAEjD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,SAAQ,SAAQ,WF1B9B,oBAU8C,GAC5C,cACE,MAAM,4BAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,0DAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,GAAI,IAAK,CAAC,EAAG,GAAI,SAEjC,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,oCAGC,2BAA2B,GACnC,MAAO,IAA+B,GAG9B,cAAc,GACtB,MAAO,IAAkB,KGjD7B,oBAI2C,IACzC,YAAY,EAAiD,GAAI,KAC/D,MAAM,wBAAyB,GAGvB,sBACR,MAAO,8BAGC,0BACR,MAAO,OCdX,oBAKqC,MCLrC,MAAoB,OCApB,OAAoB,OCApB,OAAoB,OAIb,YAAe,EAAgB,GACpC,MAAO,AAAG,QAAI,AAAG,OAAI,EAAG,EAAO,SAAU,EAAO,QDAlD,YACE,EACA,EACA,EACA,EACA,EAA4B,QAE5B,GAAM,CAAE,UAAS,QAAS,EAAO,KAE7B,EAAM,AAAG,UAAO,EAAG,EAAS,EAAS,GACzC,SAAM,AAAG,OAAI,EAAK,GAClB,EAAM,GAAM,EAAK,EAAO,OACjB,EAAW,AAAG,QAAK,GAAO,EAG5B,YAAc,EAAgB,GACnC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAoB,EAAgB,GACzC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAkB,EAAgB,GACvC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,GAAM,SE7B5C,MAAoB,OAUpB,YAA2B,EAAwC,GACjE,WAA6B,EAAyB,EAAoB,GACxE,GAAM,GAAU,EAAe,GACzB,EAAQ,EAAQ,OAAU,GAAa,EAAa,GAE1D,GAAI,GAAQ,GACV,KAAM,IAAI,OAAM,+BAA+B,sBAA0B,EAAQ,uBAAuB,kBAA2B,KAGrI,MAAO,AAAG,QACR,IAAM,AAAG,YACP,AAAG,WAAS,EAAS,CAAC,EAAY,EAAO,EAAY,IACrD,CAAC,EAAG,EAAG,EAAG,KAKhB,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAU,EAAoB,EAAiB,EAAY,GAC3D,EAAO,AAAG,WAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,QAGpB,WAAiC,EAAoB,GACnD,GAAM,GAAU,AAAG,WAAS,EAAe,IACrC,EAAS,AAAG,WAAS,EAAe,IAE1C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,aAGX,CACL,UACA,UAIJ,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAO,EAAkB,EAAiB,EAAY,EAAY,GAAG,UACrE,EAAQ,EAAwB,EAAY,GAAG,WAErD,MAAO,CAAE,OAAM,SAGjB,WACE,EACA,EACA,EACA,EACA,EAAkB,IAElB,GAAM,GAAQ,EAAwB,GAAS,GAAM,GAAK,EAAiB,EAAY,EAAY,GAAG,WAChG,EAAQ,EAAuB,EAAiB,EAAY,EAAY,GAAG,WAEjF,MAAO,CAAE,QAAO,SAGlB,MAAO,CACL,yBACA,8BAIG,YAAuB,GAC5B,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAgB,GAEhC,EAAc,EAAuB,KAAM,GAAI,EAAG,eAClD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YAEnD,EAAc,EAA2B,MAAO,GAAI,EAAG,cAAe,IACtE,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YAEpD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aAEvD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAmB,EAA2B,OAAQ,IAAK,EAAG,oBAE9D,EAAK,AAAG,OACZ,IAAM,AAAG,YAAU,AAAG,WAAS,EAAe,IAAM,KAAM,CAAC,IAAK,MAAO,CAAC,EAAG,KAI7E,GAFA,EAAc,KAAK,CAAE,UAAW,OAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAsB1E,MAAO,CAAE,OAnBM,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGe,iBC9InB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAiC,GAC/B,GAAM,GAAU,EAAmB,GAAG,kBAAwB,GACxD,EAAS,EAAmB,GAAG,iBAAuB,GAE5D,MAAO,CAAE,UAAS,UAGpB,WAAgC,GAC9B,GAAM,GAAU,EAAmB,GAAG,iBAAuB,GACvD,EAAO,EAAmB,GAAG,cAAoB,GACjD,EAAQ,EAAwB,GAEtC,MAAO,CAAE,KAAM,CAAE,UAAS,QAAQ,SAGpC,WAAoC,GAClC,MAAO,CACL,MAAO,EAAuB,GAAG,WACjC,MAAO,EAAuB,GAAG,YAIrC,MAAO,CACL,yBACA,8BAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAW,GAE3B,EAAc,EAAuB,eACrC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAc,EAA2B,eACzC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aAEvC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aACvC,EAAmB,EAA2B,oBAE9C,CAAE,MAAO,EAGf,GAFA,EAAc,KAAK,CAAE,aAAc,KAAM,UAAW,OAEhD,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yDAAyD,KAG3E,GAAM,GAAS,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGF,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBChGnB,MAAoB,OAKb,YAAkB,EAAgB,GACvC,GAAI,GAAM,GAAK,EAAG,EAAO,OACzB,SAAM,GAAW,EAAK,EAAO,OAC7B,EAAM,AAAG,MAAI,EAAK,GAClB,EAAM,AAAG,OAAK,GACP,EAGF,YAAsB,EAAgB,GAC3C,GAAI,GAAM,GAAS,EAAG,EAAO,OAC7B,EAAM,GAAW,EAAK,EAAO,OAE7B,GAAI,GAAS,AAAG,UAAQ,EAAG,EAAG,EAAG,SAC3B,EAAQ,AAAG,QAAkB,EAAO,OACpC,EAAQ,EAAO,MAAM,KAAO,EAAI,MAAM,GAG5C,GAFsB,EAAO,MAAM,KAAO,EAAI,MAAM,IAAM,EAAO,MAAM,KAAO,EAAI,MAAM,IAGtF,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAE/B,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAGjC,SAAS,EAAQ,AAAG,SAAO,CAAC,EAAQ,GAAQ,GAAK,EACjD,EAAM,AAAG,MAAI,EAAQ,GAErB,EAAM,AAAG,OAAK,GACP,ELtCT,oBAWwC,GACtC,cACE,MAAM,sBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,QAAK,KAEb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAGtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,GAAS,EAAY,EAAO,aACtC,EAAM,AAAG,UAAQ,EAAK,EAAG,EAAG,SAE5B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,aAC/B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAa,EAAK,EAAO,kBAE/B,GAAM,GAAY,EAAI,KAAK,CAAC,EAAG,IAG/B,MAFuB,AAAG,UAAO,EAAW,EAAO,WAM1C,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,uBAAsB,GACjC,GAAM,GAAW,KAAM,GAAW,GAE5B,EAAwB,AAAG,OAC/B,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAA0B,KAAM,SAAQ,IAAI,EAAsB,IACtE,AAAC,GAAM,EAAE,SAGX,SAAsB,QAAQ,AAAC,GAAM,EAAE,WAEhC,EAAS,aACZ,EACA,EAAwB,GAGpB,sBACR,MAAO,yBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KMrFlB,YAAkC,GACvC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECHF,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,eCNf,YAAmB,GACxB,MAAO,OAAO,GAAI,KAAQ,SAGrB,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,QCNf,YAAsB,GAC3B,MAAQ,GAAI,SAAW,GAAO,MAAQ,EAAI,SAAW,GAAO,SACvD,GAAmB,EAAI,mBAGvB,YAGL,EACA,EACA,GAGA,MAAO,IAAK,KADM,CAAE,SAAQ,sBCpB9B,OAAoB,OCApB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,WAAoC,EAAqB,GACvD,GAAM,GAAU,AAAG,YAAS,EAAe,EAAI,EAAI,GAAc,CAAC,EAAG,EAAG,EAAa,IAC/E,EAAmB,AAAG,YAAS,EAAe,IAC9C,EAAoB,AAAG,YAAS,EAAe,IAC/C,EAAkB,AAAG,YAAS,EAAe,IAC7C,EAAsB,AAAG,YAAS,EAAe,IAEvD,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,uBAChB,CAAE,UAAW,GAAG,qBAChB,CAAE,UAAW,GAAG,0BAGX,CACL,UACA,mBACA,oBACA,kBACA,uBAIJ,WACE,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,KAAgB,EAAkB,oBAAsB,WAGnE,CAAE,UAAS,QAGpB,WACE,EACA,EACA,EACA,GAEA,GAAM,CACJ,UACA,QACE,EAAkB,EAAY,EAAa,EAAY,EAAc,IAEzE,MAAO,CACL,UACA,kBAAmB,GAIvB,WACE,EACA,EACA,GAEA,GAAM,GAAiB,EAA2B,EAAY,GAAG,oBAC3D,EAAiB,EAA2B,EAAY,EAAa,EAAG,GAAG,oBAEjF,MAAO,CAAE,iBAAgB,kBAG3B,aACE,GAAM,GAAS,EAA2B,EAAG,GAAI,EAAG,sBAE9C,EAAS,EAAsB,GAAI,GAAI,sBACvC,EAAS,EAAsB,GAAI,IAAK,sBACxC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,KAAM,uBAC3C,EAAU,EAAsB,KAAM,KAAM,uBAElD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,UACA,UACA,UACA,WAIJ,aACE,GAAM,GAAS,EAA2B,KAAM,IAAK,EAAG,2BAClD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,GAAI,EAAG,2BAChD,EAAS,EAA2B,GAAI,IAAK,EAAG,2BAEhD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,EAAG,EAAG,oDACjD,EAA2B,EAAkB,KAAM,GAAI,EAAG,2DAC1D,EAAoB,EAAkB,KAAM,GAAI,EAAG,oDACnD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDA2BxD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,gBAlCsB,CACtB,uBAAwB,EACxB,gBAAiB,GAiCjB,gBA/BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA8BjB,gBA5BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA2BjB,gBAzBsB,CACtB,uBAAwB,GACxB,gBAAiB,IAwBjB,gBAtBsB,CACtB,uBAAwB,EACxB,gBAAiB,IAqBjB,gBAnBsB,CACtB,uBAAwB,GACxB,gBAAiB,KAqBrB,MAAO,CACL,2BACA,gCAIG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,2BACA,gCACE,GAAkB,EAAgB,GAEhC,EAAc,IACd,EAAmB,IAKnB,EAAe,CACnB,UALgB,AAAG,YACnB,EAAe,KAAO,GACtB,CAAC,EAAG,KAAM,KAQZ,GAFA,EAAc,KAAK,CAAE,UAAW,2BAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,OAAQ,CACN,cACA,mBACA,gBAEF,iBCvNJ,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAoC,EAAgB,EAAa,GAC/D,GAAM,GAAU,EAAmB,GAAG,YAAiB,sBAAyB,EAAG,GAAG,aAChF,EAAoB,EAAmB,GAAG,YAAiB,oCAAuC,EAAG,GAAG,uBAE9G,MAAO,CAAE,UAAS,qBAGpB,WAA+B,GAC7B,GAAM,GAAe,oBAAoB,IACnC,EAAsB,sBAAsB,cAC5C,EAA4B,GAAG,mBAC/B,EAA4B,GAAG,mBAE/B,EAAU,EAAmB,GAAG,sBAAyC,EAAG,GAAG,aAC/E,EAAmB,EAAmB,GAAG,oBAAuC,EAAG,GAAG,sBACtF,EAAoB,EAAmB,GAAG,mBAAsC,EAAG,GAAG,uBACtF,EAAkB,EAAmB,GAAG,0BAA6C,EAAG,GAAG,qBAC3F,EAAsB,EAAmB,GAAG,8BAAiD,EAAG,GAAG,yBAEzG,MAAO,CACL,eAAgB,CACd,UACA,mBACA,oBACA,kBACA,uBAEF,eAAgB,EAA2B,cAAe,EAAK,IAInE,aACE,MAAO,CACL,OAAQ,EAA2B,cAAe,EAAG,sBACrD,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,KAInC,WAA2B,EAAgB,GACzC,GAAM,GAAU,EAAmB,GAAG,YAAkB,EAAG,GAAG,aACxD,EAAO,EAAmB,GAAG,WAAiB,EAAG,GAAG,UAE1D,MAAO,CAAE,UAAS,QAGpB,WAAmC,GACjC,GAAM,GAAyB,EAC7B,2BAA2B,yBAC3B,kCAAkC,4BAE9B,EAAkB,EACtB,2BAA2B,mBAC3B,kCAAkC,qBAGpC,MAAO,CAAE,yBAAwB,mBAGnC,aACE,MAAO,CACL,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,IAI/C,MAAO,CACL,2BACA,gCAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,2BACA,gCACE,GAAkB,EAAW,GAE3B,EAAY,EAAU,oBAG5B,GAFA,EAAc,KAAK,CAAE,aAAc,mBAAoB,UAAW,2BAE9D,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yEAAyE,KAG3F,GAAM,GAAS,CACb,YAAa,IACb,iBAAkB,IAClB,aAAc,CACZ,cAIJ,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCvInB,OAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,UAAO,EAAG,EAAO,QAAS,EAAS,QAChD,SAAM,AAAG,OAAI,EAAK,EAAO,mBAClB,AAAG,eAAY,EAAK,EAAG,KDPlC,GAAM,IAAU,qBAEhB,YACE,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,QAAS,EAAS,QACzD,SAAM,AAAG,aACP,EACA,EAAO,gBACP,EAAO,oBACP,EAAO,kBACP,EAAO,iBACP,IAEK,AAAG,eAAY,EAAK,EAAG,KAIlC,YAA+B,GAC7B,MAAO,CAAC,EAAG,EAAG,EAAG,IAAI,KAAK,AAAC,GAAQ,IAAQ,GAAY,CAAC,EAAG,GAAK,CAAC,EAAG,GAG/D,YAAqB,EAAgB,GAC1C,MAAO,AAAG,SAAK,KACb,GAAI,GACA,EAAM,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IA4BnD,GAVA,AAhBuB,CACrB,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,QACP,EAAO,QACP,EAAO,QACP,EAAO,SAGM,QAAQ,CAAC,EAAO,KAC7B,GAAM,GAAW,EAAI,EACf,EAAuB,GAAsB,GACnD,EAAM,GAAmB,EAAK,EAAM,eAAgB,GACpD,EAAM,EAAmB,EAAK,EAAM,eAAgB,CAAC,EAAG,IACpD,IAAa,IACf,GAAS,KAIT,IAAW,KACb,KAAM,IAAI,OAAM,iDAGlB,MAAO,CACL,MACA,OAAQ,KEjEd,YAAa,EAAoB,EAAW,GAC1C,GAAM,GAAY,EAAM,YAClB,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAS,GAAQ,GAAU,GAAQ,GACnC,EAAS,GAAQ,GAAU,GAAQ,GACzC,GAAI,GAAS,GAAK,GAAS,EACzB,MAAO,GAET,GAAM,GAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAmB,EAAkB,GACjE,KAAK,IAAI,EAAmB,EAAkB,GACpD,MAAO,GAAoB,GAAQ,EAAQ,GAGtC,YACL,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAW,EAAM,MAAM,GACvB,EAAa,KAAK,IACtB,EACA,GAGI,EAAa,EAChB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,OAAO,AAAC,GAAM,EAAE,MAAQ,GACxB,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAE5B,EAAe,AAAC,GAAe,GAAK,EAAe,EAAI,EAEvD,EAAqB,GAE3B,SAAW,QAAQ,AAAC,IAClB,GAAI,EAAS,QAAU,EACrB,OAEF,GAAM,GAAgB,EAAE,MAExB,OAAS,GAAI,EAAS,OAAS,EAAG,GAAK,EAAG,EAAE,GAC1C,GAAM,GAAM,GAAI,EAAO,EAAE,SAAU,EAAS,IAC5C,GAAI,IAAQ,GACZ,GAAE,OAAS,EAAa,GACpB,EAAE,OAAS,GAAgB,MAEjC,AAAI,IAAkB,EAAE,OACtB,EAAS,KAAK,EAAE,YAIb,ECjET,MAAoB,OAIpB,YAA2C,GACzC,GAAM,GAAM,AAAG,UAAQ,AAAG,YAAU,EAAG,CAAC,EAAG,KAErC,EAAQ,CACZ,AAAG,MAAI,EAAI,GAAI,EAAI,IACnB,AAAG,MAAI,EAAI,GAAI,EAAI,KAGf,EAAU,CACd,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,KAC1C,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,MAG5C,MAAO,CACL,QACA,WAIJ,YAA0B,EAAiB,GACzC,GAAM,CACJ,QACA,WACE,GAAkC,GAEhC,EAAM,AAAG,UAAQ,AAAG,YAAU,EAAI,CAAC,EAAG,KAEtC,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAE3E,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAEjF,MAAO,AAAG,aACR,AAAG,QAAM,CACP,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,KAEnB,CAAC,EAAG,IAID,YACL,EACA,EACA,GAEA,MAAO,AAAG,QAAK,KACb,GAAM,GAAY,EAAe,MAAM,GAEnC,EAAQ,GACV,AAAG,UAAQ,AAAG,OAAK,EAAO,UAAW,CAAC,EAAW,EAAG,IAAK,CAAC,GAAI,IAC9D,AAAG,UAAQ,EAAgB,CAAC,GAAI,KAElC,EAAQ,AAAG,UACT,EACA,CAAC,EAAY,EAAM,MAAM,GAAK,EAAY,IAG5C,GAAM,GAAmB,AAAG,UAAQ,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,MAC/E,EAAS,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,IAE5D,EAAS,AAAG,UACV,EACA,CAAC,EAAW,EAAO,MAAM,KAG3B,GAAM,GAAe,AAAG,UAAQ,GAC1B,EAAgB,AAAG,UAAQ,GAEjC,MAAO,CACL,MAAO,EACP,OAAQ,KC9Ed,OAAoB,OCApB,OAAoB,OAKb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAY,EAAE,MAAM,GAEpB,EAAwB,AAAG,WAC/B,GAAU,EAAG,EAAO,wBACpB,CAAC,EAAW,GAAI,EAAG,IAEf,EAAkB,AAAG,WACzB,GAAU,EAAG,EAAO,iBACpB,CAAC,EAAW,GAAI,IAGlB,MAAO,CACL,wBACA,qBDjBC,YACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAQ,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IACjD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IAErD,EAAiB,GAAmB,EAAQ,EAAO,iBACnD,EAAiB,GAAmB,EAAG,EAAO,iBAC9C,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAElD,EAAiB,AAAG,UAAO,CAC/B,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,uBACd,GAEG,EAAmB,AAAG,UAAO,CACjC,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,iBACd,GAEH,MAAO,CACL,iBACA,sBEhDN,YAYE,YAAY,CAAE,gBAAe,cAAuC,IAN1D,WAAgB,wBAUxB,GAHA,KAAK,eAAiB,GAAiB,GACvC,KAAK,YAAc,GAAc,IAE7B,MAAO,MAAK,gBAAmB,UAAY,KAAK,gBAAkB,GAAK,KAAK,gBAAkB,EAChG,KAAM,IAAI,OAAM,GAAG,KAAK,iEAG1B,GAAI,MAAO,MAAK,aAAgB,SAC9B,KAAM,IAAI,OAAM,GAAG,KAAK,iDAIxB,iBAA0B,MAAO,MAAK,kBAEtC,cAAuB,MAAO,MAAK,cT3BzC,oBAeoC,GAClC,cACE,MAAM,kBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,AAAG,SAAK,KAEb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAQ,WAEvD,EAAI,AAAG,OAAI,AAAG,OAAI,EAAa,AAAG,UAAO,sBAAwB,AAAG,UAAO,IAC3E,EAAW,GAAY,EAAG,EAAO,aAEjC,CACJ,iBACA,oBACE,GAAgB,EAAS,IAAK,EAAS,OAAQ,EAAO,kBAE1D,MAAO,IAAY,EAAgB,EAAkB,EAAO,qBAInD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,aACX,EACA,EAAkC,IAElC,GAAM,CAAE,aAAY,iBAAkB,GAAI,GAAsB,GAE1D,EAAW,KAAM,GAAW,GAE5B,CACJ,MAAO,EACP,OAAQ,GACN,KAAK,aAAa,GAGhB,EAAQ,EAAO,GACf,EAAS,EAAQ,GACvB,OAAS,GAAI,EAAG,EAAI,EAAO,OAAQ,IACjC,EAAO,GAAG,UACV,EAAQ,GAAG,UAIb,GAAM,GAAa,MAAM,KAAK,KAAM,GAAO,QAGrC,EAAU,GACd,EACA,EACA,EAJmB,GAMnB,GAGI,EAAe,EAAS,2BAA2B,GACnD,EAAY,EAAS,UACrB,EAAO,EAAY,EAAa,MAChC,EAAO,EAAY,EAAa,OAEhC,EAAY,EAAM,YAClB,EAAU,EACb,IAAI,AAAC,IACJ,GAAM,CAAC,EAAK,GAAU,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACf,CAAC,GAAM,IAAS,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACrB,MAAO,IAAI,GACT,EAAW,GACX,GAAI,IACF,GACA,EACA,GAAQ,GACR,EAAS,GAEX,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,OAKtC,SAAM,UACN,EAAO,UAEA,EAGC,sBACR,MAAO,wBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KUzHlB,YAA8B,GACnC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,EAGF,YAAgC,GACrC,MAAO,IAAqB,GAZ9B,oBAgBsC,MCd/B,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,QAAU,SACpB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,OAAQ,SAClB,GAAI,GAAM,QAAS,UAGR,GAAwB,CACnC,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAA+C,CAAC,QAAS,QAAS,QAElE,GAAqB,oBACrB,GAAoC,mCCvBjD,MAAoB,OCapB,GAAM,IAAW,AAAC,GAAa,MAAO,IAAQ,SAEvC,YAAwB,GAC7B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mBAAmB,KAGrC,GAAI,MAAO,GAAO,oBAAuB,UACvC,KAAM,IAAI,OAAM,wDAAwD,EAAO,sBAGjF,GAAI,CAAC,GAAS,EAAO,eAAiB,EAAO,aAAe,GAAK,EAAO,aAAe,EACrF,KAAM,IAAI,OAAM,gEAAgE,EAAO,gBAGzF,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,MAAM,AAAC,GAAW,MAAO,IAAM,UAElD,KAAM,IAAI,OAAM,kEAAkE,KAAK,UAAU,EAAO,YAG1G,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,IAAI,AAAC,GAAW,GAAK,IAAI,MAAM,AAAC,GAAW,GAAS,EAAE,IAAM,GAAS,EAAE,IAE1F,KAAM,IAAI,OAAM,wEAAwE,KAAK,UAAU,EAAO,YAGhH,GAAI,EAAO,SACT,EAAC,MAAM,QAAQ,EAAO,UACnB,EAAO,QAAQ,SAAW,GAC1B,CAAC,EAAO,QAAQ,MAAM,KAEzB,KAAM,IAAI,OAAM,8EAA8E,KAAK,UAAU,EAAO,YCjDxH,MAAoB,OCApB,MAAoB,OAEb,YAAe,GACpB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,AAAG,MAAI,EAAG,AAAG,SAAO,qBAChC,MAAO,AAAG,OAAI,AAAG,OAAK,AAAG,MAAI,EAAG,IAAO,KDApC,YAA2B,EAAgB,GAChD,MAAO,AAAG,QAAK,KACb,GAAI,GAAM,AAAG,MAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KAEjD,SAAM,AAAG,SAAO,EAAK,EAAO,KAAK,QAAS,CAAC,EAAG,GAAI,SAClD,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,KAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,SAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,KAAK,MAEvB,GAAM,KEdjB,OAAoB,OAKb,YAAgC,EAAgB,GACrD,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,OAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KAEjD,SAAM,AAAG,mBAAgB,EAAK,EAAO,iBAAkB,EAAO,iBAAkB,CAAC,EAAG,GAAI,SACxF,EAAM,AAAG,OAAI,EAAK,EAAO,MAElB,GAAM,KCZjB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAEnE,WAAgC,EAAc,GAC5C,GAAM,GAAM,AAAG,YAAS,EAAe,IACjC,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,SAChB,CAAE,UAAW,GAAG,cAGX,CAAE,MAAK,WAGhB,WAAwC,EAAoB,EAAqB,GAC/E,GAAM,GAAO,EAAkB,EAAY,EAAa,EAAG,GAAG,UACxD,EAAK,EAAuB,EAAa,GAAG,QAElD,MAAO,CAAE,OAAM,MAEjB,GAAM,GAA6B,GAAkC,EAAgB,GAErF,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,EACA,EACA,GAEA,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAgB,GAElC,EAEJ,GAAI,EAAO,oBACT,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EAEvC,EAAQ,EAAO,mBACjB,EAAkB,EAAI,EAAI,EAAG,SAC7B,EAA2B,EAAI,EAAI,SACjC,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAkB,GAAM,GAAM,EAAI,EAAI,EAAiB,EAAG,SACxE,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,eAG1D,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAAkB,EAAI,EAAI,EAAiB,EAAG,SAC5D,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,UAI5D,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CAAE,SAAQ,iBCvFnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAgC,GAC9B,GAAM,GAAM,EAAmB,GAAG,QAAc,GAC1C,EAAU,EAAmB,GAAG,YAAkB,GACxD,MAAO,CAAE,MAAK,WAGhB,WAA2B,GACzB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,WAAwC,GACtC,GAAM,GAAO,EAAkB,GAAG,UAC5B,EAAK,EAAuB,GAAG,QACrC,MAAO,CAAE,OAAM,MAGjB,GAAM,GAA6B,GAA+B,GAElE,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAW,GAE7B,EAEJ,GAAI,EAAO,oBAET,GAAM,GAAc,EAAO,aAAe,EAAO,YAAY,QAAU,EACvE,EAAS,CACP,MAAO,EAAO,mBAAqB,EAAkB,SAAW,EAA2B,SAC3F,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAkB,cAG3B,GAAS,CACP,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAAkB,UAI7B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCpFnB,aAYE,YAAY,CAAE,YAAW,kBAAuC,IANtD,WAAgB,oBAUxB,GAHA,KAAK,WAAa,GAAa,IAC/B,KAAK,gBAAkB,GAAkB,GAErC,MAAO,MAAK,YAAe,UAAY,KAAK,WAAa,IAAO,EAClE,KAAM,IAAI,OAAM,GAAG,KAAK,6DAG1B,GAAI,MAAO,MAAK,iBAAoB,UAAY,KAAK,iBAAmB,GAAK,KAAK,iBAAmB,EACnG,KAAM,IAAI,OAAM,GAAG,KAAK,qEAIxB,aAAsB,MAAO,MAAK,cAElC,kBAA2B,MAAO,MAAK,kBP3B7C,oBAuBoC,GAOlC,YAAY,GACV,MAAM,cACN,GAAe,GACf,KAAK,QAAU,KAGN,UACT,MAAO,MAAK,WAGH,mBACT,MAAO,MAAK,OAAO,iBAAmB,KAAK,OAAO,QAAQ,OAAS,KAG1D,mBACT,MAAO,GAAK,MAAK,gBAAkB,KAAK,OAAO,QAAQ,OAAS,GAG3D,cAAc,EAAgB,GACnC,GAAI,GAAM,GAAkB,EAAG,EAAO,OACtC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,GAAkB,EAAK,EAAO,OAE7B,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAgB,GAClC,GAAI,GAAM,KAAK,OAAO,mBAClB,GAAM,GAAU,EAAG,EAAO,MAAqB,QAAS,KACxD,GAAuB,EAAG,EAAO,OACrC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EACjE,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EAE1D,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAiB,GACnC,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,4CAGlB,MAAO,AAAG,QAAK,KAEb,GAAI,GAAc,AAAG,OAAK,EAAM,cAAc,EAAW,IAAQ,WACjE,SAAc,KAAK,OAAO,QACtB,GAAU,EAAa,KAAK,OAAO,SACnC,EACJ,EAAc,EAAY,IAAI,AAAG,SAAO,MAEjC,KAAK,OAAO,mBACf,KAAK,aAAa,EAAa,GAC/B,KAAK,cAAc,EAAa,UAI3B,SAAQ,EAAkB,GACrC,MAAO,MAAK,aAAa,KAAM,GAAW,GAAQ,QAGvC,QAAO,EAAkB,EAAoC,IACxE,GAAM,CAAE,YAAW,kBAAmB,GAAI,IAAkB,GAEtD,EAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,EAAU,GACxC,EAAO,AAAG,OAAK,IAAM,AAAG,UAAQ,GAAK,GAAG,cAExC,EAAkB,CACtB,MAAO,EAAS,cAAc,GAC9B,OAAQ,EAAS,eAAe,IAG5B,EAAU,KAAM,MAAK,aAAa,EAAM,EAAS,2BAA2B,GAAI,GACtF,EAAI,UACJ,EAAK,UAEL,GAAM,GAAQ,EAAQ,IAAI,AAAC,GAAQ,EAAI,KACjC,EAAS,EAAQ,IAAI,AAAC,GAAQ,EAAI,OAClC,EAAc,EAAQ,IAAI,AAAC,GAAQ,EAAI,YACvC,EAAa,EAAQ,IAAI,AAAC,GAAQ,KAAK,OAAO,QAAQ,EAAI,QAiBhE,MARmB,AAPH,IACd,EAAM,IAAI,AAAC,GAAQ,EAAI,QAAQ,IAC/B,EACA,KAAK,OAAO,aACZ,IAGyB,IAAI,AAAC,GAAQ,GAAI,IAC1C,EAAO,GACP,EAAY,GACZ,EAAW,GACX,EAAM,GACN,IAMM,sBACR,MAAO,GAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,QAG1C,cAAc,GACtB,GAAM,GAAc,KAAK,OAAO,aAAe,GAAe,qBAExD,EAAa,EAAc,EAAY,OAAS,OACtD,GAAI,IAAe,GAAK,IAAe,GAAK,IAAe,EACzD,KAAM,IAAI,OAAM,oEAAoE,2BAEtF,MAAO,IAAc,EAAS,KAAK,OAAQ,KAAK,gBAAiB,QAGnD,cACd,EACA,EACA,GAEA,GAAM,CAAE,QAAO,UAAW,EACpB,EAAY,KAAK,IAAI,EAAO,GAC5B,EAAoB,EAAY,EAChC,EAAoB,EAAY,EAEhC,EAAW,EAAa,MAAM,GAC9B,EAAW,KAAK,OAAO,QAAQ,OAE/B,CAAC,EAAa,EAAc,GAAqB,AAAG,OAAK,KAC7D,GAAM,GAAW,EAAa,QAAQ,CAAC,EAAU,EAAU,EAAU,KAAK,kBAEpE,EAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACpE,EAAS,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACrE,EAAc,KAAK,gBACrB,AAAG,UAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,KAAK,OAAO,QAAQ,SAAU,GACrG,AAAG,SAAO,GACd,MAAO,CAAC,EAAO,EAAQ,KAGnB,EAAU,GAEV,EAAa,KAAM,GAAa,QAChC,EAAY,KAAM,GAAY,QACpC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAS,EAAG,EAAS,EAAU,KACtC,GAAM,GAAQ,GAAQ,EAAW,GAAK,GAAK,GAAQ,IACnD,GAAI,CAAC,GAAkB,EAAQ,GAC7B,GAAM,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAe,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACvG,EAAgB,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EAExG,GAAK,EAAO,GAAa,EACzB,GAAK,GAAO,EAAc,EAE1B,GAAM,CAAE,MAAK,MAAK,UAClB,CAAE,cAAY,UAAU,KAAK,gBAC/B,KAAM,MAAK,sBAAsB,EAAkC,IACnE,CAAE,WAAY,EAAG,MAAO,GAE5B,EAAQ,KAAK,CACX,IAAK,GAAI,IAAY,GAAG,GAAG,GAAI,GAAY,GAAI,GAC/C,QACA,WAAY,EAAQ,GACpB,YACG,MAOb,SAAY,UACZ,EAAa,UACb,EAAkB,UAEX,OAGK,uBAAsB,EAA4B,GAC9D,GAAM,CAAE,MAAK,MAAK,UAAW,EACvB,EAAc,KAAM,GAAc,QACxC,MAAO,OAAM,KAAK,OAAO,QAAQ,QAAQ,KAAK,GAC3C,IAAI,CAAC,EAAG,IAAM,EAAY,GAAK,GAAK,GAAQ,IAC5C,IAAI,CAAC,EAAY,IAAW,EAC3B,aACA,WAED,OAAO,CAAC,EAAK,IAAU,EAAI,WAAa,EAAK,WAAa,EAAM,KApPvE,MAwBgB,AAxBhB,GAwBgB,qBAAuB,CACnC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,IAAK,KAAM,MQzBxC,oBAiBgC,IAC9B,YAAY,EAA8B,IACxC,GAAM,GAAS,CACb,qBACA,aAAc,GACd,QAAS,CAAC,WACN,EACA,CACA,QAAS,GACT,QAAS,IAET,CACA,QAAS,GACT,gBAAiB,KAIvB,MAAM,MAGG,sBACT,MAAO,MAAK,OAAO,sBAGV,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,MAAK,mBAAqB,GAAoC,GAG7D,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KC9CrC,YAA0B,EAAuB,EAA8B,IACpF,GAAM,GAAM,GAAI,IAAW,GAC3B,SAAI,eAAe,GACZ,ECZT,oBAI6C,IAJ7C,kCAKY,WAAgB,4BCL5B,kBACe,MAEX,GAEA,MAAO,GAAY,KAAM,MAAK,YAGnB,OACX,KAAM,IAAI,OAAM,6CCRpB,OAAoB,OCDpB,OAAoB,OAOpB,kBACE,EACA,EAEA,EACA,EAEA,EAAwF,CAAC,CAAE,iBAAkB,GAE7G,GAAM,GAAY,EAAc,IAAI,AAAC,GAAkB,GAAoB,GACvE,EAAoB,GACpB,EAAa,WACX,EAAgD,GACpD,aAAoB,WAChB,KAAM,IAAmB,EAAO,GAChC,KAAM,IAAa,EAAO,IAG1B,EAAU,KAAM,GAAe,GAErC,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAGT,kBACE,EACA,EAEA,EACA,EAEA,GAEA,MAAO,IACL,CAAC,GACD,EACA,KAAO,IAAU,EAAc,EAAM,IACrC,EACA,GC5CG,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAAqC,CAAC,QAAS,QAAS,QCZrE,oBAUsC,IACpC,cACE,GAAM,GAAS,CACb,mBAAoB,GACpB,aAAc,GACd,QAAS,CAAC,QACV,QAAS,GACT,QAAS,GACT,mBAAoB,GACpB,YAAa,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,MAGzC,MAAM,MAGG,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,2BAGC,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KCvBrC,GAAM,GAAO,CAClB,eAAgB,GAAI,IACpB,iBAAkB,GAAI,IACtB,WAAY,GAAI,IAChB,kBAAmB,GAAI,IACvB,sBAAuB,GAAI,IAC3B,mBAAoB,GAAI,IACxB,kBAAmB,GAAI,IACvB,aAAc,GAAI,KAUP,GAAiB,CAAC,EAAkB,IAA6D,EAAK,eAAe,YAAY,EAAO,GASxI,GAAmB,CAAC,EAAkB,IAA+D,EAAK,iBAAiB,YAAY,EAAO,GAS9I,GAAa,CAAC,EAAkB,IAA0D,EAAK,WAAW,YAAY,EAAO,GAS7H,GAAsB,AAAC,GAAmE,EAAK,kBAAkB,gBAAgB,GAWjI,GAA0B,AAAC,GAAmE,EAAK,sBAAsB,gBAAgB,GAYzI,GAAwB,AAAC,GAA6D,EAAK,mBAAmB,sBAAsB,GASpI,GAA2B,AAAC,GAAmE,EAAK,kBAAkB,mBAAmB,GASzI,GAAsB,AAAC,GAAiF,EAAK,aAAa,oBAAoB,GAE9I,GAA0B,AAAC,GAAgB,EAAK,eAAe,KAAK,GACpE,GAA4B,AAAC,GAAgB,EAAK,iBAAiB,KAAK,GACxE,GAAsB,AAAC,GAAgB,EAAK,WAAW,KAAK,GAC5D,GAAwB,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACrE,GAA4B,AAAC,GAAgB,EAAK,sBAAsB,KAAK,GAC7E,GAA2B,AAAC,GAAgB,EAAK,mBAAmB,KAAK,GACzE,GAA0B,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACvE,GAAqB,AAAC,GAAgB,EAAK,aAAa,KAAK,GAG7D,GAAyB,GACzB,GAAc,GACd,GAAkB,GCpH/B,oBAmB4E,IAC1E,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA1Bd,gBAkCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAwB,KAAM,IAClC,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,KAEtD,KAAK,gBAGP,MAAO,GAAc,IACnB,CAAC,EAAc,IAAM,GAAmC,EAAc,EAAsB,KAIhG,mBACE,MAAO,IAAI,IAA2B,KAAM,KAAK,SArDrD,gBA2DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,GAAkB,KAAM,IAC5B,EACA,KAAK,MACL,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,GACpD,KAAK,gBAGP,MAAO,IAA0B,EAAc,GAGjD,mBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA7ExD,gBAmFU,IACR,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAzFxD,gBA+FU,IACR,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCrG1D,oBAoByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA3Bd,gBAmCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAqB,KAAM,IAC/B,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,aAAa,oBAAoB,KAElD,KAAK,gBAGP,MAAO,GAAc,IAAI,CAAC,EAAc,KACtC,GAAM,CAAE,MAAK,SAAQ,qBAAsB,EAAmB,GAC9D,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,KAIpF,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAvDxD,gBA6DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,MAAK,SAAQ,qBAAsB,KAAM,IAC/C,EACA,KAAK,MACL,AAAC,GAAS,EAAK,aAAa,oBAAoB,GAChD,KAAK,gBAGP,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,GAGlF,sBACE,MAAO,IAAI,IAAiC,KAAM,KAAK,SA/E3D,gBAqFU,IACR,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA3FxD,gBAiGU,IACR,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCvG1D,oBAiB4E,IAC1E,YAEY,EAEA,GAEV,QAJU,kBAEA,eAtBd,gBA8BU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAUjC,MAAO,AARa,MAAM,IACxB,EACA,KAAK,MACL,AAAC,GAAU,QAAQ,IAAI,EAAM,IAAI,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,KACzF,KACA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,OAGxD,IAAI,CAAC,EAAY,IAAM,GAAkC,EAAc,GAAI,IAGhG,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,SAlDtE,gBAwDU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAEF,GAAM,GAAa,KAAM,IACvB,EACA,KAAK,MACL,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,GACxD,KAEA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,MAG3E,MAAO,IAAyB,EAAc,GAGhD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,SP/EzE,oBAqByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,6BAKE,eACZ,MAAO,MAAK,mBACR,EAAK,sBACL,EAAK,oBApCb,gBA0CU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAC3B,EAAa,EAAc,IAAI,AAAC,GAAQ,EAAI,WAE5C,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,GACrC,KAAM,IAAa,KAAK,MAAO,GAE7B,EAAsB,KAAM,SAAQ,IAAI,EAAM,IAClD,AAAC,GAAS,KAAK,YAAY,gBAAgB,KAG7C,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAAc,IAAI,CAAC,EAAc,IAAM,GAAiC,EAAc,EAAoB,KAGnH,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SArExD,gBA2EU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,aAAc,EAChB,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,CAAC,IACtC,KAAM,IAAa,KAAK,MAAO,CAAC,IAE9B,EAAY,KAAM,MAAK,YAAY,gBAAgB,EAAM,IAE/D,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,GAAiC,EAAc,GAGxD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SQvG1D,oBAckD,IAChD,YAEY,EAEA,EAAgC,GAAI,IAE9C,QAJU,aAEA,iBAnBd,gBAyBwC,SACzB,OACX,GAAM,CAAE,QAAO,WAAY,KAGrB,EAAwB,YAAmB,IAE7C,AAAC,GAAqB,EAAK,iBAAiB,YAAY,EAAO,GAG/D,YAAmB,GAEf,AAAC,GAAqB,EAAK,eAAe,YAAY,EAAO,GAE7D,YAAmB,IAEf,AAAC,GAAqB,EAAK,WAAW,YAAY,EAAO,GACzD,KAIZ,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,uIAGlB,MAAO,GAAsB,GAGvB,iCAEN,MAAO,IAAI,SAAiC,KAAO,KACjD,GAAM,GAAa,KAAM,MAAK,MAC9B,EAAQ,EAAW,IAAI,AAAC,GAAc,GAAwB,GAAI,OAItE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,SA/EX,gBAoF0C,SAC3B,OACX,GAAM,GAAiB,KAAM,IAAI,IAAmB,KAAK,MAAO,KAAK,SACjE,EAAgC,EAAe,GACnD,SAAe,QAAQ,AAAC,IACtB,AAAI,EAAc,MAAQ,EAA8B,OACtD,GAAgC,KAG7B,EAGD,gCAEN,MAAO,IAAI,SAA2C,KAAO,KAC3D,GAAM,GAAY,KAAM,MAAK,MAC7B,EAAQ,EAAY,GAA4B,GAAI,GAAa,UAIrE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,SCrHJ,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAqB,EAAO,GAGlC,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAmB,EAAO,GCRvC,kBACE,EACA,GAEA,MAAO,IAAe,EAAO,GAAI,GAAsB,EAAgB,CAAE,iBAAkB,KACxF,oBACA,sBAGL,kBACE,EACA,EAAoC,IAEpC,MAAO,IAAe,EAAO,GAAI,IAAkB,IAChD,oBACA,sBAGE,GAAM,IAAW,GC1BjB,YAA2B,EAA+B,GAC/D,GAAI,EAAK,SAAW,EAAK,OAAQ,KAAM,IAAI,OAAM,kDAEjD,GAAM,GAAQ,MAAM,KAAK,GACnB,EAAQ,MAAM,KAAK,GAEzB,MAAO,MAAK,KACV,EACG,IAAI,CAAC,EAAK,IAAM,EAAM,EAAM,IAC5B,OAAO,CAAC,EAAK,IAAS,EAAO,GAAQ,EAAI,ICThD,aAUE,YACE,EACA,EAA4B,IAE5B,KAAK,mBAAqB,EAE1B,GAAM,GAAa,MAAM,QAAQ,GAAU,EAAS,CAAC,GAErD,GAAI,CAAC,EAAW,OACd,KAAM,IAAI,OAAM,2DAGlB,GAAI,GAAQ,EACN,EAAoB,IAAM,UAAU,MAE1C,KAAK,oBAAsB,EAAW,IAAI,AAAC,IACzC,GAAI,YAAgB,IAClB,MAAO,GAGT,GAAI,YAAgB,cAClB,MAAO,IAAI,IAAuB,IAAqB,CAAC,IAG1D,GAAI,EAAK,YAAc,EAAK,qBAAsB,cAChD,MAAO,IAAI,IAAuB,IAAqB,CAAC,EAAK,aAG/D,KAAM,IAAI,OAAM,4MAIT,sBAAiD,MAAO,MAAK,uBAE7D,qBAA8B,MAAO,MAAK,mBAE9C,oBAAoB,EAA+B,GACxD,MAAO,GACJ,IAAI,AAAC,GAAM,GAAkB,EAAG,IAChC,OAAO,CAAC,EAAI,IAAO,EAAK,EAAI,GACxB,GAAY,QAAU,GAGxB,gBAAgB,GACrB,MAAO,MAAK,mBACT,IAAI,CAAC,CAAE,cAAa,WAAY,GAAI,IACnC,EACA,KAAK,oBAAoB,EAAiB,KAE3C,OAAO,CAAC,EAAM,IAAU,EAAK,SAAW,EAAK,SAAW,EAAO,GAG7D,cAAc,GACnB,GAAM,GAAY,KAAK,gBAAgB,GACvC,MAAO,GAAU,SAAW,KAAK,kBAC7B,EACA,GAAI,IAAU,UAAW,EAAU,UAGlC,SACL,MAAO,CACL,kBAAmB,KAAK,kBACxB,mBAAoB,KAAK,mBAAmB,IAAI,AAAC,GAAO,EAAG,iBAIjD,UAAS,GACrB,GAAM,GAAqB,EAAK,mBAC7B,IAAI,AAAC,GAAY,GAAuB,SAAS,IACpD,MAAO,IAAI,IAAY,EAAoB,EAAK,qBC1E7C,YAAgC,GACrC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECFF,YAA0B,EAAY,GAC3C,GAAM,CAAE,QAAO,UAAW,GAAI,GAAW,EAAW,MAAO,EAAW,QAEtE,GAAI,GAAS,GAAK,GAAU,EAC1B,KAAM,IAAI,OAAM,uCAAuC,KAAK,UAAU,CAAE,QAAO,cAGjF,GAAI,MAAM,QAAQ,GAEhB,MAAQ,GAAuB,IAAI,AAAC,GAAQ,GAAc,EAAK,CAAE,QAAO,YAG1E,GAAI,GAAoB,IACtB,GAAM,GAAmB,EAAQ,UAAU,QAAQ,EAAO,GACpD,EAAmB,EAAQ,mBAAmB,QAAQ,EAAiB,IAAI,MAAO,EAAiB,IAAI,QAC7G,MAAO,IAAwB,GAAwB,EAAS,GAAmB,GAGrF,MAAI,IAAoB,GACf,GAAwB,EAAS,EAAQ,UAAU,QAAQ,EAAO,IAGvE,YAAmB,IAAiB,YAAmB,GACjD,EAAgB,QAAQ,EAAO,GAGlC,EjJRT,GAAM,IAAQ,MAAO,UAAY,YAE3B,GAAW,MAAO,YAAc,aAAiB,MAAO,WAAU,WAAc,YACzE,GAAU,CAAE,QAAa,GAAmB,QAAM", + "sourcesContent": ["/* eslint-disable import/no-extraneous-dependencies */\n/* eslint-disable node/no-unpublished-import */\n\n// wrapper to load tfjs in a single place so version can be changed quickly\n\nexport * from '@tensorflow/tfjs/dist/index.js';\nexport * from '@tensorflow/tfjs-backend-wasm';\n", "export function isNodejs(): boolean {\n return typeof global === 'object'\n && typeof require === 'function'\n && typeof module !== 'undefined'\n // issues with gatsby.js: module.exports is undefined\n // && !!module.exports\n && typeof process !== 'undefined' && !!process.version;\n}\n", "import * as tf from '../dist/tfjs.esm';\nimport * as draw from './draw/index';\nimport * as utils from './utils/index';\nimport * as pkg from '../package.json';\n\nexport { tf, draw, utils };\n\nexport * from './ageGenderNet/index';\nexport * from './classes/index';\nexport * from './dom/index';\nexport * from './env/index';\nexport * from './faceExpressionNet/index';\nexport * from './faceLandmarkNet/index';\nexport * from './faceRecognitionNet/index';\nexport * from './factories/index';\nexport * from './globalApi/index';\nexport * from './ops/index';\nexport * from './ssdMobilenetv1/index';\nexport * from './tinyFaceDetector/index';\nexport * from './tinyYolov2/index';\nexport * from './euclideanDistance';\nexport * from './NeuralNetwork';\nexport * from './resizeResults';\n\nconst node = (typeof process !== 'undefined');\nconst browser = (typeof navigator !== 'undefined') && (typeof navigator.userAgent !== 'undefined');\nexport const version = { faceapi: pkg.version as string, node, browser };\n", "export * from './drawContour';\nexport * from './drawDetections';\nexport * from './drawFaceExpressions';\nexport * from './DrawBox';\nexport * from './DrawFaceLandmarks';\nexport * from './DrawTextField';\n", "import { Point } from '../classes/index';\n\nexport function drawContour(\n ctx: CanvasRenderingContext2D,\n points: Point[],\n isClosed: boolean = false,\n) {\n ctx.beginPath();\n\n points.slice(1).forEach(({ x, y }, prevIdx) => {\n const from = points[prevIdx];\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(x, y);\n });\n\n if (isClosed) {\n const from = points[points.length - 1];\n const to = points[0];\n if (!from || !to) {\n return;\n }\n\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(to.x, to.y);\n }\n\n ctx.stroke();\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Point } from '../classes/index';\nimport { Dimensions, IDimensions } from '../classes/Dimensions';\n\nexport function isTensor(tensor: any, dim: number) {\n return tensor instanceof tf.Tensor && tensor.shape.length === dim;\n}\n\nexport function isTensor1D(tensor: any): tensor is tf.Tensor1D {\n return isTensor(tensor, 1);\n}\n\nexport function isTensor2D(tensor: any): tensor is tf.Tensor2D {\n return isTensor(tensor, 2);\n}\n\nexport function isTensor3D(tensor: any): tensor is tf.Tensor3D {\n return isTensor(tensor, 3);\n}\n\nexport function isTensor4D(tensor: any): tensor is tf.Tensor4D {\n return isTensor(tensor, 4);\n}\n\nexport function isFloat(num: number) {\n return num % 1 !== 0;\n}\n\nexport function isEven(num: number) {\n return num % 2 === 0;\n}\n\nexport function round(num: number, prec: number = 2) {\n const f = 10 ** prec;\n return Math.floor(num * f) / f;\n}\n\nexport function isDimensions(obj: any): boolean {\n return obj && obj.width && obj.height;\n}\n\nexport function computeReshapedDimensions({ width, height }: IDimensions, inputSize: number) {\n const scale = inputSize / Math.max(height, width);\n return new Dimensions(Math.round(width * scale), Math.round(height * scale));\n}\n\nexport function getCenterPoint(pts: Point[]): Point {\n return pts.reduce((sum, pt) => sum.add(pt), new Point(0, 0))\n .div(new Point(pts.length, pts.length));\n}\n\nexport function range(num: number, start: number, step: number): number[] {\n return Array(num).fill(0).map((_, i) => start + (i * step));\n}\n\nexport function isValidNumber(num: any) {\n return !!num && (num !== Infinity) && (num !== -Infinity) && !Number.isNaN(num) || num === 0;\n}\n\nexport function isValidProbablitiy(num: any) {\n return isValidNumber(num) && num >= 0 && num <= 1.0;\n}\n", "import { isValidNumber } from '../utils/index';\n\nexport interface IDimensions {\n width: number\n height: number\n}\n\nexport class Dimensions implements IDimensions {\n private _width: number\n\n private _height: number\n\n constructor(width: number, height: number) {\n if (!isValidNumber(width) || !isValidNumber(height)) {\n throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({ width, height })}`);\n }\n\n this._width = width;\n this._height = height;\n }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public reverse(): Dimensions {\n return new Dimensions(1 / this.width, 1 / this.height);\n }\n}\n", "export interface IPoint {\n x: number\n y: number\n}\n\nexport class Point implements IPoint {\n private _x: number\n\n private _y: number\n\n constructor(x: number, y: number) {\n this._x = x;\n this._y = y;\n }\n\n get x(): number { return this._x; }\n\n get y(): number { return this._y; }\n\n public add(pt: IPoint): Point {\n return new Point(this.x + pt.x, this.y + pt.y);\n }\n\n public sub(pt: IPoint): Point {\n return new Point(this.x - pt.x, this.y - pt.y);\n }\n\n public mul(pt: IPoint): Point {\n return new Point(this.x * pt.x, this.y * pt.y);\n }\n\n public div(pt: IPoint): Point {\n return new Point(this.x / pt.x, this.y / pt.y);\n }\n\n public abs(): Point {\n return new Point(Math.abs(this.x), Math.abs(this.y));\n }\n\n public magnitude(): number {\n return Math.sqrt((this.x ** 2) + (this.y ** 2));\n }\n\n public floor(): Point {\n return new Point(Math.floor(this.x), Math.floor(this.y));\n }\n}\n", "import { isDimensions, isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { IDimensions } from './Dimensions';\nimport { Point } from './Point';\nimport { IRect } from './Rect';\n\nexport class Box implements IBoundingBox, IRect {\n public static isRect(rect: any): boolean {\n return !!rect && [rect.x, rect.y, rect.width, rect.height].every(isValidNumber);\n }\n\n public static assertIsValidBox(box: any, callee: string, allowNegativeDimensions: boolean = false) {\n if (!Box.isRect(box)) {\n throw new Error(`${callee} - invalid box: ${JSON.stringify(box)}, expected object with properties x, y, width, height`);\n }\n\n if (!allowNegativeDimensions && (box.width < 0 || box.height < 0)) {\n throw new Error(`${callee} - width (${box.width}) and height (${box.height}) must be positive numbers`);\n }\n }\n\n private _x: number\n\n private _y: number\n\n private _width: number\n\n private _height: number\n\n constructor(_box: IBoundingBox | IRect, allowNegativeDimensions: boolean = true) {\n const box = (_box || {}) as any;\n\n const isBbox = [box.left, box.top, box.right, box.bottom].every(isValidNumber);\n const isRect = [box.x, box.y, box.width, box.height].every(isValidNumber);\n\n if (!isRect && !isBbox) {\n throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(box)}`);\n }\n\n const [x, y, width, height] = isRect\n ? [box.x, box.y, box.width, box.height]\n : [box.left, box.top, box.right - box.left, box.bottom - box.top];\n\n Box.assertIsValidBox({\n x, y, width, height,\n }, 'Box.constructor', allowNegativeDimensions);\n\n this._x = x;\n this._y = y;\n this._width = width;\n this._height = height;\n }\n\n public get x(): number { return this._x; }\n\n public get y(): number { return this._y; }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public get left(): number { return this.x; }\n\n public get top(): number { return this.y; }\n\n public get right(): number { return this.x + this.width; }\n\n public get bottom(): number { return this.y + this.height; }\n\n public get area(): number { return this.width * this.height; }\n\n public get topLeft(): Point { return new Point(this.left, this.top); }\n\n public get topRight(): Point { return new Point(this.right, this.top); }\n\n public get bottomLeft(): Point { return new Point(this.left, this.bottom); }\n\n public get bottomRight(): Point { return new Point(this.right, this.bottom); }\n\n public round(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.round(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public floor(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.floor(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public toSquare(): Box {\n let {\n x, y, width, height,\n } = this;\n const diff = Math.abs(width - height);\n if (width < height) {\n x -= (diff / 2);\n width += diff;\n }\n if (height < width) {\n y -= (diff / 2);\n height += diff;\n }\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public rescale(s: IDimensions | number): Box {\n const scaleX = isDimensions(s) ? (s as IDimensions).width : s as number;\n const scaleY = isDimensions(s) ? (s as IDimensions).height : s as number;\n return new Box({\n x: this.x * scaleX,\n y: this.y * scaleY,\n width: this.width * scaleX,\n height: this.height * scaleY,\n });\n }\n\n public pad(padX: number, padY: number): Box {\n const [x, y, width, height] = [\n this.x - (padX / 2),\n this.y - (padY / 2),\n this.width + padX,\n this.height + padY,\n ];\n return new Box({\n x, y, width, height,\n });\n }\n\n public clipAtImageBorders(imgWidth: number, imgHeight: number): Box {\n const {\n x, y, right, bottom,\n } = this;\n const clippedX = Math.max(x, 0);\n const clippedY = Math.max(y, 0);\n\n const newWidth = right - clippedX;\n const newHeight = bottom - clippedY;\n const clippedWidth = Math.min(newWidth, imgWidth - clippedX);\n const clippedHeight = Math.min(newHeight, imgHeight - clippedY);\n\n return (new Box({\n x: clippedX, y: clippedY, width: clippedWidth, height: clippedHeight,\n })).floor();\n }\n\n public shift(sx: number, sy: number): Box {\n const { width, height } = this;\n const x = this.x + sx;\n const y = this.y + sy;\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public padAtBorders(imageHeight: number, imageWidth: number) {\n const w = this.width + 1;\n const h = this.height + 1;\n\n const dx = 1;\n const dy = 1;\n let edx = w;\n let edy = h;\n\n let x = this.left;\n let y = this.top;\n let ex = this.right;\n let ey = this.bottom;\n\n if (ex > imageWidth) {\n edx = -ex + imageWidth + w;\n ex = imageWidth;\n }\n if (ey > imageHeight) {\n edy = -ey + imageHeight + h;\n ey = imageHeight;\n }\n if (x < 1) {\n edy = 2 - x;\n x = 1;\n }\n if (y < 1) {\n edy = 2 - y;\n y = 1;\n }\n\n return {\n dy, edy, dx, edx, y, ey, x, ex, w, h,\n };\n }\n\n public calibrate(region: Box) {\n return new Box({\n left: this.left + (region.left * this.width),\n top: this.top + (region.top * this.height),\n right: this.right + (region.right * this.width),\n bottom: this.bottom + (region.bottom * this.height),\n }).toSquare().round();\n }\n}\n", "import { Box } from './Box';\n\nexport interface IBoundingBox {\n left: number\n top: number\n right: number\n bottom: number\n}\n\nexport class BoundingBox extends Box implements IBoundingBox {\n constructor(left: number, top: number, right: number, bottom: number, allowNegativeDimensions: boolean = false) {\n super({\n left, top, right, bottom,\n }, allowNegativeDimensions);\n }\n}\n", "import { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { IRect, Rect } from './Rect';\n\nexport class ObjectDetection {\n private _score: number\n\n private _classScore: number\n\n private _className: string\n\n private _box: Rect\n\n private _imageDims: Dimensions\n\n constructor(\n score: number,\n classScore: number,\n className: string,\n relativeBox: IRect,\n imageDims: IDimensions,\n ) {\n this._imageDims = new Dimensions(imageDims.width, imageDims.height);\n this._score = score;\n this._classScore = classScore;\n this._className = className;\n this._box = new Box(relativeBox).rescale(this._imageDims);\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n\n public get className(): string { return this._className; }\n\n public get box(): Box { return this._box; }\n\n public get imageDims(): Dimensions { return this._imageDims; }\n\n public get imageWidth(): number { return this.imageDims.width; }\n\n public get imageHeight(): number { return this.imageDims.height; }\n\n public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()); }\n\n public forSize(width: number, height: number): ObjectDetection {\n return new ObjectDetection(\n this.score,\n this.classScore,\n this.className,\n this.relativeBox,\n { width, height },\n );\n }\n}\n", "import { Box } from './Box';\nimport { IDimensions } from './Dimensions';\nimport { ObjectDetection } from './ObjectDetection';\nimport { Rect } from './Rect';\n\nexport interface IFaceDetecion {\n score: number\n box: Box\n}\n\nexport class FaceDetection extends ObjectDetection implements IFaceDetecion {\n constructor(\n score: number,\n relativeBox: Rect,\n imageDims: IDimensions,\n ) {\n super(score, score, '', relativeBox, imageDims);\n }\n\n public forSize(width: number, height: number): FaceDetection {\n const { score, relativeBox, imageDims } = super.forSize(width, height);\n return new FaceDetection(score, relativeBox, imageDims);\n }\n}\n", "import { Box } from '../classes/Box';\n\nexport function iou(box1: Box, box2: Box, isIOU: boolean = true) {\n const width = Math.max(0.0, Math.min(box1.right, box2.right) - Math.max(box1.left, box2.left));\n const height = Math.max(0.0, Math.min(box1.bottom, box2.bottom) - Math.max(box1.top, box2.top));\n const interSection = width * height;\n\n return isIOU\n ? interSection / (box1.area + box2.area - interSection)\n : interSection / Math.min(box1.area, box2.area);\n}\n", "import { BoundingBox, IPoint } from '../classes/index';\n\nexport function minBbox(pts: IPoint[]): BoundingBox {\n const xs = pts.map((pt) => pt.x);\n const ys = pts.map((pt) => pt.y);\n const minX = xs.reduce((min, x) => (x < min ? x : min), Infinity);\n const minY = ys.reduce((min, y) => (y < min ? y : min), Infinity);\n const maxX = xs.reduce((max, x) => (max < x ? x : max), 0);\n const maxY = ys.reduce((max, y) => (max < y ? y : max), 0);\n\n return new BoundingBox(minX, minY, maxX, maxY);\n}\n", "import { Box } from '../classes/Box';\nimport { iou } from './iou';\n\nexport function nonMaxSuppression(\n boxes: Box[],\n scores: number[],\n iouThreshold: number,\n isIOU: boolean = true,\n): number[] {\n let indicesSortedByScore = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .sort((c1, c2) => c1.score - c2.score)\n .map((c) => c.boxIndex);\n\n const pick: number[] = [];\n\n while (indicesSortedByScore.length > 0) {\n const curr = indicesSortedByScore.pop() as number;\n pick.push(curr);\n\n const indices = indicesSortedByScore;\n\n const outputs: number[] = [];\n for (let i = 0; i < indices.length; i++) {\n const idx = indices[i];\n\n const currBox = boxes[curr];\n const idxBox = boxes[idx];\n\n outputs.push(iou(currBox, idxBox, isIOU));\n }\n\n indicesSortedByScore = indicesSortedByScore.filter(\n (_, j) => outputs[j] <= iouThreshold,\n );\n }\n\n return pick;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function normalize(x: tf.Tensor4D, meanRgb: number[]): tf.Tensor4D {\n return tf.tidy(() => {\n const [r, g, b] = meanRgb;\n const avg_r = tf.fill([...x.shape.slice(0, 3), 1], r, 'float32');\n const avg_g = tf.fill([...x.shape.slice(0, 3), 1], g, 'float32');\n const avg_b = tf.fill([...x.shape.slice(0, 3), 1], b, 'float32');\n const avg_rgb = tf.concat([avg_r, avg_g, avg_b], 3);\n\n return tf.sub(x, avg_rgb);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n/**\n * Pads the smaller dimension of an image tensor with zeros, such that width === height.\n *\n * @param imgTensor The image tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The padded tensor with width === height.\n */\nexport function padToSquare(\n imgTensor: tf.Tensor4D,\n isCenterImage: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const [height, width] = imgTensor.shape.slice(1);\n if (height === width) {\n return imgTensor;\n }\n\n const dimDiff = Math.abs(height - width);\n const paddingAmount = Math.round(dimDiff * (isCenterImage ? 0.5 : 1));\n const paddingAxis = height > width ? 2 : 1;\n\n const createPaddingTensor = (paddingAmountLocal: number): tf.Tensor => {\n const paddingTensorShape = imgTensor.shape.slice();\n paddingTensorShape[paddingAxis] = paddingAmountLocal;\n return tf.fill(paddingTensorShape, 0, 'float32');\n };\n\n const paddingTensorAppend = createPaddingTensor(paddingAmount);\n const remainingPaddingAmount = dimDiff - (paddingTensorAppend.shape[paddingAxis] as number);\n\n const paddingTensorPrepend = isCenterImage && remainingPaddingAmount\n ? createPaddingTensor(remainingPaddingAmount)\n : null;\n\n const tensorsToStack = [\n paddingTensorPrepend,\n imgTensor,\n paddingTensorAppend,\n ]\n .filter((t) => !!t)\n // .map((t: tf.Tensor) => t.toFloat()) as tf.Tensor4D[]\n .map((t: tf.Tensor) => tf.cast(t, 'float32')) as tf.Tensor4D[];\n return tf.concat(tensorsToStack, paddingAxis);\n });\n}\n", "export function shuffleArray(inputArray: any[]) {\n const array = inputArray.slice();\n for (let i = array.length - 1; i > 0; i--) {\n const j = Math.floor(Math.random() * (i + 1));\n const x = array[i];\n array[i] = array[j];\n array[j] = x;\n }\n return array;\n}\n", "export * from './iou';\nexport * from './minBbox';\nexport * from './nonMaxSuppression';\nexport * from './normalize';\nexport * from './padToSquare';\nexport * from './shuffleArray';\n\nexport function sigmoid(x: number) {\n return 1 / (1 + Math.exp(-x));\n}\n\nexport function inverseSigmoid(x: number) {\n return Math.log(x / (1 - x));\n}\n", "import { Box } from './Box';\n\nexport interface IRect {\n x: number\n y: number\n width: number\n height: number\n}\n\nexport class Rect extends Box implements IRect {\n constructor(x: number, y: number, width: number, height: number, allowNegativeDimensions: boolean = false) {\n super({\n x, y, width, height,\n }, allowNegativeDimensions);\n }\n}\n", "import { minBbox } from '../ops/index';\nimport { getCenterPoint } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { FaceDetection } from './FaceDetection';\nimport { Point } from './Point';\nimport { IRect, Rect } from './Rect';\n\n// face alignment constants\nconst relX = 0.5;\nconst relY = 0.43;\nconst relScale = 0.45;\n\nexport interface IFaceLandmarks {\n positions: Point[]\n shift: Point\n}\n\nexport class FaceLandmarks implements IFaceLandmarks {\n protected _shift: Point\n\n protected _positions: Point[]\n\n protected _imgDims: Dimensions\n\n constructor(\n relativeFaceLandmarkPositions: Point[],\n imgDims: IDimensions,\n shift: Point = new Point(0, 0),\n ) {\n const { width, height } = imgDims;\n this._imgDims = new Dimensions(width, height);\n this._shift = shift;\n this._positions = relativeFaceLandmarkPositions.map(\n (pt) => pt.mul(new Point(width, height)).add(shift),\n );\n }\n\n public get shift(): Point { return new Point(this._shift.x, this._shift.y); }\n\n public get imageWidth(): number { return this._imgDims.width; }\n\n public get imageHeight(): number { return this._imgDims.height; }\n\n public get positions(): Point[] { return this._positions; }\n\n public get relativePositions(): Point[] {\n return this._positions.map(\n (pt) => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight)),\n );\n }\n\n public forSize(width: number, height: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n { width, height },\n );\n }\n\n public shiftBy(x: number, y: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n this._imgDims,\n new Point(x, y),\n );\n }\n\n public shiftByPoint(pt: Point): T {\n return this.shiftBy(pt.x, pt.y);\n }\n\n /**\n * Aligns the face landmarks after face detection from the relative positions of the faces\n * bounding box, or it's current shift. This function should be used to align the face images\n * after face detection has been performed, before they are passed to the face recognition net.\n * This will make the computed face descriptor more accurate.\n *\n * @param detection (optional) The bounding box of the face or the face detection result. If\n * no argument was passed the position of the face landmarks are assumed to be relative to\n * it's current shift.\n * @returns The bounding box of the aligned face.\n */\n public align(\n detection?: FaceDetection | IRect | IBoundingBox | null,\n options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { },\n ): Box {\n if (detection) {\n const box = detection instanceof FaceDetection\n ? detection.box.floor()\n : new Box(detection);\n\n return this.shiftBy(box.x, box.y).align(null, options);\n }\n\n const { useDlibAlignment, minBoxPadding } = { useDlibAlignment: false, minBoxPadding: 0.2, ...options };\n\n if (useDlibAlignment) {\n return this.alignDlib();\n }\n\n return this.alignMinBbox(minBoxPadding);\n }\n\n private alignDlib(): Box {\n const centers = this.getRefPointsForAlignment();\n\n const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers;\n const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude();\n const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;\n\n const size = Math.floor(eyeToMouthDist / relScale);\n\n const refPoint = getCenterPoint(centers);\n // TODO: pad in case rectangle is out of image bounds\n const x = Math.floor(Math.max(0, refPoint.x - (relX * size)));\n const y = Math.floor(Math.max(0, refPoint.y - (relY * size)));\n\n return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y));\n }\n\n private alignMinBbox(padding: number): Box {\n const box = minBbox(this.positions);\n return box.pad(box.width * padding, box.height * padding);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n throw new Error('getRefPointsForAlignment not implemented by base class');\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks5 extends FaceLandmarks {\n protected getRefPointsForAlignment(): Point[] {\n const pts = this.positions;\n return [\n pts[0],\n pts[1],\n getCenterPoint([pts[3], pts[4]]),\n ];\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks68 extends FaceLandmarks {\n public getJawOutline(): Point[] {\n return this.positions.slice(0, 17);\n }\n\n public getLeftEyeBrow(): Point[] {\n return this.positions.slice(17, 22);\n }\n\n public getRightEyeBrow(): Point[] {\n return this.positions.slice(22, 27);\n }\n\n public getNose(): Point[] {\n return this.positions.slice(27, 36);\n }\n\n public getLeftEye(): Point[] {\n return this.positions.slice(36, 42);\n }\n\n public getRightEye(): Point[] {\n return this.positions.slice(42, 48);\n }\n\n public getMouth(): Point[] {\n return this.positions.slice(48, 68);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n return [\n this.getLeftEye(),\n this.getRightEye(),\n this.getMouth(),\n ].map(getCenterPoint);\n }\n}\n", "import { round } from '../utils/index';\n\nexport interface IFaceMatch {\n label: string\n distance: number\n}\n\nexport class FaceMatch implements IFaceMatch {\n private _label: string\n\n private _distance: number\n\n constructor(label: string, distance: number) {\n this._label = label;\n this._distance = distance;\n }\n\n public get label(): string { return this._label; }\n\n public get distance(): number { return this._distance; }\n\n public toString(withDistance: boolean = true): string {\n return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`;\n }\n}\n", "import { isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { IRect } from './Rect';\n\nexport class LabeledBox extends Box {\n public static assertIsValidLabeledBox(box: any, callee: string) {\n Box.assertIsValidBox(box, callee);\n\n if (!isValidNumber(box.label)) {\n throw new Error(`${callee} - expected property label (${box.label}) to be a number`);\n }\n }\n\n private _label: number\n\n constructor(box: IBoundingBox | IRect | any, label: number) {\n super(box);\n this._label = label;\n }\n\n public get label(): number { return this._label; }\n}\n", "export class LabeledFaceDescriptors {\n private _label: string\n\n private _descriptors: Float32Array[]\n\n constructor(label: string, descriptors: Float32Array[]) {\n if (!(typeof label === 'string')) {\n throw new Error('LabeledFaceDescriptors - constructor expected label to be a string');\n }\n\n if (!Array.isArray(descriptors) || descriptors.some((desc) => !(desc instanceof Float32Array))) {\n throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array');\n }\n\n this._label = label;\n this._descriptors = descriptors;\n }\n\n public get label(): string { return this._label; }\n\n public get descriptors(): Float32Array[] { return this._descriptors; }\n\n public toJSON(): any {\n return {\n label: this.label,\n descriptors: this.descriptors.map((d) => Array.from(d)),\n };\n }\n\n public static fromJSON(json: any): LabeledFaceDescriptors {\n const descriptors = json.descriptors.map((d: any) => new Float32Array(d));\n return new LabeledFaceDescriptors(json.label, descriptors);\n }\n}\n", "import { isValidProbablitiy } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { LabeledBox } from './LabeledBox';\nimport { IRect } from './Rect';\n\nexport class PredictedBox extends LabeledBox {\n public static assertIsValidPredictedBox(box: any, callee: string) {\n LabeledBox.assertIsValidLabeledBox(box, callee);\n\n if (\n !isValidProbablitiy(box.score)\n || !isValidProbablitiy(box.classScore)\n ) {\n throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`);\n }\n }\n\n private _score: number\n\n private _classScore: number\n\n constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {\n super(box, label);\n this._score = score;\n this._classScore = classScore;\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\n\nexport type WithFaceDetection = TSource & {\n detection: FaceDetection\n}\n\nexport function isWithFaceDetection(obj: any): obj is WithFaceDetection<{}> {\n return obj.detection instanceof FaceDetection;\n}\n\nexport function extendWithFaceDetection<\n TSource\n>(\n sourceObj: TSource,\n detection: FaceDetection,\n): WithFaceDetection {\n const extension = { detection };\n return { ...sourceObj, ...extension };\n}\n", "import { Environment } from './types';\n\nexport function createBrowserEnv(): Environment {\n const fetch = window.fetch;\n if (!fetch) throw new Error('fetch - missing fetch implementation for browser environment');\n\n const readFile = () => {\n throw new Error('readFile - filesystem not available for browser environment');\n };\n\n return {\n Canvas: HTMLCanvasElement,\n CanvasRenderingContext2D,\n Image: HTMLImageElement,\n ImageData,\n Video: HTMLVideoElement,\n createCanvasElement: () => document.createElement('canvas'),\n createImageElement: () => document.createElement('img'),\n fetch,\n readFile,\n };\n}\n", "import { FileSystem } from './types';\n\nexport function createFileSystem(fs?: any): FileSystem {\n let requireFsError = '';\n\n if (!fs) {\n try {\n // eslint-disable-next-line global-require\n fs = require('fs');\n } catch (err) {\n requireFsError = err.toString();\n }\n }\n\n const readFile = fs\n ? (filePath: string) => new Promise((resolve, reject) => {\n fs.readFile(filePath, (err: any, buffer: Buffer) => (err ? reject(err) : resolve(buffer)));\n })\n : () => {\n throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`);\n };\n\n return {\n readFile,\n };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { createFileSystem } from './createFileSystem';\nimport { Environment } from './types';\n\nexport function createNodejsEnv(): Environment {\n // eslint-disable-next-line dot-notation\n const Canvas = global['Canvas'] || global.HTMLCanvasElement;\n const Image = global.Image || global.HTMLImageElement;\n\n const createCanvasElement = () => {\n if (Canvas) return new Canvas();\n throw new Error('createCanvasElement - missing Canvas implementation for nodejs environment');\n };\n\n const createImageElement = () => {\n if (Image) return new Image();\n throw new Error('createImageElement - missing Image implementation for nodejs environment');\n };\n\n const fetch = global.fetch;\n // if (!fetch) throw new Error('fetch - missing fetch implementation for nodejs environment');\n\n const fileSystem = createFileSystem();\n\n return {\n Canvas: Canvas || class {},\n CanvasRenderingContext2D: global.CanvasRenderingContext2D || class {},\n Image: Image || class {},\n ImageData: global.ImageData || class {},\n Video: global.HTMLVideoElement || class {},\n createCanvasElement,\n createImageElement,\n fetch,\n ...fileSystem,\n };\n}\n", "export function isBrowser(): boolean {\n return typeof window === 'object'\n && typeof document !== 'undefined'\n && typeof HTMLImageElement !== 'undefined'\n && typeof HTMLCanvasElement !== 'undefined'\n && typeof HTMLVideoElement !== 'undefined'\n && typeof ImageData !== 'undefined'\n && typeof CanvasRenderingContext2D !== 'undefined';\n}\n", "import { createBrowserEnv } from './createBrowserEnv';\nimport { createFileSystem } from './createFileSystem';\nimport { createNodejsEnv } from './createNodejsEnv';\nimport { isBrowser } from './isBrowser';\nimport { isNodejs } from './isNodejs';\nimport { Environment } from './types';\n\nlet environment: Environment | null;\n\nfunction getEnv(): Environment {\n if (!environment) {\n throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()');\n }\n return environment;\n}\n\nfunction setEnv(env: Environment) {\n environment = env;\n}\n\nfunction initialize() {\n // check for isBrowser() first to prevent electron renderer process\n // to be initialized with wrong environment due to isNodejs() returning true\n if (isBrowser()) return setEnv(createBrowserEnv());\n if (isNodejs()) return setEnv(createNodejsEnv());\n return null;\n}\n\nfunction monkeyPatch(env: Partial) {\n if (!environment) {\n initialize();\n }\n\n if (!environment) {\n throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()');\n }\n\n const { Canvas = environment.Canvas, Image = environment.Image } = env;\n environment.Canvas = Canvas;\n environment.Image = Image;\n environment.createCanvasElement = env.createCanvasElement || (() => new Canvas());\n environment.createImageElement = env.createImageElement || (() => new Image());\n\n environment.ImageData = env.ImageData || environment.ImageData;\n environment.Video = env.Video || environment.Video;\n environment.fetch = env.fetch || environment.fetch;\n environment.readFile = env.readFile || environment.readFile;\n}\n\nexport const env = {\n getEnv,\n setEnv,\n initialize,\n createBrowserEnv,\n createFileSystem,\n createNodejsEnv,\n monkeyPatch,\n isBrowser,\n isNodejs,\n};\n\ninitialize();\n\nexport * from './types';\n", "import { env } from '../env/index';\n\nexport function resolveInput(arg: string | any) {\n if (!env.isNodejs() && typeof arg === 'string') {\n return document.getElementById(arg);\n }\n return arg;\n}\n", "import { env } from '../env/index';\nimport { resolveInput } from './resolveInput';\n\nexport function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {\n const { Canvas, CanvasRenderingContext2D } = env.getEnv();\n\n if (canvasArg instanceof CanvasRenderingContext2D) {\n return canvasArg;\n }\n\n const canvas = resolveInput(canvasArg);\n\n if (!(canvas instanceof Canvas)) {\n throw new Error('resolveContext2d - expected canvas to be of instance of Canvas');\n }\n\n const ctx = canvas.getContext('2d');\n if (!ctx) {\n throw new Error('resolveContext2d - canvas 2d context is null');\n }\n\n return ctx;\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IDimensions, IPoint } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { resolveInput } from '../dom/resolveInput';\n\n// eslint-disable-next-line no-shadow\nexport enum AnchorPosition {\n // eslint-disable-next-line no-unused-vars\n TOP_LEFT = 'TOP_LEFT',\n // eslint-disable-next-line no-unused-vars\n TOP_RIGHT = 'TOP_RIGHT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_LEFT = 'BOTTOM_LEFT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_RIGHT = 'BOTTOM_RIGHT'\n}\n\nexport interface IDrawTextFieldOptions {\n anchorPosition?: AnchorPosition\n backgroundColor?: string\n fontColor?: string\n fontSize?: number\n fontStyle?: string\n padding?: number\n}\n\nexport class DrawTextFieldOptions implements IDrawTextFieldOptions {\n public anchorPosition: AnchorPosition\n\n public backgroundColor: string\n\n public fontColor: string\n\n public fontSize: number\n\n public fontStyle: string\n\n public padding: number\n\n constructor(options: IDrawTextFieldOptions = {}) {\n const {\n anchorPosition, backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = options;\n this.anchorPosition = anchorPosition || AnchorPosition.TOP_LEFT;\n this.backgroundColor = backgroundColor || 'rgba(0, 0, 0, 0.5)';\n this.fontColor = fontColor || 'rgba(255, 255, 255, 1)';\n this.fontSize = fontSize || 14;\n this.fontStyle = fontStyle || 'Georgia';\n this.padding = padding || 4;\n }\n}\n\nexport class DrawTextField {\n public text: string[]\n\n public anchor : IPoint\n\n public options: DrawTextFieldOptions\n\n constructor(\n text: string | string[] | DrawTextField,\n anchor: IPoint,\n options: IDrawTextFieldOptions = {},\n ) {\n // eslint-disable-next-line no-nested-ternary\n this.text = typeof text === 'string'\n ? [text]\n : (text instanceof DrawTextField ? text.text : text);\n this.anchor = anchor;\n this.options = new DrawTextFieldOptions(options);\n }\n\n measureWidth(ctx: CanvasRenderingContext2D): number {\n const { padding } = this.options;\n return this.text.map((l) => ctx.measureText(l).width).reduce((w0, w1) => (w0 < w1 ? w1 : w0), 0) + (2 * padding);\n }\n\n measureHeight(): number {\n const { fontSize, padding } = this.options;\n return this.text.length * fontSize + (2 * padding);\n }\n\n getUpperLeft(ctx: CanvasRenderingContext2D, canvasDims?: IDimensions): IPoint {\n const { anchorPosition } = this.options;\n const isShiftLeft = anchorPosition === AnchorPosition.BOTTOM_RIGHT || anchorPosition === AnchorPosition.TOP_RIGHT;\n const isShiftTop = anchorPosition === AnchorPosition.BOTTOM_LEFT || anchorPosition === AnchorPosition.BOTTOM_RIGHT;\n\n const textFieldWidth = this.measureWidth(ctx);\n const textFieldHeight = this.measureHeight();\n const x = (isShiftLeft ? this.anchor.x - textFieldWidth : this.anchor.x);\n const y = isShiftTop ? this.anchor.y - textFieldHeight : this.anchor.y;\n\n // adjust anchor if text box exceeds canvas borders\n if (canvasDims) {\n const { width, height } = canvasDims;\n const newX = Math.max(Math.min(x, width - textFieldWidth), 0);\n const newY = Math.max(Math.min(y, height - textFieldHeight), 0);\n return { x: newX, y: newY };\n }\n return { x, y };\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const canvas = resolveInput(canvasArg);\n const ctx = getContext2dOrThrow(canvas);\n\n const {\n backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = this.options;\n\n ctx.font = `${fontSize}px ${fontStyle}`;\n const maxTextWidth = this.measureWidth(ctx);\n const textHeight = this.measureHeight();\n\n ctx.fillStyle = backgroundColor;\n const upperLeft = this.getUpperLeft(ctx, canvas);\n ctx.fillRect(upperLeft.x, upperLeft.y, maxTextWidth, textHeight);\n\n ctx.fillStyle = fontColor;\n this.text.forEach((textLine, i) => {\n const x = padding + upperLeft.x;\n const y = padding + upperLeft.y + ((i + 1) * fontSize);\n ctx.fillText(textLine, x, y);\n });\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { Box, IBoundingBox, IRect } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport {\n AnchorPosition, DrawTextField, DrawTextFieldOptions, IDrawTextFieldOptions,\n} from './DrawTextField';\n\nexport interface IDrawBoxOptions {\n boxColor?: string\n lineWidth?: number\n drawLabelOptions?: IDrawTextFieldOptions\n label?: string\n}\n\nexport class DrawBoxOptions {\n public boxColor: string\n\n public lineWidth: number\n\n public drawLabelOptions: DrawTextFieldOptions\n\n public label?: string\n\n constructor(options: IDrawBoxOptions = {}) {\n const {\n boxColor, lineWidth, label, drawLabelOptions,\n } = options;\n this.boxColor = boxColor || 'rgba(0, 0, 255, 1)';\n this.lineWidth = lineWidth || 2;\n this.label = label;\n\n const defaultDrawLabelOptions = {\n anchorPosition: AnchorPosition.BOTTOM_LEFT,\n backgroundColor: this.boxColor,\n };\n this.drawLabelOptions = new DrawTextFieldOptions({ ...defaultDrawLabelOptions, ...drawLabelOptions });\n }\n}\n\nexport class DrawBox {\n public box: Box\n\n public options: DrawBoxOptions\n\n constructor(\n box: IBoundingBox | IRect,\n options: IDrawBoxOptions = {},\n ) {\n this.box = new Box(box);\n this.options = new DrawBoxOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const { boxColor, lineWidth } = this.options;\n\n const {\n x, y, width, height,\n } = this.box;\n ctx.strokeStyle = boxColor;\n ctx.lineWidth = lineWidth;\n ctx.strokeRect(x, y, width, height);\n\n const { label } = this.options;\n if (label) {\n new DrawTextField([label], { x: x - (lineWidth / 2), y }, this.options.drawLabelOptions).draw(canvasArg);\n }\n }\n}\n", "import { Box, IBoundingBox, IRect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { round } from '../utils/index';\nimport { DrawBox } from './DrawBox';\n\nexport type TDrawDetectionsInput = IRect | IBoundingBox | FaceDetection | WithFaceDetection<{}>\n\nexport function drawDetections(\n canvasArg: string | HTMLCanvasElement,\n detections: TDrawDetectionsInput | Array,\n) {\n const detectionsArray = Array.isArray(detections) ? detections : [detections];\n\n detectionsArray.forEach((det) => {\n // eslint-disable-next-line no-nested-ternary\n const score = det instanceof FaceDetection\n ? det.score\n : (isWithFaceDetection(det) ? det.detection.score : undefined);\n\n // eslint-disable-next-line no-nested-ternary\n const box = det instanceof FaceDetection\n ? det.box\n : (isWithFaceDetection(det) ? det.detection.box : new Box(det));\n\n const label = score ? `${round(score)}` : undefined;\n new DrawBox(box, { label }).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { FaceExpressions } from './FaceExpressions';\n\nexport class FaceExpressionNet extends FaceProcessor {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceExpressionNet', faceFeatureExtractor);\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n return tf.tidy(() => tf.softmax(this.runNet(input)));\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictExpressions(input: TNetInput) {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n const probabilitesByBatch = await Promise.all(tf.unstack(out).map(async (t) => {\n const data = await t.data();\n t.dispose();\n return data;\n }));\n out.dispose();\n\n const predictionsByBatch = probabilitesByBatch\n .map((probabilites) => new FaceExpressions(probabilites as Float32Array));\n\n return netInput.isBatchInput\n ? predictionsByBatch\n : predictionsByBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_expression_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n\n protected getClassifierChannelsOut(): number {\n return 7;\n }\n}\n", "import { env } from '../env/index';\n\nexport function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {\n const { Image, Video } = env.getEnv();\n\n return (media instanceof Image && media.complete)\n || (media instanceof Video && media.readyState >= 3);\n}\n", "import { env } from '../env/index';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {\n // eslint-disable-next-line consistent-return\n return new Promise((resolve, reject) => {\n if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {\n return resolve(null);\n }\n\n function onError(e: Event) {\n if (!e.currentTarget) return;\n // eslint-disable-next-line no-use-before-define\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n reject(e);\n }\n\n function onLoad(e: Event) {\n if (!e.currentTarget) return;\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n resolve(e);\n }\n\n media.addEventListener('load', onLoad);\n media.addEventListener('error', onError);\n });\n}\n", "import { env } from '../env/index';\n\nexport function bufferToImage(buf: Blob): Promise {\n return new Promise((resolve, reject) => {\n if (!(buf instanceof Blob)) reject(new Error('bufferToImage - expected buf to be of type: Blob'));\n const reader = new FileReader();\n reader.onload = () => {\n if (typeof reader.result !== 'string') reject(new Error('bufferToImage - expected reader.result to be a string, in onload'));\n const img = env.getEnv().createImageElement();\n img.onload = () => resolve(img);\n img.onerror = reject;\n img.src = reader.result as string;\n };\n reader.onerror = reject;\n reader.readAsDataURL(buf);\n });\n}\n", "import { Dimensions, IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\n\nexport function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {\n const { Image, Video } = env.getEnv();\n\n if (input instanceof Image) {\n return new Dimensions(input.naturalWidth, input.naturalHeight);\n }\n if (input instanceof Video) {\n return new Dimensions(input.videoWidth, input.videoHeight);\n }\n return new Dimensions(input.width, input.height);\n}\n", "import { IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {\n const { createCanvasElement } = env.getEnv();\n const canvas = createCanvasElement();\n canvas.width = width;\n canvas.height = height;\n return canvas;\n}\n\nexport function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {\n const { ImageData } = env.getEnv();\n\n if (!(media instanceof ImageData) && !isMediaLoaded(media)) {\n throw new Error('createCanvasFromMedia - media has not finished loading yet');\n }\n\n const { width, height } = dims || getMediaDimensions(media);\n const canvas = createCanvas({ width, height });\n\n if (media instanceof ImageData) {\n getContext2dOrThrow(canvas).putImageData(media, 0, 0);\n } else {\n getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height);\n }\n return canvas;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { env } from '../env/index';\nimport { isTensor4D } from '../utils/index';\n\nexport async function imageTensorToCanvas(\n imgTensor: tf.Tensor,\n canvas?: HTMLCanvasElement,\n): Promise {\n const targetCanvas = canvas || env.getEnv().createCanvasElement();\n\n const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0);\n const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt());\n await tf.browser.toPixels(imgTensor3D, targetCanvas);\n\n imgTensor3D.dispose();\n\n return targetCanvas;\n}\n", "import { env } from '../env/index';\n\nexport function isMediaElement(input: any) {\n const { Image, Canvas, Video } = env.getEnv();\n\n return input instanceof Image\n || input instanceof Canvas\n || input instanceof Video;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Dimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { padToSquare } from '../ops/padToSquare';\nimport {\n computeReshapedDimensions, isTensor3D, isTensor4D, range,\n} from '../utils/index';\nimport { createCanvasFromMedia } from './createCanvas';\nimport { imageToSquare } from './imageToSquare';\nimport { TResolvedNetInput } from './types';\n\nexport class NetInput {\n private _imageTensors: Array = []\n\n private _canvases: HTMLCanvasElement[] = []\n\n private _batchSize: number\n\n private _treatAsBatchInput: boolean = false\n\n private _inputDimensions: number[][] = []\n\n private _inputSize: number\n\n constructor(\n inputs: Array,\n treatAsBatchInput: boolean = false,\n ) {\n if (!Array.isArray(inputs)) {\n throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`);\n }\n\n this._treatAsBatchInput = treatAsBatchInput;\n this._batchSize = inputs.length;\n\n inputs.forEach((input, idx) => {\n if (isTensor3D(input)) {\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = input.shape;\n return;\n }\n\n if (isTensor4D(input)) {\n const batchSize = (input as any).shape[0];\n if (batchSize !== 1) {\n throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = (input as any).shape.slice(1);\n return;\n }\n\n const canvas = (input as any) instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input);\n this._canvases[idx] = canvas;\n this._inputDimensions[idx] = [canvas.height, canvas.width, 3];\n });\n }\n\n public get imageTensors(): Array {\n return this._imageTensors;\n }\n\n public get canvases(): HTMLCanvasElement[] {\n return this._canvases;\n }\n\n public get isBatchInput(): boolean {\n return this.batchSize > 1 || this._treatAsBatchInput;\n }\n\n public get batchSize(): number {\n return this._batchSize;\n }\n\n public get inputDimensions(): number[][] {\n return this._inputDimensions;\n }\n\n public get inputSize(): number | undefined {\n return this._inputSize;\n }\n\n public get reshapedInputDimensions(): Dimensions[] {\n return range(this.batchSize, 0, 1).map(\n (_, batchIdx) => this.getReshapedInputDimensions(batchIdx),\n );\n }\n\n public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {\n return this.canvases[batchIdx] || this.imageTensors[batchIdx];\n }\n\n public getInputDimensions(batchIdx: number): number[] {\n return this._inputDimensions[batchIdx];\n }\n\n public getInputHeight(batchIdx: number): number {\n return this._inputDimensions[batchIdx][0];\n }\n\n public getInputWidth(batchIdx: number): number {\n return this._inputDimensions[batchIdx][1];\n }\n\n public getReshapedInputDimensions(batchIdx: number): Dimensions {\n if (typeof this.inputSize !== 'number') {\n throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet');\n }\n\n const width = this.getInputWidth(batchIdx);\n const height = this.getInputHeight(batchIdx);\n return computeReshapedDimensions({ width, height }, this.inputSize);\n }\n\n /**\n * Create a batch tensor from all input canvases and tensors\n * with size [batchSize, inputSize, inputSize, 3].\n *\n * @param inputSize Height and width of the tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The batch tensor.\n */\n public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {\n this._inputSize = inputSize;\n\n return tf.tidy(() => {\n const inputTensors = range(this.batchSize, 0, 1).map((batchIdx) => {\n const input = this.getInput(batchIdx);\n\n if (input instanceof tf.Tensor) {\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n let imgTensor = isTensor4D(input) ? input : input.expandDims();\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n imgTensor = padToSquare(imgTensor, isCenterInputs);\n\n if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {\n imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize]);\n }\n\n return imgTensor.as3D(inputSize, inputSize, 3);\n }\n\n if (input instanceof env.getEnv().Canvas) {\n return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs));\n }\n\n throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`);\n });\n\n // const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)\n const batchTensor = tf.stack(inputTensors.map((t) => tf.cast(t, 'float32'))).as4D(this.batchSize, inputSize, inputSize, 3);\n // const batchTensor = tf.stack(inputTensors.map(t => tf.Tensor.as4D(tf.cast(t, 'float32'))), this.batchSize, inputSize, inputSize, 3);\n\n return batchTensor;\n });\n }\n}\n", "import { env } from '../env/index';\nimport { createCanvas, createCanvasFromMedia } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {\n const { Image, Canvas } = env.getEnv();\n\n if (!(input instanceof Image || input instanceof Canvas)) {\n throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement');\n }\n\n const dims = getMediaDimensions(input);\n const scale = inputSize / Math.max(dims.height, dims.width);\n const width = scale * dims.width;\n const height = scale * dims.height;\n\n const targetCanvas = createCanvas({ width: inputSize, height: inputSize });\n const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input);\n\n const offset = Math.abs(width - height) / 2;\n const dx = centerImage && width < height ? offset : 0;\n const dy = centerImage && height < width ? offset : 0;\n getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height);\n\n return targetCanvas;\n}\n", "import { isTensor3D, isTensor4D } from '../utils/index';\nimport { awaitMediaLoaded } from './awaitMediaLoaded';\nimport { isMediaElement } from './isMediaElement';\nimport { NetInput } from './NetInput';\nimport { resolveInput } from './resolveInput';\nimport { TNetInput } from './types';\n\n/**\n * Validates the input to make sure, they are valid net inputs and awaits all media elements\n * to be finished loading.\n *\n * @param input The input, which can be a media element or an array of different media elements.\n * @returns A NetInput instance, which can be passed into one of the neural networks.\n */\nexport async function toNetInput(inputs: TNetInput): Promise {\n if (inputs instanceof NetInput) {\n return inputs;\n }\n\n const inputArgArray = Array.isArray(inputs)\n ? inputs\n : [inputs];\n\n if (!inputArgArray.length) {\n throw new Error('toNetInput - empty array passed as input');\n }\n\n const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');\n\n const inputArray = inputArgArray.map(resolveInput);\n\n inputArray.forEach((input, i) => {\n if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {\n if (typeof inputArgArray[i] === 'string') {\n throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);\n }\n\n throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);\n }\n\n if (isTensor4D(input)) {\n // if tf.Tensor4D is passed in the input array, the batch size has to be 1\n const batchSize = input.shape[0];\n if (batchSize !== 1) {\n throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n }\n });\n\n // wait for all media elements being loaded\n await Promise.all(\n inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),\n );\n\n return new NetInput(inputArray, Array.isArray(inputs));\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { Rect } from '../classes/Rect';\nimport { env } from '../env/index';\nimport { createCanvas } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { imageTensorToCanvas } from './imageTensorToCanvas';\nimport { toNetInput } from './toNetInput';\nimport { TNetInput } from './types';\n\n/**\n * Extracts the image regions containing the detected faces.\n *\n * @param input The image that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns The Canvases of the corresponding image region for each detected face.\n */\nexport async function extractFaces(\n input: TNetInput,\n detections: Array,\n): Promise {\n const { Canvas } = env.getEnv();\n\n let canvas = input as HTMLCanvasElement;\n\n if (!(input instanceof Canvas)) {\n const netInput = await toNetInput(input);\n\n if (netInput.batchSize > 1) {\n throw new Error('extractFaces - batchSize > 1 not supported');\n }\n\n const tensorOrCanvas = netInput.getInput(0);\n canvas = tensorOrCanvas instanceof Canvas\n ? tensorOrCanvas\n : await imageTensorToCanvas(tensorOrCanvas);\n }\n\n const ctx = getContext2dOrThrow(canvas);\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(canvas.width, canvas.height).box.floor()\n : det),\n )\n .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));\n\n return boxes.map(({\n x, y, width, height,\n }) => {\n const faceImg = createCanvas({ width, height });\n getContext2dOrThrow(faceImg)\n .putImageData(ctx.getImageData(x, y, width, height), 0, 0);\n return faceImg;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isTensor3D, isTensor4D } from '../utils/index';\n\n/**\n * Extracts the tensors of the image regions containing the detected faces.\n * Useful if you want to compute the face descriptors for the face images.\n * Using this method is faster then extracting a canvas for each face and\n * converting them to tensors individually.\n *\n * @param imageTensor The image tensor that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns Tensors of the corresponding image region for each detected face.\n */\nexport async function extractFaceTensors(\n imageTensor: tf.Tensor3D | tf.Tensor4D,\n detections: Array,\n): Promise {\n if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {\n throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D');\n }\n\n if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {\n throw new Error('extractFaceTensors - batchSize > 1 not supported');\n }\n\n return tf.tidy(() => {\n const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0);\n\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(imgWidth, imgHeight).box\n : det),\n )\n .map((box) => box.clipAtImageBorders(imgWidth, imgHeight));\n\n const faceTensors = boxes.map(({\n x, y, width, height,\n }) => tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels]));\n\n return faceTensors;\n });\n}\n", "import { env } from '../env/index';\n\nexport async function fetchOrThrow(\n url: string,\n // eslint-disable-next-line no-undef\n init?: RequestInit,\n): Promise {\n const { fetch } = env.getEnv();\n const res = await fetch(url, init);\n if (!(res.status < 400)) {\n throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`);\n }\n return res;\n}\n", "import { bufferToImage } from './bufferToImage';\nimport { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchImage(uri: string): Promise {\n const res = await fetchOrThrow(uri);\n const blob = await (res).blob();\n\n if (!blob.type.startsWith('image/')) {\n throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`);\n }\n return bufferToImage(blob);\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchJson(uri: string): Promise {\n return (await fetchOrThrow(uri)).json();\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchNetWeights(uri: string): Promise {\n return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer());\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { getModelUris } from '../common/getModelUris';\nimport { fetchJson } from './fetchJson';\n\nexport async function loadWeightMap(\n uri: string | undefined,\n defaultModelName: string,\n): Promise {\n const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName);\n const manifest = await fetchJson(manifestUri);\n // if (manifest['weightsManifest']) manifest = manifest['weightsManifest'];\n return tf.io.loadWeights(manifest, modelBaseUri);\n}\n", "export function getModelUris(uri: string | undefined, defaultModelName: string) {\n const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`;\n\n if (!uri) {\n return {\n modelBaseUri: '',\n manifestUri: defaultManifestFilename,\n };\n }\n\n if (uri === '/') {\n return {\n modelBaseUri: '/',\n manifestUri: `/${defaultManifestFilename}`,\n };\n }\n // eslint-disable-next-line no-nested-ternary\n const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';\n uri = uri.replace(protocol, '');\n\n const parts = uri.split('/').filter((s) => s);\n\n const manifestFile = uri.endsWith('.json')\n ? parts[parts.length - 1]\n : defaultManifestFilename;\n\n let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/');\n modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri;\n\n return {\n modelBaseUri,\n manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`,\n };\n}\n", "import { IDimensions } from '../classes/index';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {\n const { width, height } = useMediaDimensions\n ? getMediaDimensions(reference)\n : reference;\n input.width = width;\n input.height = height;\n return { width, height };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock4 } from './denseBlock';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';\n\nexport class FaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('FaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock4(normalized, params.dense0, true);\n out = denseBlock4(out, params.dense1);\n out = denseBlock4(out, params.dense2);\n out = denseBlock4(out, params.dense3);\n out = tf.avgPool(out, [7, 7], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../dist/tfjs.esm';\n\nimport { ParamMapping } from './common/index';\nimport { getModelUris } from './common/getModelUris';\nimport { loadWeightMap } from './dom/index';\nimport { env } from './env/index';\n\nexport abstract class NeuralNetwork {\n constructor(name: string) {\n this._name = name;\n }\n\n protected _params: TNetParams | undefined = undefined\n\n protected _paramMappings: ParamMapping[] = []\n\n public _name: any;\n\n public get params(): TNetParams | undefined { return this._params; }\n\n public get paramMappings(): ParamMapping[] { return this._paramMappings; }\n\n public get isLoaded(): boolean { return !!this.params; }\n\n public getParamFromPath(paramPath: string): tf.Tensor {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n return obj[objProp];\n }\n\n public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n obj[objProp].dispose();\n obj[objProp] = tensor;\n }\n\n public getParamList() {\n return this._paramMappings.map(({ paramPath }) => ({\n path: paramPath,\n tensor: this.getParamFromPath(paramPath),\n }));\n }\n\n public getTrainableParams() {\n return this.getParamList().filter((param) => param.tensor instanceof tf.Variable);\n }\n\n public getFrozenParams() {\n return this.getParamList().filter((param) => !(param.tensor instanceof tf.Variable));\n }\n\n public variable() {\n this.getFrozenParams().forEach(({ path, tensor }) => {\n this.reassignParamFromPath(path, tensor.variable());\n });\n }\n\n public freeze() {\n this.getTrainableParams().forEach(({ path, tensor: variable }) => {\n const tensor = tf.tensor(variable.dataSync());\n variable.dispose();\n this.reassignParamFromPath(path, tensor);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.getParamList().forEach((param) => {\n if (throwOnRedispose && param.tensor.isDisposed) {\n throw new Error(`param tensor has already been disposed for path ${param.path}`);\n }\n param.tensor.dispose();\n });\n this._params = undefined;\n }\n\n public serializeParams(): Float32Array {\n return new Float32Array(\n this.getParamList()\n .map(({ tensor }) => Array.from(tensor.dataSync()) as number[])\n .reduce((flat, arr) => flat.concat(arr)),\n );\n }\n\n public async load(weightsOrUrl: Float32Array | string | undefined): Promise {\n if (weightsOrUrl instanceof Float32Array) {\n this.extractWeights(weightsOrUrl);\n return;\n }\n await this.loadFromUri(weightsOrUrl);\n }\n\n public async loadFromUri(uri: string | undefined) {\n if (uri && typeof uri !== 'string') {\n throw new Error(`${this._name}.loadFromUri - expected model uri`);\n }\n const weightMap = await loadWeightMap(uri, this.getDefaultModelName());\n this.loadFromWeightMap(weightMap);\n }\n\n public async loadFromDisk(filePath: string | undefined) {\n if (filePath && typeof filePath !== 'string') {\n throw new Error(`${this._name}.loadFromDisk - expected model file path`);\n }\n const { readFile } = env.getEnv();\n const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName());\n const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(filePaths.map((fp) => readFile(fp).then((buf) => buf.buffer)));\n const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk);\n const manifest = JSON.parse((await readFile(manifestUri)).toString());\n const weightMap = await loadWeights(manifest, modelBaseUri);\n this.loadFromWeightMap(weightMap);\n }\n\n public loadFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { paramMappings, params } = this.extractParamsFromWeightMap(weightMap);\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n public extractWeights(weights: Float32Array) {\n const { paramMappings, params } = this.extractParams(weights);\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n private traversePropertyPath(paramPath: string) {\n if (!this.params) {\n throw new Error('traversePropertyPath - model has no loaded params');\n }\n\n const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {\n // eslint-disable-next-line no-prototype-builtins\n if (!res.nextObj.hasOwnProperty(objProp)) {\n throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`);\n }\n return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] };\n }, { nextObj: this.params });\n\n const { obj, objProp } = result;\n if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {\n throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`);\n }\n\n return { obj, objProp };\n }\n\n protected abstract getDefaultModelName(): string\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, SeparableConvParams } from '../common/index';\nimport { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function denseBlock3(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock3Params,\n isFirstLayer: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n });\n}\n\nexport function denseBlock4(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock4Params,\n isFirstLayer: boolean = false,\n isScaleDown: boolean = true,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from './types';\n\nexport function depthwiseSeparableConv(\n x: tf.Tensor4D,\n params: SeparableConvParams,\n stride: [number, number],\n): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same');\n out = tf.add(out, params.bias);\n return out;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\nexport function convLayer(\n x: tf.Tensor4D,\n params: ConvParams,\n padding: 'valid' | 'same' = 'same',\n withRelu: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out = tf.add(\n tf.conv2d(x, params.filters, [1, 1], padding),\n params.bias,\n ) as tf.Tensor4D;\n\n return withRelu ? tf.relu(out) : out;\n });\n}\n", "import { ParamMapping } from './types';\n\nexport function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {\n Object.keys(weightMap).forEach((path) => {\n if (!paramMappings.some((pm) => pm.originalPath === path)) {\n weightMap[path].dispose();\n }\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';\n\nexport function extractConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams => {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, FCParams, ParamMapping } from './types';\n\nexport function extractFCParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): FCParams => {\n const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);\n const fc_bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return {\n weights: fc_weights,\n bias: fc_bias,\n };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';\n\nexport function extractSeparableConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams => {\n const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1]);\n const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut]);\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/depthwise_filter` },\n { paramPath: `${mappedPrefix}/pointwise_filter` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n\nexport function loadSeparableConvParamsFactory(\n // eslint-disable-next-line no-unused-vars\n extractWeightEntry: (originalPath: string, paramRank: number) => T,\n) {\n return (prefix: string): SeparableConvParams => {\n const depthwise_filter = extractWeightEntry(`${prefix}/depthwise_filter`, 4);\n const pointwise_filter = extractWeightEntry(`${prefix}/pointwise_filter`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n// eslint-disable-next-line no-unused-vars\nexport type ExtractWeightsFunction = (numWeights: number) => Float32Array\n\nexport type ParamMapping = {\n originalPath?: string\n paramPath: string\n}\n\nexport type ConvParams = {\n filters: tf.Tensor4D\n bias: tf.Tensor1D\n}\n\nexport type FCParams = {\n weights: tf.Tensor2D\n bias: tf.Tensor1D\n}\n\nexport class SeparableConvParams {\n // eslint-disable-next-line no-useless-constructor\n constructor(\n // eslint-disable-next-line no-unused-vars\n public depthwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public pointwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public bias: tf.Tensor1D,\n // eslint-disable-next-line no-empty-function\n ) {}\n}\n", "import { isTensor } from '../utils/index';\nimport { ParamMapping } from './types';\n\nexport function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {\n return (originalPath: string, paramRank: number, mappedPath?: string) => {\n const tensor = weightMap[originalPath];\n\n if (!isTensor(tensor, paramRank)) {\n throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`);\n }\n\n paramMappings.push(\n { originalPath, paramPath: mappedPath || originalPath },\n );\n\n return tensor;\n };\n}\n", "export function extractWeightsFactory(weights: Float32Array) {\n let remainingWeights = weights;\n\n function extractWeights(numWeights: number): Float32Array {\n const ret = remainingWeights.slice(0, numWeights);\n remainingWeights = remainingWeights.slice(numWeights);\n return ret;\n }\n\n function getRemainingWeights(): Float32Array {\n return remainingWeights;\n }\n\n return {\n extractWeights,\n getRemainingWeights,\n };\n}\n", "import {\n extractConvParamsFactory,\n extractSeparableConvParamsFactory,\n ExtractWeightsFunction,\n ParamMapping,\n} from '../common/index';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)\n : extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`);\n const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`);\n const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer);\n const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock4Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock4Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock4Params(64, 128, 'dense2');\n const dense3 = extractDenseBlock4Params(128, 256, 'dense3');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: {\n dense0, dense1, dense2, dense3,\n },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\n// eslint-disable-next-line no-unused-vars\nexport function loadConvParamsFactory(extractWeightEntry: (originalPath: string, paramRank: number) => T) {\n return (prefix: string): ConvParams => {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return { filters, bias };\n };\n}\n", "import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n const conv3 = extractSeparableConvParams(`${prefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock4Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock4Params('dense0', true),\n dense1: extractDenseBlock4Params('dense1'),\n dense2: extractDenseBlock4Params('dense2'),\n dense3: extractDenseBlock4Params('dense3'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { NetInput } from '../dom/index';\nimport {\n FaceFeatureExtractorParams,\n IFaceFeatureExtractor,\n TinyFaceFeatureExtractorParams,\n} from '../faceFeatureExtractor/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { NetParams } from './types';\nimport { seperateWeightMaps } from './util';\n\nexport abstract class FaceProcessor<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends NeuralNetwork {\n protected _faceFeatureExtractor: IFaceFeatureExtractor\n\n constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor) {\n super(_name);\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): IFaceFeatureExtractor {\n return this._faceFeatureExtractor;\n }\n\n protected abstract getDefaultModelName(): string\n\n protected abstract getClassifierChannelsIn(): number\n\n protected abstract getClassifierChannelsOut(): number\n\n public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut());\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const cIn = this.getClassifierChannelsIn();\n const cOut = this.getClassifierChannelsOut();\n const classifierWeightSize = (cOut * cIn) + cOut;\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from './types';\n\nexport function fullyConnectedLayer(\n x: tf.Tensor2D,\n params: FCParams,\n): tf.Tensor2D {\n return tf.tidy(() => tf.add(\n tf.matMul(x, params.weights),\n params.bias,\n ));\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const fc = extractFCParams(channelsIn, channelsOut, 'fc');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: extractFcParams('fc'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function seperateWeightMaps(weightMap: tf.NamedTensorMap) {\n const featureExtractorMap: tf.NamedTensorMap = {};\n const classifierMap: tf.NamedTensorMap = {};\n\n Object.keys(weightMap).forEach((key) => {\n const map = key.startsWith('fc') ? classifierMap : featureExtractorMap;\n map[key] = weightMap[key];\n });\n\n return { featureExtractorMap, classifierMap };\n}\n", "export const FACE_EXPRESSION_LABELS = ['neutral', 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised'];\n\nexport class FaceExpressions {\n public neutral: number\n\n public happy: number\n\n public sad: number\n\n public angry: number\n\n public fearful: number\n\n public disgusted: number\n\n public surprised: number\n\n constructor(probabilities: number[] | Float32Array) {\n if (probabilities.length !== 7) {\n throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${probabilities.length}`);\n }\n\n FACE_EXPRESSION_LABELS.forEach((expression, idx) => {\n this[expression] = probabilities[idx];\n });\n }\n\n asSortedArray() {\n return FACE_EXPRESSION_LABELS\n .map((expression) => ({ expression, probability: this[expression] as number }))\n .sort((e0, e1) => e1.probability - e0.probability);\n }\n}\n", "import { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\n\nexport type WithFaceExpressions = TSource & {\n expressions: FaceExpressions\n}\n\nexport function isWithFaceExpressions(obj: any): obj is WithFaceExpressions<{}> {\n return obj.expressions instanceof FaceExpressions;\n}\n\nexport function extendWithFaceExpressions<\n TSource\n>(\n sourceObj: TSource,\n expressions: FaceExpressions,\n): WithFaceExpressions {\n const extension = { expressions };\n return { ...sourceObj, ...extension };\n}\n", "import { IPoint, Point } from '../classes/index';\nimport { FaceExpressions } from '../faceExpressionNet/index';\nimport { isWithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { round } from '../utils/index';\nimport { DrawTextField } from './DrawTextField';\n\nexport type DrawFaceExpressionsInput = FaceExpressions | WithFaceExpressions<{}>\n\nexport function drawFaceExpressions(\n canvasArg: string | HTMLCanvasElement,\n faceExpressions: DrawFaceExpressionsInput | Array,\n minConfidence = 0.1,\n textFieldAnchor?: IPoint,\n) {\n const faceExpressionsArray = Array.isArray(faceExpressions) ? faceExpressions : [faceExpressions];\n\n faceExpressionsArray.forEach((e) => {\n // eslint-disable-next-line no-nested-ternary\n const expr = e instanceof FaceExpressions\n ? e\n : (isWithFaceExpressions(e) ? e.expressions : undefined);\n if (!expr) {\n throw new Error('drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof');\n }\n\n const sorted = expr.asSortedArray();\n const resultsToDisplay = sorted.filter((exprLocal) => exprLocal.probability > minConfidence);\n\n const anchor = isWithFaceDetection(e)\n ? e.detection.box.bottomLeft\n : (textFieldAnchor || new Point(0, 0));\n\n const drawTextField = new DrawTextField(\n resultsToDisplay.map((exprLocal) => `${exprLocal.expression} (${round(exprLocal.probability)})`),\n anchor,\n );\n drawTextField.draw(canvasArg);\n });\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { isWithFaceDetection, WithFaceDetection } from './WithFaceDetection';\n\nexport type WithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 > = TSource & {\n landmarks: TFaceLandmarks\n unshiftedLandmarks: TFaceLandmarks\n alignedRect: FaceDetection\n }\n\nexport function isWithFaceLandmarks(obj: any): obj is WithFaceLandmarks, FaceLandmarks> {\n return isWithFaceDetection(obj)\n // eslint-disable-next-line dot-notation\n && obj['landmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['unshiftedLandmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['alignedRect'] instanceof FaceDetection;\n}\n\nexport function extendWithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 >(sourceObj: TSource, unshiftedLandmarks: TFaceLandmarks): WithFaceLandmarks {\n const { box: shift } = sourceObj.detection;\n const landmarks = unshiftedLandmarks.shiftBy(shift.x, shift.y);\n\n const rect = landmarks.align();\n const { imageDims } = sourceObj.detection;\n const alignedRect = new FaceDetection(sourceObj.detection.score, rect.rescale(imageDims.reverse()), imageDims);\n\n const extension = {\n landmarks,\n unshiftedLandmarks,\n alignedRect,\n };\n\n return { ...sourceObj, ...extension };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IPoint } from '../classes/index';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { drawContour } from './drawContour';\n\nexport interface IDrawFaceLandmarksOptions {\n drawLines?: boolean\n drawPoints?: boolean\n lineWidth?: number\n pointSize?: number\n lineColor?: string\n pointColor?: string\n}\n\nexport class DrawFaceLandmarksOptions {\n public drawLines: boolean\n\n public drawPoints: boolean\n\n public lineWidth: number\n\n public pointSize: number\n\n public lineColor: string\n\n public pointColor: string\n\n constructor(options: IDrawFaceLandmarksOptions = {}) {\n const {\n drawLines = true, drawPoints = true, lineWidth, lineColor, pointSize, pointColor,\n } = options;\n this.drawLines = drawLines;\n this.drawPoints = drawPoints;\n this.lineWidth = lineWidth || 1;\n this.pointSize = pointSize || 2;\n this.lineColor = lineColor || 'rgba(0, 255, 255, 1)';\n this.pointColor = pointColor || 'rgba(255, 0, 255, 1)';\n }\n}\n\nexport class DrawFaceLandmarks {\n public faceLandmarks: FaceLandmarks\n\n public options: DrawFaceLandmarksOptions\n\n constructor(\n faceLandmarks: FaceLandmarks,\n options: IDrawFaceLandmarksOptions = {},\n ) {\n this.faceLandmarks = faceLandmarks;\n this.options = new DrawFaceLandmarksOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const {\n drawLines, drawPoints, lineWidth, lineColor, pointSize, pointColor,\n } = this.options;\n\n if (drawLines && this.faceLandmarks instanceof FaceLandmarks68) {\n ctx.strokeStyle = lineColor;\n ctx.lineWidth = lineWidth;\n drawContour(ctx, this.faceLandmarks.getJawOutline());\n drawContour(ctx, this.faceLandmarks.getLeftEyeBrow());\n drawContour(ctx, this.faceLandmarks.getRightEyeBrow());\n drawContour(ctx, this.faceLandmarks.getNose());\n drawContour(ctx, this.faceLandmarks.getLeftEye(), true);\n drawContour(ctx, this.faceLandmarks.getRightEye(), true);\n drawContour(ctx, this.faceLandmarks.getMouth(), true);\n }\n\n if (drawPoints) {\n ctx.strokeStyle = pointColor;\n ctx.fillStyle = pointColor;\n\n const drawPoint = (pt: IPoint) => {\n ctx.beginPath();\n ctx.arc(pt.x, pt.y, pointSize, 0, 2 * Math.PI);\n ctx.fill();\n };\n this.faceLandmarks.positions.forEach(drawPoint);\n }\n }\n}\n\nexport type DrawFaceLandmarksInput = FaceLandmarks | WithFaceLandmarks>\n\nexport function drawFaceLandmarks(\n canvasArg: string | HTMLCanvasElement,\n faceLandmarks: DrawFaceLandmarksInput | Array,\n) {\n const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];\n faceLandmarksArray.forEach((f) => {\n // eslint-disable-next-line no-nested-ternary\n const landmarks = f instanceof FaceLandmarks\n ? f\n : (isWithFaceLandmarks(f) ? f.landmarks : undefined);\n if (!landmarks) {\n throw new Error('drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof');\n }\n\n new DrawFaceLandmarks(landmarks).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { seperateWeightMaps } from '../faceProcessor/util';\nimport { TinyXception } from '../xception/TinyXception';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport {\n AgeAndGenderPrediction, Gender, NetOutput, NetParams,\n} from './types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\n\nexport class AgeGenderNet extends NeuralNetwork {\n private _faceFeatureExtractor: TinyXception\n\n constructor(faceFeatureExtractor: TinyXception = new TinyXception(2)) {\n super('AgeGenderNet');\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): TinyXception {\n return this._faceFeatureExtractor;\n }\n\n public runNet(input: NetInput | tf.Tensor4D): NetOutput {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n\n const pooled = tf.avgPool(bottleneckFeatures, [7, 7], [2, 2], 'valid').as2D(bottleneckFeatures.shape[0], -1);\n const age = fullyConnectedLayer(pooled, params.fc.age).as1D();\n const gender = fullyConnectedLayer(pooled, params.fc.gender);\n return { age, gender };\n });\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): NetOutput {\n return tf.tidy(() => {\n const { age, gender } = this.runNet(input);\n return { age, gender: tf.softmax(gender) };\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictAgeAndGender(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n\n const ages = tf.unstack(out.age);\n const genders = tf.unstack(out.gender);\n const ageAndGenderTensors = ages.map((ageTensor, i) => ({\n ageTensor,\n genderTensor: genders[i],\n }));\n\n const predictionsByBatch = await Promise.all(\n ageAndGenderTensors.map(async ({ ageTensor, genderTensor }) => {\n const age = (await ageTensor.data())[0];\n const probMale = (await genderTensor.data())[0];\n const isMale = probMale > 0.5;\n const gender = isMale ? Gender.MALE : Gender.FEMALE;\n const genderProbability = isMale ? probMale : (1 - probMale);\n\n ageTensor.dispose();\n genderTensor.dispose();\n return { age, gender, genderProbability };\n }),\n );\n out.age.dispose();\n out.gender.dispose();\n\n return netInput.isBatchInput ? predictionsByBatch as AgeAndGenderPrediction[] : predictionsByBatch[0] as AgeAndGenderPrediction;\n }\n\n protected getDefaultModelName(): string {\n return 'age_gender_model';\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights);\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const classifierWeightSize = (512 * 1 + 1) + (512 * 2 + 2);\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, depthwiseSeparableConv } from '../common/index';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { range } from '../utils/index';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction conv(x: tf.Tensor4D, params: ConvParams, stride: [number, number]): tf.Tensor4D {\n return tf.add(tf.conv2d(x, params.filters, stride, 'same'), params.bias);\n}\n\nfunction reductionBlock(x: tf.Tensor4D, params: ReductionBlockParams, isActivateInput: boolean = true): tf.Tensor4D {\n let out = isActivateInput ? tf.relu(x) : x;\n out = depthwiseSeparableConv(out, params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = tf.maxPool(out, [3, 3], [2, 2], 'same');\n out = tf.add(out, conv(x, params.expansion_conv, [2, 2]));\n return out;\n}\n\nfunction mainBlock(x: tf.Tensor4D, params: MainBlockParams): tf.Tensor4D {\n let out = depthwiseSeparableConv(tf.relu(x), params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv2, [1, 1]);\n out = tf.add(out, x);\n return out;\n}\n\nexport class TinyXception extends NeuralNetwork {\n private _numMainBlocks: number\n\n constructor(numMainBlocks: number) {\n super('TinyXception');\n this._numMainBlocks = numMainBlocks;\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n if (!params) {\n throw new Error('TinyXception - load model before inference');\n }\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n let out = tf.relu(conv(normalized, params.entry_flow.conv_in, [2, 2]));\n out = reductionBlock(out, params.entry_flow.reduction_block_0, false);\n out = reductionBlock(out, params.entry_flow.reduction_block_1);\n range(this._numMainBlocks, 0, 1).forEach((idx) => {\n out = mainBlock(out, params.middle_flow[`main_block_${idx}`]);\n });\n out = reductionBlock(out, params.exit_flow.reduction_block);\n out = tf.relu(depthwiseSeparableConv(out, params.exit_flow.separable_conv, [1, 1]));\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_xception_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this._numMainBlocks);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights, this._numMainBlocks);\n }\n}\n", "import { extractConvParamsFactory, extractSeparableConvParamsFactory, extractWeightsFactory } from '../common/index';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractReductionBlockParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(channels: number, mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParams(weights: Float32Array, numMainBlocks: number): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const entry_flow_conv_in = extractConvParams(3, 32, 3, 'entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams(32, 64, 'entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams(64, 128, 'entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(128, `middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams(128, 256, 'exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams(256, 512, 'exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { entry_flow, middle_flow, exit_flow },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors,\n extractWeightEntryFactory,\n loadSeparableConvParamsFactory,\n ParamMapping,\n} from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractReductionBlockParams(mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(`${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(`${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n numMainBlocks: number,\n): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const entry_flow_conv_in = extractConvParams('entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams('entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams('entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(`middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams('exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams('exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params: { entry_flow, middle_flow, exit_flow }, paramMappings };\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const age = extractFCParams(512, 1, 'fc/age');\n const gender = extractFCParams(512, 2, 'fc/gender');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc: { age, gender } },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: {\n age: extractFcParams('fc/age'),\n gender: extractFcParams('fc/gender'),\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from '../common/index';\n\n// eslint-disable-next-line no-shadow\nexport enum Gender {\n // eslint-disable-next-line no-unused-vars\n FEMALE = 'female',\n // eslint-disable-next-line no-unused-vars\n MALE = 'male'\n}\n\nexport type AgeAndGenderPrediction = {\n age: number\n gender: Gender\n genderProbability: number\n}\n\nexport type NetOutput = { age: tf.Tensor1D, gender: tf.Tensor2D }\n\nexport type NetParams = {\n fc: {\n age: FCParams\n gender: FCParams\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { IDimensions, Point } from '../classes/index';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { isEven } from '../utils/index';\n\nexport abstract class FaceLandmark68NetBase<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends FaceProcessor {\n public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {\n const inputDimensions = originalDimensions.map(({ width, height }) => {\n const scale = inputSize / Math.max(height, width);\n return {\n width: width * scale,\n height: height * scale,\n };\n });\n\n const batchSize = inputDimensions.length;\n\n return tf.tidy(() => {\n const createInterleavedTensor = (fillX: number, fillY: number) => tf.stack([tf.fill([68], fillX, 'float32'), tf.fill([68], fillY, 'float32')], 1).as2D(1, 136).as1D();\n\n // eslint-disable-next-line no-unused-vars\n const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {\n const { width, height } = inputDimensions[batchIdx];\n return cond(width, height) ? Math.abs(width - height) / 2 : 0;\n };\n\n const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h);\n const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w);\n\n const landmarkTensors = output\n .mul(tf.fill([batchSize, 136], inputSize, 'float32'))\n .sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n getPaddingX(batchIdx),\n getPaddingY(batchIdx),\n ))))\n .div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n inputDimensions[batchIdx].width,\n inputDimensions[batchIdx].height,\n ))));\n\n return landmarkTensors as tf.Tensor2D;\n });\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n return tf.tidy(() => {\n const out = this.runNet(input);\n return this.postProcess(\n out,\n input.inputSize as number,\n input.inputDimensions.map(([height, width]) => ({ height, width })),\n );\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async detectLandmarks(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const landmarkTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const landmarksForBatch = await Promise.all(landmarkTensors.map(\n async (landmarkTensor, batchIdx) => {\n const landmarksArray = Array.from(await landmarkTensor.data());\n const xCoords = landmarksArray.filter((_, i) => isEven(i));\n const yCoords = landmarksArray.filter((_, i) => !isEven(i));\n\n return new FaceLandmarks68(\n Array(68).fill(0).map((_, i) => new Point(xCoords[i] as number, yCoords[i] as number)),\n {\n height: netInput.getInputHeight(batchIdx),\n width: netInput.getInputWidth(batchIdx),\n },\n );\n },\n ));\n\n landmarkTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput ? landmarksForBatch as FaceLandmarks68[] : landmarksForBatch[0] as FaceLandmarks68;\n }\n\n protected getClassifierChannelsOut(): number {\n return 136;\n }\n}\n", "import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68Net extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceLandmark68Net', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock3 } from './denseBlock';\nimport { extractParamsFromWeightMapTiny } from './extractParamsFromWeightMapTiny';\nimport { extractParamsTiny } from './extractParamsTiny';\nimport { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';\n\nexport class TinyFaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('TinyFaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyFaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock3(normalized, params.dense0, true);\n out = denseBlock3(out, params.dense1);\n out = denseBlock3(out, params.dense2);\n out = tf.avgPool(out, [14, 14], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_tiny_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMapTiny(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParamsTiny(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMapTiny(\n weightMap: tf.NamedTensorMap,\n): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock3Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock3Params('dense0', true),\n dense1: extractDenseBlock3Params('dense1'),\n dense2: extractDenseBlock3Params('dense2'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock3Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock3Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock3Params(64, 128, 'dense2');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { dense0, dense1, dense2 },\n };\n}\n", "import { TinyFaceFeatureExtractor } from '../faceFeatureExtractor/TinyFaceFeatureExtractor';\nimport { TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68TinyNet extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: TinyFaceFeatureExtractor = new TinyFaceFeatureExtractor()) {\n super('FaceLandmark68TinyNet', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_tiny_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 128;\n }\n}\n", "import { FaceLandmark68Net } from './FaceLandmark68Net';\n\nexport * from './FaceLandmark68Net';\nexport * from './FaceLandmark68TinyNet';\nexport class FaceLandmarkNet extends FaceLandmark68Net {}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { convDown } from './convLayer';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { residual, residualDown } from './residualLayer';\nimport { NetParams } from './types';\n\nexport class FaceRecognitionNet extends NeuralNetwork {\n constructor() {\n super('FaceRecognitionNet');\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceRecognitionNet - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(150, true), 'float32');\n\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = convDown(normalized, params.conv32_down);\n out = tf.maxPool(out, 3, 2, 'valid');\n\n out = residual(out, params.conv32_1);\n out = residual(out, params.conv32_2);\n out = residual(out, params.conv32_3);\n\n out = residualDown(out, params.conv64_down);\n out = residual(out, params.conv64_1);\n out = residual(out, params.conv64_2);\n out = residual(out, params.conv64_3);\n\n out = residualDown(out, params.conv128_down);\n out = residual(out, params.conv128_1);\n out = residual(out, params.conv128_2);\n\n out = residualDown(out, params.conv256_down);\n out = residual(out, params.conv256_1);\n out = residual(out, params.conv256_2);\n out = residualDown(out, params.conv256_down_out);\n\n const globalAvg = out.mean([1, 2]) as tf.Tensor2D;\n const fullyConnected = tf.matMul(globalAvg, params.fc);\n\n return fullyConnected;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async computeFaceDescriptor(input: TNetInput): Promise {\n if (input?.shape?.some((dim) => dim <= 0)) return new Float32Array(128);\n const netInput = await toNetInput(input);\n const faceDescriptorTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map((t) => t.data())) as Float32Array[];\n faceDescriptorTensors.forEach((t) => t.dispose());\n return netInput.isBatchInput ? faceDescriptorsForBatch : faceDescriptorsForBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_recognition_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { scale } from './scaleLayer';\nimport { ConvLayerParams } from './types';\n\nfunction convLayer(\n x: tf.Tensor4D,\n params: ConvLayerParams,\n strides: [number, number],\n withRelu: boolean,\n padding: 'valid' | 'same' = 'same',\n): tf.Tensor4D {\n const { filters, bias } = params.conv;\n\n let out = tf.conv2d(x, filters, strides, padding);\n out = tf.add(out, bias);\n out = scale(out, params.scale);\n return withRelu ? tf.relu(out) : out;\n}\n\nexport function conv(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], true);\n}\n\nexport function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], false);\n}\n\nexport function convDown(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [2, 2], true, 'valid');\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ScaleLayerParams } from './types';\n\nexport function scale(x: tf.Tensor4D, params: ScaleLayerParams): tf.Tensor4D {\n return tf.add(tf.mul(x, params.weights), params.biases);\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping,\n} from '../common/index';\nimport { isFloat } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {\n const weights = extractWeights(numFilterValues);\n const depth = weights.length / (numFilters * filterSize * filterSize);\n\n if (isFloat(depth)) {\n throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`);\n }\n\n return tf.tidy(\n () => tf.transpose(\n tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),\n [2, 3, 1, 0],\n ),\n );\n }\n\n function extractConvParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams {\n const filters = extractFilterValues(numFilterValues, numFilters, filterSize);\n const bias = tf.tensor1d(extractWeights(numFilters));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n }\n\n function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {\n const weights = tf.tensor1d(extractWeights(numWeights));\n const biases = tf.tensor1d(extractWeights(numWeights));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/biases` },\n );\n\n return {\n weights,\n biases,\n };\n }\n\n function extractConvLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvLayerParams {\n const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`);\n const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`);\n\n return { conv, scale };\n }\n\n function extractResidualLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n isDown: boolean = false,\n ): ResidualLayerParams {\n const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`);\n const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`);\n\n return { conv1, conv2 };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down');\n const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1');\n const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2');\n const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3');\n\n const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true);\n const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1');\n const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2');\n const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3');\n\n const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true);\n const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1');\n const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2');\n\n const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true);\n const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1');\n const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2');\n const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out');\n\n const fc = tf.tidy(\n () => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0]),\n );\n paramMappings.push({ paramPath: 'fc' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common/index';\nimport { isTensor2D } from '../utils/index';\nimport { ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractScaleLayerParams(prefix: string): ScaleLayerParams {\n const weights = extractWeightEntry(`${prefix}/scale/weights`, 1);\n const biases = extractWeightEntry(`${prefix}/scale/biases`, 1);\n\n return { weights, biases };\n }\n\n function extractConvLayerParams(prefix: string): ConvLayerParams {\n const filters = extractWeightEntry(`${prefix}/conv/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/conv/bias`, 1);\n const scale = extractScaleLayerParams(prefix);\n\n return { conv: { filters, bias }, scale };\n }\n\n function extractResidualLayerParams(prefix: string): ResidualLayerParams {\n return {\n conv1: extractConvLayerParams(`${prefix}/conv1`),\n conv2: extractConvLayerParams(`${prefix}/conv2`),\n };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const conv32_down = extractConvLayerParams('conv32_down');\n const conv32_1 = extractResidualLayerParams('conv32_1');\n const conv32_2 = extractResidualLayerParams('conv32_2');\n const conv32_3 = extractResidualLayerParams('conv32_3');\n\n const conv64_down = extractResidualLayerParams('conv64_down');\n const conv64_1 = extractResidualLayerParams('conv64_1');\n const conv64_2 = extractResidualLayerParams('conv64_2');\n const conv64_3 = extractResidualLayerParams('conv64_3');\n\n const conv128_down = extractResidualLayerParams('conv128_down');\n const conv128_1 = extractResidualLayerParams('conv128_1');\n const conv128_2 = extractResidualLayerParams('conv128_2');\n\n const conv256_down = extractResidualLayerParams('conv256_down');\n const conv256_1 = extractResidualLayerParams('conv256_1');\n const conv256_2 = extractResidualLayerParams('conv256_2');\n const conv256_down_out = extractResidualLayerParams('conv256_down_out');\n\n const { fc } = weightMap;\n paramMappings.push({ originalPath: 'fc', paramPath: 'fc' });\n\n if (!isTensor2D(fc)) {\n throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { conv, convDown, convNoRelu } from './convLayer';\nimport { ResidualLayerParams } from './types';\n\nexport function residual(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = conv(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n out = tf.add(out, x);\n out = tf.relu(out);\n return out;\n}\n\nexport function residualDown(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = convDown(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n\n let pooled = tf.avgPool(x, 2, 2, 'valid') as tf.Tensor4D;\n const zeros = tf.zeros(pooled.shape);\n const isPad = pooled.shape[3] !== out.shape[3];\n const isAdjustShape = pooled.shape[1] !== out.shape[1] || pooled.shape[2] !== out.shape[2];\n\n if (isAdjustShape) {\n const padShapeX = [...out.shape] as [number, number, number, number];\n padShapeX[1] = 1;\n const zerosW = tf.zeros(padShapeX);\n out = tf.concat([out, zerosW], 1);\n\n const padShapeY = [...out.shape] as [number, number, number, number];\n padShapeY[2] = 1;\n const zerosH = tf.zeros(padShapeY);\n out = tf.concat([out, zerosH], 2);\n }\n\n pooled = isPad ? tf.concat([pooled, zeros], 3) : pooled;\n out = tf.add(pooled, out) as tf.Tensor4D;\n\n out = tf.relu(out);\n return out;\n}\n", "import { FaceRecognitionNet } from './FaceRecognitionNet';\n\nexport * from './FaceRecognitionNet';\n\nexport function createFaceRecognitionNet(weights: Float32Array) {\n const net = new FaceRecognitionNet();\n net.extractWeights(weights);\n return net;\n}\n", "export type WithFaceDescriptor = TSource & {\n descriptor: Float32Array\n}\n\nexport function extendWithFaceDescriptor<\n TSource\n>(\n sourceObj: TSource,\n descriptor: Float32Array,\n): WithFaceDescriptor {\n const extension = { descriptor };\n return { ...sourceObj, ...extension };\n}\n", "export type WithAge = TSource & {\n age: number\n}\n\nexport function isWithAge(obj: any): obj is WithAge<{}> {\n return typeof obj.age === 'number';\n}\n\nexport function extendWithAge<\n TSource\n>(\n sourceObj: TSource,\n age: number,\n): WithAge {\n const extension = { age };\n return { ...sourceObj, ...extension };\n}\n", "import { Gender } from '../ageGenderNet/types';\nimport { isValidProbablitiy } from '../utils/index';\n\nexport type WithGender = TSource & {\n gender: Gender\n genderProbability: number\n}\n\nexport function isWithGender(obj: any): obj is WithGender<{}> {\n return (obj.gender === Gender.MALE || obj.gender === Gender.FEMALE)\n && isValidProbablitiy(obj.genderProbability);\n}\n\nexport function extendWithGender<\n TSource\n>(\n sourceObj: TSource,\n gender: Gender,\n genderProbability: number,\n): WithGender {\n const extension = { gender, genderProbability };\n return { ...sourceObj, ...extension };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { mobileNetV1 } from './mobileNetV1';\nimport { nonMaxSuppression } from './nonMaxSuppression';\nimport { outputLayer } from './outputLayer';\nimport { predictionLayer } from './predictionLayer';\nimport { ISsdMobilenetv1Options, SsdMobilenetv1Options } from './SsdMobilenetv1Options';\nimport { NetParams } from './types';\n\nexport class SsdMobilenetv1 extends NeuralNetwork {\n constructor() {\n super('SsdMobilenetv1');\n }\n\n public forwardInput(input: NetInput) {\n const { params } = this;\n\n if (!params) {\n throw new Error('SsdMobilenetv1 - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(512, false), 'float32');\n const x = tf.sub(tf.mul(batchTensor, tf.scalar(0.007843137718737125)), tf.scalar(1)) as tf.Tensor4D;\n const features = mobileNetV1(x, params.mobilenetv1);\n\n const {\n boxPredictions,\n classPredictions,\n } = predictionLayer(features.out, features.conv11, params.prediction_layer);\n\n return outputLayer(boxPredictions, classPredictions, params.output_layer);\n });\n }\n\n public async forward(input: TNetInput) {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async locateFaces(\n input: TNetInput,\n options: ISsdMobilenetv1Options = {},\n ): Promise {\n const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);\n\n const netInput = await toNetInput(input);\n\n const {\n boxes: _boxes,\n scores: _scores,\n } = this.forwardInput(netInput);\n\n const boxes = _boxes[0];\n const scores = _scores[0];\n for (let i = 1; i < _boxes.length; i++) {\n _boxes[i].dispose();\n _scores[i].dispose();\n }\n\n const scoresData = Array.from(await scores.data());\n const iouThreshold = 0.5;\n const indices = nonMaxSuppression(\n boxes,\n scoresData as number[],\n maxResults,\n iouThreshold,\n minConfidence,\n );\n\n const reshapedDims = netInput.getReshapedInputDimensions(0);\n const inputSize = netInput.inputSize as number;\n const padX = inputSize / reshapedDims.width;\n const padY = inputSize / reshapedDims.height;\n\n const boxesData = boxes.arraySync();\n const results = indices\n .map((idx) => {\n const [top, bottom] = [\n Math.max(0, boxesData[idx][0]),\n Math.min(1.0, boxesData[idx][2]),\n ].map((val) => val * padY);\n const [left, right] = [\n Math.max(0, boxesData[idx][1]),\n Math.min(1.0, boxesData[idx][3]),\n ].map((val) => val * padX);\n return new FaceDetection(\n scoresData[idx] as number,\n new Rect(\n left,\n top,\n right - left,\n bottom - top,\n ),\n {\n height: netInput.getInputHeight(0),\n width: netInput.getInputWidth(0),\n },\n );\n });\n\n boxes.dispose();\n scores.dispose();\n return results;\n }\n\n protected getDefaultModelName(): string {\n return 'ssd_mobilenetv1_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ExtractWeightsFunction, ParamMapping, ConvParams, extractWeightsFactory,\n} from '../common/index';\nimport {\n MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractDepthwiseConvParams(numChannels: number, mappedPrefix: string): MobileNetV1.DepthwiseConvParams {\n const filters = tf.tensor4d(extractWeights(3 * 3 * numChannels), [3, 3, numChannels, 1]);\n const batch_norm_scale = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_offset = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_mean = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_variance = tf.tensor1d(extractWeights(numChannels));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/batch_norm_scale` },\n { paramPath: `${mappedPrefix}/batch_norm_offset` },\n { paramPath: `${mappedPrefix}/batch_norm_mean` },\n { paramPath: `${mappedPrefix}/batch_norm_variance` },\n );\n\n return {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n };\n }\n\n function extractConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n isPointwiseConv?: boolean,\n ): ConvParams {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/${isPointwiseConv ? 'batch_norm_offset' : 'bias'}` },\n );\n\n return { filters, bias };\n }\n\n function extractPointwiseConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): PointwiseConvParams {\n const {\n filters,\n bias,\n } = extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix, true);\n\n return {\n filters,\n batch_norm_offset: bias,\n };\n }\n\n function extractConvPairParams(\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): MobileNetV1.ConvPairParams {\n const depthwise_conv = extractDepthwiseConvParams(channelsIn, `${mappedPrefix}/depthwise_conv`);\n const pointwise_conv = extractPointwiseConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/pointwise_conv`);\n\n return { depthwise_conv, pointwise_conv };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n const conv_0 = extractPointwiseConvParams(3, 32, 3, 'mobilenetv1/conv_0');\n const conv_1 = extractConvPairParams(32, 64, 'mobilenetv1/conv_1');\n const conv_2 = extractConvPairParams(64, 128, 'mobilenetv1/conv_2');\n const conv_3 = extractConvPairParams(128, 128, 'mobilenetv1/conv_3');\n const conv_4 = extractConvPairParams(128, 256, 'mobilenetv1/conv_4');\n const conv_5 = extractConvPairParams(256, 256, 'mobilenetv1/conv_5');\n const conv_6 = extractConvPairParams(256, 512, 'mobilenetv1/conv_6');\n const conv_7 = extractConvPairParams(512, 512, 'mobilenetv1/conv_7');\n const conv_8 = extractConvPairParams(512, 512, 'mobilenetv1/conv_8');\n const conv_9 = extractConvPairParams(512, 512, 'mobilenetv1/conv_9');\n const conv_10 = extractConvPairParams(512, 512, 'mobilenetv1/conv_10');\n const conv_11 = extractConvPairParams(512, 512, 'mobilenetv1/conv_11');\n const conv_12 = extractConvPairParams(512, 1024, 'mobilenetv1/conv_12');\n const conv_13 = extractConvPairParams(1024, 1024, 'mobilenetv1/conv_13');\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n conv_8,\n conv_9,\n conv_10,\n conv_11,\n conv_12,\n conv_13,\n };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n const conv_0 = extractPointwiseConvParams(1024, 256, 1, 'prediction_layer/conv_0');\n const conv_1 = extractPointwiseConvParams(256, 512, 3, 'prediction_layer/conv_1');\n const conv_2 = extractPointwiseConvParams(512, 128, 1, 'prediction_layer/conv_2');\n const conv_3 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_3');\n const conv_4 = extractPointwiseConvParams(256, 128, 1, 'prediction_layer/conv_4');\n const conv_5 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_5');\n const conv_6 = extractPointwiseConvParams(256, 64, 1, 'prediction_layer/conv_6');\n const conv_7 = extractPointwiseConvParams(64, 128, 3, 'prediction_layer/conv_7');\n const box_encoding_0_predictor = extractConvParams(512, 12, 1, 'prediction_layer/box_predictor_0/box_encoding_predictor');\n const class_predictor_0 = extractConvParams(512, 9, 1, 'prediction_layer/box_predictor_0/class_predictor');\n const box_encoding_1_predictor = extractConvParams(1024, 24, 1, 'prediction_layer/box_predictor_1/box_encoding_predictor');\n const class_predictor_1 = extractConvParams(1024, 18, 1, 'prediction_layer/box_predictor_1/class_predictor');\n const box_encoding_2_predictor = extractConvParams(512, 24, 1, 'prediction_layer/box_predictor_2/box_encoding_predictor');\n const class_predictor_2 = extractConvParams(512, 18, 1, 'prediction_layer/box_predictor_2/class_predictor');\n const box_encoding_3_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_3/box_encoding_predictor');\n const class_predictor_3 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_3/class_predictor');\n const box_encoding_4_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_4/box_encoding_predictor');\n const class_predictor_4 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_4/class_predictor');\n const box_encoding_5_predictor = extractConvParams(128, 24, 1, 'prediction_layer/box_predictor_5/box_encoding_predictor');\n const class_predictor_5 = extractConvParams(128, 18, 1, 'prediction_layer/box_predictor_5/class_predictor');\n\n const box_predictor_0 = {\n box_encoding_predictor: box_encoding_0_predictor,\n class_predictor: class_predictor_0,\n };\n const box_predictor_1 = {\n box_encoding_predictor: box_encoding_1_predictor,\n class_predictor: class_predictor_1,\n };\n const box_predictor_2 = {\n box_encoding_predictor: box_encoding_2_predictor,\n class_predictor: class_predictor_2,\n };\n const box_predictor_3 = {\n box_encoding_predictor: box_encoding_3_predictor,\n class_predictor: class_predictor_3,\n };\n const box_predictor_4 = {\n box_encoding_predictor: box_encoding_4_predictor,\n class_predictor: class_predictor_4,\n };\n const box_predictor_5 = {\n box_encoding_predictor: box_encoding_5_predictor,\n class_predictor: class_predictor_5,\n };\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n box_predictor_0,\n box_predictor_1,\n box_predictor_2,\n box_predictor_3,\n box_predictor_4,\n box_predictor_5,\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n const mobilenetv1 = extractMobilenetV1Params();\n const prediction_layer = extractPredictionLayerParams();\n const extra_dim = tf.tensor3d(\n extractWeights(5118 * 4),\n [1, 5118, 4],\n );\n const output_layer = {\n extra_dim,\n };\n paramMappings.push({ paramPath: 'output_layer/extra_dim' });\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n params: {\n mobilenetv1,\n prediction_layer,\n output_layer,\n },\n paramMappings,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping,\n} from '../common/index';\nimport { isTensor3D } from '../utils/index';\nimport {\n BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractPointwiseConvParams(prefix: string, idx: number, mappedPrefix: string): PointwiseConvParams {\n const filters = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/weights`, 4, `${mappedPrefix}/filters`);\n const batch_norm_offset = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/convolution_bn_offset`, 1, `${mappedPrefix}/batch_norm_offset`);\n return { filters, batch_norm_offset };\n }\n\n function extractConvPairParams(idx: number): MobileNetV1.ConvPairParams {\n const mappedPrefix = `mobilenetv1/conv_${idx}`;\n const prefixDepthwiseConv = `MobilenetV1/Conv2d_${idx}_depthwise`;\n const mappedPrefixDepthwiseConv = `${mappedPrefix}/depthwise_conv`;\n const mappedPrefixPointwiseConv = `${mappedPrefix}/pointwise_conv`;\n\n const filters = extractWeightEntry(`${prefixDepthwiseConv}/depthwise_weights`, 4, `${mappedPrefixDepthwiseConv}/filters`);\n const batch_norm_scale = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/gamma`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_scale`);\n const batch_norm_offset = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/beta`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_offset`);\n const batch_norm_mean = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_mean`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_mean`);\n const batch_norm_variance = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_variance`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_variance`);\n\n return {\n depthwise_conv: {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n },\n pointwise_conv: extractPointwiseConvParams('MobilenetV1', idx, mappedPrefixPointwiseConv),\n };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n return {\n conv_0: extractPointwiseConvParams('MobilenetV1', 0, 'mobilenetv1/conv_0'),\n conv_1: extractConvPairParams(1),\n conv_2: extractConvPairParams(2),\n conv_3: extractConvPairParams(3),\n conv_4: extractConvPairParams(4),\n conv_5: extractConvPairParams(5),\n conv_6: extractConvPairParams(6),\n conv_7: extractConvPairParams(7),\n conv_8: extractConvPairParams(8),\n conv_9: extractConvPairParams(9),\n conv_10: extractConvPairParams(10),\n conv_11: extractConvPairParams(11),\n conv_12: extractConvPairParams(12),\n conv_13: extractConvPairParams(13),\n };\n }\n\n function extractConvParams(prefix: string, mappedPrefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/weights`, 4, `${mappedPrefix}/filters`);\n const bias = extractWeightEntry(`${prefix}/biases`, 1, `${mappedPrefix}/bias`);\n return { filters, bias };\n }\n\n function extractBoxPredictorParams(idx: number): BoxPredictionParams {\n const box_encoding_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/BoxEncodingPredictor`,\n `prediction_layer/box_predictor_${idx}/box_encoding_predictor`,\n );\n const class_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/ClassPredictor`,\n `prediction_layer/box_predictor_${idx}/class_predictor`,\n );\n return { box_encoding_predictor, class_predictor };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n return {\n conv_0: extractPointwiseConvParams('Prediction', 0, 'prediction_layer/conv_0'),\n conv_1: extractPointwiseConvParams('Prediction', 1, 'prediction_layer/conv_1'),\n conv_2: extractPointwiseConvParams('Prediction', 2, 'prediction_layer/conv_2'),\n conv_3: extractPointwiseConvParams('Prediction', 3, 'prediction_layer/conv_3'),\n conv_4: extractPointwiseConvParams('Prediction', 4, 'prediction_layer/conv_4'),\n conv_5: extractPointwiseConvParams('Prediction', 5, 'prediction_layer/conv_5'),\n conv_6: extractPointwiseConvParams('Prediction', 6, 'prediction_layer/conv_6'),\n conv_7: extractPointwiseConvParams('Prediction', 7, 'prediction_layer/conv_7'),\n box_predictor_0: extractBoxPredictorParams(0),\n box_predictor_1: extractBoxPredictorParams(1),\n box_predictor_2: extractBoxPredictorParams(2),\n box_predictor_3: extractBoxPredictorParams(3),\n box_predictor_4: extractBoxPredictorParams(4),\n box_predictor_5: extractBoxPredictorParams(5),\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n const extra_dim = weightMap['Output/extra_dim'];\n paramMappings.push({ originalPath: 'Output/extra_dim', paramPath: 'output_layer/extra_dim' });\n if (!isTensor3D(extra_dim)) {\n throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${extra_dim}`);\n }\n\n const params = {\n mobilenetv1: extractMobilenetV1Params(),\n prediction_layer: extractPredictionLayerParams(),\n output_layer: {\n extra_dim,\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { MobileNetV1 } from './types';\n\nconst epsilon = 0.0010000000474974513;\n\nfunction depthwiseConvLayer(\n x: tf.Tensor4D,\n params: MobileNetV1.DepthwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.depthwiseConv2d(x, params.filters, strides, 'same');\n out = tf.batchNorm(\n out,\n params.batch_norm_mean,\n params.batch_norm_variance,\n params.batch_norm_offset,\n params.batch_norm_scale,\n epsilon,\n );\n return tf.clipByValue(out, 0, 6);\n });\n}\n\nfunction getStridesForLayerIdx(layerIdx: number): [number, number] {\n return [2, 4, 6, 12].some((idx) => idx === layerIdx) ? [2, 2] : [1, 1];\n}\n\nexport function mobileNetV1(x: tf.Tensor4D, params: MobileNetV1.Params) {\n return tf.tidy(() => {\n let conv11;\n let out = pointwiseConvLayer(x, params.conv_0, [2, 2]);\n\n const convPairParams = [\n params.conv_1,\n params.conv_2,\n params.conv_3,\n params.conv_4,\n params.conv_5,\n params.conv_6,\n params.conv_7,\n params.conv_8,\n params.conv_9,\n params.conv_10,\n params.conv_11,\n params.conv_12,\n params.conv_13,\n ];\n\n convPairParams.forEach((param, i) => {\n const layerIdx = i + 1;\n const depthwiseConvStrides = getStridesForLayerIdx(layerIdx);\n out = depthwiseConvLayer(out, param.depthwise_conv, depthwiseConvStrides);\n out = pointwiseConvLayer(out, param.pointwise_conv, [1, 1]);\n if (layerIdx === 11) {\n conv11 = out;\n }\n });\n\n if (conv11 === null) {\n throw new Error('mobileNetV1 - output of conv layer 11 is null');\n }\n\n return {\n out,\n conv11: conv11 as any,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { PointwiseConvParams } from './types';\n\nexport function pointwiseConvLayer(\n x: tf.Tensor4D,\n params: PointwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.conv2d(x, params.filters, strides, 'same');\n out = tf.add(out, params.batch_norm_offset);\n return tf.clipByValue(out, 0, 6);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nfunction IOU(boxes: tf.Tensor2D, i: number, j: number) {\n const boxesData = boxes.arraySync();\n const yminI = Math.min(boxesData[i][0], boxesData[i][2]);\n const xminI = Math.min(boxesData[i][1], boxesData[i][3]);\n const ymaxI = Math.max(boxesData[i][0], boxesData[i][2]);\n const xmaxI = Math.max(boxesData[i][1], boxesData[i][3]);\n const yminJ = Math.min(boxesData[j][0], boxesData[j][2]);\n const xminJ = Math.min(boxesData[j][1], boxesData[j][3]);\n const ymaxJ = Math.max(boxesData[j][0], boxesData[j][2]);\n const xmaxJ = Math.max(boxesData[j][1], boxesData[j][3]);\n const areaI = (ymaxI - yminI) * (xmaxI - xminI);\n const areaJ = (ymaxJ - yminJ) * (xmaxJ - xminJ);\n if (areaI <= 0 || areaJ <= 0) {\n return 0.0;\n }\n const intersectionYmin = Math.max(yminI, yminJ);\n const intersectionXmin = Math.max(xminI, xminJ);\n const intersectionYmax = Math.min(ymaxI, ymaxJ);\n const intersectionXmax = Math.min(xmaxI, xmaxJ);\n const intersectionArea = Math.max(intersectionYmax - intersectionYmin, 0.0)\n * Math.max(intersectionXmax - intersectionXmin, 0.0);\n return intersectionArea / (areaI + areaJ - intersectionArea);\n}\n\nexport function nonMaxSuppression(\n boxes: tf.Tensor2D,\n scores: number[],\n maxOutputSize: number,\n iouThreshold: number,\n scoreThreshold: number,\n): number[] {\n const numBoxes = boxes.shape[0];\n const outputSize = Math.min(\n maxOutputSize,\n numBoxes,\n );\n\n const candidates = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .filter((c) => c.score > scoreThreshold)\n .sort((c1, c2) => c2.score - c1.score);\n\n const suppressFunc = (x: number) => (x <= iouThreshold ? 1 : 0);\n const selected: number[] = [];\n\n candidates.forEach((c) => {\n if (selected.length >= outputSize) return;\n const originalScore = c.score;\n for (let j = selected.length - 1; j >= 0; --j) {\n const iou = IOU(boxes, c.boxIndex, selected[j]);\n if (iou === 0.0) continue;\n c.score *= suppressFunc(iou);\n if (c.score <= scoreThreshold) break;\n }\n if (originalScore === c.score) {\n selected.push(c.boxIndex);\n }\n });\n return selected;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { OutputLayerParams } from './types';\n\nfunction getCenterCoordinatesAndSizesLayer(x: tf.Tensor2D) {\n const vec = tf.unstack(tf.transpose(x, [1, 0]));\n\n const sizes = [\n tf.sub(vec[2], vec[0]),\n tf.sub(vec[3], vec[1]),\n ];\n const centers = [\n tf.add(vec[0], tf.div(sizes[0], tf.scalar(2))),\n tf.add(vec[1], tf.div(sizes[1], tf.scalar(2))),\n ];\n return {\n sizes,\n centers,\n };\n}\n\nfunction decodeBoxesLayer(x0: tf.Tensor2D, x1: tf.Tensor2D) {\n const {\n sizes,\n centers,\n } = getCenterCoordinatesAndSizesLayer(x0);\n\n const vec = tf.unstack(tf.transpose(x1, [1, 0]));\n const div0_out = tf.div(tf.mul(tf.exp(tf.div(vec[2], tf.scalar(5))), sizes[0]), tf.scalar(2));\n const add0_out = tf.add(tf.mul(tf.div(vec[0], tf.scalar(10)), sizes[0]), centers[0]);\n const div1_out = tf.div(tf.mul(tf.exp(tf.div(vec[3], tf.scalar(5))), sizes[1]), tf.scalar(2));\n const add1_out = tf.add(tf.mul(tf.div(vec[1], tf.scalar(10)), sizes[1]), centers[1]);\n\n return tf.transpose(\n tf.stack([\n tf.sub(add0_out, div0_out),\n tf.sub(add1_out, div1_out),\n tf.add(add0_out, div0_out),\n tf.add(add1_out, div1_out),\n ]),\n [1, 0],\n );\n}\n\nexport function outputLayer(\n boxPredictions: tf.Tensor4D,\n classPredictions: tf.Tensor4D,\n params: OutputLayerParams,\n) {\n return tf.tidy(() => {\n const batchSize = boxPredictions.shape[0];\n\n let boxes = decodeBoxesLayer(\n tf.reshape(tf.tile(params.extra_dim, [batchSize, 1, 1]), [-1, 4]) as tf.Tensor2D,\n tf.reshape(boxPredictions, [-1, 4]) as tf.Tensor2D,\n );\n boxes = tf.reshape(\n boxes,\n [batchSize, (boxes.shape[0] / batchSize), 4],\n );\n\n const scoresAndClasses = tf.sigmoid(tf.slice(classPredictions, [0, 0, 1], [-1, -1, -1]));\n let scores = tf.slice(scoresAndClasses, [0, 0, 0], [-1, -1, 1]) as tf.Tensor;\n\n scores = tf.reshape(\n scores,\n [batchSize, scores.shape[1] as number],\n );\n\n const boxesByBatch = tf.unstack(boxes) as tf.Tensor2D[];\n const scoresByBatch = tf.unstack(scores) as tf.Tensor1D[];\n\n return {\n boxes: boxesByBatch,\n scores: scoresByBatch,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { boxPredictionLayer } from './boxPredictionLayer';\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { PredictionLayerParams } from './types';\n\nexport function predictionLayer(\n x: tf.Tensor4D,\n conv11: tf.Tensor4D,\n params: PredictionLayerParams,\n) {\n return tf.tidy(() => {\n const conv0 = pointwiseConvLayer(x, params.conv_0, [1, 1]);\n const conv1 = pointwiseConvLayer(conv0, params.conv_1, [2, 2]);\n const conv2 = pointwiseConvLayer(conv1, params.conv_2, [1, 1]);\n const conv3 = pointwiseConvLayer(conv2, params.conv_3, [2, 2]);\n const conv4 = pointwiseConvLayer(conv3, params.conv_4, [1, 1]);\n const conv5 = pointwiseConvLayer(conv4, params.conv_5, [2, 2]);\n const conv6 = pointwiseConvLayer(conv5, params.conv_6, [1, 1]);\n const conv7 = pointwiseConvLayer(conv6, params.conv_7, [2, 2]);\n\n const boxPrediction0 = boxPredictionLayer(conv11, params.box_predictor_0);\n const boxPrediction1 = boxPredictionLayer(x, params.box_predictor_1);\n const boxPrediction2 = boxPredictionLayer(conv1, params.box_predictor_2);\n const boxPrediction3 = boxPredictionLayer(conv3, params.box_predictor_3);\n const boxPrediction4 = boxPredictionLayer(conv5, params.box_predictor_4);\n const boxPrediction5 = boxPredictionLayer(conv7, params.box_predictor_5);\n\n const boxPredictions = tf.concat([\n boxPrediction0.boxPredictionEncoding,\n boxPrediction1.boxPredictionEncoding,\n boxPrediction2.boxPredictionEncoding,\n boxPrediction3.boxPredictionEncoding,\n boxPrediction4.boxPredictionEncoding,\n boxPrediction5.boxPredictionEncoding,\n ], 1) as tf.Tensor4D;\n\n const classPredictions = tf.concat([\n boxPrediction0.classPrediction,\n boxPrediction1.classPrediction,\n boxPrediction2.classPrediction,\n boxPrediction3.classPrediction,\n boxPrediction4.classPrediction,\n boxPrediction5.classPrediction,\n ], 1) as tf.Tensor4D;\n\n return {\n boxPredictions,\n classPredictions,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { convLayer } from '../common/index';\nimport { BoxPredictionParams } from './types';\n\nexport function boxPredictionLayer(\n x: tf.Tensor4D,\n params: BoxPredictionParams,\n) {\n return tf.tidy(() => {\n const batchSize = x.shape[0];\n const boxPredictionEncoding = tf.reshape(\n convLayer(x, params.box_encoding_predictor),\n [batchSize, -1, 1, 4],\n );\n const classPrediction = tf.reshape(\n convLayer(x, params.class_predictor),\n [batchSize, -1, 3],\n );\n return { boxPredictionEncoding, classPrediction };\n });\n}\n", "export interface ISsdMobilenetv1Options {\n minConfidence?: number\n maxResults?: number\n}\n\nexport class SsdMobilenetv1Options {\n protected _name: string = 'SsdMobilenetv1Options'\n\n private _minConfidence: number\n\n private _maxResults: number\n\n constructor({ minConfidence, maxResults }: ISsdMobilenetv1Options = {}) {\n this._minConfidence = minConfidence || 0.5;\n this._maxResults = maxResults || 100;\n\n if (typeof this._minConfidence !== 'number' || this._minConfidence <= 0 || this._minConfidence >= 1) {\n throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);\n }\n\n if (typeof this._maxResults !== 'number') {\n throw new Error(`${this._name} - expected maxResults to be a number`);\n }\n }\n\n get minConfidence(): number { return this._minConfidence; }\n\n get maxResults(): number { return this._maxResults; }\n}\n", "import { SsdMobilenetv1 } from './SsdMobilenetv1';\n\nexport * from './SsdMobilenetv1';\nexport * from './SsdMobilenetv1Options';\n\nexport function createSsdMobilenetv1(weights: Float32Array) {\n const net = new SsdMobilenetv1();\n net.extractWeights(weights);\n return net;\n}\n\nexport function createFaceDetectionNet(weights: Float32Array) {\n return createSsdMobilenetv1(weights);\n}\n\n// alias for backward compatibily\nexport class FaceDetectionNet extends SsdMobilenetv1 {}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(0.738768, 0.874946),\n new Point(2.42204, 2.65704),\n new Point(4.30971, 7.04493),\n new Point(10.246, 4.59428),\n new Point(12.6868, 11.8741),\n];\n\nexport const BOX_ANCHORS_SEPARABLE = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB_SEPARABLE: [number, number, number] = [117.001, 114.697, 97.404];\n\nexport const DEFAULT_MODEL_NAME = 'tiny_yolov2_model';\nexport const DEFAULT_MODEL_NAME_SEPARABLE_CONV = 'tiny_yolov2_separable_conv_model';\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { BoundingBox } from '../classes/BoundingBox';\nimport { Dimensions } from '../classes/Dimensions';\nimport { ObjectDetection } from '../classes/ObjectDetection';\nimport { convLayer } from '../common/index';\nimport { ConvParams, SeparableConvParams } from '../common/types';\nimport { toNetInput } from '../dom/index';\nimport { NetInput } from '../dom/NetInput';\nimport { TNetInput } from '../dom/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { sigmoid } from '../ops/index';\nimport { nonMaxSuppression } from '../ops/nonMaxSuppression';\nimport { normalize } from '../ops/normalize';\nimport { TinyYolov2Config, validateConfig } from './config';\nimport { convWithBatchNorm } from './convWithBatchNorm';\nimport { depthwiseSeparableConv } from './depthwiseSeparableConv';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { leaky } from './leaky';\nimport { ITinyYolov2Options, TinyYolov2Options } from './TinyYolov2Options';\nimport { DefaultTinyYolov2NetParams, MobilenetParams, TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2Base extends NeuralNetwork {\n public static DEFAULT_FILTER_SIZES = [3, 16, 32, 64, 128, 256, 512, 1024, 1024];\n\n private _config: TinyYolov2Config\n\n constructor(config: TinyYolov2Config) {\n super('TinyYolov2');\n validateConfig(config);\n this._config = config;\n }\n\n public get config(): TinyYolov2Config {\n return this._config;\n }\n\n public get withClassScores(): boolean {\n return this.config.withClassScores || this.config.classes.length > 1;\n }\n\n public get boxEncodingSize(): number {\n return 5 + (this.withClassScores ? this.config.classes.length : 0);\n }\n\n public runTinyYolov2(x: tf.Tensor4D, params: DefaultTinyYolov2NetParams): tf.Tensor4D {\n let out = convWithBatchNorm(x, params.conv0);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = convWithBatchNorm(out, params.conv6);\n out = convWithBatchNorm(out, params.conv7);\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public runMobilenet(x: tf.Tensor4D, params: MobilenetParams): tf.Tensor4D {\n let out = this.config.isFirstLayerConv2d\n ? leaky(convLayer(x, params.conv0 as ConvParams, 'valid', false))\n : depthwiseSeparableConv(x, params.conv0 as SeparableConvParams);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = params.conv6 ? depthwiseSeparableConv(out, params.conv6) : out;\n out = params.conv7 ? depthwiseSeparableConv(out, params.conv7) : out;\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public forwardInput(input: NetInput, inputSize: number): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyYolov2 - load model before inference');\n }\n\n return tf.tidy(() => {\n let batchTensor = tf.cast(input.toBatchTensor(inputSize, false), 'float32');\n batchTensor = this.config.meanRgb\n ? normalize(batchTensor, this.config.meanRgb)\n : batchTensor;\n batchTensor = batchTensor.div(tf.scalar(256)) as tf.Tensor4D;\n return this.config.withSeparableConvs\n ? this.runMobilenet(batchTensor, params as MobilenetParams)\n : this.runTinyYolov2(batchTensor, params as DefaultTinyYolov2NetParams);\n });\n }\n\n public async forward(input: TNetInput, inputSize: number): Promise {\n return this.forwardInput(await toNetInput(input), inputSize);\n }\n\n public async detect(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise {\n const { inputSize, scoreThreshold } = new TinyYolov2Options(forwardParams);\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput, inputSize);\n const out0 = tf.tidy(() => tf.unstack(out)[0].expandDims()) as tf.Tensor4D;\n const inputDimensions = {\n width: netInput.getInputWidth(0),\n height: netInput.getInputHeight(0),\n };\n\n const results = await this.extractBoxes(out0, netInput.getReshapedInputDimensions(0), scoreThreshold);\n out.dispose();\n out0.dispose();\n\n const boxes = results.map((res) => res.box);\n const scores = results.map((res) => res.score);\n const classScores = results.map((res) => res.classScore);\n const classNames = results.map((res) => this.config.classes[res.label]);\n\n const indices = nonMaxSuppression(\n boxes.map((box) => box.rescale(inputSize)),\n scores,\n this.config.iouThreshold,\n true,\n );\n\n const detections = indices.map((idx) => new ObjectDetection(\n scores[idx],\n classScores[idx],\n classNames[idx],\n boxes[idx],\n inputDimensions,\n ));\n return detections;\n }\n\n protected getDefaultModelName(): string {\n return '';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this.config);\n }\n\n protected extractParams(weights: Float32Array) {\n const filterSizes = this.config.filterSizes || TinyYolov2Base.DEFAULT_FILTER_SIZES;\n\n const numFilters = filterSizes ? filterSizes.length : undefined;\n if (numFilters !== 7 && numFilters !== 8 && numFilters !== 9) {\n throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${numFilters} filterSizes in config`);\n }\n return extractParams(weights, this.config, this.boxEncodingSize, filterSizes);\n }\n\n protected async extractBoxes(\n outputTensor: tf.Tensor4D,\n inputBlobDimensions: Dimensions,\n scoreThreshold?: number,\n ) {\n const { width, height } = inputBlobDimensions;\n const inputSize = Math.max(width, height);\n const correctionFactorX = inputSize / width;\n const correctionFactorY = inputSize / height;\n\n const numCells = outputTensor.shape[1];\n const numBoxes = this.config.anchors.length;\n\n const [boxesTensor, scoresTensor, classScoresTensor] = tf.tidy(() => {\n const reshaped = outputTensor.reshape([numCells, numCells, numBoxes, this.boxEncodingSize]);\n\n const boxes = reshaped.slice([0, 0, 0, 0], [numCells, numCells, numBoxes, 4]);\n const scores = reshaped.slice([0, 0, 0, 4], [numCells, numCells, numBoxes, 1]);\n const classScores = this.withClassScores\n ? tf.softmax(reshaped.slice([0, 0, 0, 5], [numCells, numCells, numBoxes, this.config.classes.length]), 3)\n : tf.scalar(0);\n return [boxes, scores, classScores];\n });\n\n const results = [] as any;\n const scoresData = await scoresTensor.array();\n const boxesData = await boxesTensor.array();\n for (let row = 0; row < numCells; row++) {\n for (let col = 0; col < numCells; col++) {\n for (let anchor = 0; anchor < numBoxes; anchor++) {\n const score = sigmoid(scoresData[row][col][anchor][0]);\n if (!scoreThreshold || score > scoreThreshold) {\n const ctX = ((col + sigmoid(boxesData[row][col][anchor][0])) / numCells) * correctionFactorX;\n const ctY = ((row + sigmoid(boxesData[row][col][anchor][1])) / numCells) * correctionFactorY;\n const widthLocal = ((Math.exp(boxesData[row][col][anchor][2]) * this.config.anchors[anchor].x) / numCells) * correctionFactorX;\n const heightLocal = ((Math.exp(boxesData[row][col][anchor][3]) * this.config.anchors[anchor].y) / numCells) * correctionFactorY;\n const x = (ctX - (widthLocal / 2));\n const y = (ctY - (heightLocal / 2));\n const pos = { row, col, anchor };\n const { classScore, label } = this.withClassScores\n ? await this.extractPredictedClass(classScoresTensor as tf.Tensor4D, pos)\n : { classScore: 1, label: 0 };\n results.push({\n box: new BoundingBox(x, y, x + widthLocal, y + heightLocal),\n score,\n classScore: score * classScore,\n label,\n ...pos,\n });\n }\n }\n }\n }\n\n boxesTensor.dispose();\n scoresTensor.dispose();\n classScoresTensor.dispose();\n return results;\n }\n\n private async extractPredictedClass(classesTensor: tf.Tensor4D, pos: { row: number, col: number, anchor: number }) {\n const { row, col, anchor } = pos;\n const classesData = await classesTensor.array();\n return Array(this.config.classes.length).fill(0)\n .map((_, i) => classesData[row][col][anchor][i])\n .map((classScore, label) => ({\n classScore,\n label,\n }))\n .reduce((max, curr) => (max.classScore > curr.classScore ? max : curr));\n }\n}\n", "import { Point } from '../classes/Point';\n\nexport type TinyYolov2Config = {\n withSeparableConvs: boolean\n iouThreshold: number\n anchors: Point[]\n classes: string[]\n meanRgb?: [number, number, number]\n withClassScores?: boolean,\n filterSizes?: number[]\n isFirstLayerConv2d?: boolean\n}\n\nconst isNumber = (arg: any) => typeof arg === 'number';\n\nexport function validateConfig(config: any) {\n if (!config) {\n throw new Error(`invalid config: ${config}`);\n }\n\n if (typeof config.withSeparableConvs !== 'boolean') {\n throw new Error(`config.withSeparableConvs has to be a boolean, have: ${config.withSeparableConvs}`);\n }\n\n if (!isNumber(config.iouThreshold) || config.iouThreshold < 0 || config.iouThreshold > 1.0) {\n throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${config.iouThreshold}`);\n }\n\n if (\n !Array.isArray(config.classes)\n || !config.classes.length\n || !config.classes.every((c: any) => typeof c === 'string')\n ) {\n throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(config.classes)}`);\n }\n\n if (\n !Array.isArray(config.anchors)\n || !config.anchors.length\n || !config.anchors.map((a: any) => a || {}).every((a: any) => isNumber(a.x) && isNumber(a.y))\n ) {\n throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(config.anchors)}`);\n }\n\n if (config.meanRgb && (\n !Array.isArray(config.meanRgb)\n || config.meanRgb.length !== 3\n || !config.meanRgb.every(isNumber)\n )) {\n throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(config.meanRgb)}`);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { leaky } from './leaky';\nimport { ConvWithBatchNorm } from './types';\n\nexport function convWithBatchNorm(x: tf.Tensor4D, params: ConvWithBatchNorm): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n out = tf.conv2d(out, params.conv.filters, [1, 1], 'valid');\n out = tf.sub(out, params.bn.sub);\n out = tf.mul(out, params.bn.truediv);\n out = tf.add(out, params.conv.bias);\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function leaky(x: tf.Tensor4D): tf.Tensor4D {\n return tf.tidy(() => {\n const min = tf.mul(x, tf.scalar(0.10000000149011612));\n return tf.add(tf.relu(tf.sub(x, min)), min);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from '../common/types';\nimport { leaky } from './leaky';\n\nexport function depthwiseSeparableConv(x: tf.Tensor4D, params: SeparableConvParams): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n out = tf.separableConv2d(out, params.depthwise_filter, params.pointwise_filter, [1, 1], 'valid');\n out = tf.add(out, params.bias);\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { extractConvParamsFactory } from '../common/index';\nimport { extractSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightsFactory } from '../common/extractWeightsFactory';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n\n function extractBatchNormParams(size: number, mappedPrefix: string): BatchNorm {\n const sub = tf.tensor1d(extractWeights(size));\n const truediv = tf.tensor1d(extractWeights(size));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/sub` },\n { paramPath: `${mappedPrefix}/truediv` },\n );\n return { sub, truediv };\n }\n\n function extractConvWithBatchNormParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv`);\n const bn = extractBatchNormParams(channelsOut, `${mappedPrefix}/bn`);\n return { conv, bn };\n }\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParams(\n weights: Float32Array,\n config: TinyYolov2Config,\n boxEncodingSize: number,\n filterSizes: number[],\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(extractWeights, paramMappings);\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = config.isFirstLayerConv2d\n ? extractConvParams(s0, s1, 3, 'conv0')\n : extractSeparableConvParams(s0, s1, 'conv0');\n const conv1 = extractSeparableConvParams(s1, s2, 'conv1');\n const conv2 = extractSeparableConvParams(s2, s3, 'conv2');\n const conv3 = extractSeparableConvParams(s3, s4, 'conv3');\n const conv4 = extractSeparableConvParams(s4, s5, 'conv4');\n const conv5 = extractSeparableConvParams(s5, s6, 'conv5');\n const conv6 = s7 ? extractSeparableConvParams(s6, s7, 'conv6') : undefined;\n const conv7 = s8 ? extractSeparableConvParams(s7, s8, 'conv7') : undefined;\n const conv8 = extractConvParams(s8 || s7 || s6, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n } else {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = extractConvWithBatchNormParams(s0, s1, 'conv0');\n const conv1 = extractConvWithBatchNormParams(s1, s2, 'conv1');\n const conv2 = extractConvWithBatchNormParams(s2, s3, 'conv2');\n const conv3 = extractConvWithBatchNormParams(s3, s4, 'conv3');\n const conv4 = extractConvWithBatchNormParams(s4, s5, 'conv4');\n const conv5 = extractConvWithBatchNormParams(s5, s6, 'conv5');\n const conv6 = extractConvWithBatchNormParams(s6, s7, 'conv6');\n const conv7 = extractConvWithBatchNormParams(s7, s8, 'conv7');\n const conv8 = extractConvParams(s8, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n }\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from '../common/index';\nimport { disposeUnusedWeightTensors } from '../common/disposeUnusedWeightTensors';\nimport { loadSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightEntryFactory } from '../common/extractWeightEntryFactory';\nimport { ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractBatchNormParams(prefix: string): BatchNorm {\n const sub = extractWeightEntry(`${prefix}/sub`, 1);\n const truediv = extractWeightEntry(`${prefix}/truediv`, 1);\n return { sub, truediv };\n }\n\n function extractConvParams(prefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { filters, bias };\n }\n\n function extractConvWithBatchNormParams(prefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(`${prefix}/conv`);\n const bn = extractBatchNormParams(`${prefix}/bn`);\n return { conv, bn };\n }\n\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n config: TinyYolov2Config,\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n // eslint-disable-next-line no-mixed-operators\n const numFilters = (config.filterSizes && config.filterSizes.length || 9);\n params = {\n conv0: config.isFirstLayerConv2d ? extractConvParams('conv0') : extractSeparableConvParams('conv0'),\n conv1: extractSeparableConvParams('conv1'),\n conv2: extractSeparableConvParams('conv2'),\n conv3: extractSeparableConvParams('conv3'),\n conv4: extractSeparableConvParams('conv4'),\n conv5: extractSeparableConvParams('conv5'),\n conv6: numFilters > 7 ? extractSeparableConvParams('conv6') : undefined,\n conv7: numFilters > 8 ? extractSeparableConvParams('conv7') : undefined,\n conv8: extractConvParams('conv8'),\n };\n } else {\n params = {\n conv0: extractConvWithBatchNormParams('conv0'),\n conv1: extractConvWithBatchNormParams('conv1'),\n conv2: extractConvWithBatchNormParams('conv2'),\n conv3: extractConvWithBatchNormParams('conv3'),\n conv4: extractConvWithBatchNormParams('conv4'),\n conv5: extractConvWithBatchNormParams('conv5'),\n conv6: extractConvWithBatchNormParams('conv6'),\n conv7: extractConvWithBatchNormParams('conv7'),\n conv8: extractConvParams('conv8'),\n };\n }\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n return { params, paramMappings };\n}\n", "export interface ITinyYolov2Options {\n inputSize?: number\n scoreThreshold?: number\n}\n\nexport class TinyYolov2Options {\n protected _name: string = 'TinyYolov2Options'\n\n private _inputSize: number\n\n private _scoreThreshold: number\n\n constructor({ inputSize, scoreThreshold }: ITinyYolov2Options = {}) {\n this._inputSize = inputSize || 416;\n this._scoreThreshold = scoreThreshold || 0.5;\n\n if (typeof this._inputSize !== 'number' || this._inputSize % 32 !== 0) {\n throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);\n }\n\n if (typeof this._scoreThreshold !== 'number' || this._scoreThreshold <= 0 || this._scoreThreshold >= 1) {\n throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`);\n }\n }\n\n get inputSize(): number { return this._inputSize; }\n\n get scoreThreshold(): number { return this._scoreThreshold; }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/types';\nimport { TNetInput } from '../dom/types';\nimport {\n BOX_ANCHORS,\n BOX_ANCHORS_SEPARABLE,\n DEFAULT_MODEL_NAME,\n DEFAULT_MODEL_NAME_SEPARABLE_CONV,\n IOU_THRESHOLD,\n MEAN_RGB_SEPARABLE,\n} from './const';\nimport { TinyYolov2Base } from './TinyYolov2Base';\nimport { ITinyYolov2Options } from './TinyYolov2Options';\nimport { TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2 extends TinyYolov2Base {\n constructor(withSeparableConvs: boolean = true) {\n const config = {\n withSeparableConvs,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n ...(withSeparableConvs\n ? {\n anchors: BOX_ANCHORS_SEPARABLE,\n meanRgb: MEAN_RGB_SEPARABLE,\n }\n : {\n anchors: BOX_ANCHORS,\n withClassScores: true,\n }),\n };\n\n super(config);\n }\n\n public get withSeparableConvs(): boolean {\n return this.config.withSeparableConvs;\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return this.withSeparableConvs ? DEFAULT_MODEL_NAME_SEPARABLE_CONV : DEFAULT_MODEL_NAME;\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { TinyYolov2 } from './TinyYolov2';\n\nexport * from './TinyYolov2Options';\nexport * from './config';\nexport * from './types';\nexport { TinyYolov2 };\n\nexport function createTinyYolov2(weights: Float32Array, withSeparableConvs: boolean = true) {\n const net = new TinyYolov2(withSeparableConvs);\n net.extractWeights(weights);\n return net;\n}\n", "import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\n\nexport interface ITinyFaceDetectorOptions extends ITinyYolov2Options {}\n\nexport class TinyFaceDetectorOptions extends TinyYolov2Options {\n protected _name: string = 'TinyFaceDetectorOptions'\n}\n", "export class ComposableTask {\n public async then(\n // eslint-disable-next-line no-unused-vars\n onfulfilled: (value: T) => T | PromiseLike,\n ): Promise {\n return onfulfilled(await this.run());\n }\n\n public async run(): Promise {\n throw new Error('ComposableTask - run is not implemented');\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class DetectFaceLandmarksTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected useTinyLandmarkNet: boolean,\n ) {\n super();\n }\n\n protected get landmarkNet(): FaceLandmark68Net | FaceLandmark68TinyNet {\n return this.useTinyLandmarkNet\n ? nets.faceLandmark68TinyNet\n : nets.faceLandmark68Net;\n }\n}\n\nexport class DetectAllFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n const detections = parentResults.map((res) => res.detection);\n\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, detections)\n : await extractFaces(this.input, detections);\n\n const faceLandmarksByFace = await Promise.all(faces.map(\n (face) => this.landmarkNet.detectLandmarks(face),\n )) as FaceLandmarks68[];\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return parentResults.map((parentResult, i) => extendWithFaceLandmarks(parentResult, faceLandmarksByFace[i]));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class DetectSingleFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { detection } = parentResult;\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, [detection])\n : await extractFaces(this.input, [detection]);\n\n const landmarks = await this.landmarkNet.detectLandmarks(faces[0]) as FaceLandmarks68;\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return extendWithFaceLandmarks(parentResult, landmarks);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\n\nexport async function extractAllFacesAndComputeResults, TResult>(\n parentResults: TSource[],\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResults: (faces: Array) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment: (parentResult: WithFaceLandmarks) => FaceDetection = ({ alignedRect }) => alignedRect,\n) {\n const faceBoxes = parentResults.map((parentResult) => (isWithFaceLandmarks(parentResult)\n ? getRectForAlignment(parentResult)\n : parentResult.detection));\n const faces: Array = extractedFaces || (\n input instanceof tf.Tensor\n ? await extractFaceTensors(input, faceBoxes)\n : await extractFaces(input, faceBoxes)\n );\n\n const results = await computeResults(faces);\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return results;\n}\n\nexport async function extractSingleFaceAndComputeResult, TResult>(\n parentResult: TSource,\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResult: (face: HTMLCanvasElement | tf.Tensor3D) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment?: (parentResultLocal: WithFaceLandmarks) => FaceDetection,\n) {\n return extractAllFacesAndComputeResults(\n [parentResult],\n input,\n async (faces) => computeResult(faces[0]),\n extractedFaces,\n getRectForAlignment,\n );\n}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB: [number, number, number] = [117.001, 114.697, 97.404];\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/index';\nimport { TNetInput } from '../dom/index';\nimport { ITinyYolov2Options } from '../tinyYolov2/index';\nimport { TinyYolov2Base } from '../tinyYolov2/TinyYolov2Base';\nimport { TinyYolov2NetParams } from '../tinyYolov2/types';\nimport { BOX_ANCHORS, IOU_THRESHOLD, MEAN_RGB } from './const';\n\nexport class TinyFaceDetector extends TinyYolov2Base {\n constructor() {\n const config = {\n withSeparableConvs: true,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n anchors: BOX_ANCHORS,\n meanRgb: MEAN_RGB,\n isFirstLayerConv2d: true,\n filterSizes: [3, 16, 32, 64, 128, 256, 512],\n };\n\n super(config);\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_face_detector_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { AgeGenderNet } from '../ageGenderNet/AgeGenderNet';\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressionNet } from '../faceExpressionNet/FaceExpressionNet';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { FaceRecognitionNet } from '../faceRecognitionNet/FaceRecognitionNet';\nimport { SsdMobilenetv1 } from '../ssdMobilenetv1/SsdMobilenetv1';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetector } from '../tinyFaceDetector/TinyFaceDetector';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { ITinyYolov2Options, TinyYolov2 } from '../tinyYolov2/index';\n\nexport const nets = {\n ssdMobilenetv1: new SsdMobilenetv1(),\n tinyFaceDetector: new TinyFaceDetector(),\n tinyYolov2: new TinyYolov2(),\n faceLandmark68Net: new FaceLandmark68Net(),\n faceLandmark68TinyNet: new FaceLandmark68TinyNet(),\n faceRecognitionNet: new FaceRecognitionNet(),\n faceExpressionNet: new FaceExpressionNet(),\n ageGenderNet: new AgeGenderNet(),\n};\n\n/**\n * Attempts to detect all faces in an image using SSD Mobilenetv1 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see SsdMobilenetv1Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const ssdMobilenetv1 = (input: TNetInput, options: SsdMobilenetv1Options): Promise => nets.ssdMobilenetv1.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Face Detector.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyFaceDetectorOptions constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyFaceDetector = (input: TNetInput, options: TinyFaceDetectorOptions): Promise => nets.tinyFaceDetector.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Yolov2 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyYolov2Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyYolov2 = (input: TNetInput, options: ITinyYolov2Options): Promise => nets.tinyYolov2.locateFaces(input, options);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarks = (input: TNetInput): Promise => nets.faceLandmark68Net.detectLandmarks(input);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image\n * using a tinier version of the 68 point face landmark model, which is slightly\n * faster at inference, but also slightly less accurate.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarksTiny = (input: TNetInput): Promise => nets.faceLandmark68TinyNet.detectLandmarks(input);\n\n/**\n * Computes a 128 entry vector (face descriptor / face embeddings) from the face shown in an image,\n * which uniquely represents the features of that persons face. The computed face descriptor can\n * be used to measure the similarity between faces, by computing the euclidean distance of two\n * face descriptors.\n *\n * @param inputs The face image extracted from the aligned bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Face descriptor with 128 entries or array thereof in case of batch input.\n */\nexport const computeFaceDescriptor = (input: TNetInput): Promise => nets.faceRecognitionNet.computeFaceDescriptor(input);\n\n/**\n * Recognizes the facial expressions from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Facial expressions with corresponding probabilities or array thereof in case of batch input.\n */\nexport const recognizeFaceExpressions = (input: TNetInput): Promise => nets.faceExpressionNet.predictExpressions(input);\n\n/**\n * Predicts age and gender from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Predictions with age, gender and gender probability or array thereof in case of batch input.\n */\nexport const predictAgeAndGender = (input: TNetInput): Promise => nets.ageGenderNet.predictAgeAndGender(input);\n\nexport const loadSsdMobilenetv1Model = (url: string) => nets.ssdMobilenetv1.load(url);\nexport const loadTinyFaceDetectorModel = (url: string) => nets.tinyFaceDetector.load(url);\nexport const loadTinyYolov2Model = (url: string) => nets.tinyYolov2.load(url);\nexport const loadFaceLandmarkModel = (url: string) => nets.faceLandmark68Net.load(url);\nexport const loadFaceLandmarkTinyModel = (url: string) => nets.faceLandmark68TinyNet.load(url);\nexport const loadFaceRecognitionModel = (url: string) => nets.faceRecognitionNet.load(url);\nexport const loadFaceExpressionModel = (url: string) => nets.faceExpressionNet.load(url);\nexport const loadAgeGenderModel = (url: string) => nets.ageGenderNet.load(url);\n\n// backward compatibility\nexport const loadFaceDetectionModel = loadSsdMobilenetv1Model;\nexport const locateFaces = ssdMobilenetv1;\nexport const detectLandmarks = detectFaceLandmarks;\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderTask,\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\n\nexport class PredictFaceExpressionsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const faceExpressionsByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map(\n (parentResult, i) => extendWithFaceExpressions(parentResult, faceExpressionsByFace[i]),\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const faceExpressions = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithFaceExpressions(parentResult, faceExpressions);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictAllFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { TNetInput } from '../dom/index';\nimport { extendWithAge, WithAge } from '../factories/WithAge';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { extendWithGender, WithGender } from '../factories/WithGender';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllFaceExpressionsTask,\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class PredictAgeAndGenderTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase>[], TSource[]> {\n public async run(): Promise>[]> {\n const parentResults = await this.parentTask;\n\n const ageAndGenderByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map((parentResult, i) => {\n const { age, gender, genderProbability } = ageAndGenderByFace[i];\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n });\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase> | undefined, TSource | undefined> {\n public async run(): Promise> | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { age, gender, genderProbability } = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictAllAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDescriptor, WithFaceDescriptor } from '../factories/WithFaceDescriptor';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class ComputeFaceDescriptorsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n ) {\n super();\n }\n}\n\nexport class ComputeAllFaceDescriptorsTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const descriptors = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n (faces) => Promise.all(faces.map((face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise)),\n null,\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return descriptors.map((descriptor, i) => extendWithFaceDescriptor(parentResults[i], descriptor));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n\nexport class ComputeSingleFaceDescriptorTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n const descriptor = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise,\n null,\n // eslint-disable-next-line no-shadow\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return extendWithFaceDescriptor(parentResult, descriptor);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { TinyYolov2Options } from '../tinyYolov2/index';\nimport { ComposableTask } from './ComposableTask';\nimport { DetectAllFaceLandmarksTask, DetectSingleFaceLandmarksTask } from './DetectFaceLandmarksTasks';\nimport { nets } from './nets';\nimport { PredictAllAgeAndGenderTask, PredictSingleAgeAndGenderTask } from './PredictAgeAndGenderTask';\nimport { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from './PredictFaceExpressionsTask';\nimport { FaceDetectionOptions } from './types';\n\nexport class DetectFacesTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n ) {\n super();\n }\n}\n\nexport class DetectAllFacesTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const { input, options } = this;\n\n // eslint-disable-next-line no-nested-ternary\n const faceDetectionFunction = options instanceof TinyFaceDetectorOptions\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyFaceDetector.locateFaces(input, options)\n : (\n // eslint-disable-next-line no-nested-ternary\n options instanceof SsdMobilenetv1Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.ssdMobilenetv1.locateFaces(input, options)\n : (\n options instanceof TinyYolov2Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyYolov2.locateFaces(input, options)\n : null\n )\n );\n\n if (!faceDetectionFunction) {\n throw new Error('detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options');\n }\n\n return faceDetectionFunction(input);\n }\n\n private runAndExtendWithFaceDetections(): Promise[]> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise[]>(async (resolve) => {\n const detections = await this.run();\n resolve(detections.map((detection) => extendWithFaceDetection({}, detection)));\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectAllFaceLandmarksTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n}\n\nexport class DetectSingleFaceTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const faceDetections = await new DetectAllFacesTask(this.input, this.options);\n let faceDetectionWithHighestScore = faceDetections[0];\n faceDetections.forEach((faceDetection) => {\n if (faceDetection.score > faceDetectionWithHighestScore.score) {\n faceDetectionWithHighestScore = faceDetection;\n }\n });\n return faceDetectionWithHighestScore;\n }\n\n private runAndExtendWithFaceDetection(): Promise | undefined> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise | undefined>(async (resolve) => {\n const detection = await this.run();\n resolve(detection ? extendWithFaceDetection<{}>({}, detection) : undefined);\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectSingleFaceLandmarksTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n}\n", "import { TNetInput } from '../dom/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { DetectAllFacesTask, DetectSingleFaceTask } from './DetectFacesTasks';\nimport { FaceDetectionOptions } from './types';\n\nexport function detectSingleFace(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectSingleFaceTask {\n return new DetectSingleFaceTask(input, options);\n}\n\nexport function detectAllFaces(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectAllFacesTask {\n return new DetectAllFacesTask(input, options);\n}\n", "import { TNetInput } from '../dom/index';\nimport { WithFaceDescriptor, WithFaceDetection, WithFaceLandmarks } from '../factories/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';\nimport { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\nimport { detectAllFaces } from './detectFaces';\n\n// export allFaces API for backward compatibility\n\nexport async function allFacesSsdMobilenetv1(\n input: TNetInput,\n minConfidence?: number,\n): Promise>>[]> {\n return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport async function allFacesTinyYolov2(\n input: TNetInput,\n forwardParams: ITinyYolov2Options = {},\n): Promise>>[]> {\n return detectAllFaces(input, new TinyYolov2Options(forwardParams))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport const allFaces = allFacesSsdMobilenetv1;\n", "export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {\n if (arr1.length !== arr2.length) throw new Error('euclideanDistance: arr1.length !== arr2.length');\n\n const desc1 = Array.from(arr1);\n const desc2 = Array.from(arr2);\n\n return Math.sqrt(\n desc1\n .map((val, i) => val - desc2[i])\n .reduce((res, diff) => res + (diff ** 2), 0),\n );\n}\n", "import { FaceMatch } from '../classes/FaceMatch';\nimport { LabeledFaceDescriptors } from '../classes/LabeledFaceDescriptors';\nimport { euclideanDistance } from '../euclideanDistance';\nimport { WithFaceDescriptor } from '../factories/index';\n\nexport class FaceMatcher {\n private _labeledDescriptors: LabeledFaceDescriptors[]\n\n private _distanceThreshold: number\n\n constructor(\n inputs: LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>,\n distanceThreshold: number = 0.6,\n ) {\n this._distanceThreshold = distanceThreshold;\n\n const inputArray = Array.isArray(inputs) ? inputs : [inputs];\n\n if (!inputArray.length) {\n throw new Error('FaceRecognizer.constructor - expected atleast one input');\n }\n\n let count = 1;\n const createUniqueLabel = () => `person ${count++}`;\n\n this._labeledDescriptors = inputArray.map((desc) => {\n if (desc instanceof LabeledFaceDescriptors) {\n return desc;\n }\n\n if (desc instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc]);\n }\n\n if (desc.descriptor && desc.descriptor instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc.descriptor]);\n }\n\n throw new Error('FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>');\n });\n }\n\n public get labeledDescriptors(): LabeledFaceDescriptors[] { return this._labeledDescriptors; }\n\n public get distanceThreshold(): number { return this._distanceThreshold; }\n\n public computeMeanDistance(queryDescriptor: Float32Array, descriptors: Float32Array[]): number {\n return descriptors\n .map((d) => euclideanDistance(d, queryDescriptor))\n .reduce((d1, d2) => d1 + d2, 0)\n / (descriptors.length || 1);\n }\n\n public matchDescriptor(queryDescriptor: Float32Array): FaceMatch {\n return this.labeledDescriptors\n .map(({ descriptors, label }) => new FaceMatch(\n label,\n this.computeMeanDistance(queryDescriptor, descriptors),\n ))\n .reduce((best, curr) => (best.distance < curr.distance ? best : curr));\n }\n\n public findBestMatch(queryDescriptor: Float32Array): FaceMatch {\n const bestMatch = this.matchDescriptor(queryDescriptor);\n return bestMatch.distance < this.distanceThreshold\n ? bestMatch\n : new FaceMatch('unknown', bestMatch.distance);\n }\n\n public toJSON(): any {\n return {\n distanceThreshold: this.distanceThreshold,\n labeledDescriptors: this.labeledDescriptors.map((ld) => ld.toJSON()),\n };\n }\n\n public static fromJSON(json: any): FaceMatcher {\n const labeledDescriptors = json.labeledDescriptors\n .map((ld: any) => LabeledFaceDescriptors.fromJSON(ld));\n return new FaceMatcher(labeledDescriptors, json.distanceThreshold);\n }\n}\n", "import { TinyFaceDetector } from './TinyFaceDetector';\n\nexport * from './TinyFaceDetector';\nexport * from './TinyFaceDetectorOptions';\n\nexport function createTinyFaceDetector(weights: Float32Array) {\n const net = new TinyFaceDetector();\n net.extractWeights(weights);\n return net;\n}\n", "import { Dimensions, IDimensions } from './classes/index';\nimport { FaceDetection } from './classes/FaceDetection';\nimport { FaceLandmarks } from './classes/FaceLandmarks';\nimport { extendWithFaceDetection, isWithFaceDetection } from './factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, isWithFaceLandmarks } from './factories/WithFaceLandmarks';\n\nexport function resizeResults(results: T, dimensions: IDimensions): T {\n const { width, height } = new Dimensions(dimensions.width, dimensions.height);\n\n if (width <= 0 || height <= 0) {\n throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({ width, height })}`);\n }\n\n if (Array.isArray(results)) {\n // return results.map(obj => resizeResults(obj, { width, height })) as any as T\n return (results as Array).map((obj) => resizeResults(obj, { width, height } as IDimensions)) as any as T;\n }\n\n if (isWithFaceLandmarks(results)) {\n const resizedDetection = results.detection.forSize(width, height);\n const resizedLandmarks = results.unshiftedLandmarks.forSize(resizedDetection.box.width, resizedDetection.box.height);\n return extendWithFaceLandmarks(extendWithFaceDetection(results, resizedDetection), resizedLandmarks);\n }\n\n if (isWithFaceDetection(results)) {\n return extendWithFaceDetection(results, results.detection.forSize(width, height));\n }\n\n if (results instanceof FaceLandmarks || results instanceof FaceDetection) {\n return (results as any).forSize(width, height);\n }\n\n return results;\n}\n"], + "mappings": ";;;;;;;wmBAKA,kDACA,+DADA,UACA,YCNA,6CAAO,cACL,MAAO,OAAO,SAAW,UACpB,IACA,MAAO,KAAW,aAGlB,MAAO,UAAY,aAAe,CAAC,CAAC,QAAQ,WCNnD,OAAoB,OCApB,qRCEO,YACL,EACA,EACA,EAAoB,IAUpB,GARA,EAAI,YAEJ,EAAO,MAAM,GAAG,QAAQ,CAAC,CAAE,IAAG,KAAK,KACjC,GAAM,GAAO,EAAO,GACpB,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,KAGZ,GACF,GAAM,GAAO,EAAO,EAAO,OAAS,GAC9B,EAAK,EAAO,GAClB,GAAI,CAAC,GAAQ,CAAC,EACZ,OAGF,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,EAAG,EAAG,GAGtB,EAAI,SC1BN,2RAAA,OAAoB,OCApB,YAYE,YAAY,EAAe,GACzB,GAAI,CAAC,GAAc,IAAU,CAAC,GAAc,GAC1C,KAAM,IAAI,OAAM,wFAAwF,KAAK,UAAU,CAAE,QAAO,cAGlI,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,QAEnC,UACL,MAAO,IAAI,GAAW,EAAI,KAAK,MAAO,EAAI,KAAK,UDrB5C,YAAkB,EAAa,GACpC,MAAO,aAAqB,YAAU,EAAO,MAAM,SAAW,EAGzD,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,WAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAiB,GACtB,MAAO,GAAM,GAAM,EAGd,YAAgB,GACrB,MAAO,GAAM,GAAM,EAGd,YAAe,EAAa,EAAe,GAChD,GAAM,GAAI,IAAM,EAChB,MAAO,MAAK,MAAM,EAAM,GAAK,EAGxB,YAAsB,GAC3B,MAAO,IAAO,EAAI,OAAS,EAAI,OAG1B,YAAmC,CAAE,QAAO,UAAuB,GACxE,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,IAAI,GAAW,KAAK,MAAM,EAAQ,GAAQ,KAAK,MAAM,EAAS,IAGhE,YAAwB,GAC7B,MAAO,GAAI,OAAO,CAAC,EAAK,IAAO,EAAI,IAAI,GAAK,GAAI,GAAM,EAAG,IACtD,IAAI,GAAI,GAAM,EAAI,OAAQ,EAAI,SAG5B,YAAe,EAAa,EAAe,GAChD,MAAO,OAAM,GAAK,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,EAAS,EAAI,GAGhD,YAAuB,GAC5B,MAAO,CAAC,CAAC,GAAQ,IAAQ,UAAc,IAAQ,WAAc,CAAC,OAAO,MAAM,IAAQ,IAAQ,EAGtF,YAA4B,GACjC,MAAO,IAAc,IAAQ,GAAO,GAAK,GAAO,EE7DlD,YAUE,YAAY,EAAW,GACrB,KAAK,GAAK,EACV,KAAK,GAAK,KAGR,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,GAEvB,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,MACL,MAAO,IAAI,GAAM,KAAK,IAAI,KAAK,GAAI,KAAK,IAAI,KAAK,IAG5C,YACL,MAAO,MAAK,KAAM,KAAK,GAAK,EAAM,KAAK,GAAK,GAGvC,QACL,MAAO,IAAI,GAAM,KAAK,MAAM,KAAK,GAAI,KAAK,MAAM,KAAK,MC5CzD,kBAOgB,QAAO,GACnB,MAAO,CAAC,CAAC,GAAQ,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,MAAO,EAAK,QAAQ,MAAM,UAGrD,kBAAiB,EAAU,EAAgB,EAAmC,IAC1F,GAAI,CAAC,EAAI,OAAO,GACd,KAAM,IAAI,OAAM,GAAG,oBAAyB,KAAK,UAAU,2DAG7D,GAAI,CAAC,GAA4B,GAAI,MAAQ,GAAK,EAAI,OAAS,GAC7D,KAAM,IAAI,OAAM,GAAG,cAAmB,EAAI,sBAAsB,EAAI,oCAYxE,YAAY,EAA4B,EAAmC,IACzE,GAAM,GAAO,GAAQ,GAEf,EAAS,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAO,EAAI,QAAQ,MAAM,IAC1D,EAAS,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAAQ,MAAM,IAE3D,GAAI,CAAC,GAAU,CAAC,EACd,KAAM,IAAI,OAAM,2EAA2E,KAAK,UAAU,MAG5G,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,EAC1B,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAC9B,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAQ,EAAI,KAAM,EAAI,OAAS,EAAI,KAE/D,EAAI,iBAAiB,CACnB,IAAG,IAAG,QAAO,UACZ,kBAAmB,GAEtB,KAAK,GAAK,EACV,KAAK,GAAK,EACV,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,MAE1B,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,WAE/B,QAAiB,MAAO,MAAK,KAE7B,OAAgB,MAAO,MAAK,KAE5B,SAAkB,MAAO,MAAK,EAAI,KAAK,SAEvC,UAAmB,MAAO,MAAK,EAAI,KAAK,UAExC,QAAiB,MAAO,MAAK,MAAQ,KAAK,UAE1C,WAAmB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,QAEpD,YAAoB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAEtD,cAAsB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,WAEvD,eAAuB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAE7D,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,WACL,GAAI,CACF,IAAG,IAAG,QAAO,UACX,KACE,EAAO,KAAK,IAAI,EAAQ,GAC9B,MAAI,GAAQ,GACV,IAAM,EAAO,EACb,GAAS,GAEP,EAAS,GACX,IAAM,EAAO,EACb,GAAU,GAGL,GAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QAAQ,GACb,GAAM,GAAS,GAAa,GAAM,EAAkB,MAAQ,EACtD,EAAS,GAAa,GAAM,EAAkB,OAAS,EAC7D,MAAO,IAAI,GAAI,CACb,EAAG,KAAK,EAAI,EACZ,EAAG,KAAK,EAAI,EACZ,MAAO,KAAK,MAAQ,EACpB,OAAQ,KAAK,OAAS,IAInB,IAAI,EAAc,GACvB,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAC5B,KAAK,EAAK,EAAO,EACjB,KAAK,EAAK,EAAO,EACjB,KAAK,MAAQ,EACb,KAAK,OAAS,GAEhB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,mBAAmB,EAAkB,GAC1C,GAAM,CACJ,IAAG,IAAG,QAAO,UACX,KACE,EAAW,KAAK,IAAI,EAAG,GACvB,EAAW,KAAK,IAAI,EAAG,GAEvB,EAAW,EAAQ,EACnB,EAAY,EAAS,EACrB,EAAe,KAAK,IAAI,EAAU,EAAW,GAC7C,EAAgB,KAAK,IAAI,EAAW,EAAY,GAEtD,MAAQ,IAAI,GAAI,CACd,EAAG,EAAU,EAAG,EAAU,MAAO,EAAc,OAAQ,IACrD,QAGC,MAAM,EAAY,GACvB,GAAM,CAAE,QAAO,UAAW,KACpB,EAAI,KAAK,EAAI,EACb,EAAI,KAAK,EAAI,EAEnB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,aAAa,EAAqB,GACvC,GAAM,GAAI,KAAK,MAAQ,EACjB,EAAI,KAAK,OAAS,EAElB,EAAK,EACL,EAAK,EACP,EAAM,EACN,EAAM,EAEN,EAAI,KAAK,KACT,EAAI,KAAK,IACT,EAAK,KAAK,MACV,EAAK,KAAK,OAEd,MAAI,GAAK,GACP,GAAM,CAAC,EAAK,EAAa,EACzB,EAAK,GAEH,EAAK,GACP,GAAM,CAAC,EAAK,EAAc,EAC1B,EAAK,GAEH,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAEF,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAGC,CACL,KAAI,MAAK,KAAI,MAAK,IAAG,KAAI,IAAG,KAAI,IAAG,KAIhC,UAAU,GACf,MAAO,IAAI,GAAI,CACb,KAAM,KAAK,KAAQ,EAAO,KAAO,KAAK,MACtC,IAAK,KAAK,IAAO,EAAO,IAAM,KAAK,OACnC,MAAO,KAAK,MAAS,EAAO,MAAQ,KAAK,MACzC,OAAQ,KAAK,OAAU,EAAO,OAAS,KAAK,SAC3C,WAAW,UC9MlB,oBASiC,GAC/B,YAAY,EAAc,EAAa,EAAe,EAAgB,EAAmC,IACvG,MAAM,CACJ,OAAM,MAAK,QAAO,UACjB,KCbP,aAeE,YACE,EACA,EACA,EACA,EACA,GAEA,KAAK,WAAa,GAAI,GAAW,EAAU,MAAO,EAAU,QAC5D,KAAK,OAAS,EACd,KAAK,YAAc,EACnB,KAAK,WAAa,EAClB,KAAK,KAAO,GAAI,GAAI,GAAa,QAAQ,KAAK,eAGrC,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,eAEnC,aAAsB,MAAO,MAAK,cAElC,OAAa,MAAO,MAAK,QAEzB,aAA0B,MAAO,MAAK,cAEtC,cAAuB,MAAO,MAAK,UAAU,SAE7C,eAAwB,MAAO,MAAK,UAAU,UAE9C,eAAqB,MAAO,IAAI,GAAI,KAAK,MAAM,QAAQ,KAAK,UAAU,WAE1E,QAAQ,EAAe,GAC5B,MAAO,IAAI,IACT,KAAK,MACL,KAAK,WACL,KAAK,UACL,KAAK,YACL,CAAE,QAAO,aCnDf,mBAUmC,IACjC,YACE,EACA,EACA,GAEA,MAAM,EAAO,EAAO,GAAI,EAAa,GAGhC,QAAQ,EAAe,GAC5B,GAAM,CAAE,QAAO,cAAa,aAAc,MAAM,QAAQ,EAAO,GAC/D,MAAO,IAAI,GAAc,EAAO,EAAa,KCnB1C,YAAa,EAAW,EAAW,EAAiB,IACzD,GAAM,GAAQ,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,MAAO,EAAK,OAAS,KAAK,IAAI,EAAK,KAAM,EAAK,OAClF,EAAS,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,OAAQ,EAAK,QAAU,KAAK,IAAI,EAAK,IAAK,EAAK,MACpF,EAAe,EAAQ,EAE7B,MAAO,GACH,EAAgB,GAAK,KAAO,EAAK,KAAO,GACxC,EAAe,KAAK,IAAI,EAAK,KAAM,EAAK,MCPvC,YAAiB,GACtB,GAAM,GAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAExD,MAAO,IAAI,IAAY,EAAM,EAAM,EAAM,GCPpC,YACL,EACA,EACA,EACA,EAAiB,IAEjB,GAAI,GAAuB,EACxB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAC/B,IAAI,AAAC,GAAM,EAAE,UAEV,EAAiB,GAEvB,KAAO,EAAqB,OAAS,IACnC,GAAM,GAAO,EAAqB,MAClC,EAAK,KAAK,GAEV,GAAM,GAAU,EAEV,EAAoB,GAC1B,OAAS,GAAI,EAAG,EAAI,EAAQ,OAAQ,KAClC,GAAM,GAAM,EAAQ,GAEd,EAAU,EAAM,GAChB,EAAS,EAAM,GAErB,EAAQ,KAAK,GAAI,EAAS,EAAQ,IAGpC,EAAuB,EAAqB,OAC1C,CAAC,EAAG,IAAM,EAAQ,IAAM,GAI5B,MAAO,GCrCT,OAAoB,OAEb,YAAmB,EAAgB,GACxC,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAG,EAAG,GAAK,EACZ,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAU,AAAG,UAAO,CAAC,EAAO,EAAO,GAAQ,GAEjD,MAAO,AAAG,QAAI,EAAG,KCVrB,OAAoB,OAUb,YACL,EACA,EAAyB,IAEzB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAQ,GAAS,EAAU,MAAM,MAAM,GAC9C,GAAI,IAAW,EACb,MAAO,GAGT,GAAM,GAAU,KAAK,IAAI,EAAS,GAC5B,EAAgB,KAAK,MAAM,EAAW,GAAgB,GAAM,IAC5D,EAAc,EAAS,EAAQ,EAAI,EAEnC,EAAsB,AAAC,IAC3B,GAAM,GAAqB,EAAU,MAAM,QAC3C,SAAmB,GAAe,EAC3B,AAAG,QAAK,EAAoB,EAAG,YAGlC,EAAsB,EAAoB,GAC1C,EAAyB,EAAW,EAAoB,MAAM,GAM9D,EAAiB,CAJM,GAAiB,EAC1C,EAAoB,GACpB,KAIF,EACA,GAEC,OAAO,AAAC,GAAM,CAAC,CAAC,GAEhB,IAAI,AAAC,GAAiB,AAAG,QAAK,EAAG,YACpC,MAAO,AAAG,WAAO,EAAgB,KC7C9B,YAAsB,GAC3B,GAAM,GAAQ,EAAW,QACzB,OAAS,GAAI,EAAM,OAAS,EAAG,EAAI,EAAG,KACpC,GAAM,GAAI,KAAK,MAAM,KAAK,SAAY,GAAI,IACpC,EAAI,EAAM,GAChB,EAAM,GAAK,EAAM,GACjB,EAAM,GAAK,EAEb,MAAO,GCDF,YAAiB,GACtB,MAAO,GAAK,GAAI,KAAK,IAAI,CAAC,IAGrB,YAAwB,GAC7B,MAAO,MAAK,IAAI,EAAK,GAAI,ICZ3B,oBAS0B,GACxB,YAAY,EAAW,EAAW,EAAe,EAAgB,EAAmC,IAClG,MAAM,CACJ,IAAG,IAAG,QAAO,UACZ,KCHP,GAAM,IAAO,GACP,GAAO,IACP,GAAW,IAZjB,QA0BE,YACE,EACA,EACA,EAAe,GAAI,GAAM,EAAG,IAE5B,GAAM,CAAE,QAAO,UAAW,EAC1B,KAAK,SAAW,GAAI,GAAW,EAAO,GACtC,KAAK,OAAS,EACd,KAAK,WAAa,EAA8B,IAC9C,AAAC,GAAO,EAAG,IAAI,GAAI,GAAM,EAAO,IAAS,IAAI,OAItC,SAAiB,MAAO,IAAI,GAAM,KAAK,OAAO,EAAG,KAAK,OAAO,MAE7D,cAAuB,MAAO,MAAK,SAAS,SAE5C,eAAwB,MAAO,MAAK,SAAS,UAE7C,aAAuB,MAAO,MAAK,cAEnC,qBACT,MAAO,MAAK,WAAW,IACrB,AAAC,GAAO,EAAG,IAAI,KAAK,QAAQ,IAAI,GAAI,GAAM,KAAK,WAAY,KAAK,eAI7D,QAAiC,EAAe,GACrD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,CAAE,QAAO,WAIN,QAAiC,EAAW,GACjD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,KAAK,SACL,GAAI,GAAM,EAAG,IAIV,aAAsC,GAC3C,MAAO,MAAK,QAAQ,EAAG,EAAG,EAAG,GAcxB,MACL,EACA,EAAkE,IAElE,GAAI,GACF,GAAM,GAAM,YAAqB,GAC7B,EAAU,IAAI,QACd,GAAI,GAAI,GAEZ,MAAO,MAAK,QAAQ,EAAI,EAAG,EAAI,GAAG,MAAM,KAAM,GAGhD,GAAM,CAAE,mBAAkB,iBAAkB,CAAE,iBAAkB,GAAO,cAAe,MAAQ,GAE9F,MAAI,GACK,KAAK,YAGP,KAAK,aAAa,GAGnB,YACN,GAAM,GAAU,KAAK,2BAEf,CAAC,EAAe,EAAgB,GAAe,EAC/C,EAAc,AAAC,GAAc,EAAY,IAAI,GAAI,YACjD,EAAkB,GAAY,GAAiB,EAAY,IAAmB,EAE9E,EAAO,KAAK,MAAM,EAAiB,IAEnC,EAAW,GAAe,GAE1B,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAChD,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAEtD,MAAO,IAAI,IAAK,EAAG,EAAG,KAAK,IAAI,EAAM,KAAK,WAAa,GAAI,KAAK,IAAI,EAAM,KAAK,YAAc,IAGvF,aAAa,GACnB,GAAM,GAAM,GAAQ,KAAK,WACzB,MAAO,GAAI,IAAI,EAAI,MAAQ,EAAS,EAAI,OAAS,GAGzC,2BACR,KAAM,IAAI,OAAM,4DC/HpB,oBAIoC,GACxB,2BACR,GAAM,GAAM,KAAK,UACjB,MAAO,CACL,EAAI,GACJ,EAAI,GACJ,GAAe,CAAC,EAAI,GAAI,EAAI,QCVlC,oBAIqC,GAC5B,gBACL,MAAO,MAAK,UAAU,MAAM,EAAG,IAG1B,iBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,kBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,UACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,aACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,cACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,WACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAGxB,2BACR,MAAO,CACL,KAAK,aACL,KAAK,cACL,KAAK,YACL,IAAI,MCtCV,aAYE,YAAY,EAAe,GACzB,KAAK,OAAS,EACd,KAAK,UAAY,KAGR,SAAkB,MAAO,MAAK,UAE9B,YAAqB,MAAO,MAAK,UAErC,SAAS,EAAwB,IACtC,MAAO,GAAG,KAAK,QAAQ,EAAe,KAAK,GAAM,KAAK,aAAe,OCtBzE,oBAKgC,SAChB,yBAAwB,EAAU,GAG9C,GAFA,EAAI,iBAAiB,EAAK,GAEtB,CAAC,GAAc,EAAI,OACrB,KAAM,IAAI,OAAM,GAAG,gCAAqC,EAAI,yBAMhE,YAAY,EAAiC,GAC3C,MAAM,GACN,KAAK,OAAS,KAGL,SAAkB,MAAO,MAAK,SCrB3C,aAKE,YAAY,EAAe,GACzB,GAAM,MAAO,IAAU,SACrB,KAAM,IAAI,OAAM,sEAGlB,GAAI,CAAC,MAAM,QAAQ,IAAgB,EAAY,KAAK,AAAC,GAAS,CAAE,aAAgB,gBAC9E,KAAM,IAAI,OAAM,4FAGlB,KAAK,OAAS,EACd,KAAK,aAAe,KAGX,SAAkB,MAAO,MAAK,UAE9B,eAAgC,MAAO,MAAK,aAEhD,SACL,MAAO,CACL,MAAO,KAAK,MACZ,YAAa,KAAK,YAAY,IAAI,AAAC,GAAM,MAAM,KAAK,WAI1C,UAAS,GACrB,GAAM,GAAc,EAAK,YAAY,IAAI,AAAC,GAAW,GAAI,cAAa,IACtE,MAAO,IAAI,IAAuB,EAAK,MAAO,KC/BlD,oBAKkC,UAClB,2BAA0B,EAAU,GAGhD,GAFA,GAAW,wBAAwB,EAAK,GAGtC,CAAC,GAAmB,EAAI,QACrB,CAAC,GAAmB,EAAI,YAE3B,KAAM,IAAI,OAAM,GAAG,kCAAuC,EAAI,eAAe,EAAI,6CAQrF,YAAY,EAAiC,EAAe,EAAe,GACzE,MAAM,EAAK,GACX,KAAK,OAAS,EACd,KAAK,YAAc,KAGV,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,cCvBzC,YAA6B,GAClC,MAAO,GAAI,oBAAqB,GAG3B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,cCdf,cACL,GAAM,GAAQ,OAAO,MACrB,GAAI,CAAC,EAAO,KAAM,IAAI,OAAM,gEAE5B,GAAM,GAAW,KACf,KAAM,IAAI,OAAM,gEAGlB,MAAO,CACL,OAAQ,kBACR,yBACA,MAAO,iBACP,UACA,MAAO,iBACP,oBAAqB,IAAM,SAAS,cAAc,UAClD,mBAAoB,IAAM,SAAS,cAAc,OACjD,QACA,YCjBG,YAA0B,GAC/B,GAAI,GAAiB,GAErB,GAAI,CAAC,EACH,IAEE,EAAa,oBACN,GACP,EAAiB,EAAI,WAYzB,MAAO,CACL,SATe,EACb,AAAC,GAAqB,GAAI,SAAgB,CAAC,EAAS,KACpD,EAAG,SAAS,EAAU,CAAC,EAAU,IAAoB,EAAM,EAAO,GAAO,EAAQ,MAEjF,KACA,KAAM,IAAI,OAAM,qEAAqE,OCfpF,cAEL,GAAM,GAAS,OAAO,QAAa,OAAO,kBACpC,EAAQ,OAAO,OAAS,OAAO,iBAE/B,EAAsB,KAC1B,GAAI,EAAQ,MAAO,IAAI,GACvB,KAAM,IAAI,OAAM,+EAGZ,EAAqB,KACzB,GAAI,EAAO,MAAO,IAAI,GACtB,KAAM,IAAI,OAAM,6EAGZ,EAAQ,OAAO,MAGf,EAAa,KAEnB,MAAO,CACL,OAAQ,GAAU,QAClB,yBAA0B,OAAO,0BAA4B,QAC7D,MAAO,GAAS,QAChB,UAAW,OAAO,WAAa,QAC/B,MAAO,OAAO,kBAAoB,QAClC,sBACA,qBACA,WACG,GCjCA,cACL,MAAO,OAAO,SAAW,UACpB,MAAO,WAAa,aACpB,MAAO,mBAAqB,aAC5B,MAAO,oBAAsB,aAC7B,MAAO,mBAAqB,aAC5B,MAAO,YAAc,aACrB,MAAO,2BAA6B,YCH3C,OAAyB,QAGrB,EAEJ,cACE,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,yEAElB,MAAO,GAGT,YAAgB,GACd,EAAc,EAGhB,cAGE,MAAI,MAAoB,GAAO,MAC3B,cAAmB,GAAO,MACvB,KAGT,YAAqB,GAKnB,GAJK,GACH,KAGE,CAAC,EACH,KAAM,IAAI,OAAM,8EAGlB,GAAM,CAAE,SAAS,EAAY,OAAQ,QAAQ,EAAY,OAAU,EACnE,EAAY,OAAS,EACrB,EAAY,MAAQ,EACpB,EAAY,oBAAsB,EAAI,qBAAwB,KAAM,GAAI,IACxE,EAAY,mBAAqB,EAAI,oBAAuB,KAAM,GAAI,IAEtE,EAAY,UAAY,EAAI,WAAa,EAAY,UACrD,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,SAAW,EAAI,UAAY,EAAY,SAG9C,GAAM,GAAM,CACjB,UACA,UACA,cACA,oBACA,oBACA,mBACA,eACA,aACA,sBAGF,KC3DO,YAAsB,GAC3B,MAAI,CAAC,EAAI,YAAc,MAAO,IAAQ,SAC7B,SAAS,eAAe,GAE1B,ECHF,WAA6B,GAClC,GAAM,CAAE,SAAQ,4BAA6B,EAAI,SAEjD,GAAI,YAAqB,GACvB,MAAO,GAGT,GAAM,GAAS,GAAa,GAE5B,GAAI,CAAE,aAAkB,IACtB,KAAM,IAAI,OAAM,kEAGlB,GAAM,GAAM,EAAO,WAAW,MAC9B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,GCfF,GAAK,IAAL,UAAK,GAEV,WAAW,WAEX,YAAY,YAEZ,cAAc,cAEd,eAAe,iBARL,aANZ,aAuCE,YAAY,EAAiC,IAC3C,GAAM,CACJ,iBAAgB,kBAAiB,YAAW,WAAU,YAAW,WAC/D,EACJ,KAAK,eAAiB,GAAkB,GAAe,SACvD,KAAK,gBAAkB,GAAmB,qBAC1C,KAAK,UAAY,GAAa,yBAC9B,KAAK,SAAW,GAAY,GAC5B,KAAK,UAAY,GAAa,UAC9B,KAAK,QAAU,GAAW,IAhD9B,SA2DE,YACE,EACA,EACA,EAAiC,IAGjC,KAAK,KAAO,MAAO,IAAS,SACxB,CAAC,GACA,YAAgB,IAAgB,EAAK,KAAO,EACjD,KAAK,OAAS,EACd,KAAK,QAAU,GAAI,IAAqB,GAG1C,aAAa,GACX,GAAM,CAAE,WAAY,KAAK,QACzB,MAAO,MAAK,KAAK,IAAI,AAAC,GAAM,EAAI,YAAY,GAAG,OAAO,OAAO,CAAC,EAAI,IAAQ,EAAK,EAAK,EAAK,EAAK,GAAM,EAAI,EAG1G,gBACE,GAAM,CAAE,WAAU,WAAY,KAAK,QACnC,MAAO,MAAK,KAAK,OAAS,EAAY,EAAI,EAG5C,aAAa,EAA+B,GAC1C,GAAM,CAAE,kBAAmB,KAAK,QAC1B,EAAc,IAAmB,GAAe,cAAgB,IAAmB,GAAe,UAClG,EAAa,IAAmB,GAAe,aAAe,IAAmB,GAAe,aAEhG,EAAiB,KAAK,aAAa,GACnC,EAAkB,KAAK,gBACvB,EAAK,EAAc,KAAK,OAAO,EAAI,EAAiB,KAAK,OAAO,EAChE,EAAI,EAAa,KAAK,OAAO,EAAI,EAAkB,KAAK,OAAO,EAGrE,GAAI,GACF,GAAM,CAAE,QAAO,UAAW,EACpB,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAQ,GAAiB,GACrD,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAS,GAAkB,GAC7D,MAAO,CAAE,EAAG,EAAM,EAAG,GAEvB,MAAO,CAAE,IAAG,KAGd,KAAK,GACH,GAAM,GAAS,GAAa,GACtB,EAAM,EAAoB,GAE1B,CACJ,kBAAiB,YAAW,WAAU,YAAW,WAC/C,KAAK,QAET,EAAI,KAAO,GAAG,OAAc,IAC5B,GAAM,GAAe,KAAK,aAAa,GACjC,EAAa,KAAK,gBAExB,EAAI,UAAY,EAChB,GAAM,GAAY,KAAK,aAAa,EAAK,GACzC,EAAI,SAAS,EAAU,EAAG,EAAU,EAAG,EAAc,GAErD,EAAI,UAAY,EAChB,KAAK,KAAK,QAAQ,CAAC,EAAU,KAC3B,GAAM,GAAI,EAAU,EAAU,EACxB,EAAI,EAAU,EAAU,EAAM,GAAI,GAAK,EAC7C,EAAI,SAAS,EAAU,EAAG,OC1HhC,aAuBE,YAAY,EAA2B,IACrC,GAAM,CACJ,WAAU,YAAW,QAAO,oBAC1B,EACJ,KAAK,SAAW,GAAY,qBAC5B,KAAK,UAAY,GAAa,EAC9B,KAAK,MAAQ,EAEb,GAAM,GAA0B,CAC9B,eAAgB,GAAe,YAC/B,gBAAiB,KAAK,UAExB,KAAK,iBAAmB,GAAI,IAAqB,IAAK,KAA4B,MAnCtF,SA4CE,YACE,EACA,EAA2B,IAE3B,KAAK,IAAM,GAAI,GAAI,GACnB,KAAK,QAAU,GAAI,IAAe,GAGpC,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CAAE,WAAU,aAAc,KAAK,QAE/B,CACJ,IAAG,IAAG,QAAO,UACX,KAAK,IACT,EAAI,YAAc,EAClB,EAAI,UAAY,EAChB,EAAI,WAAW,EAAG,EAAG,EAAO,GAE5B,GAAM,CAAE,SAAU,KAAK,QACvB,AAAI,GACF,GAAI,IAAc,CAAC,GAAQ,CAAE,EAAG,EAAK,EAAY,EAAI,KAAK,KAAK,QAAQ,kBAAkB,KAAK,KC1D7F,YACL,EACA,GAIA,AAFwB,OAAM,QAAQ,GAAc,EAAa,CAAC,IAElD,QAAQ,AAAC,IAEvB,GAAM,GAAQ,YAAe,GACzB,EAAI,MACH,GAAoB,GAAO,EAAI,UAAU,MAAQ,OAGhD,EAAM,YAAe,GACvB,EAAI,IACH,GAAoB,GAAO,EAAI,UAAU,IAAM,GAAI,GAAI,GAEtD,EAAQ,EAAQ,GAAG,GAAM,KAAW,OAC1C,GAAI,IAAQ,EAAK,CAAE,UAAS,KAAK,KC1BrC,OAAoB,OCEb,YAAuB,GAC5B,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAQ,aAAiB,IAAS,EAAM,UAClC,YAAiB,IAAS,EAAM,YAAc,ECH/C,YAA0B,GAE/B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,GAAI,YAAiB,GAAI,SAAS,QAAU,GAAc,GACxD,MAAO,GAAQ,MAGjB,WAAiB,GACf,AAAI,CAAC,EAAE,eAEP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAO,IAGT,WAAgB,GACd,AAAI,CAAC,EAAE,eACP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAQ,IAGV,EAAM,iBAAiB,OAAQ,GAC/B,EAAM,iBAAiB,QAAS,KCxB7B,YAAuB,GAC5B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,AAAM,YAAe,OAAO,EAAO,GAAI,OAAM,qDAC7C,GAAM,GAAS,GAAI,YACnB,EAAO,OAAS,KACd,AAAI,MAAO,GAAO,QAAW,UAAU,EAAO,GAAI,OAAM,qEACxD,GAAM,GAAM,EAAI,SAAS,qBACzB,EAAI,OAAS,IAAM,EAAQ,GAC3B,EAAI,QAAU,EACd,EAAI,IAAM,EAAO,QAEnB,EAAO,QAAU,EACjB,EAAO,cAAc,KCXlB,YAA4B,GACjC,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAI,aAAiB,GACZ,GAAI,GAAW,EAAM,aAAc,EAAM,eAE9C,YAAiB,GACZ,GAAI,GAAW,EAAM,WAAY,EAAM,aAEzC,GAAI,GAAW,EAAM,MAAO,EAAM,QCNpC,YAAsB,CAAE,QAAO,WACpC,GAAM,CAAE,uBAAwB,EAAI,SAC9B,EAAS,IACf,SAAO,MAAQ,EACf,EAAO,OAAS,EACT,EAGF,YAA+B,EAAwD,GAC5F,GAAM,CAAE,aAAc,EAAI,SAE1B,GAAI,CAAE,aAAiB,KAAc,CAAC,GAAc,GAClD,KAAM,IAAI,OAAM,8DAGlB,GAAM,CAAE,QAAO,UAAW,GAAQ,GAAmB,GAC/C,EAAS,GAAa,CAAE,QAAO,WAErC,MAAI,aAAiB,GACnB,EAAoB,GAAQ,aAAa,EAAO,EAAG,GAEnD,EAAoB,GAAQ,UAAU,EAAO,EAAG,EAAG,EAAO,GAErD,EC7BT,OAAoB,OAKpB,kBACE,EACA,GAEA,GAAM,GAAe,GAAU,EAAI,SAAS,sBAEtC,CAAC,EAAQ,EAAO,GAAe,EAAU,MAAM,MAAM,EAAW,GAAa,EAAI,GACjF,EAAc,AAAG,QAAK,IAAM,EAAU,KAAK,EAAQ,EAAO,GAAa,SAC7E,YAAM,AAAG,YAAQ,SAAS,EAAa,GAEvC,EAAY,UAEL,ECfF,YAAwB,GAC7B,GAAM,CAAE,QAAO,SAAQ,SAAU,EAAI,SAErC,MAAO,aAAiB,IACnB,YAAiB,IACjB,YAAiB,GCPxB,MAAoB,OCKb,YAAuB,EAA6C,EAAmB,EAAuB,IACnH,GAAM,CAAE,QAAO,UAAW,EAAI,SAE9B,GAAI,CAAE,aAAiB,IAAS,YAAiB,IAC/C,KAAM,IAAI,OAAM,4EAGlB,GAAM,GAAO,GAAmB,GAC1B,EAAQ,EAAY,KAAK,IAAI,EAAK,OAAQ,EAAK,OAC/C,EAAQ,EAAQ,EAAK,MACrB,EAAS,EAAQ,EAAK,OAEtB,EAAe,GAAa,CAAE,MAAO,EAAW,OAAQ,IACxD,EAAc,YAAiB,GAAS,EAAQ,GAAsB,GAEtE,EAAS,KAAK,IAAI,EAAQ,GAAU,EACpC,EAAK,GAAe,EAAQ,EAAS,EAAS,EAC9C,EAAK,GAAe,EAAS,EAAQ,EAAS,EACpD,SAAoB,GAAc,UAAU,EAAa,EAAI,EAAI,EAAO,GAEjE,EDzBT,aAyBE,YACE,EACA,EAA6B,IAdvB,mBAAkD,GAElD,eAAiC,GAIjC,wBAA8B,GAE9B,sBAA+B,GAQrC,GAAI,CAAC,MAAM,QAAQ,GACjB,KAAM,IAAI,OAAM,4HAA4H,KAG9I,KAAK,mBAAqB,EAC1B,KAAK,WAAa,EAAO,OAEzB,EAAO,QAAQ,CAAC,EAAO,KACrB,GAAI,GAAW,IACb,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAO,EAAM,MACnC,OAGF,GAAI,EAAW,IACb,GAAM,GAAa,EAAc,MAAM,GACvC,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,yCAAyC,8CAG3D,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAQ,EAAc,MAAM,MAAM,GACxD,OAGF,GAAM,GAAU,YAAyB,GAAI,SAAS,OAAS,EAAQ,GAAsB,GAC7F,KAAK,UAAU,GAAO,EACtB,KAAK,iBAAiB,GAAO,CAAC,EAAO,OAAQ,EAAO,MAAO,QAIpD,gBACT,MAAO,MAAK,iBAGH,YACT,MAAO,MAAK,aAGH,gBACT,MAAO,MAAK,UAAY,GAAK,KAAK,sBAGzB,aACT,MAAO,MAAK,cAGH,mBACT,MAAO,MAAK,oBAGH,aACT,MAAO,MAAK,cAGH,2BACT,MAAO,IAAM,KAAK,UAAW,EAAG,GAAG,IACjC,CAAC,EAAG,IAAa,KAAK,2BAA2B,IAI9C,SAAS,GACd,MAAO,MAAK,SAAS,IAAa,KAAK,aAAa,GAG/C,mBAAmB,GACxB,MAAO,MAAK,iBAAiB,GAGxB,eAAe,GACpB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,cAAc,GACnB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,2BAA2B,GAChC,GAAI,MAAO,MAAK,WAAc,SAC5B,KAAM,IAAI,OAAM,yFAGlB,GAAM,GAAQ,KAAK,cAAc,GAC3B,EAAS,KAAK,eAAe,GACnC,MAAO,IAA0B,CAAE,QAAO,UAAU,KAAK,WAYpD,cAAc,EAAmB,EAA0B,IAChE,YAAK,WAAa,EAEX,AAAG,OAAK,KACb,GAAM,GAAe,GAAM,KAAK,UAAW,EAAG,GAAG,IAAI,AAAC,IACpD,GAAM,GAAQ,KAAK,SAAS,GAE5B,GAAI,YAAoB,WAEtB,GAAI,GAAY,EAAW,GAAS,EAAQ,EAAM,aAElD,SAAY,GAAY,EAAW,GAE/B,GAAU,MAAM,KAAO,GAAa,EAAU,MAAM,KAAO,IAC7D,GAAY,AAAG,QAAM,eAAe,EAAW,CAAC,EAAW,KAGtD,EAAU,KAAK,EAAW,EAAW,GAG9C,GAAI,YAAiB,GAAI,SAAS,OAChC,MAAO,AAAG,WAAQ,WAAW,GAAc,EAAO,EAAW,IAG/D,KAAM,IAAI,OAAM,+BAA+B,8FAAqG,OAOtJ,MAHoB,AAAG,SAAM,EAAa,IAAI,AAAC,GAAM,AAAG,OAAK,EAAG,aAAa,KAAK,KAAK,UAAW,EAAW,EAAW,OE3I9H,iBAAiC,GAC/B,GAAI,YAAkB,IACpB,MAAO,GAGT,GAAM,GAAgB,MAAM,QAAQ,GAChC,EACA,CAAC,GAEL,GAAI,CAAC,EAAc,OACjB,KAAM,IAAI,OAAM,4CAGlB,GAAM,GAAa,AAAC,GAAiB,MAAM,QAAQ,GAAU,mBAAmB,KAAS,GAEnF,EAAa,EAAc,IAAI,IAErC,SAAW,QAAQ,CAAC,EAAO,KACzB,GAAI,CAAC,GAAe,IAAU,CAAC,GAAW,IAAU,CAAC,EAAW,GAC9D,KAAI,OAAO,GAAc,IAAO,SACxB,GAAI,OAAM,eAAe,EAAW,sEAAsE,EAAc,MAG1H,GAAI,OAAM,eAAe,EAAW,iIAG5C,GAAI,EAAW,IAEb,GAAM,GAAY,EAAM,MAAM,GAC9B,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,eAAe,EAAW,iCAAiC,iDAMjF,KAAM,SAAQ,IACZ,EAAW,IAAI,AAAC,GAAU,GAAe,IAAU,GAAiB,KAG/D,GAAI,IAAS,EAAY,MAAM,QAAQ,ICtChD,kBACE,EACA,GAEA,GAAM,CAAE,UAAW,EAAI,SAEnB,EAAS,EAEb,GAAI,CAAE,aAAiB,KACrB,GAAM,GAAW,KAAM,GAAW,GAElC,GAAI,EAAS,UAAY,EACvB,KAAM,IAAI,OAAM,8CAGlB,GAAM,GAAiB,EAAS,SAAS,GACzC,EAAS,YAA0B,GAC/B,EACA,KAAM,IAAoB,GAGhC,GAAM,GAAM,EAAoB,GAQhC,MAAO,AAPO,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAO,MAAO,EAAO,QAAQ,IAAI,QAC7C,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAO,MAAO,EAAO,SAE/C,IAAI,CAAC,CAChB,IAAG,IAAG,QAAO,aAEb,GAAM,GAAU,GAAa,CAAE,QAAO,WACtC,SAAoB,GACjB,aAAa,EAAI,aAAa,EAAG,EAAG,EAAO,GAAS,EAAG,GACnD,ICnDX,OAAoB,OAgBpB,kBACE,EACA,GAEA,GAAI,CAAC,GAAW,IAAgB,CAAC,EAAW,GAC1C,KAAM,IAAI,OAAM,6DAGlB,GAAI,EAAW,IAAgB,EAAY,MAAM,GAAK,EACpD,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAW,EAAU,GAAe,EAAY,MAAM,MAAM,EAAW,GAAe,EAAI,GAajG,MAJoB,AAPN,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAU,GAAW,IACjC,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAU,IAEvB,IAAI,CAAC,CAC7B,IAAG,IAAG,QAAO,YACT,AAAG,WAAQ,EAAY,KAAK,EAAW,EAAU,GAAc,CAAC,EAAG,EAAG,GAAI,CAAC,EAAQ,EAAO,OCtCpG,kBACE,EAEA,GAEA,GAAM,CAAE,SAAU,EAAI,SAChB,EAAM,KAAM,GAAM,EAAK,GAC7B,GAAI,CAAE,GAAI,OAAS,KACjB,KAAM,IAAI,OAAM,qBAAqB,EAAI,WAAW,EAAI,yBAAyB,EAAI,OAEvF,MAAO,GCTT,kBAAiC,GAC/B,GAAM,GAAM,KAAM,IAAa,GACzB,EAAO,KAAO,GAAK,OAEzB,GAAI,CAAC,EAAK,KAAK,WAAW,UACxB,KAAM,IAAI,OAAM,wEAAwE,EAAK,kBAAkB,EAAI,OAErH,MAAO,IAAc,GCRvB,kBAAmC,GACjC,MAAQ,MAAM,IAAa,IAAM,OCDnC,kBAAsC,GACpC,MAAO,IAAI,cAAa,KAAO,MAAM,IAAa,IAAM,eCH1D,OAAoB,OCAb,YAAsB,EAAyB,GACpD,GAAM,GAA0B,GAAG,0BAEnC,GAAI,CAAC,EACH,MAAO,CACL,aAAc,GACd,YAAa,GAIjB,GAAI,IAAQ,IACV,MAAO,CACL,aAAc,IACd,YAAa,IAAI,KAIrB,GAAM,GAAW,EAAI,WAAW,WAAa,UAAY,EAAI,WAAW,YAAc,WAAa,GACnG,EAAM,EAAI,QAAQ,EAAU,IAE5B,GAAM,GAAQ,EAAI,MAAM,KAAK,OAAO,AAAC,GAAM,GAErC,EAAe,EAAI,SAAS,SAC9B,EAAM,EAAM,OAAS,GACrB,EAEA,EAAe,EAAY,GAAI,SAAS,SAAW,EAAM,MAAM,EAAG,EAAM,OAAS,GAAK,GAAO,KAAK,KACtG,SAAe,EAAI,WAAW,KAAO,IAAI,IAAiB,EAEnD,CACL,eACA,YAAa,IAAiB,IAAM,IAAI,IAAiB,GAAG,KAAgB,KD1BhF,kBACE,EACA,GAEA,GAAM,CAAE,cAAa,gBAAiB,GAAa,EAAK,GAClD,EAAW,KAAM,IAAuC,GAE9D,MAAO,AAAG,OAAG,YAAY,EAAU,GET9B,YAAyB,EAAoB,EAAwB,EAA8B,IACxG,GAAM,CAAE,QAAO,UAAW,EACtB,GAAmB,GACnB,EACJ,SAAM,MAAQ,EACd,EAAM,OAAS,EACR,CAAE,QAAO,UCTlB,OAAoB,OCApB,OAAoB,OAApB,YAQE,YAAY,GAIF,aAAkC,OAElC,oBAAiC,GALzC,KAAK,MAAQ,KASJ,UAAmC,MAAO,MAAK,WAE/C,iBAAkC,MAAO,MAAK,kBAE9C,YAAsB,MAAO,CAAC,CAAC,KAAK,OAExC,iBAAiB,GACtB,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,MAAO,GAAI,GAGN,sBAAsB,EAAmB,GAC9C,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,EAAI,GAAS,UACb,EAAI,GAAW,EAGV,eACL,MAAO,MAAK,eAAe,IAAI,CAAC,CAAE,eAAiB,EACjD,KAAM,EACN,OAAQ,KAAK,iBAAiB,MAI3B,qBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,EAAM,iBAAqB,cAGnE,kBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,CAAE,GAAM,iBAAqB,eAGrE,WACL,KAAK,kBAAkB,QAAQ,CAAC,CAAE,OAAM,aACtC,KAAK,sBAAsB,EAAM,EAAO,cAIrC,SACL,KAAK,qBAAqB,QAAQ,CAAC,CAAE,OAAM,OAAQ,MACjD,GAAM,GAAS,AAAG,UAAO,EAAS,YAClC,EAAS,UACT,KAAK,sBAAsB,EAAM,KAI9B,QAAQ,EAA4B,IACzC,KAAK,eAAe,QAAQ,AAAC,IAC3B,GAAI,GAAoB,EAAM,OAAO,WACnC,KAAM,IAAI,OAAM,mDAAmD,EAAM,QAE3E,EAAM,OAAO,YAEf,KAAK,QAAU,OAGV,kBACL,MAAO,IAAI,cACT,KAAK,eACF,IAAI,CAAC,CAAE,YAAa,MAAM,KAAK,EAAO,aACtC,OAAO,CAAC,EAAM,IAAQ,EAAK,OAAO,UAI5B,MAAK,GAChB,GAAI,YAAwB,eAC1B,KAAK,eAAe,GACpB,OAEF,KAAM,MAAK,YAAY,QAGZ,aAAY,GACvB,GAAI,GAAO,MAAO,IAAQ,SACxB,KAAM,IAAI,OAAM,GAAG,KAAK,0CAE1B,GAAM,GAAY,KAAM,IAAc,EAAK,KAAK,uBAChD,KAAK,kBAAkB,QAGZ,cAAa,GACxB,GAAI,GAAY,MAAO,IAAa,SAClC,KAAM,IAAI,OAAM,GAAG,KAAK,iDAE1B,GAAM,CAAE,YAAa,EAAI,SACnB,CAAE,cAAa,gBAAiB,GAAa,EAAU,KAAK,uBAC5D,EAAuB,AAAC,GAAwB,QAAQ,IAAI,EAAU,IAAI,AAAC,GAAO,EAAS,GAAI,KAAK,AAAC,GAAQ,EAAI,UACjH,EAAc,AAAG,MAAG,qBAAqB,GACzC,EAAW,KAAK,MAAO,MAAM,GAAS,IAAc,YACpD,EAAY,KAAM,GAAY,EAAU,GAC9C,KAAK,kBAAkB,GAGlB,kBAAkB,GACvB,GAAM,CAAE,gBAAe,UAAW,KAAK,2BAA2B,GAClE,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGV,eAAe,GACpB,GAAM,CAAE,gBAAe,UAAW,KAAK,cAAc,GACrD,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGT,qBAAqB,GAC3B,GAAI,CAAC,KAAK,OACR,KAAM,IAAI,OAAM,qDAGlB,GAAM,GAAS,EAAU,MAAM,KAAK,OAAO,CAAC,EAAoD,KAE9F,GAAI,CAAC,EAAI,QAAQ,eAAe,GAC9B,KAAM,IAAI,OAAM,wDAAwD,eAAqB,KAE/F,MAAO,CAAE,IAAK,EAAI,QAAS,UAAS,QAAS,EAAI,QAAQ,KACxD,CAAE,QAAS,KAAK,SAEb,CAAE,MAAK,WAAY,EACzB,GAAI,CAAC,GAAO,CAAC,GAAW,CAAE,GAAI,YAAuB,YACnD,KAAM,IAAI,OAAM,8DAA8D,KAGhF,MAAO,CAAE,MAAK,aC7IlB,MAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,iBAAkB,EAAO,iBAAkB,EAAQ,QAC1F,SAAM,AAAG,OAAI,EAAK,EAAO,MAClB,IDNJ,YACL,EACA,EACA,EAAwB,IAExB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,CAAC,EAAG,GAAI,QACrE,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,CAAC,EAAG,KAE7E,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,OAItC,YACL,EACA,EACA,EAAwB,GACxB,EAAuB,IAEvB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,GAAI,QAC5F,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,KAEpG,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAE/D,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,KACxC,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,QEpD1D,OAAoB,OAIb,YACL,EACA,EACA,EAA4B,OAC5B,EAAoB,IAEpB,MAAO,AAAG,SAAK,KACb,GAAM,GAAM,AAAG,OACb,AAAG,UAAO,EAAG,EAAO,QAAS,CAAC,EAAG,GAAI,GACrC,EAAO,MAGT,MAAO,GAAW,AAAG,QAAK,GAAO,ICd9B,WAAoC,EAAgB,GACzD,OAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,AAAK,EAAc,KAAK,AAAC,GAAO,EAAG,eAAiB,IAClD,EAAU,GAAM,YCLtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,EACA,KAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,SCzBtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,KAEA,GAAM,GAAa,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAY,IAChF,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CACL,QAAS,EACT,KAAM,ICvBZ,OAAoB,OCApB,aAsBE,YAES,EAEA,EAEA,GAJA,wBAEA,wBAEA,cDxBJ,YACL,EACA,GAEA,MAAO,CAAC,EAAoB,EAAqB,KAC/C,GAAM,GAAmB,AAAG,YAAS,EAAe,EAAI,EAAI,GAAa,CAAC,EAAG,EAAG,EAAY,IACtF,EAAmB,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAG,EAAG,EAAY,IAC5F,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,WAGX,GAAI,IACT,EACA,EACA,IAKC,YAEL,GAEA,MAAO,AAAC,KACN,GAAM,GAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,IAAI,IACT,EACA,EACA,IEpCC,WAAmC,EAAgB,GACxD,MAAO,CAAC,EAAsB,EAAmB,KAC/C,GAAM,GAAS,EAAU,GAEzB,GAAI,CAAC,GAAS,EAAQ,GACpB,KAAM,IAAI,OAAM,sBAAsB,oBAA+B,oBAA4B,KAGnG,SAAc,KACZ,CAAE,eAAc,UAAW,GAAc,IAGpC,GCfJ,WAA+B,GACpC,GAAI,GAAmB,EAEvB,WAAwB,GACtB,GAAM,GAAM,EAAiB,MAAM,EAAG,GACtC,SAAmB,EAAiB,MAAM,GACnC,EAGT,aACE,MAAO,GAGT,MAAO,CACL,iBACA,uBCPG,YAA2B,EAAwC,GACxE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,GAAQ,EACV,EAAkB,EAAY,EAAa,EAAG,GAAG,WACjD,EAA2B,EAAY,EAAa,GAAG,WACrD,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAChE,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,CAAE,QAAO,QAAO,SAAU,EAAyB,EAAY,EAAa,EAAc,GAC1F,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAC3C,EAAS,EAAyB,IAAK,IAAK,UAElD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CACN,SAAQ,SAAQ,SAAQ,WCvBvB,YAA+B,GACpC,MAAO,AAAC,KACN,GAAM,GAAU,EAAgC,GAAG,YAAkB,GAC/D,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,CAAE,UAAS,SCNf,YAA2B,EAAgB,GAChD,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBhBxBnB,oBAU0C,GACxC,cACE,MAAM,wBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,sDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAE/B,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,+BAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KiBlDzB,OAAoB,OCApB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,IAAM,AAAG,OACtB,AAAG,UAAO,EAAG,EAAO,SACpB,EAAO,OCPJ,YAAuB,EAAuB,EAAoB,GACvE,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAIpB,EAAK,AAFa,GAAuB,EAAgB,GAEpC,EAAY,EAAa,MAEpD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,OCdP,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,EAAgB,OAGtB,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,YAA4B,GACjC,GAAM,GAAyC,GACzC,EAAmC,GAEzC,cAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,GAAM,GAAM,EAAI,WAAW,MAAQ,EAAgB,EACnD,EAAI,GAAO,EAAU,KAGhB,CAAE,sBAAqB,iBJXhC,oBAkBU,GAGR,YAAY,EAAe,GACzB,MAAM,GACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBASP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EACJ,MAAO,IAAoB,EAAmB,KAAK,EAAmB,MAAM,GAAI,IAAK,EAAO,MAIzF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,EAAS,KAAK,0BAA2B,KAAK,4BAG3D,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAM,KAAK,0BACX,EAAO,KAAK,2BACZ,EAAwB,EAAO,EAAO,EAEtC,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KKnFjC,GAAM,IAAyB,CAAC,UAAW,QAAS,MAAO,QAAS,UAAW,YAAa,aAAnG,SAiBE,YAAY,GACV,GAAI,EAAc,SAAW,EAC3B,KAAM,IAAI,OAAM,8EAA8E,EAAc,UAG9G,GAAuB,QAAQ,CAAC,EAAY,KAC1C,KAAK,GAAc,EAAc,KAIrC,gBACE,MAAO,IACJ,IAAI,AAAC,GAAgB,EAAE,aAAY,YAAa,KAAK,MACrD,KAAK,CAAC,EAAI,IAAO,EAAG,YAAc,EAAG,e1C9B5C,oBAQuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGtB,aAAa,GAClB,MAAO,AAAG,SAAK,IAAM,AAAG,WAAQ,KAAK,OAAO,UAGjC,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,oBAAmB,GAC9B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAC9B,EAAsB,KAAM,SAAQ,IAAI,AAAG,WAAQ,GAAK,IAAI,KAAO,KACvE,GAAM,GAAO,KAAM,GAAE,OACrB,SAAE,UACK,KAET,EAAI,UAEJ,GAAM,GAAqB,EACxB,IAAI,AAAC,GAAiB,GAAI,IAAgB,IAE7C,MAAO,GAAS,aACZ,EACA,EAAmB,GAGf,sBACR,MAAO,wBAGC,0BACR,MAAO,KAGC,2BACR,MAAO,K2C1CJ,YAA+B,GACpC,MAAO,GAAI,sBAAuB,IAG7B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,gBCPf,YACL,EACA,EACA,EAAgB,GAChB,GAIA,AAF6B,OAAM,QAAQ,GAAmB,EAAkB,CAAC,IAE5D,QAAQ,AAAC,IAE5B,GAAM,GAAO,YAAa,IACtB,EACC,GAAsB,GAAK,EAAE,YAAc,OAChD,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mHAIlB,GAAM,GAAmB,AADV,EAAK,gBACY,OAAO,AAAC,GAAc,EAAU,YAAc,GAExE,EAAS,GAAoB,GAC/B,EAAE,UAAU,IAAI,WACf,GAAmB,GAAI,GAAM,EAAG,GAMrC,AAJsB,GAAI,IACxB,EAAiB,IAAI,AAAC,GAAc,GAAG,EAAU,eAAe,GAAM,EAAU,iBAChF,GAEY,KAAK,KCxBhB,YAA6B,GAClC,MAAO,IAAoB,IAEtB,EAAI,oBAAwB,IAE5B,EAAI,6BAAiC,IAErC,EAAI,sBAA0B,GAG9B,YAEoD,EAAoB,GAC7E,GAAM,CAAE,IAAK,GAAU,EAAU,UAC3B,EAAY,EAAmB,QAAwB,EAAM,EAAG,EAAM,GAEtE,EAAO,EAAU,QACjB,CAAE,aAAc,EAAU,UAC1B,EAAc,GAAI,GAAc,EAAU,UAAU,MAAO,EAAK,QAAQ,EAAU,WAAY,GAQpG,MAAO,IAAK,KANM,CAChB,YACA,qBACA,gBCpCJ,aA+BE,YAAY,EAAqC,IAC/C,GAAM,CACJ,YAAY,GAAM,aAAa,GAAM,YAAW,YAAW,YAAW,cACpE,EACJ,KAAK,UAAY,EACjB,KAAK,WAAa,EAClB,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,uBAC9B,KAAK,WAAa,GAAc,yBAxCpC,SAiDE,YACE,EACA,EAAqC,IAErC,KAAK,cAAgB,EACrB,KAAK,QAAU,GAAI,IAAyB,GAG9C,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CACJ,YAAW,aAAY,YAAW,YAAW,YAAW,cACtD,KAAK,QAcT,GAZI,GAAa,KAAK,wBAAyB,KAC7C,GAAI,YAAc,EAClB,EAAI,UAAY,EAChB,GAAY,EAAK,KAAK,cAAc,iBACpC,GAAY,EAAK,KAAK,cAAc,kBACpC,GAAY,EAAK,KAAK,cAAc,mBACpC,GAAY,EAAK,KAAK,cAAc,WACpC,GAAY,EAAK,KAAK,cAAc,aAAc,IAClD,GAAY,EAAK,KAAK,cAAc,cAAe,IACnD,GAAY,EAAK,KAAK,cAAc,WAAY,KAG9C,GACF,EAAI,YAAc,EAClB,EAAI,UAAY,EAEhB,GAAM,GAAY,AAAC,IACjB,EAAI,YACJ,EAAI,IAAI,EAAG,EAAG,EAAG,EAAG,EAAW,EAAG,EAAI,KAAK,IAC3C,EAAI,QAEN,KAAK,cAAc,UAAU,QAAQ,MAOpC,YACL,EACA,GAGA,AAD2B,OAAM,QAAQ,GAAiB,EAAgB,CAAC,IACxD,QAAQ,AAAC,IAE1B,GAAM,GAAY,YAAa,GAC3B,EACC,GAAoB,GAAK,EAAE,UAAY,OAC5C,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gIAGlB,GAAI,IAAkB,GAAW,KAAK,qBC1G1C,OAAoB,OCApB,MAAoB,OCKpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAqC,EAAoB,EAAqB,GAC5E,GAAM,GAAkB,EAA2B,EAAY,EAAa,GAAG,qBACzE,EAAkB,EAA2B,EAAa,EAAa,GAAG,qBAC1E,EAAiB,EAAkB,EAAY,EAAa,EAAG,GAAG,oBAExE,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,EAAkB,GAChD,GAAM,GAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBAE1E,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YAAuB,EAAuB,GACnD,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAgB,GAEhC,EAAqB,EAAkB,EAAG,GAAI,EAAG,sBACjD,EAA+B,EAA4B,GAAI,GAAI,gCACnE,EAA+B,EAA4B,GAAI,IAAK,gCAEpE,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,IAAK,0BAA0B,OAG3F,GAAM,GAA4B,EAA4B,IAAK,IAAK,6BAClE,EAA2B,EAA2B,IAAK,IAAK,4BAEhE,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,aAAY,cAAa,cCjEvC,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAqC,GACnC,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAiB,EAAkB,GAAG,oBAE5C,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,GAC9B,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAEtD,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAW,GAE3B,EAAqB,EAAkB,sBACvC,EAA+B,EAA4B,gCAC3D,EAA+B,EAA4B,gCAE3D,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,0BAA0B,OAGtF,GAAM,GAA4B,EAA4B,6BACxD,EAA2B,EAA2B,4BAEtD,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,SAA2B,EAAW,GAE/B,CAAE,OAAQ,CAAE,aAAY,cAAa,aAAa,iBFrE3D,YAAc,EAAgB,EAAoB,GAChD,MAAO,AAAG,OAAI,AAAG,SAAO,EAAG,EAAO,QAAS,EAAQ,QAAS,EAAO,MAGrE,YAAwB,EAAgB,EAA8B,EAA2B,IAC/F,GAAI,GAAM,EAAkB,AAAG,OAAK,GAAK,EACzC,SAAM,EAAuB,EAAK,EAAO,gBAAiB,CAAC,EAAG,IAC9D,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,AAAG,MAAI,EAAK,GAAK,EAAG,EAAO,eAAgB,CAAC,EAAG,KAC9C,EAGT,YAAmB,EAAgB,GACjC,GAAI,GAAM,EAAuB,AAAG,OAAK,GAAI,EAAO,gBAAiB,CAAC,EAAG,IACzE,SAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,MAAI,EAAK,GACX,EA7BT,oBAgCkC,GAGhC,YAAY,GACV,MAAM,gBACN,KAAK,eAAiB,EAGjB,aAAa,GAClB,GAAM,CAAE,UAAW,KACnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,8CAElB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAC7D,EAAM,AAAG,OAAK,GAAK,EAAY,EAAO,WAAW,QAAS,CAAC,EAAG,KAClE,SAAM,GAAe,EAAK,EAAO,WAAW,kBAAmB,IAC/D,EAAM,GAAe,EAAK,EAAO,WAAW,mBAC5C,GAAM,KAAK,eAAgB,EAAG,GAAG,QAAQ,AAAC,IACxC,EAAM,GAAU,EAAK,EAAO,YAAY,cAAc,QAExD,EAAM,GAAe,EAAK,EAAO,UAAU,iBAC3C,EAAM,AAAG,OAAK,EAAuB,EAAK,EAAO,UAAU,eAAgB,CAAC,EAAG,KACxE,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,sBAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,gBAG1C,cAAc,GACtB,MAAO,IAAc,EAAS,KAAK,kBGvEhC,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAkB,GAAuB,EAAgB,GAEzD,EAAM,EAAgB,IAAK,EAAG,UAC9B,EAAS,EAAgB,IAAK,EAAG,aAEvC,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,GAAI,CAAE,MAAK,YCflB,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,CACF,IAAK,EAAgB,UACrB,OAAQ,EAAgB,eAI5B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,GAAK,IAAL,UAAK,GAEV,SAAS,SAET,OAAO,SAJG,aNLZ,oBAakC,GAGhC,YAAY,EAAqC,GAAI,IAAa,IAChE,MAAM,gBACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBAGP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EAEE,EAAS,AAAG,WAAQ,EAAoB,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAAS,KAAK,EAAmB,MAAM,GAAI,IACnG,EAAM,GAAoB,EAAQ,EAAO,GAAG,KAAK,OACjD,EAAS,GAAoB,EAAQ,EAAO,GAAG,QACrD,MAAO,CAAE,MAAK,YAIX,aAAa,GAClB,MAAO,AAAG,SAAK,KACb,GAAM,CAAE,MAAK,UAAW,KAAK,OAAO,GACpC,MAAO,CAAE,MAAK,OAAQ,AAAG,WAAQ,WAIxB,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,qBAAoB,GAC/B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAE9B,EAAO,AAAG,WAAQ,EAAI,KACtB,EAAU,AAAG,WAAQ,EAAI,QACzB,EAAsB,EAAK,IAAI,CAAC,EAAW,IAAO,EACtD,YACA,aAAc,EAAQ,MAGlB,EAAqB,KAAM,SAAQ,IACvC,EAAoB,IAAI,MAAO,CAAE,YAAW,mBAC1C,GAAM,GAAO,MAAM,GAAU,QAAQ,GAC/B,EAAY,MAAM,GAAa,QAAQ,GACvC,EAAS,EAAW,GACpB,EAAS,EAAS,GAAO,KAAO,GAAO,OACvC,EAAoB,EAAS,EAAY,EAAI,EAEnD,SAAU,UACV,EAAa,UACN,CAAE,MAAK,SAAQ,wBAG1B,SAAI,IAAI,UACR,EAAI,OAAO,UAEJ,EAAS,aAAe,EAAiD,EAAmB,GAG3F,sBACR,MAAO,mBAGF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,GAGb,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAwB,IAAM,EAAI,EAAM,KAAM,EAAI,GAElD,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KOvHxC,MAAoB,OAApB,oBAYU,IACD,YAAY,EAAqB,EAAmB,GACzD,GAAM,GAAkB,EAAmB,IAAI,CAAC,CAAE,QAAO,aACvD,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,CACL,MAAO,EAAQ,EACf,OAAQ,EAAS,KAIf,EAAY,EAAgB,OAElC,MAAO,AAAG,QAAK,KACb,GAAM,GAA0B,CAAC,EAAe,IAAkB,AAAG,QAAM,CAAC,AAAG,OAAK,CAAC,IAAK,EAAO,WAAY,AAAG,OAAK,CAAC,IAAK,EAAO,YAAa,GAAG,KAAK,EAAG,KAAK,OAGzJ,EAAa,CAAC,EAAkB,KACpC,GAAM,CAAE,QAAO,UAAW,EAAgB,GAC1C,MAAO,GAAK,EAAO,GAAU,KAAK,IAAI,EAAQ,GAAU,EAAI,GAGxD,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GACvE,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GAa7E,MAXwB,GACrB,IAAI,AAAG,OAAK,CAAC,EAAW,KAAM,EAAW,YACzC,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAY,GACZ,EAAY,OAEb,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAgB,GAAU,MAC1B,EAAgB,GAAU,aAO3B,aAAa,GAClB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,KAAK,OAAO,GACxB,MAAO,MAAK,YACV,EACA,EAAM,UACN,EAAM,gBAAgB,IAAI,CAAC,CAAC,EAAQ,KAAY,EAAE,SAAQ,mBAKnD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,iBAAgB,GAC3B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAkB,AAAG,OACzB,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAAoB,KAAM,SAAQ,IAAI,EAAgB,IAC1D,MAAO,EAAgB,KACrB,GAAM,GAAiB,MAAM,KAAK,KAAM,GAAe,QACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,GAAO,IACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,CAAC,GAAO,IAExD,MAAO,IAAI,IACT,MAAM,IAAI,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,GAAI,GAAM,EAAQ,GAAc,EAAQ,KACxE,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,QAMtC,SAAgB,QAAQ,AAAC,GAAM,EAAE,WAE1B,EAAS,aAAe,EAAyC,EAAkB,GAGlF,2BACR,MAAO,OC9FX,oBAIuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGnB,sBACR,MAAO,yBAGC,0BACR,MAAO,OCdX,OAAoB,OCMb,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCnBZ,YAA2B,GAChC,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAEjD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,SAAQ,SAAQ,WF1B9B,oBAU8C,GAC5C,cACE,MAAM,4BAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,0DAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,GAAI,IAAK,CAAC,EAAG,GAAI,SAEjC,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,oCAGC,2BAA2B,GACnC,MAAO,IAA+B,GAG9B,cAAc,GACtB,MAAO,IAAkB,KGjD7B,oBAI2C,IACzC,YAAY,EAAiD,GAAI,KAC/D,MAAM,wBAAyB,GAGvB,sBACR,MAAO,8BAGC,0BACR,MAAO,OCdX,oBAIqC,MCJrC,MAAoB,OCApB,OAAoB,OCApB,OAAoB,OAIb,YAAe,EAAgB,GACpC,MAAO,AAAG,QAAI,AAAG,OAAI,EAAG,EAAO,SAAU,EAAO,QDAlD,YACE,EACA,EACA,EACA,EACA,EAA4B,QAE5B,GAAM,CAAE,UAAS,QAAS,EAAO,KAE7B,EAAM,AAAG,UAAO,EAAG,EAAS,EAAS,GACzC,SAAM,AAAG,OAAI,EAAK,GAClB,EAAM,GAAM,EAAK,EAAO,OACjB,EAAW,AAAG,QAAK,GAAO,EAG5B,YAAc,EAAgB,GACnC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAoB,EAAgB,GACzC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAkB,EAAgB,GACvC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,GAAM,SE7B5C,MAAoB,OAUpB,YAA2B,EAAwC,GACjE,WAA6B,EAAyB,EAAoB,GACxE,GAAM,GAAU,EAAe,GACzB,EAAQ,EAAQ,OAAU,GAAa,EAAa,GAE1D,GAAI,GAAQ,GACV,KAAM,IAAI,OAAM,+BAA+B,sBAA0B,EAAQ,uBAAuB,kBAA2B,KAGrI,MAAO,AAAG,QACR,IAAM,AAAG,YACP,AAAG,WAAS,EAAS,CAAC,EAAY,EAAO,EAAY,IACrD,CAAC,EAAG,EAAG,EAAG,KAKhB,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAU,EAAoB,EAAiB,EAAY,GAC3D,EAAO,AAAG,WAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,QAGpB,WAAiC,EAAoB,GACnD,GAAM,GAAU,AAAG,WAAS,EAAe,IACrC,EAAS,AAAG,WAAS,EAAe,IAE1C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,aAGX,CACL,UACA,UAIJ,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAO,EAAkB,EAAiB,EAAY,EAAY,GAAG,UACrE,EAAQ,EAAwB,EAAY,GAAG,WAErD,MAAO,CAAE,OAAM,SAGjB,WACE,EACA,EACA,EACA,EACA,EAAkB,IAElB,GAAM,GAAQ,EAAwB,GAAS,GAAM,GAAK,EAAiB,EAAY,EAAY,GAAG,WAChG,EAAQ,EAAuB,EAAiB,EAAY,EAAY,GAAG,WAEjF,MAAO,CAAE,QAAO,SAGlB,MAAO,CACL,yBACA,8BAIG,YAAuB,GAC5B,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAgB,GAEhC,EAAc,EAAuB,KAAM,GAAI,EAAG,eAClD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YAEnD,EAAc,EAA2B,MAAO,GAAI,EAAG,cAAe,IACtE,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YAEpD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aAEvD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAmB,EAA2B,OAAQ,IAAK,EAAG,oBAE9D,EAAK,AAAG,OACZ,IAAM,AAAG,YAAU,AAAG,WAAS,EAAe,IAAM,KAAM,CAAC,IAAK,MAAO,CAAC,EAAG,KAI7E,GAFA,EAAc,KAAK,CAAE,UAAW,OAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAsB1E,MAAO,CAAE,OAnBM,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGe,iBChJnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAiC,GAC/B,GAAM,GAAU,EAAmB,GAAG,kBAAwB,GACxD,EAAS,EAAmB,GAAG,iBAAuB,GAE5D,MAAO,CAAE,UAAS,UAGpB,WAAgC,GAC9B,GAAM,GAAU,EAAmB,GAAG,iBAAuB,GACvD,EAAO,EAAmB,GAAG,cAAoB,GACjD,EAAQ,EAAwB,GAEtC,MAAO,CAAE,KAAM,CAAE,UAAS,QAAQ,SAGpC,WAAoC,GAClC,MAAO,CACL,MAAO,EAAuB,GAAG,WACjC,MAAO,EAAuB,GAAG,YAIrC,MAAO,CACL,yBACA,8BAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAW,GAE3B,EAAc,EAAuB,eACrC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAc,EAA2B,eACzC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aAEvC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aACvC,EAAmB,EAA2B,oBAE9C,CAAE,MAAO,EAGf,GAFA,EAAc,KAAK,CAAE,aAAc,KAAM,UAAW,OAEhD,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yDAAyD,KAG3E,GAAM,GAAS,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGF,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBC9FnB,MAAoB,OAKb,YAAkB,EAAgB,GACvC,GAAI,GAAM,GAAK,EAAG,EAAO,OACzB,SAAM,GAAW,EAAK,EAAO,OAC7B,EAAM,AAAG,MAAI,EAAK,GAClB,EAAM,AAAG,OAAK,GACP,EAGF,YAAsB,EAAgB,GAC3C,GAAI,GAAM,GAAS,EAAG,EAAO,OAC7B,EAAM,GAAW,EAAK,EAAO,OAE7B,GAAI,GAAS,AAAG,UAAQ,EAAG,EAAG,EAAG,SAC3B,EAAQ,AAAG,QAAkB,EAAO,OACpC,EAAQ,EAAO,MAAM,KAAO,EAAI,MAAM,GAG5C,GAFsB,EAAO,MAAM,KAAO,EAAI,MAAM,IAAM,EAAO,MAAM,KAAO,EAAI,MAAM,IAGtF,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAE/B,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAGjC,SAAS,EAAQ,AAAG,SAAO,CAAC,EAAQ,GAAQ,GAAK,EACjD,EAAM,AAAG,MAAI,EAAQ,GAErB,EAAM,AAAG,OAAK,GACP,ELtCT,oBAWwC,GACtC,cACE,MAAM,sBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAGtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,GAAS,EAAY,EAAO,aACtC,EAAM,AAAG,UAAQ,EAAK,EAAG,EAAG,SAE5B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,aAC/B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAa,EAAK,EAAO,kBAE/B,GAAM,GAAY,EAAI,KAAK,CAAC,EAAG,IAG/B,MAFuB,AAAG,UAAO,EAAW,EAAO,WAM1C,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,uBAAsB,GA7DrC,MA8DI,GAAI,oBAAO,QAAP,cAAc,KAAK,AAAC,GAAQ,GAAO,GAAI,MAAO,IAAI,cAAa,KACnE,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAwB,AAAG,OAC/B,IAAM,AAAG,UAAQ,KAAK,aAAa,KAE/B,EAA0B,KAAM,SAAQ,IAAI,EAAsB,IAAI,AAAC,GAAM,EAAE,SACrF,SAAsB,QAAQ,AAAC,GAAM,EAAE,WAChC,EAAS,aAAe,EAA0B,EAAwB,GAGzE,sBACR,MAAO,yBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KM7ElB,YAAkC,GACvC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECHF,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,eCNf,YAAmB,GACxB,MAAO,OAAO,GAAI,KAAQ,SAGrB,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,QCNf,YAAsB,GAC3B,MAAQ,GAAI,SAAW,GAAO,MAAQ,EAAI,SAAW,GAAO,SACvD,GAAmB,EAAI,mBAGvB,YAGL,EACA,EACA,GAGA,MAAO,IAAK,KADM,CAAE,SAAQ,sBCpB9B,OAAoB,OCApB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,WAAoC,EAAqB,GACvD,GAAM,GAAU,AAAG,YAAS,EAAe,EAAI,EAAI,GAAc,CAAC,EAAG,EAAG,EAAa,IAC/E,EAAmB,AAAG,YAAS,EAAe,IAC9C,EAAoB,AAAG,YAAS,EAAe,IAC/C,EAAkB,AAAG,YAAS,EAAe,IAC7C,EAAsB,AAAG,YAAS,EAAe,IAEvD,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,uBAChB,CAAE,UAAW,GAAG,qBAChB,CAAE,UAAW,GAAG,0BAGX,CACL,UACA,mBACA,oBACA,kBACA,uBAIJ,WACE,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,KAAgB,EAAkB,oBAAsB,WAGnE,CAAE,UAAS,QAGpB,WACE,EACA,EACA,EACA,GAEA,GAAM,CACJ,UACA,QACE,EAAkB,EAAY,EAAa,EAAY,EAAc,IAEzE,MAAO,CACL,UACA,kBAAmB,GAIvB,WACE,EACA,EACA,GAEA,GAAM,GAAiB,EAA2B,EAAY,GAAG,oBAC3D,EAAiB,EAA2B,EAAY,EAAa,EAAG,GAAG,oBAEjF,MAAO,CAAE,iBAAgB,kBAG3B,aACE,GAAM,GAAS,EAA2B,EAAG,GAAI,EAAG,sBAC9C,EAAS,EAAsB,GAAI,GAAI,sBACvC,EAAS,EAAsB,GAAI,IAAK,sBACxC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,KAAM,uBAC3C,EAAU,EAAsB,KAAM,KAAM,uBAClD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,UACA,UACA,UACA,WAIJ,aACE,GAAM,GAAS,EAA2B,KAAM,IAAK,EAAG,2BAClD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,GAAI,EAAG,2BAChD,EAAS,EAA2B,GAAI,IAAK,EAAG,2BAChD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,EAAG,EAAG,oDACjD,EAA2B,EAAkB,KAAM,GAAI,EAAG,2DAC1D,EAAoB,EAAkB,KAAM,GAAI,EAAG,oDACnD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDA0BxD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,gBAjCsB,CACtB,uBAAwB,EACxB,gBAAiB,GAgCjB,gBA9BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA6BjB,gBA3BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA0BjB,gBAxBsB,CACtB,uBAAwB,GACxB,gBAAiB,IAuBjB,gBArBsB,CACtB,uBAAwB,EACxB,gBAAiB,IAoBjB,gBAlBsB,CACtB,uBAAwB,GACxB,gBAAiB,KAoBrB,MAAO,CACL,2BACA,gCAIG,YAAuB,GAC5B,GAAM,GAAgC,GAChC,CACJ,iBACA,uBACE,EAAsB,GACpB,CACJ,2BACA,gCACE,GAAkB,EAAgB,GAChC,EAAc,IACd,EAAmB,IAKnB,EAAe,CACnB,UALgB,AAAG,YACnB,EAAe,KAAO,GACtB,CAAC,EAAG,KAAM,KAMZ,GADA,EAAc,KAAK,CAAE,UAAW,2BAC5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,OAAQ,CACN,cACA,mBACA,gBAEF,iBC9MJ,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAoC,EAAgB,EAAa,GAC/D,GAAM,GAAU,EAAmB,GAAG,YAAiB,sBAAyB,EAAG,GAAG,aAChF,EAAoB,EAAmB,GAAG,YAAiB,oCAAuC,EAAG,GAAG,uBAC9G,MAAO,CAAE,UAAS,qBAGpB,WAA+B,GAC7B,GAAM,GAAe,oBAAoB,IACnC,EAAsB,sBAAsB,cAC5C,EAA4B,GAAG,mBAC/B,EAA4B,GAAG,mBAE/B,EAAU,EAAmB,GAAG,sBAAyC,EAAG,GAAG,aAC/E,EAAmB,EAAmB,GAAG,oBAAuC,EAAG,GAAG,sBACtF,EAAoB,EAAmB,GAAG,mBAAsC,EAAG,GAAG,uBACtF,EAAkB,EAAmB,GAAG,0BAA6C,EAAG,GAAG,qBAC3F,EAAsB,EAAmB,GAAG,8BAAiD,EAAG,GAAG,yBAEzG,MAAO,CACL,eAAgB,CACd,UACA,mBACA,oBACA,kBACA,uBAEF,eAAgB,EAA2B,cAAe,EAAK,IAInE,aACE,MAAO,CACL,OAAQ,EAA2B,cAAe,EAAG,sBACrD,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,KAInC,WAA2B,EAAgB,GACzC,GAAM,GAAU,EAAmB,GAAG,YAAkB,EAAG,GAAG,aACxD,EAAO,EAAmB,GAAG,WAAiB,EAAG,GAAG,UAC1D,MAAO,CAAE,UAAS,QAGpB,WAAmC,GACjC,GAAM,GAAyB,EAC7B,2BAA2B,yBAC3B,kCAAkC,4BAE9B,EAAkB,EACtB,2BAA2B,mBAC3B,kCAAkC,qBAEpC,MAAO,CAAE,yBAAwB,mBAGnC,aACE,MAAO,CACL,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,IAI/C,MAAO,CACL,2BACA,gCAIG,YACL,GAEA,GAAM,GAAgC,GAChC,CACJ,2BACA,gCACE,GAAkB,EAAW,GAC3B,EAAY,EAAU,oBAE5B,GADA,EAAc,KAAK,CAAE,aAAc,mBAAoB,UAAW,2BAC9D,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yEAAyE,KAG3F,GAAM,GAAS,CACb,YAAa,IACb,iBAAkB,IAClB,aAAc,CACZ,cAIJ,SAA2B,EAAW,GAC/B,CAAE,SAAQ,iBChInB,OAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,UAAO,EAAG,EAAO,QAAS,EAAS,QAChD,SAAM,AAAG,OAAI,EAAK,EAAO,mBAClB,AAAG,eAAY,EAAK,EAAG,KDPlC,GAAM,IAAU,qBAEhB,YACE,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,QAAS,EAAS,QACzD,SAAM,AAAG,aACP,EACA,EAAO,gBACP,EAAO,oBACP,EAAO,kBACP,EAAO,iBACP,IAEK,AAAG,eAAY,EAAK,EAAG,KAIlC,YAA+B,GAC7B,MAAO,CAAC,EAAG,EAAG,EAAG,IAAI,KAAK,AAAC,GAAQ,IAAQ,GAAY,CAAC,EAAG,GAAK,CAAC,EAAG,GAG/D,YAAqB,EAAgB,GAC1C,MAAO,AAAG,SAAK,KACb,GAAI,GACA,EAAM,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IA4BnD,GAVA,AAhBuB,CACrB,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,QACP,EAAO,QACP,EAAO,QACP,EAAO,SAGM,QAAQ,CAAC,EAAO,KAC7B,GAAM,GAAW,EAAI,EACf,EAAuB,GAAsB,GACnD,EAAM,GAAmB,EAAK,EAAM,eAAgB,GACpD,EAAM,EAAmB,EAAK,EAAM,eAAgB,CAAC,EAAG,IACpD,IAAa,IACf,GAAS,KAIT,IAAW,KACb,KAAM,IAAI,OAAM,iDAGlB,MAAO,CACL,MACA,OAAQ,KEjEd,YAAa,EAAoB,EAAW,GAC1C,GAAM,GAAY,EAAM,YAClB,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAS,GAAQ,GAAU,GAAQ,GACnC,EAAS,GAAQ,GAAU,GAAQ,GACzC,GAAI,GAAS,GAAK,GAAS,EACzB,MAAO,GAET,GAAM,GAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAmB,EAAkB,GACjE,KAAK,IAAI,EAAmB,EAAkB,GACpD,MAAO,GAAoB,GAAQ,EAAQ,GAGtC,YACL,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAW,EAAM,MAAM,GACvB,EAAa,KAAK,IACtB,EACA,GAGI,EAAa,EAChB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,OAAO,AAAC,GAAM,EAAE,MAAQ,GACxB,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAE5B,EAAe,AAAC,GAAe,GAAK,EAAe,EAAI,EACvD,EAAqB,GAE3B,SAAW,QAAQ,AAAC,IAClB,GAAI,EAAS,QAAU,EAAY,OACnC,GAAM,GAAgB,EAAE,MACxB,OAAS,GAAI,EAAS,OAAS,EAAG,GAAK,EAAG,EAAE,GAC1C,GAAM,GAAM,GAAI,EAAO,EAAE,SAAU,EAAS,IAC5C,GAAI,IAAQ,GACZ,GAAE,OAAS,EAAa,GACpB,EAAE,OAAS,GAAgB,MAEjC,AAAI,IAAkB,EAAE,OACtB,EAAS,KAAK,EAAE,YAGb,EC5DT,MAAoB,OAIpB,YAA2C,GACzC,GAAM,GAAM,AAAG,UAAQ,AAAG,YAAU,EAAG,CAAC,EAAG,KAErC,EAAQ,CACZ,AAAG,MAAI,EAAI,GAAI,EAAI,IACnB,AAAG,MAAI,EAAI,GAAI,EAAI,KAEf,EAAU,CACd,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,KAC1C,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,MAE5C,MAAO,CACL,QACA,WAIJ,YAA0B,EAAiB,GACzC,GAAM,CACJ,QACA,WACE,GAAkC,GAEhC,EAAM,AAAG,UAAQ,AAAG,YAAU,EAAI,CAAC,EAAG,KACtC,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAC3E,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAEjF,MAAO,AAAG,aACR,AAAG,QAAM,CACP,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,KAEnB,CAAC,EAAG,IAID,YACL,EACA,EACA,GAEA,MAAO,AAAG,QAAK,KACb,GAAM,GAAY,EAAe,MAAM,GAEnC,EAAQ,GACV,AAAG,UAAQ,AAAG,OAAK,EAAO,UAAW,CAAC,EAAW,EAAG,IAAK,CAAC,GAAI,IAC9D,AAAG,UAAQ,EAAgB,CAAC,GAAI,KAElC,EAAQ,AAAG,UACT,EACA,CAAC,EAAY,EAAM,MAAM,GAAK,EAAY,IAG5C,GAAM,GAAmB,AAAG,UAAQ,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,MAC/E,EAAS,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,IAE5D,EAAS,AAAG,UACV,EACA,CAAC,EAAW,EAAO,MAAM,KAG3B,GAAM,GAAe,AAAG,UAAQ,GAC1B,EAAgB,AAAG,UAAQ,GAEjC,MAAO,CACL,MAAO,EACP,OAAQ,KC1Ed,OAAoB,OCApB,OAAoB,OAKb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAY,EAAE,MAAM,GACpB,EAAwB,AAAG,WAC/B,GAAU,EAAG,EAAO,wBACpB,CAAC,EAAW,GAAI,EAAG,IAEf,EAAkB,AAAG,WACzB,GAAU,EAAG,EAAO,iBACpB,CAAC,EAAW,GAAI,IAElB,MAAO,CAAE,wBAAuB,qBDb7B,YACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAQ,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IACjD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IAErD,EAAiB,GAAmB,EAAQ,EAAO,iBACnD,EAAiB,GAAmB,EAAG,EAAO,iBAC9C,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAElD,EAAiB,AAAG,UAAO,CAC/B,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,uBACd,GAEG,EAAmB,AAAG,UAAO,CACjC,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,iBACd,GAEH,MAAO,CACL,iBACA,sBEhDN,YAYE,YAAY,CAAE,gBAAe,cAAuC,IAN1D,WAAgB,wBAUxB,GAHA,KAAK,eAAiB,GAAiB,GACvC,KAAK,YAAc,GAAc,IAE7B,MAAO,MAAK,gBAAmB,UAAY,KAAK,gBAAkB,GAAK,KAAK,gBAAkB,EAChG,KAAM,IAAI,OAAM,GAAG,KAAK,iEAG1B,GAAI,MAAO,MAAK,aAAgB,SAC9B,KAAM,IAAI,OAAM,GAAG,KAAK,iDAIxB,iBAA0B,MAAO,MAAK,kBAEtC,cAAuB,MAAO,MAAK,cT3BzC,oBAeoC,GAClC,cACE,MAAM,kBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAQ,WACvD,EAAI,AAAG,OAAI,AAAG,OAAI,EAAa,AAAG,UAAO,sBAAwB,AAAG,UAAO,IAC3E,EAAW,GAAY,EAAG,EAAO,aAEjC,CACJ,iBACA,oBACE,GAAgB,EAAS,IAAK,EAAS,OAAQ,EAAO,kBAE1D,MAAO,IAAY,EAAgB,EAAkB,EAAO,qBAInD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,aACX,EACA,EAAkC,IAElC,GAAM,CAAE,aAAY,iBAAkB,GAAI,GAAsB,GAE1D,EAAW,KAAM,GAAW,GAE5B,CACJ,MAAO,EACP,OAAQ,GACN,KAAK,aAAa,GAEhB,EAAQ,EAAO,GACf,EAAS,EAAQ,GACvB,OAAS,GAAI,EAAG,EAAI,EAAO,OAAQ,IACjC,EAAO,GAAG,UACV,EAAQ,GAAG,UAGb,GAAM,GAAa,MAAM,KAAK,KAAM,GAAO,QAErC,EAAU,GACd,EACA,EACA,EAJmB,GAMnB,GAGI,EAAe,EAAS,2BAA2B,GACnD,EAAY,EAAS,UACrB,EAAO,EAAY,EAAa,MAChC,EAAO,EAAY,EAAa,OAEhC,EAAY,EAAM,YAClB,EAAU,EACb,IAAI,AAAC,IACJ,GAAM,CAAC,EAAK,GAAU,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACf,CAAC,GAAM,IAAS,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACrB,MAAO,IAAI,GACT,EAAW,GACX,GAAI,IACF,GACA,EACA,GAAQ,GACR,EAAS,GAEX,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,OAKtC,SAAM,UACN,EAAO,UACA,EAGC,sBACR,MAAO,wBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KUnHlB,YAA8B,GACnC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,EAGF,YAAgC,GACrC,MAAO,IAAqB,GAZ9B,oBAgBsC,MCd/B,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,QAAU,SACpB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,OAAQ,SAClB,GAAI,GAAM,QAAS,UAGR,GAAwB,CACnC,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAA+C,CAAC,QAAS,QAAS,QAElE,GAAqB,oBACrB,GAAoC,mCCvBjD,MAAoB,OCapB,GAAM,IAAW,AAAC,GAAa,MAAO,IAAQ,SAEvC,YAAwB,GAC7B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mBAAmB,KAGrC,GAAI,MAAO,GAAO,oBAAuB,UACvC,KAAM,IAAI,OAAM,wDAAwD,EAAO,sBAGjF,GAAI,CAAC,GAAS,EAAO,eAAiB,EAAO,aAAe,GAAK,EAAO,aAAe,EACrF,KAAM,IAAI,OAAM,gEAAgE,EAAO,gBAGzF,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,MAAM,AAAC,GAAW,MAAO,IAAM,UAElD,KAAM,IAAI,OAAM,kEAAkE,KAAK,UAAU,EAAO,YAG1G,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,IAAI,AAAC,GAAW,GAAK,IAAI,MAAM,AAAC,GAAW,GAAS,EAAE,IAAM,GAAS,EAAE,IAE1F,KAAM,IAAI,OAAM,wEAAwE,KAAK,UAAU,EAAO,YAGhH,GAAI,EAAO,SACT,EAAC,MAAM,QAAQ,EAAO,UACnB,EAAO,QAAQ,SAAW,GAC1B,CAAC,EAAO,QAAQ,MAAM,KAEzB,KAAM,IAAI,OAAM,8EAA8E,KAAK,UAAU,EAAO,YCjDxH,MAAoB,OCApB,MAAoB,OAEb,YAAe,GACpB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,AAAG,MAAI,EAAG,AAAG,SAAO,qBAChC,MAAO,AAAG,OAAI,AAAG,OAAK,AAAG,MAAI,EAAG,IAAO,KDApC,YAA2B,EAAgB,GAChD,MAAO,AAAG,QAAK,KACb,GAAI,GAAM,AAAG,MAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KACjD,SAAM,AAAG,SAAO,EAAK,EAAO,KAAK,QAAS,CAAC,EAAG,GAAI,SAClD,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,KAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,SAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,KAAK,MACvB,GAAM,KEZjB,OAAoB,OAKb,YAAgC,EAAgB,GACrD,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,OAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KACjD,SAAM,AAAG,mBAAgB,EAAK,EAAO,iBAAkB,EAAO,iBAAkB,CAAC,EAAG,GAAI,SACxF,EAAM,AAAG,OAAI,EAAK,EAAO,MAClB,GAAM,KCVjB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAEnE,WAAgC,EAAc,GAC5C,GAAM,GAAM,AAAG,YAAS,EAAe,IACjC,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,SAChB,CAAE,UAAW,GAAG,cAEX,CAAE,MAAK,WAGhB,WAAwC,EAAoB,EAAqB,GAC/E,GAAM,GAAO,EAAkB,EAAY,EAAa,EAAG,GAAG,UACxD,EAAK,EAAuB,EAAa,GAAG,QAClD,MAAO,CAAE,OAAM,MAEjB,GAAM,GAA6B,GAAkC,EAAgB,GAErF,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,EACA,EACA,GAEA,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAChC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAgB,GAClC,EAEJ,GAAI,EAAO,oBACT,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAAO,mBACjB,EAAkB,EAAI,EAAI,EAAG,SAC7B,EAA2B,EAAI,EAAI,SACjC,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAkB,GAAM,GAAM,EAAI,EAAI,EAAiB,EAAG,SACxE,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,eAG1D,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAAkB,EAAI,EAAI,EAAiB,EAAG,SAC5D,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,UAG5D,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAE1E,MAAO,CAAE,SAAQ,iBChFnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAgC,GAC9B,GAAM,GAAM,EAAmB,GAAG,QAAc,GAC1C,EAAU,EAAmB,GAAG,YAAkB,GACxD,MAAO,CAAE,MAAK,WAGhB,WAA2B,GACzB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,WAAwC,GACtC,GAAM,GAAO,EAAkB,GAAG,UAC5B,EAAK,EAAuB,GAAG,QACrC,MAAO,CAAE,OAAM,MAGjB,GAAM,GAA6B,GAA+B,GAClE,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAW,GAE7B,EAEJ,GAAI,EAAO,oBAET,GAAM,GAAc,EAAO,aAAe,EAAO,YAAY,QAAU,EACvE,EAAS,CACP,MAAO,EAAO,mBAAqB,EAAkB,SAAW,EAA2B,SAC3F,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAkB,cAG3B,GAAS,CACP,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAAkB,UAI7B,SAA2B,EAAW,GAC/B,CAAE,SAAQ,iBClFnB,aAYE,YAAY,CAAE,YAAW,kBAAuC,IANtD,WAAgB,oBAUxB,GAHA,KAAK,WAAa,GAAa,IAC/B,KAAK,gBAAkB,GAAkB,GAErC,MAAO,MAAK,YAAe,UAAY,KAAK,WAAa,IAAO,EAClE,KAAM,IAAI,OAAM,GAAG,KAAK,6DAG1B,GAAI,MAAO,MAAK,iBAAoB,UAAY,KAAK,iBAAmB,GAAK,KAAK,iBAAmB,EACnG,KAAM,IAAI,OAAM,GAAG,KAAK,qEAIxB,aAAsB,MAAO,MAAK,cAElC,kBAA2B,MAAO,MAAK,kBP3B7C,oBAuBoC,GAKlC,YAAY,GACV,MAAM,cACN,GAAe,GACf,KAAK,QAAU,KAGN,UACT,MAAO,MAAK,WAGH,mBACT,MAAO,MAAK,OAAO,iBAAmB,KAAK,OAAO,QAAQ,OAAS,KAG1D,mBACT,MAAO,GAAK,MAAK,gBAAkB,KAAK,OAAO,QAAQ,OAAS,GAG3D,cAAc,EAAgB,GACnC,GAAI,GAAM,GAAkB,EAAG,EAAO,OACtC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,GAAkB,EAAK,EAAO,OAC7B,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAgB,GAClC,GAAI,GAAM,KAAK,OAAO,mBAClB,GAAM,GAAU,EAAG,EAAO,MAAqB,QAAS,KACxD,GAAuB,EAAG,EAAO,OACrC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EACjE,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EAC1D,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAiB,GACnC,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,4CAGlB,MAAO,AAAG,QAAK,KACb,GAAI,GAAc,AAAG,OAAK,EAAM,cAAc,EAAW,IAAQ,WACjE,SAAc,KAAK,OAAO,QACtB,GAAU,EAAa,KAAK,OAAO,SACnC,EACJ,EAAc,EAAY,IAAI,AAAG,SAAO,MACjC,KAAK,OAAO,mBACf,KAAK,aAAa,EAAa,GAC/B,KAAK,cAAc,EAAa,UAI3B,SAAQ,EAAkB,GACrC,MAAO,MAAK,aAAa,KAAM,GAAW,GAAQ,QAGvC,QAAO,EAAkB,EAAoC,IACxE,GAAM,CAAE,YAAW,kBAAmB,GAAI,IAAkB,GACtD,EAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,EAAU,GACxC,EAAO,AAAG,OAAK,IAAM,AAAG,UAAQ,GAAK,GAAG,cACxC,EAAkB,CACtB,MAAO,EAAS,cAAc,GAC9B,OAAQ,EAAS,eAAe,IAG5B,EAAU,KAAM,MAAK,aAAa,EAAM,EAAS,2BAA2B,GAAI,GACtF,EAAI,UACJ,EAAK,UAEL,GAAM,GAAQ,EAAQ,IAAI,AAAC,GAAQ,EAAI,KACjC,EAAS,EAAQ,IAAI,AAAC,GAAQ,EAAI,OAClC,EAAc,EAAQ,IAAI,AAAC,GAAQ,EAAI,YACvC,EAAa,EAAQ,IAAI,AAAC,GAAQ,KAAK,OAAO,QAAQ,EAAI,QAgBhE,MAPmB,AAPH,IACd,EAAM,IAAI,AAAC,GAAQ,EAAI,QAAQ,IAC/B,EACA,KAAK,OAAO,aACZ,IAGyB,IAAI,AAAC,GAAQ,GAAI,IAC1C,EAAO,GACP,EAAY,GACZ,EAAW,GACX,EAAM,GACN,IAKM,sBACR,MAAO,GAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,QAG1C,cAAc,GACtB,GAAM,GAAc,KAAK,OAAO,aAAe,GAAe,qBAExD,EAAa,EAAc,EAAY,OAAS,OACtD,GAAI,IAAe,GAAK,IAAe,GAAK,IAAe,EACzD,KAAM,IAAI,OAAM,oEAAoE,2BAEtF,MAAO,IAAc,EAAS,KAAK,OAAQ,KAAK,gBAAiB,QAGnD,cACd,EACA,EACA,GAEA,GAAM,CAAE,QAAO,UAAW,EACpB,EAAY,KAAK,IAAI,EAAO,GAC5B,EAAoB,EAAY,EAChC,EAAoB,EAAY,EAEhC,EAAW,EAAa,MAAM,GAC9B,EAAW,KAAK,OAAO,QAAQ,OAE/B,CAAC,EAAa,EAAc,GAAqB,AAAG,OAAK,KAC7D,GAAM,GAAW,EAAa,QAAQ,CAAC,EAAU,EAAU,EAAU,KAAK,kBAEpE,EAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACpE,EAAS,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACrE,EAAc,KAAK,gBACrB,AAAG,UAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,KAAK,OAAO,QAAQ,SAAU,GACrG,AAAG,SAAO,GACd,MAAO,CAAC,EAAO,EAAQ,KAGnB,EAAU,GACV,EAAa,KAAM,GAAa,QAChC,EAAY,KAAM,GAAY,QACpC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAS,EAAG,EAAS,EAAU,KACtC,GAAM,GAAQ,GAAQ,EAAW,GAAK,GAAK,GAAQ,IACnD,GAAI,CAAC,GAAkB,EAAQ,GAC7B,GAAM,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAe,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACvG,EAAgB,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACxG,GAAK,EAAO,GAAa,EACzB,GAAK,GAAO,EAAc,EAC1B,GAAM,CAAE,MAAK,MAAK,UAClB,CAAE,cAAY,UAAU,KAAK,gBAC/B,KAAM,MAAK,sBAAsB,EAAkC,IACnE,CAAE,WAAY,EAAG,MAAO,GAC5B,EAAQ,KAAK,CACX,IAAK,GAAI,IAAY,GAAG,GAAG,GAAI,GAAY,GAAI,GAC/C,QACA,WAAY,EAAQ,GACpB,YACG,MAOb,SAAY,UACZ,EAAa,UACb,EAAkB,UACX,OAGK,uBAAsB,EAA4B,GAC9D,GAAM,CAAE,MAAK,MAAK,UAAW,EACvB,EAAc,KAAM,GAAc,QACxC,MAAO,OAAM,KAAK,OAAO,QAAQ,QAAQ,KAAK,GAC3C,IAAI,CAAC,EAAG,IAAM,EAAY,GAAK,GAAK,GAAQ,IAC5C,IAAI,CAAC,EAAY,IAAW,EAC3B,aACA,WAED,OAAO,CAAC,EAAK,IAAU,EAAI,WAAa,EAAK,WAAa,EAAM,KAtOvE,MAwBgB,AAxBhB,GAwBgB,qBAAuB,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,IAAK,KAAM,MQxB5E,oBAiBgC,IAC9B,YAAY,EAA8B,IACxC,GAAM,GAAS,CACb,qBACA,aAAc,GACd,QAAS,CAAC,WACN,EACA,CACA,QAAS,GACT,QAAS,IAET,CACA,QAAS,GACT,gBAAiB,KAIvB,MAAM,MAGG,sBACT,MAAO,MAAK,OAAO,sBAGV,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,MAAK,mBAAqB,GAAoC,GAG7D,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KChDrC,YAA0B,EAAuB,EAA8B,IACpF,GAAM,GAAM,GAAI,IAAW,GAC3B,SAAI,eAAe,GACZ,ECVT,oBAI6C,IAJ7C,kCAKY,WAAgB,4BCL5B,kBACe,MAEX,GAEA,MAAO,GAAY,KAAM,MAAK,YAGnB,OACX,KAAM,IAAI,OAAM,6CCRpB,OAAoB,OCDpB,OAAoB,OAOpB,kBACE,EACA,EAEA,EACA,EAEA,EAAwF,CAAC,CAAE,iBAAkB,GAE7G,GAAM,GAAY,EAAc,IAAI,AAAC,GAAkB,GAAoB,GACvE,EAAoB,GACpB,EAAa,WACX,EAAgD,GACpD,aAAoB,WAChB,KAAM,IAAmB,EAAO,GAChC,KAAM,IAAa,EAAO,IAG1B,EAAU,KAAM,GAAe,GAErC,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAGT,kBACE,EACA,EAEA,EACA,EAEA,GAEA,MAAO,IACL,CAAC,GACD,EACA,KAAO,IAAU,EAAc,EAAM,IACrC,EACA,GC5CG,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAAqC,CAAC,QAAS,QAAS,QCZrE,oBAUsC,IACpC,cACE,GAAM,GAAS,CACb,mBAAoB,GACpB,aAAc,GACd,QAAS,CAAC,QACV,QAAS,GACT,QAAS,GACT,mBAAoB,GACpB,YAAa,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,MAGzC,MAAM,MAGG,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,2BAGC,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KCvBrC,GAAM,GAAO,CAClB,eAAgB,GAAI,IACpB,iBAAkB,GAAI,IACtB,WAAY,GAAI,IAChB,kBAAmB,GAAI,IACvB,sBAAuB,GAAI,IAC3B,mBAAoB,GAAI,IACxB,kBAAmB,GAAI,IACvB,aAAc,GAAI,KAUP,GAAiB,CAAC,EAAkB,IAA6D,EAAK,eAAe,YAAY,EAAO,GASxI,GAAmB,CAAC,EAAkB,IAA+D,EAAK,iBAAiB,YAAY,EAAO,GAS9I,GAAa,CAAC,EAAkB,IAA0D,EAAK,WAAW,YAAY,EAAO,GAS7H,GAAsB,AAAC,GAAmE,EAAK,kBAAkB,gBAAgB,GAWjI,GAA0B,AAAC,GAAmE,EAAK,sBAAsB,gBAAgB,GAYzI,GAAwB,AAAC,GAA6D,EAAK,mBAAmB,sBAAsB,GASpI,GAA2B,AAAC,GAAmE,EAAK,kBAAkB,mBAAmB,GASzI,GAAsB,AAAC,GAAiF,EAAK,aAAa,oBAAoB,GAE9I,GAA0B,AAAC,GAAgB,EAAK,eAAe,KAAK,GACpE,GAA4B,AAAC,GAAgB,EAAK,iBAAiB,KAAK,GACxE,GAAsB,AAAC,GAAgB,EAAK,WAAW,KAAK,GAC5D,GAAwB,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACrE,GAA4B,AAAC,GAAgB,EAAK,sBAAsB,KAAK,GAC7E,GAA2B,AAAC,GAAgB,EAAK,mBAAmB,KAAK,GACzE,GAA0B,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACvE,GAAqB,AAAC,GAAgB,EAAK,aAAa,KAAK,GAG7D,GAAyB,GACzB,GAAc,GACd,GAAkB,GCpH/B,oBAmB4E,IAC1E,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA1Bd,gBAkCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAwB,KAAM,IAClC,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,KAEtD,KAAK,gBAGP,MAAO,GAAc,IACnB,CAAC,EAAc,IAAM,GAAmC,EAAc,EAAsB,KAIhG,mBACE,MAAO,IAAI,IAA2B,KAAM,KAAK,SArDrD,gBA2DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,GAAkB,KAAM,IAC5B,EACA,KAAK,MACL,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,GACpD,KAAK,gBAGP,MAAO,IAA0B,EAAc,GAGjD,mBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA7ExD,gBAmFU,IACR,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAzFxD,gBA+FU,IACR,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCrG1D,oBAoByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA3Bd,gBAmCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAqB,KAAM,IAC/B,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,aAAa,oBAAoB,KAElD,KAAK,gBAGP,MAAO,GAAc,IAAI,CAAC,EAAc,KACtC,GAAM,CAAE,MAAK,SAAQ,qBAAsB,EAAmB,GAC9D,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,KAIpF,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAvDxD,gBA6DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,MAAK,SAAQ,qBAAsB,KAAM,IAC/C,EACA,KAAK,MACL,AAAC,GAAS,EAAK,aAAa,oBAAoB,GAChD,KAAK,gBAGP,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,GAGlF,sBACE,MAAO,IAAI,IAAiC,KAAM,KAAK,SA/E3D,gBAqFU,IACR,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA3FxD,gBAiGU,IACR,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCvG1D,oBAiB4E,IAC1E,YAEY,EAEA,GAEV,QAJU,kBAEA,eAtBd,gBA8BU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAUjC,MAAO,AARa,MAAM,IACxB,EACA,KAAK,MACL,AAAC,GAAU,QAAQ,IAAI,EAAM,IAAI,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,KACzF,KACA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,OAGxD,IAAI,CAAC,EAAY,IAAM,GAAkC,EAAc,GAAI,IAGhG,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,SAlDtE,gBAwDU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAEF,GAAM,GAAa,KAAM,IACvB,EACA,KAAK,MACL,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,GACxD,KAEA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,MAG3E,MAAO,IAAyB,EAAc,GAGhD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,SP/EzE,oBAqByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,6BAKE,eACZ,MAAO,MAAK,mBACR,EAAK,sBACL,EAAK,oBApCb,gBA0CU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAC3B,EAAa,EAAc,IAAI,AAAC,GAAQ,EAAI,WAE5C,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,GACrC,KAAM,IAAa,KAAK,MAAO,GAE7B,EAAsB,KAAM,SAAQ,IAAI,EAAM,IAClD,AAAC,GAAS,KAAK,YAAY,gBAAgB,KAG7C,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAAc,IAAI,CAAC,EAAc,IAAM,GAAiC,EAAc,EAAoB,KAGnH,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SArExD,gBA2EU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,aAAc,EAChB,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,CAAC,IACtC,KAAM,IAAa,KAAK,MAAO,CAAC,IAE9B,EAAY,KAAM,MAAK,YAAY,gBAAgB,EAAM,IAE/D,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,GAAiC,EAAc,GAGxD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SQvG1D,oBAckD,IAChD,YAEY,EAEA,EAAgC,GAAI,IAE9C,QAJU,aAEA,iBAnBd,gBAyBwC,SACzB,OACX,GAAM,CAAE,QAAO,WAAY,KAGrB,EAAwB,YAAmB,IAE7C,AAAC,GAAqB,EAAK,iBAAiB,YAAY,EAAO,GAG/D,YAAmB,GAEf,AAAC,GAAqB,EAAK,eAAe,YAAY,EAAO,GAE7D,YAAmB,IAEf,AAAC,GAAqB,EAAK,WAAW,YAAY,EAAO,GACzD,KAIZ,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,uIAGlB,MAAO,GAAsB,GAGvB,iCAEN,MAAO,IAAI,SAAiC,KAAO,KACjD,GAAM,GAAa,KAAM,MAAK,MAC9B,EAAQ,EAAW,IAAI,AAAC,GAAc,GAAwB,GAAI,OAItE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,SA/EX,gBAoF0C,SAC3B,OACX,GAAM,GAAiB,KAAM,IAAI,IAAmB,KAAK,MAAO,KAAK,SACjE,EAAgC,EAAe,GACnD,SAAe,QAAQ,AAAC,IACtB,AAAI,EAAc,MAAQ,EAA8B,OACtD,GAAgC,KAG7B,EAGD,gCAEN,MAAO,IAAI,SAA2C,KAAO,KAC3D,GAAM,GAAY,KAAM,MAAK,MAC7B,EAAQ,EAAY,GAA4B,GAAI,GAAa,UAIrE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,SCrHJ,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAqB,EAAO,GAGlC,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAmB,EAAO,GCRvC,kBACE,EACA,GAEA,MAAO,IAAe,EAAO,GAAI,GAAsB,EAAgB,CAAE,iBAAkB,KACxF,oBACA,sBAGL,kBACE,EACA,EAAoC,IAEpC,MAAO,IAAe,EAAO,GAAI,IAAkB,IAChD,oBACA,sBAGE,GAAM,IAAW,GC1BjB,YAA2B,EAA+B,GAC/D,GAAI,EAAK,SAAW,EAAK,OAAQ,KAAM,IAAI,OAAM,kDAEjD,GAAM,GAAQ,MAAM,KAAK,GACnB,EAAQ,MAAM,KAAK,GAEzB,MAAO,MAAK,KACV,EACG,IAAI,CAAC,EAAK,IAAM,EAAM,EAAM,IAC5B,OAAO,CAAC,EAAK,IAAS,EAAO,GAAQ,EAAI,ICThD,aAUE,YACE,EACA,EAA4B,IAE5B,KAAK,mBAAqB,EAE1B,GAAM,GAAa,MAAM,QAAQ,GAAU,EAAS,CAAC,GAErD,GAAI,CAAC,EAAW,OACd,KAAM,IAAI,OAAM,2DAGlB,GAAI,GAAQ,EACN,EAAoB,IAAM,UAAU,MAE1C,KAAK,oBAAsB,EAAW,IAAI,AAAC,IACzC,GAAI,YAAgB,IAClB,MAAO,GAGT,GAAI,YAAgB,cAClB,MAAO,IAAI,IAAuB,IAAqB,CAAC,IAG1D,GAAI,EAAK,YAAc,EAAK,qBAAsB,cAChD,MAAO,IAAI,IAAuB,IAAqB,CAAC,EAAK,aAG/D,KAAM,IAAI,OAAM,4MAIT,sBAAiD,MAAO,MAAK,uBAE7D,qBAA8B,MAAO,MAAK,mBAE9C,oBAAoB,EAA+B,GACxD,MAAO,GACJ,IAAI,AAAC,GAAM,GAAkB,EAAG,IAChC,OAAO,CAAC,EAAI,IAAO,EAAK,EAAI,GACxB,GAAY,QAAU,GAGxB,gBAAgB,GACrB,MAAO,MAAK,mBACT,IAAI,CAAC,CAAE,cAAa,WAAY,GAAI,IACnC,EACA,KAAK,oBAAoB,EAAiB,KAE3C,OAAO,CAAC,EAAM,IAAU,EAAK,SAAW,EAAK,SAAW,EAAO,GAG7D,cAAc,GACnB,GAAM,GAAY,KAAK,gBAAgB,GACvC,MAAO,GAAU,SAAW,KAAK,kBAC7B,EACA,GAAI,IAAU,UAAW,EAAU,UAGlC,SACL,MAAO,CACL,kBAAmB,KAAK,kBACxB,mBAAoB,KAAK,mBAAmB,IAAI,AAAC,GAAO,EAAG,iBAIjD,UAAS,GACrB,GAAM,GAAqB,EAAK,mBAC7B,IAAI,AAAC,GAAY,GAAuB,SAAS,IACpD,MAAO,IAAI,IAAY,EAAoB,EAAK,qBC1E7C,YAAgC,GACrC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECFF,YAA0B,EAAY,GAC3C,GAAM,CAAE,QAAO,UAAW,GAAI,GAAW,EAAW,MAAO,EAAW,QAEtE,GAAI,GAAS,GAAK,GAAU,EAC1B,KAAM,IAAI,OAAM,uCAAuC,KAAK,UAAU,CAAE,QAAO,cAGjF,GAAI,MAAM,QAAQ,GAEhB,MAAQ,GAAuB,IAAI,AAAC,GAAQ,GAAc,EAAK,CAAE,QAAO,YAG1E,GAAI,GAAoB,IACtB,GAAM,GAAmB,EAAQ,UAAU,QAAQ,EAAO,GACpD,EAAmB,EAAQ,mBAAmB,QAAQ,EAAiB,IAAI,MAAO,EAAiB,IAAI,QAC7G,MAAO,IAAwB,GAAwB,EAAS,GAAmB,GAGrF,MAAI,IAAoB,GACf,GAAwB,EAAS,EAAQ,UAAU,QAAQ,EAAO,IAGvE,YAAmB,IAAiB,YAAmB,GACjD,EAAgB,QAAQ,EAAO,GAGlC,EjJRT,GAAM,IAAQ,MAAO,UAAY,YAC3B,GAAW,MAAO,YAAc,aAAiB,MAAO,WAAU,WAAc,YACzE,GAAU,CAAE,QAAa,GAAmB,QAAM", "names": [] } diff --git a/dist/face-api.esm-nobundle.json b/dist/face-api.esm-nobundle.json index 5a11bc7..2f5d65f 100644 --- a/dist/face-api.esm-nobundle.json +++ b/dist/face-api.esm-nobundle.json @@ -18,7 +18,7 @@ ] }, "src/utils/index.ts": { - "bytes": 1842, + "bytes": 1793, "imports": [ { "path": "dist/tfjs.esm.js", @@ -843,7 +843,7 @@ ] }, "src/NeuralNetwork.ts": { - "bytes": 5289, + "bytes": 5291, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1326,7 +1326,7 @@ ] }, "src/xception/TinyXception.ts": { - "bytes": 3148, + "bytes": 3143, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1553,7 +1553,7 @@ ] }, "src/faceLandmarkNet/index.ts": { - "bytes": 195, + "bytes": 194, "imports": [ { "path": "src/faceLandmarkNet/FaceLandmark68Net.ts", @@ -1609,7 +1609,7 @@ ] }, "src/faceRecognitionNet/extractParamsFromWeightMap.ts": { - "bytes": 3101, + "bytes": 3098, "imports": [ { "path": "src/common/index.ts", @@ -1635,7 +1635,7 @@ ] }, "src/faceRecognitionNet/FaceRecognitionNet.ts": { - "bytes": 2981, + "bytes": 2959, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1735,7 +1735,7 @@ ] }, "src/ssdMobilenetv1/extractParams.ts": { - "bytes": 8339, + "bytes": 8330, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1748,7 +1748,7 @@ ] }, "src/ssdMobilenetv1/extractParamsFromWeightMap.ts": { - "bytes": 5782, + "bytes": 5775, "imports": [ { "path": "src/common/index.ts", @@ -1783,11 +1783,11 @@ ] }, "src/ssdMobilenetv1/nonMaxSuppression.ts": { - "bytes": 2187, + "bytes": 2170, "imports": [] }, "src/ssdMobilenetv1/outputLayer.ts": { - "bytes": 2187, + "bytes": 2183, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1796,7 +1796,7 @@ ] }, "src/ssdMobilenetv1/boxPredictionLayer.ts": { - "bytes": 617, + "bytes": 598, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1830,7 +1830,7 @@ "imports": [] }, "src/ssdMobilenetv1/SsdMobilenetv1.ts": { - "bytes": 3826, + "bytes": 3675, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1913,7 +1913,7 @@ "imports": [] }, "src/tinyYolov2/leaky.ts": { - "bytes": 271, + "bytes": 238, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1922,7 +1922,7 @@ ] }, "src/tinyYolov2/convWithBatchNorm.ts": { - "bytes": 532, + "bytes": 530, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1935,7 +1935,7 @@ ] }, "src/tinyYolov2/depthwiseSeparableConv.ts": { - "bytes": 502, + "bytes": 500, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1948,7 +1948,7 @@ ] }, "src/tinyYolov2/extractParams.ts": { - "bytes": 3918, + "bytes": 3911, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1969,7 +1969,7 @@ ] }, "src/tinyYolov2/extractParamsFromWeightMap.ts": { - "bytes": 3284, + "bytes": 3282, "imports": [ { "path": "src/common/disposeUnusedWeightTensors.ts", @@ -1990,7 +1990,7 @@ "imports": [] }, "src/tinyYolov2/TinyYolov2Base.ts": { - "bytes": 9700, + "bytes": 9606, "imports": [ { "path": "dist/tfjs.esm.js", @@ -2080,7 +2080,7 @@ "imports": [] }, "src/tinyYolov2/index.ts": { - "bytes": 349, + "bytes": 347, "imports": [ { "path": "src/tinyYolov2/TinyYolov2.ts", @@ -2501,7 +2501,7 @@ ] }, "src/index.ts": { - "bytes": 1024, + "bytes": 987, "imports": [ { "path": "dist/tfjs.esm.js", @@ -2590,7 +2590,7 @@ "dist/face-api.esm-nobundle.js.map": { "imports": [], "inputs": {}, - "bytes": 310237 + "bytes": 309774 }, "dist/face-api.esm-nobundle.js": { "imports": [], @@ -2901,7 +2901,7 @@ "bytesInOutput": 621 }, "src/NeuralNetwork.ts": { - "bytesInOutput": 2640 + "bytesInOutput": 2654 }, "src/faceFeatureExtractor/denseBlock.ts": { "bytesInOutput": 568 @@ -3033,7 +3033,7 @@ "bytesInOutput": 176 }, "src/faceRecognitionNet/FaceRecognitionNet.ts": { - "bytesInOutput": 1062 + "bytesInOutput": 1156 }, "src/faceRecognitionNet/convLayer.ts": { "bytesInOutput": 277 @@ -3186,7 +3186,7 @@ "bytesInOutput": 443 } }, - "bytes": 82050 + "bytes": 82158 } } } diff --git a/dist/face-api.esm.js b/dist/face-api.esm.js index 19f12a4..2a6148a 100644 --- a/dist/face-api.esm.js +++ b/dist/face-api.esm.js @@ -4045,7 +4045,7 @@ return a / b;`,hZ=` } setOutput(${l}); } - `}};function Dee(e){let{inputs:t,backend:n,attrs:a}=e,{x:r,segmentIds:s}=t,{numSegments:i}=a,o=r.shape.length,l=[],c=0,u=E.getAxesPermutation([c],o),p=r;u!=null&&(p=Sn({inputs:{x:r},backend:n,attrs:{perm:u}}),l.push(p),c=E.getInnerMostAxes(1,o)[0]);let d=E.segment_util.computeOutShape(p.shape,c,i),h=k.sizeFromShape([p.shape[c]]),m=ve({inputs:{x:p},backend:n,attrs:{shape:[-1,h]}});l.push(m);let f=eh(r.dtype),g=(x,N,T,C,$)=>{let F=x.shape[0],O=x.shape[1],W=E.segment_util.segOpComputeOptimalWindowSize(O,$),V={windowSize:W,inSize:O,batchSize:F,numSegments:$},H=new $ee(V,N),K=n.compileAndRun(H,[x,T],C);if(l.push(K),K.shape[1]===$)return K;let j=a2({backend:n,attrs:{start:0,stop:$,step:1,dtype:"float32"}}),Y=i2({inputs:{x:j},backend:n,attrs:{reps:[O/W]}});return l.push(j),l.push(Y),g(K,N,Y,C,$)},y=g(m,"unsortedSegmentSum",s,f,i),b=ve({inputs:{x:y},backend:n,attrs:{shape:d}}),v=b;if(u!=null){l.push(b);let x=E.getUndoAxesPermutation(u);v=Sn({inputs:{x:v},backend:n,attrs:{perm:x}})}return l.forEach(x=>n.disposeIntermediateTensorInfo(x)),v}var Mee={kernelName:Nc,backendName:"webgl",kernelFunc:Dee},Ree=[C9,A9,fX,yX,vX,IX,TX,_X,AX,$X,PX,LX,WX,GX,JX,qX,eY,rY,nY,lY,cY,dY,gY,IY,TY,FY,DY,OY,BY,YK,GY,e7,n7,KY,i7,l7,r7,p7,m7,y7,x7,w7,N7,A7,$7,S7,R7,L7,V7,j7,Y7,Q7,eJ,tJ,aJ,sJ,oJ,uJ,pJ,fJ,xJ,wJ,IJ,SJ,AJ,MJ,LJ,XK,BJ,UY,UJ,jJ,XJ,ZK,QJ,a9,s9,d9,u9,g9,x9,I9,$9,B9,L9,G9,j9,K9,P9,Y9,Z9,nZ,iZ,cZ,bZ,aX,vZ,IZ,SZ,EZ,CY,$Z,MZ,PZ,zZ,UZ,eX,HZ,jZ,_Y,mZ,XZ,aQ,QZ,sX,oQ,cQ,hQ,gQ,vQ,kQ,TQ,_Q,AQ,DQ,PQ,zQ,VQ,HQ,KQ,wY,gZ,JQ,QQ,tee,aee,iee,uee,pee,hee,gee,fZ,dX,xee,kee,Tee,Cee,hX,Eee,Fee,Mee,DZ];for(let e of Ree)Sc(e);var Pee="2.8.5",Oee={"tfjs-core":X0,"tfjs-backend-cpu":hG,"tfjs-backend-webgl":KK,"tfjs-data":PN,"tfjs-layers":mm,"tfjs-converter":AN,tfjs:Pee},Vn;(function(e){e[e.float32=0]="float32",e[e.int32=1]="int32",e[e.bool=2]="bool",e[e.string=3]="string",e[e.complex64=4]="complex64"})(Vn||(Vn={}));var Cp;(function(e){e[e.linear=0]="linear",e[e.relu=1]="relu",e[e.relu6=2]="relu6",e[e.prelu=3]="prelu",e[e.leakyrelu=4]="leakyrelu"})(Cp||(Cp={}));var o2;function Lee(e){o2=e.wasm.cwrap(bi,null,["number","array","number","number","array","number","number","number","number","number","number","number","number"])}function zee(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s,bias:i,preluActivationWeights:o}=t;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("_FusedMatMul for non non-float32 tensors not yet supported.");let{transposeA:l,transposeB:c,activation:u,leakyreluAlpha:p}=a,d=n.dataIdMap.get(r.dataId).id,h=n.dataIdMap.get(s.dataId).id,m=0;if(i!=null){let $=n.dataIdMap.get(i.dataId);if($.shape.length!==1)throw new Error(`_FusedMatMul only supports rank-1 bias but got rank ${$.shape.length}.`);m=$.id}let f=o==null?0:n.dataIdMap.get(o.dataId).id,g=Cp[u];if(g==null)throw new Error(`${u} activation not yet supported for FusedConv2D in the wasm backend.`);let y=l?r.shape[2]:r.shape[1],b=c?s.shape[1]:s.shape[2],v=r.shape[0],x=n.makeOutput([v,y,b],r.dtype),N=n.dataIdMap.get(x.dataId).id,T=new Uint8Array(new Int32Array(r.shape).buffer),C=new Uint8Array(new Int32Array(s.shape).buffer);return o2(d,T,r.shape.length,h,C,s.shape.length,l,c,g,m,f,p||0,N),x}var Bee={kernelName:bi,backendName:"wasm",setupFunc:Lee,kernelFunc:zee};function Un(e){let t;function n(r){t=r.wasm.cwrap(e,null,["number","number"])}function a(r){let{backend:s,inputs:{x:i}}=r,o=s.dataIdMap.get(i.dataId).id,l=s.makeOutput(i.shape,i.dtype),c=s.dataIdMap.get(l.dataId).id;return k.sizeFromShape(l.shape)===0||t(o,c),l}return{kernelName:e,backendName:"wasm",setupFunc:n,kernelFunc:a}}var Wee=Un(Co);function gn(e,t,n){let a;function r(i){a=i.wasm.cwrap(e,null,["number","array","number","number","array","number","number","number"])}function s(i){let{backend:o,inputs:l}=i,{a:c,b:u}=l,p=o.dataIdMap.get(c.dataId).id,d=o.dataIdMap.get(u.dataId).id,h=n!=null?n:c.dtype,m=E.assertAndGetBroadcastShape(c.shape,u.shape),f=o.makeOutput(m,h);if(k.sizeFromShape(m)===0)return f;let g=new Uint8Array(new Int32Array(c.shape).buffer),y=new Uint8Array(new Int32Array(u.shape).buffer),b=o.dataIdMap.get(f.dataId).id,v=()=>a(p,g,c.shape.length,d,y,u.shape.length,Vn[c.dtype],b);if(t&&c.dtype==="float32")return v(),f;let x=E.getBroadcastDims(c.shape,m),N=E.getBroadcastDims(u.shape,m),T=x.every(($,F)=>$===F),C=N.every(($,F)=>$===F);if(T&&C)return v(),f;throw new Error(`Broadcasting along outer dims is not yet supported for ${c.dtype} ${e}.`)}return{kernelName:e,backendName:"wasm",setupFunc:r,kernelFunc:s}}var Vee=!0,Uee=gn(Wr,Vee),l2;function Gee(e){l2=e.wasm.cwrap(_s,null,["array","number","number","number"])}function Hee(e){let{inputs:t,backend:n}=e,a=n.makeOutput(t[0].shape,t[0].dtype);if(k.sizeFromShape(a.shape)===0)return a;let r=t.map(o=>n.dataIdMap.get(o.dataId).id),s=new Uint8Array(new Int32Array(r).buffer),i=n.dataIdMap.get(a.dataId).id;return l2(s,r.length,Vn[a.dtype],i),a}var jee={kernelName:_s,backendName:"wasm",setupFunc:Gee,kernelFunc:Hee};function Km(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype),r=n.typedArrayFromHeap(t);return n.typedArrayFromHeap(a).set(r),a}var qee={kernelName:Xo,backendName:"wasm",kernelFunc:Km},u2;function Kee(e){u2=e.wasm.cwrap(yi,null,["number","array","number","number","number","array","number"])}function Xm(e){let{inputs:t,backend:n,attrs:a}=e,[r,s]=Yee(t.x.shape,a.perm),i=!0;for(let m=0;m=r&&(s===-1||a[s]>a[i])&&(s=i);a[s]=r}return[n,a]}var Jee={kernelName:yi,backendName:"wasm",kernelFunc:Xm,setupFunc:Kee};function gu(e,t,n){let a=e.shape,r=e.shape.length,s=k.parseAxisParam(t,a),i=s,o=E.getAxesPermutation(i,r),l=null,c=!1;if(o!=null){let u=new Array(r);for(let d=0;d`new shape: ${i}, old shape: ${a.shape}. New shape and old shape must have the same number of elements.`),{dataId:a.dataId,shape:i,dtype:a.dtype}}var rte={kernelName:hl,backendName:"wasm",kernelFunc:La},d2;function ste(e){d2=e.wasm.cwrap(Fs,null,["number","array","number","number","array","number","number","number","number"])}function ite(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s}=t,{transposeA:i,transposeB:o}=a;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("BatchMatMul for non non-float32 tensors not yet supported.");let l=r.shape.length,c=s.shape.length,u=i?r.shape[l-2]:r.shape[l-1],p=o?s.shape[c-1]:s.shape[c-2],d=i?r.shape[l-1]:r.shape[l-2],h=o?s.shape[c-2]:s.shape[c-1],m=r.shape.slice(0,-2),f=s.shape.slice(0,-2),g=k.sizeFromShape(m),y=k.sizeFromShape(f),b=g===y||g===1||y===1;k.assert(l>=2&&c>=2&&b,()=>`Error in matMul: the input batch dimensions must either be the same or at least one input batch dimension must be 1. Got input batch dimensions of (${m}) and (${f}).`);let v=(g>y?r.shape.slice(0,-2):s.shape.slice(0,-2)).concat([d,h]);k.assert(u===p,()=>`Error in matMul: inner shapes (${u}) and (${p}) of Tensors with shapes ${r.shape} and ${s.shape} and transposeA=${i} and transposeB=${o} must match.`);let x=i?[g,u,d]:[g,d,u],N=o?[y,h,p]:[y,p,h],T=La({inputs:{x:r},backend:n,attrs:{shape:x}}),C=La({inputs:{x:s},backend:n,attrs:{shape:N}}),$=n.dataIdMap.get(T.dataId).id,F=n.dataIdMap.get(C.dataId).id,O=i?T.shape[2]:T.shape[1],W=o?C.shape[1]:C.shape[2],V=Math.max(g,y),H=n.makeOutput([V,O,W],T.dtype),K=n.dataIdMap.get(H.dataId).id,j=new Uint8Array(new Int32Array(T.shape).buffer),Y=new Uint8Array(new Int32Array(C.shape).buffer);return d2($,j,T.shape.length,F,Y,C.shape.length,i,o,K),H.shape=v,H}var ote={kernelName:Fs,backendName:"wasm",setupFunc:ste,kernelFunc:ite};function Ym(e){let{inputs:{x:t},attrs:{dtype:n},backend:a}=e,r=a.makeOutput(t.shape,n),s=a.typedArrayFromHeap(t);return a.typedArrayFromHeap(r).set(s),r}var lte={kernelName:$s,backendName:"wasm",kernelFunc:Ym},h2;function ute(e){h2=e.wasm.cwrap(Vr,null,["number","number","number","number"])}function cte(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{clipValueMin:s,clipValueMax:i}=a,o=n.dataIdMap.get(r.dataId).id,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(l.dataId).id;return h2(o,s,i,c),l}var pte={kernelName:Vr,backendName:"wasm",setupFunc:ute,kernelFunc:cte};function m2(e){let{inputs:t,backend:n}=e,a=k.parseAxisParam(e.attrs.axis,t[0].shape)[0],r=E.computeOutShape(t.map(h=>h.shape),a),s=t.filter(h=>k.sizeFromShape(h.shape)>0);if(s.length===1)return Km({inputs:{x:s[0]},backend:n});let i=n.makeOutput(r,t[0].dtype);if(k.sizeFromShape(r)===0)return i;let o=s.map(h=>h.shape);if(E.assertParamsConsistent(o,a),s[0].dtype==="string"){let h=s.map(v=>{let x=k.sizeFromShape(v.shape.slice(a));return La({inputs:{x:v},backend:n,attrs:{shape:[-1,x]}})}),m=h.map(v=>({vals:n.readSync(v.dataId),shape:v.shape}));r=E.computeOutShape(h.map(v=>v.shape),1);let f=h[0].shape[0]===1,g=dv(m,r,t[0].dtype,f),y=E.computeOutShape(s.map(v=>v.shape),a);i.shape=y;let b=n.dataIdMap.get(i.dataId);return b.stringBytes=E.fromStringArrayToUint8(g),i}let l=k.sizeFromShape(s[0].shape.slice(0,a)),c=0,u=s.map(h=>{let m=k.sizeFromShape(h.shape.slice(a));return c+=m,m}),p=s.map(h=>n.typedArrayFromHeap(h)),d=n.typedArrayFromHeap(i);for(let h=0;h`cumsum does not support ${r.dtype} tensors in the WASM backend`);let c=E.getAxesPermutation([s],l),u=r;c!==null&&(u=Xm({inputs:{x:r},attrs:{perm:c},backend:n}));let p=E.getInnerMostAxes(1,l)[0];E.assertAxesAreInnerMostDims("cumsum",[p],l);let d=n.makeOutput(u.shape,u.dtype),h=u.shape[p],m=n.dataIdMap.get(u.dataId).id,f=n.dataIdMap.get(d.dataId).id;b2(m,i?1:0,o?1:0,h,f,Vn[r.dtype]);let g=d;if(c!==null){let y=E.getUndoAxesPermutation(c);g=Xm({inputs:{x:d},attrs:{perm:y},backend:n}),n.disposeData(u.dataId),n.disposeData(d.dataId)}return g}var Tte={kernelName:Ps,backendName:"wasm",setupFunc:Ite,kernelFunc:Nte},x2;function Ste(e){x2=e.wasm.cwrap(zo,null,["number","number","number","array","number","array","array","number","number"])}function Cte(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{blockSize:s,dataFormat:i}=a;k.assert(s>1,()=>`blockSize should be > 1 for depthToSpace, but was: ${s}`);let o=r.shape[0],l=i==="NHWC"?r.shape[1]:r.shape[2],c=i==="NHWC"?r.shape[2]:r.shape[3],u=i==="NHWC"?r.shape[3]:r.shape[1],p=l*s,d=c*s,h=u/(s*s),m=i==="NHWC"?[o,p,d,h]:[o,h,p,d],f=t.makeOutput(m,"float32"),g=t.dataIdMap.get(r.dataId).id,y=new Uint8Array(new Int32Array(k.computeStrides(r.shape)).buffer),b=new Uint8Array(new Int32Array(m).buffer),v=new Uint8Array(new Int32Array(k.computeStrides(m)).buffer),x=t.dataIdMap.get(f.dataId).id;return x2(g,s,i==="NHWC"?1:0,y,r.shape.length-1,b,v,m.length,x),f}var _te={kernelName:zo,backendName:"wasm",setupFunc:Ste,kernelFunc:Cte},v2;function Ete(e){v2=e.wasm.cwrap(Os,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Ate(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s}=t,i=a.dataIdMap.get(r.dataId).id,o=a.dataIdMap.get(s.dataId).id,{strides:l,dilations:c,pad:u,dimRoundingMode:p}=n,d=c==null?[1,1]:c,h=E.computeConv2DInfo(r.shape,s.shape,l,d,u,p,!0),m=h.filterHeight,f=h.filterWidth,g=h.padInfo.top,y=h.padInfo.right,b=h.padInfo.bottom,v=h.padInfo.left,x=h.dilationHeight,N=h.dilationWidth,T=h.strideHeight,C=h.strideWidth,$=h.inChannels,F=h.outChannels,O=h.padInfo.type==="SAME"?1:0;if(h.dataFormat!=="channelsLast")throw new Error(`wasm backend DepthwiseConv2dNative does not support dataFormat:'${h.dataFormat}'. Please use 'channelsLast'.`);let W=a.makeOutput(h.outShape,"float32"),V=a.dataIdMap.get(W.dataId).id;return v2(i,r.shape[0],r.shape[1],r.shape[2],o,m,f,g,y,b,v,O,x,N,T,C,$,F,V),W}var Fte={kernelName:Os,backendName:"wasm",setupFunc:Ete,kernelFunc:Ate},$te=!1,Dte=gn(Vo,$te,"bool"),Mte=Un(zs);function Uv(e){let{inputs:t,attrs:n,backend:a}=e,{input:r}=t,{dim:s}=n,i=r.shape.length,o=r.shape.slice(),l=s;return s<0&&(k.assert(-(i+1)<=s,()=>`Axis must be in the interval [${-(i+1)}, ${i}]`),l=i+s+1),o.splice(l,0,1),La({inputs:{x:r},backend:a,attrs:{shape:o}})}var Rte={kernelName:Uo,backendName:"wasm",kernelFunc:Uv};function Pte(e){let{attrs:{shape:t,value:n,dtype:a},backend:r}=e,s=r.makeOutput(t,a);return r.typedArrayFromHeap(s).fill(n),s}var Ote={kernelName:mc,backendName:"wasm",kernelFunc:Pte},w2;function Lte(e){w2=e.wasm.cwrap(Ho,null,["number","number","number","number","number","number"])}function zte(e){let{inputs:t,backend:n}=e,{image:a}=t,r=n.makeOutput(a.shape,a.dtype),s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,[o,l,c,u]=a.shape;return w2(s,o,l,c,u,i),r}var Bte={kernelName:Ho,backendName:"wasm",kernelFunc:zte,setupFunc:Lte},Wte=Un(Bs),Vte=!1,Ute=gn(Ws,Vte),k2;function Gte(e){k2=e.wasm.cwrap(Vs,null,["number","number","number","number","number","number","number"])}function Hte(e){let{backend:t,inputs:n,attrs:a}=e,{varianceEpsilon:r}=a,{x:s,mean:i,variance:o,offset:l,scale:c}=n,u=t.dataIdMap.get(s.dataId).id,p=t.dataIdMap.get(i.dataId).id,d=t.dataIdMap.get(o.dataId).id,h=l!=null?t.dataIdMap.get(l.dataId).id:0,m=c!=null?t.dataIdMap.get(c.dataId).id:0,f=t.makeOutput(s.shape,s.dtype);if(k.sizeFromShape(s.shape)===0)return f;let g=t.dataIdMap.get(f.dataId).id;return k2(u,p,d,h,m,r,g),f}var jte={kernelName:Vs,backendName:"wasm",setupFunc:Gte,kernelFunc:Hte},I2;function qte(e){I2=e.wasm.cwrap(xi,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Kte(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d),g=Cp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return I2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Xte={kernelName:xi,backendName:"wasm",setupFunc:qte,kernelFunc:Kte},N2;function Yte(e){N2=e.wasm.cwrap(vi,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Jte(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d,!0),g=Cp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedDepthwiseConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedDepthwiseConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedDepthwiseConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedDepthwiseConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return N2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Zte={kernelName:vi,backendName:"wasm",setupFunc:Yte,kernelFunc:Jte},T2;function Qte(e){T2=e.wasm.cwrap(qo,null,["number","number","number","number","number","number","array","number"])}function ene(e){let{backend:t,inputs:n}=e,{params:a,indices:r}=n,[s,i,o,l]=my.prepareAndValidate(a,r),c=t.makeOutput(s,a.dtype);if(i===0)return c;let u=r.shape,p=u[u.length-1],d=t.dataIdMap.get(a.dataId).id,h=t.dataIdMap.get(r.dataId).id,m=new Uint8Array(new Int32Array(l).buffer),f=t.dataIdMap.get(c.dataId).id;return T2(d,Vn[a.dtype],h,i,p,o,m,f),c}var tne={kernelName:qo,backendName:"wasm",setupFunc:Qte,kernelFunc:ene},S2;function nne(e){S2=e.wasm.cwrap("Gather",null,["number","number","array","number","number","number","array","number"])}function ane(e){let{backend:t,inputs:n,attrs:a}=e,{x:r,indices:s}=n,{axis:i,batchDims:o}=a,l=k.parseAxisParam(i,r.shape)[0],c=E.segment_util.collectGatherOpShapeInfo(r,s,l,o),u=La({inputs:{x:r},attrs:{shape:[c.batchSize,c.outerSize,c.dimSize,c.sliceSize]},backend:t}),p=k.sizeFromShape(s.shape),d=La({inputs:{x:s},attrs:{shape:[c.batchSize,p/c.batchSize]},backend:t}),h=[c.batchSize,c.outerSize,p/c.batchSize,c.sliceSize],m=t.makeOutput(h,r.dtype);if(k.sizeFromShape(r.shape)===0)return m;let f=u.shape.length-1,g=t.dataIdMap.get(u.dataId).id,y=t.dataIdMap.get(d.dataId).id,b=t.dataIdMap.get(m.dataId).id,v=new Uint8Array(new Int32Array(k.computeStrides(u.shape)).buffer),x=new Uint8Array(new Int32Array(k.computeStrides(h)).buffer);return S2(g,Vn[r.dtype],v,f,y,c.batchSize,x,b),m.shape=c.outputShape,m}var rne={kernelName:jo,backendName:"wasm",setupFunc:nne,kernelFunc:ane},sne=!1,ine=gn(Ko,sne,"bool"),one=!1,lne=gn(Us,one,"bool"),C2;function une(e){C2=e.wasm.cwrap(Gs,null,["number","number","number"])}function cne(e){let{inputs:{x:t},attrs:{alpha:n},backend:a}=e,r=a.dataIdMap.get(t.dataId).id,s=a.makeOutput(t.shape,t.dtype);if(k.sizeFromShape(t.shape)!==0){let i=a.dataIdMap.get(s.dataId).id;C2(r,n,i)}return s}var pne={kernelName:Gs,backendName:"wasm",setupFunc:une,kernelFunc:cne},dne=!1,hne=gn(Qo,dne,"bool"),mne=!1,fne=gn(el,mne,"bool"),gne=Un(Hs),yne=!1,bne=gn(nl,yne,"bool"),_2;function xne(e){_2=e.wasm.cwrap(js,null,["number, number, number"])}function vne(e){let{backend:t,inputs:n,attrs:a}=e,{reductionIndices:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=i,{transposed:c,axes:u,originalAxes:p,inputWasTransposed:d}=gu(i,r,t);if(d){let b=t.dataIdMap.get(c.dataId).id;l=c,o=b}let h=l.shape.length;E.assertAxesAreInnerMostDims("max",u,h);let[m,f]=E.computeOutAndReduceShapes(l.shape,u),g=k.sizeFromShape(f),y=t.makeOutput(m,i.dtype);if(k.sizeFromShape(l.shape)!==0){let b=t.dataIdMap.get(y.dataId).id;_2(o,g,b)}if(d&&t.disposeData(c.dataId),s){let b=E.expandShapeToKeepDim(y.shape,p);y.shape=b}return y}var wne={kernelName:js,backendName:"wasm",setupFunc:xne,kernelFunc:vne},kne=!1,Ine=gn(qs,kne),E2;function Nne(e){E2=e.wasm.cwrap(Ks,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Tne(e){let{inputs:t,attrs:n,backend:a}=e,r=t.x,s=a.dataIdMap.get(r.dataId).id,{filterSize:i,strides:o,pad:l,dimRoundingMode:c}=n,u=E.computePool2DInfo(r.shape,i,o,1,l,c),p=u.filterHeight,d=u.filterWidth,h=u.padInfo.top,m=u.padInfo.right,f=u.padInfo.bottom,g=u.padInfo.left,y=u.dilationHeight,b=u.dilationWidth,v=u.strideHeight,x=u.strideWidth,N=u.inChannels,T=u.outChannels;if(u.dataFormat!=="channelsLast")throw new Error(`wasm backend does not support dataFormat:'${u.dataFormat}'. Please use 'channelsLast'.`);let C=a.makeOutput(u.outShape,"float32"),$=a.dataIdMap.get(C.dataId).id;return E2(s,r.shape[0],r.shape[1],r.shape[2],p,d,h,m,f,g,y,b,v,x,N,T,$),C}var Sne={kernelName:Ks,backendName:"wasm",setupFunc:Nne,kernelFunc:Tne},A2;function Cne(e){A2=e.wasm.cwrap(Xs,null,["number, number, number"])}function _ne(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t),m=p;if(h){let x=t.dataIdMap.get(u.dataId).id;x!==o&&(c=u,l=x,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("mean",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=c;c.dtype!=="float32"&&(b=Ym({backend:t,inputs:{x:c},attrs:{dtype:"float32"}}),l=t.dataIdMap.get(b.dataId).id);let v=t.makeOutput(f,"float32");if(k.sizeFromShape(c.shape)!==0){let x=t.dataIdMap.get(v.dataId).id;A2(l,y,x)}if(h&&t.disposeData(u.dataId),s){let x=E.expandShapeToKeepDim(v.shape,d);v.shape=x}return c.dtype!=="float32"&&t.disposeData(b.dataId),v}var Ene={kernelName:Xs,backendName:"wasm",setupFunc:Cne,kernelFunc:_ne},F2;function Ane(e){F2=e.wasm.cwrap(Ys,null,["number, number, number"])}function Fne(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t);if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v)}let m=c.shape.length;E.assertAxesAreInnerMostDims("min",p,m);let[f,g]=E.computeOutAndReduceShapes(c.shape,p),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;F2(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var $ne={kernelName:Ys,backendName:"wasm",setupFunc:Ane,kernelFunc:Fne},Dne=!1,Mne=gn(Js,Dne),Rne=!0,Pne=gn(Zs,Rne),One=Un(rl);function Gv(e,t){let n=new Int32Array(e.wasm.HEAPU8.buffer,t,4),a=n[0],r=n[1],s=n[2],i=n[3];return e.wasm._free(t),{pSelectedIndices:a,selectedSize:r,pSelectedScores:s,pValidOutputs:i}}var $2;function Lne(e){$2=e.wasm.cwrap(il,"number",["number","number","number","number","number"])}function zne(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i}=a,{boxes:o,scores:l}=n,c=t.dataIdMap.get(o.dataId).id,u=t.dataIdMap.get(l.dataId).id,p=$2(c,u,s,r,i),{pSelectedIndices:d,selectedSize:h,pSelectedScores:m,pValidOutputs:f}=Gv(t,p);return t.wasm._free(m),t.wasm._free(f),t.makeOutput([h],"int32",d)}var Bne={kernelName:il,backendName:"wasm",setupFunc:Lne,kernelFunc:zne},D2;function Wne(e){D2=e.wasm.cwrap(ol,"number",["number","number","number","number","number","bool"])}function Vne(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,padToMaxOutputSize:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=D2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=Gv(t,d);t.wasm._free(f);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([],"int32",g);return[y,b]}var Une={kernelName:ol,backendName:"wasm",setupFunc:Wne,kernelFunc:Vne},M2;function Gne(e){M2=e.wasm.cwrap(ll,"number",["number","number","number","number","number","number"])}function Hne(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,softNmsSigma:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=M2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=Gv(t,d);t.wasm._free(g);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([m],"float32",f);return[y,b]}var jne={kernelName:ll,backendName:"wasm",setupFunc:Gne,kernelFunc:Hne},qne=!1,Kne=gn(sl,qne,"bool"),R2;function Xne(e){R2=e.wasm.cwrap(Qs,null,["number","number","number","number","number"])}function Yne(e){let{inputs:t,backend:n,attrs:a}=e,{indices:r}=t,{depth:s,onValue:i,offValue:o}=a,l=n.makeOutput([...r.shape,s],"int32"),c=n.dataIdMap.get(l.dataId).id,u=n.dataIdMap.get(r.dataId).id;return R2(u,s,i,o,c),l}var Jne={kernelName:Qs,backendName:"wasm",setupFunc:Xne,kernelFunc:Yne};function Zne(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(1),a}var Qne={kernelName:ul,backendName:"wasm",kernelFunc:Zne};function eae(e){let{inputs:t,backend:n,attrs:a}=e,{axis:r}=a;if(t.length===1)return Uv({inputs:{input:t[0]},backend:n,attrs:{dim:r}});let s=t[0].shape,i=t[0].dtype;t.forEach(l=>{k.assertShapesMatch(s,l.shape,"All tensors passed to stack must have matching shapes"),k.assert(i===l.dtype,()=>"All tensors passed to stack must have matching dtypes")});let o=t.map(l=>Uv({inputs:{input:l},backend:n,attrs:{dim:r}}));return m2({inputs:o,backend:n,attrs:{axis:r}})}var tae={kernelName:cl,backendName:"wasm",kernelFunc:eae},P2;function nae(e){P2=e.wasm.cwrap(ei,null,["number","array","number","number","array","array","number","number"])}function aae(e){let{inputs:{x:t},backend:n,attrs:{paddings:a,constantValue:r}}=e,s=a.map((m,f)=>m[0]+t.shape[f]+m[1]),i=n.dataIdMap.get(t.dataId).id,o=n.makeOutput(s,t.dtype),l=n.dataIdMap.get(o.dataId).id,c=new Uint8Array(new Int32Array(t.shape).buffer),u=a.map(m=>m[0]),p=a.map(m=>m[1]),d=new Uint8Array(new Int32Array(u).buffer),h=new Uint8Array(new Int32Array(p).buffer);return P2(i,c,t.shape.length,Vn[t.dtype],d,h,r,l),o}var rae={kernelName:ei,backendName:"wasm",kernelFunc:aae,setupFunc:nae},sae=!1,iae=gn(ti,sae),O2;function oae(e){O2=e.wasm.cwrap(ni,null,["number","number","number"])}function lae(e){let{inputs:t,backend:n}=e,{x:a,alpha:r}=t,s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,o=n.makeOutput(a.shape,"float32"),l=n.dataIdMap.get(o.dataId).id;return O2(s,i,l),o}var uae={kernelName:ni,backendName:"wasm",setupFunc:oae,kernelFunc:lae},L2;function cae(e){L2=e.wasm.cwrap(pl,null,["number","number","number","number"])}function pae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("prod",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;L2(l,y,Vn[b.dtype],v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var dae={kernelName:pl,backendName:"wasm",setupFunc:cae,kernelFunc:pae},hae=e=>{let{backend:t,attrs:n}=e,{start:a,stop:r,step:s,dtype:i}=n,o=fv(a,r,s,i),l=t.makeOutput([o.length],i);return t.typedArrayFromHeap(l).set(o),l},mae={kernelName:vc,backendName:"wasm",kernelFunc:hae},fae=!0,gae=gn(Ls,fae),yae=Un(ai),bae=Un(si),z2;function xae(e){z2=e.wasm.cwrap(ri,null,["number","number","number","number","number","number","number","number","number","number"])}function vae(e){let{backend:t,inputs:n,attrs:a}=e,{images:r}=n,{alignCorners:s,halfPixelCenters:i,size:o}=a,[l,c]=o,[u,p,d,h]=r.shape,m=[u,l,c,h],f=t.dataIdMap.get(r.dataId),g;f.dtype!=="float32"&&(g=Ym({backend:t,inputs:{x:r},attrs:{dtype:"float32"}}),f=t.dataIdMap.get(g.dataId));let y=f.id,b=t.makeOutput(m,"float32");if(k.sizeFromShape(r.shape)===0)return b;let v=t.dataIdMap.get(b.dataId).id;return z2(y,u,p,d,h,l,c,s?1:0,i?1:0,v),g!=null&&t.disposeData(g.dataId),b}var wae={kernelName:ri,backendName:"wasm",setupFunc:xae,kernelFunc:vae},B2;function kae(e){B2=e.wasm.cwrap(ii,null,["number","array","number","array","number","number"])}function Iae(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{dims:s}=a,i=k.parseAxisParam(s,r.shape);if(r.shape.length===0)return Km({inputs:{x:r},backend:n});let o=n.makeOutput(r.shape,r.dtype),l=n.dataIdMap.get(r.dataId).id,c=n.dataIdMap.get(o.dataId).id,u=new Uint8Array(new Int32Array(i).buffer),p=new Uint8Array(new Int32Array(r.shape).buffer);return B2(l,u,i.length,p,r.shape.length,c),La({inputs:{x:o},attrs:{shape:r.shape},backend:n})}var Nae={kernelName:ii,backendName:"wasm",kernelFunc:Iae,setupFunc:kae},W2;function Tae(e){W2=e.wasm.cwrap(Cl,null,["number","number","number","number","number","number","number","number","array","number","number"])}function Sae(e){let{inputs:t,backend:n,attrs:a}=e,{image:r}=t,{radians:s,fillValue:i,center:o}=a,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(r.dataId).id,u=n.dataIdMap.get(l.dataId).id,[p,d,h,m]=r.shape,[f,g]=E.getImageCenter(o,d,h),y=i===0,b=255,v=typeof i=="number"?[i,i,i,y?0:b]:[...i,b],x=new Uint8Array(new Int32Array(v).buffer);return W2(c,p,d,h,m,s,f,g,x,v.length,u),l}var Cae={kernelName:Cl,backendName:"wasm",kernelFunc:Sae,setupFunc:Tae},_ae=Un(oi),Eae=Un(li),V2;function Aae(e){V2=e.wasm.cwrap(ml,null,["number","number","number","number","number","number","array","number","number"])}function Fae(e){let{backend:t,inputs:n,attrs:a}=e,{indices:r,updates:s}=n,{shape:i}=a,o=t.makeOutput(i,s.dtype);if(k.sizeFromShape(i)===0)return o;let{sliceRank:l,numUpdates:c,sliceSize:u,strides:p,outputSize:d}=fy.calculateShapes(s,r,i),h=t.dataIdMap.get(r.dataId).id,m=t.dataIdMap.get(s.dataId).id,f=new Uint8Array(new Int32Array(p).buffer),g=t.dataIdMap.get(o.dataId).id;return V2(h,m,Vn[s.dtype],l,c,u,f,d,g),o}var $ae={kernelName:ml,backendName:"wasm",setupFunc:Aae,kernelFunc:Fae},U2;function Dae(e){U2=e.wasm.cwrap("SelectV2",null,["number","number","number","number","number"])}function Mae(e){let{inputs:t,backend:n}=e,{condition:a,t:r,e:s}=t,i=n.dataIdMap.get(a.dataId).id,o=n.dataIdMap.get(r.dataId).id,l=n.dataIdMap.get(s.dataId).id,c=n.makeOutput(r.shape,r.dtype),u=n.dataIdMap.get(c.dataId).id,p=a.shape.length,d=r.shape.length,h=p===0||p>1||d===1?1:k.sizeFromShape(r.shape.slice(1));return U2(i,o,l,h,u),c}var Rae={kernelName:fl,backendName:"wasm",kernelFunc:Mae,setupFunc:Dae},G2;function Pae(e){G2=e.wasm.cwrap(ci,null,["number","number"])}function Oae(e){let{backend:t,inputs:{x:n}}=e,a=t.dataIdMap.get(n.dataId).id,r=t.makeOutput(n.shape,n.dtype),s=t.dataIdMap.get(r.dataId).id;return k.sizeFromShape(r.shape)===0||G2(a,s),r}var Lae={kernelName:"Sigmoid",backendName:"wasm",setupFunc:Pae,kernelFunc:Oae},zae=Un(ui);function Jm(e){let{inputs:{x:t},attrs:{begin:n,size:a},backend:r}=e,[s,i]=pn.parseSliceParams(t,n,a),o=pn.isSliceContinous(t.shape,s,i),l=r.readSync(t.dataId),c=r.makeOutput(i,t.dtype),u=k.computeStrides(t.shape),p=r.dataIdMap.get(c.dataId);if(o){let m=pn.computeFlatOffset(s,u);return t.dtype==="string"?p.stringBytes=l.slice(m,m+k.sizeFromShape(i)):r.typedArrayFromHeap(c).set(l.subarray(m,m+k.sizeFromShape(i))),c}if(t.dtype==="string"){let m=Am(l,s,i,t.shape,t.dtype);return p.stringBytes=m,c}let d=r.typedArrayFromHeap(c),h=t.shape.length;if(h===2)Bae(l,u[0],d,s,i);else if(h===3)Wae(l,u[0],u[1],d,s,i);else if(h===4)Vae(l,u[0],u[1],u[2],d,s,i);else{let m=Am(l,s,i,t.shape,t.dtype);d.set(m)}return c}function Bae(e,t,n,a,r){let s=0,i=a[0],o=a[1],l=i+r[0];for(let c=i;c{let d=[...u];d[o]=p;let h=Jm({inputs:{x:r},attrs:{begin:c,size:d},backend:a});return c[o]+=p,h})}var Kae={kernelName:wl,backendName:"wasm",kernelFunc:qae},Xae=Un(pi),Yae=Un(Ic),Jae=!0,Zae=gn(mi,Jae),j2;function Qae(e){j2=e.wasm.cwrap(Gr,null,["number","number","number"])}function ere(e){let{backend:t,inputs:n,attrs:a}=e,{alpha:r}=a,{x:s}=n,i=t.dataIdMap.get(s.dataId).id,o=t.makeOutput(s.shape,s.dtype),l=t.dataIdMap.get(o.dataId).id;return j2(i,r,l),o}var tre={kernelName:Gr,backendName:"wasm",setupFunc:Qae,kernelFunc:ere},q2;function nre(e){q2=e.wasm.cwrap(kl,null,["number","array","number","array","array","array","array","array","number","number"])}function are(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{begin:s,end:i,strides:o}=a;o==null&&(o=new Array(s.length));let{beginMask:l,endMask:c,ellipsisMask:u,newAxisMask:p,shrinkAxisMask:d}=a,h=E.slice_util.maskToAxes(u);if(h.length>1)throw new Error("Multiple ellipses in slice is not allowed.");if(u!==0&&p!==0)throw new Error("Using both ellipsisMask and newAxisMask is not yet supported.");if(u!==0&&d!==0)throw new Error("Using both ellipsisMask and shrinkAxisMask is not yet supported.");let m=r.shape.length-s.length,f=E.slice_util.maskToAxes(p),g=r.shape.slice();f.forEach(F=>{s[F]=0,i[F]=1,g.splice(F,0,1)});let y=La({inputs:{x:r},attrs:{shape:g},backend:t}),{begin:b,end:v,strides:x}=E.slice_util.getNormalizedAxes(y.shape,h,m,s,i,o,l,c,u);s=b,i=v,o=x;let N=E.slice_util.maskToAxes(d);N.forEach(F=>{i[F]=s[F]+1,o[F]=1});let T=E.slice_util.computeOutShape(s,i,o),C=T.filter((F,O)=>N.indexOf(O)===-1);if(o.every(F=>F===1)){let F=Jm({inputs:{x:r},attrs:{begin:s,size:T},backend:t});return La({inputs:{x:F},attrs:{shape:C},backend:t})}let $=t.makeOutput(C,"float32");if(!C.some(F=>F===0)){let F=t.dataIdMap.get(y.dataId).id,O=new Uint8Array(new Int32Array(k.computeStrides(y.shape)).buffer),W=new Uint8Array(new Int32Array(s).buffer),V=new Uint8Array(new Int32Array(i).buffer),H=new Uint8Array(new Int32Array(o).buffer),K=new Uint8Array(new Int32Array(C).buffer),j=new Uint8Array(new Int32Array(k.computeStrides(C)).buffer),Y=t.dataIdMap.get($.dataId).id;q2(F,O,y.shape.length,W,V,H,K,j,C.length,Y)}return La({inputs:{x:$},attrs:{shape:C},backend:t})}var rre={kernelName:kl,backendName:"wasm",setupFunc:nre,kernelFunc:are},sre=!0,ire=gn(fi,sre),K2;function ore(e){K2=e.wasm.cwrap(di,null,["number, number, number"])}function lre(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("sum",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;K2(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var ure={kernelName:di,backendName:"wasm",setupFunc:ore,kernelFunc:lre},cre=Un(gi),X2;function pre(e){X2=e.wasm.cwrap(Ur,null,["number","array","number","array","number","number"])}function dre(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,s=n.dataIdMap.get(r.dataId).id,{reps:i}=a,o=new Array(r.shape.length);for(let d=0;d{let{x:a}=e,{k:r,sorted:s}=n,i=t.dataIdMap.get(a.dataId).id,o=new Uint8Array(new Int32Array(a.shape).buffer),l=a.shape.slice();l[l.length-1]=r;let c=t.makeOutput(l,a.dtype),u=t.dataIdMap.get(c.dataId).id,p=t.makeOutput(l,"int32"),d=t.dataIdMap.get(p.dataId).id;return Y2(i,o,a.shape.length,Vn[a.dtype],r,s,u,d),[c,p]},gre={kernelName:Nl,backendName:"wasm",setupFunc:mre,kernelFunc:fre};function yre(e){let{inputs:t,backend:n,attrs:a}=e,{value:r}=t,{axis:s}=a;s<0&&(s+=r.shape.length);let i=r.shape[s],o=r.shape.length,l=new Array(o-1),c=0;for(let h=0;h({dataId:h,dtype:m,shape:l}))}var bre={kernelName:Tl,backendName:"wasm",kernelFunc:yre};function xre(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(0),a}var vre={kernelName:Sl,backendName:"wasm",kernelFunc:xre},wre=[Wee,Uee,jee,ete,ate,ote,lte,pte,dte,fte,bte,xte,kte,Tte,_te,Fte,Dte,Mte,Rte,Ote,Bte,Wte,Ute,Bee,jte,Xte,Zte,tne,rne,ine,lne,qee,pne,hne,fne,gne,bne,wne,Ine,Sne,Ene,$ne,Mne,Pne,One,Bne,Une,jne,Kne,Jne,Qne,tae,rae,iae,uae,dae,mae,gae,yae,bae,rte,wae,Nae,Cae,Eae,_ae,$ae,Rae,Lae,zae,Uae,jae,Kae,Xae,Yae,Zae,tre,rre,ire,ure,cre,hre,gre,Jee,bre,vre];for(let e of wre)Sc(e);var Hv=te();Hv.registerFlag("WASM_HAS_SIMD_SUPPORT",async()=>WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,10,9,1,7,0,65,0,253,15,26,11])));Hv.registerFlag("WASM_HAS_MULTITHREAD_SUPPORT",async()=>{if(Hv.get("IS_NODE"))return!1;try{return new MessageChannel().port1.postMessage(new SharedArrayBuffer(1)),WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,5,4,1,3,1,1,10,11,1,9,0,65,0,254,16,2,0,26,11]))}catch(e){return!1}});var J2=No(FE()),kre='var threadInfoStruct=0;var selfThreadId=0;var parentThreadId=0;var Module={};function threadPrintErr(){var text=Array.prototype.slice.call(arguments).join(" ");console.error(text)}function threadAlert(){var text=Array.prototype.slice.call(arguments).join(" ");postMessage({cmd:"alert",text:text,threadId:selfThreadId})}var err=threadPrintErr;this.alert=threadAlert;Module["instantiateWasm"]=function(info,receiveInstance){var instance=new WebAssembly.Instance(Module["wasmModule"],info);Module["wasmModule"]=null;receiveInstance(instance);return instance.exports};this.onmessage=function(e){try{if(e.data.cmd==="load"){Module["DYNAMIC_BASE"]=e.data.DYNAMIC_BASE;Module["DYNAMICTOP_PTR"]=e.data.DYNAMICTOP_PTR;Module["wasmModule"]=e.data.wasmModule;Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;Module["ENVIRONMENT_IS_PTHREAD"]=true;if(typeof e.data.urlOrBlob==="string"){importScripts(e.data.urlOrBlob)}else{var objectUrl=URL.createObjectURL(e.data.urlOrBlob);importScripts(objectUrl);URL.revokeObjectURL(objectUrl)}Module=WasmBackendModuleThreadedSimd(Module);postMessage({"cmd":"loaded"})}else if(e.data.cmd==="objectTransfer"){Module["PThread"].receiveObjectTransfer(e.data)}else if(e.data.cmd==="run"){Module["__performance_now_clock_drift"]=performance.now()-e.data.time;threadInfoStruct=e.data.threadInfoStruct;Module["__register_pthread_ptr"](threadInfoStruct,0,0);selfThreadId=e.data.selfThreadId;parentThreadId=e.data.parentThreadId;var max=e.data.stackBase;var top=e.data.stackBase+e.data.stackSize;Module["establishStackSpace"](top,max);Module["_emscripten_tls_init"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].setThreadStatus(Module["_pthread_self"](),1);try{var result=Module["dynCall_ii"](e.data.start_routine,e.data.arg);if(!Module["getNoExitRuntime"]())Module["PThread"].threadExit(result)}catch(ex){if(ex==="Canceled!"){Module["PThread"].threadCancel()}else if(ex!="unwind"){Atomics.store(Module["HEAPU32"],threadInfoStruct+4>>2,ex instanceof Module["ExitStatus"]?ex.status:-2);Atomics.store(Module["HEAPU32"],threadInfoStruct+0>>2,1);Module["_emscripten_futex_wake"](threadInfoStruct+0,2147483647);if(!(ex instanceof Module["ExitStatus"]))throw ex}}}else if(e.data.cmd==="cancel"){if(threadInfoStruct){Module["PThread"].threadCancel()}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="processThreadQueue"){if(threadInfoStruct){Module["_emscripten_current_thread_process_queued_calls"]()}}else{err("worker.js received unknown command "+e.data.cmd);err(e.data)}}catch(ex){err("worker.js onmessage() captured an uncaught exception: "+ex);if(ex.stack)err(ex.stack);throw ex}};if(typeof process==="object"&&typeof process.versions==="object"&&typeof process.versions.node==="string"){self={location:{href:__filename}};var onmessage=this.onmessage;var nodeWorkerThreads=require("worker_threads");Worker=nodeWorkerThreads.Worker;var parentPort=nodeWorkerThreads.parentPort;parentPort.on("message",function(data){onmessage({data:data})});var nodeFS=require("fs");var nodeRead=function(filename){return nodeFS.readFileSync(filename,"utf8")};function globalEval(x){global.require=require;global.Module=Module;eval.call(null,x)}importScripts=function(f){globalEval(nodeRead(f))};postMessage=function(msg){parentPort.postMessage(msg)};if(typeof performance==="undefined"){performance={now:function(){return Date.now()}}}}',Ire=No($E()),Z2=class extends sc{constructor(e){super();this.wasm=e,this.dataIdNextNumber=1,this.wasm.tfjs.init(),this.dataIdMap=new fd(this,Jr())}write(e,t,n){let a={};return this.move(a,e,t,n),a}numDataIds(){return this.dataIdMap.numDataIds()}async time(e){let t=k.now();return e(),{kernelMs:k.now()-t}}move(e,t,n,a){let r=this.dataIdNextNumber++;if(a==="string"){let l=t;this.dataIdMap.set(e,{id:r,stringBytes:l,shape:n,dtype:a,memoryOffset:null});return}let s=k.sizeFromShape(n),i=s*k.bytesPerElement(a),o=this.wasm._malloc(i);this.dataIdMap.set(e,{id:r,memoryOffset:o,shape:n,dtype:a}),this.wasm.tfjs.registerTensor(r,s,o),t!=null&&this.wasm.HEAPU8.set(new Uint8Array(t.buffer,t.byteOffset,i),o)}async read(e){return this.readSync(e)}readSync(e){let{memoryOffset:t,dtype:n,shape:a,stringBytes:r}=this.dataIdMap.get(e);if(n==="string")return r;let s=this.wasm.HEAPU8.slice(t,t+k.sizeFromShape(a)*k.bytesPerElement(n));return Nre(s.buffer,n)}disposeData(e){let t=this.dataIdMap.get(e);this.wasm._free(t.memoryOffset),this.wasm.tfjs.disposeData(t.id),this.dataIdMap.delete(e)}floatPrecision(){return 32}getMemoryOffset(e){return this.dataIdMap.get(e).memoryOffset}dispose(){this.wasm.tfjs.dispose(),this.wasm=null}memory(){return{unreliable:!1}}makeOutput(e,t,n){let a;if(n==null)a=this.write(null,e,t);else{a={};let r=this.dataIdNextNumber++;this.dataIdMap.set(a,{id:r,memoryOffset:n,shape:e,dtype:t});let s=k.sizeFromShape(e);this.wasm.tfjs.registerTensor(r,s,n)}return{dataId:a,shape:e,dtype:t}}typedArrayFromHeap({shape:e,dtype:t,dataId:n}){let a=this.wasm.HEAPU8.buffer,{memoryOffset:r}=this.dataIdMap.get(n),s=k.sizeFromShape(e);switch(t){case"float32":return new Float32Array(a,r,s);case"int32":return new Int32Array(a,r,s);case"bool":return new Uint8Array(a,r,s);default:throw new Error(`Unknown dtype ${t}`)}}};function Tre(e){return(t,n)=>(k.fetch(e,{credentials:"same-origin"}).then(a=>{a.ok||t.env.a(`failed to load wasm binary file at '${e}'`),a.arrayBuffer().then(r=>{WebAssembly.instantiate(r,t).then(s=>{n(s.instance)})})}),{})}function Q2(e,t,n){if(Zm!=null)return Zm;let a="tfjs-backend-wasm.wasm";return e&&t?a="tfjs-backend-wasm-threaded-simd.wasm":e&&(a="tfjs-backend-wasm-simd.wasm"),_p!=null&&_p[a]!=null?_p[a]:n+a}async function Sre(){let[e,t]=await Promise.all([te().getAsync("WASM_HAS_SIMD_SUPPORT"),te().getAsync("WASM_HAS_MULTITHREAD_SUPPORT")]);return new Promise((n,a)=>{let r={};r.locateFile=(l,c)=>{if(l.endsWith(".worker.js")){let u=kre,p=new Blob([u],{type:"application/javascript"});return URL.createObjectURL(p)}return l.endsWith(".wasm")?Q2(e,t,Ep!=null?Ep:c):c+l},jv&&(r.instantiateWasm=Tre(Q2(e,t,Ep!=null?Ep:"")));let s;t&&e&&Zm==null?(s=J2.default(r),s.mainScriptUrlOrBlob=new Blob(["var WasmBackendModuleThreadedSimd = "+J2.default.toString()],{type:"text/javascript"})):s=Ire.default(r);let i=null;s.tfjs={init:s.cwrap("init",null,[]),registerTensor:s.cwrap("register_tensor",null,["number","number","number"]),disposeData:s.cwrap("dispose_data",i,["number"]),dispose:s.cwrap("dispose",i,[])};let o=!1;s.onRuntimeInitialized=()=>{o=!0,Ap=!1,n({wasm:s})},s.onAbort=()=>{o||Ap||(Ap=!0,a({message:"Make sure the server can serve the `.wasm` file relative to the bundled js file. For more details see https://github.com/tensorflow/tfjs/blob/master/tfjs-backend-wasm/README.md#using-bundlers"}))}})}function Nre(e,t){switch(t){case"float32":return new Float32Array(e);case"int32":return new Int32Array(e);case"bool":return new Uint8Array(e);default:throw new Error(`Unknown dtype ${t}`)}}var Cre=["tfjs-backend-wasm.wasm","tfjs-backend-wasm-simd.wasm","tfjs-backend-wasm-threaded-simd.wasm"],Zm=null,Ep=null,_p={},Ap=!1,jv=!1;function _re(e,t=!1){if(Rt("setWasmPath has been deprecated in favor of setWasmPaths and will be removed in a future release."),Ap)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPath()` before you call `tf.setBackend()` or `tf.ready()`");Zm=e,jv=t}function Ere(e,t=!1){if(Ap)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPaths()` before you call `tf.setBackend()` or `tf.ready()`");if(typeof e=="string")Ep=e;else{_p=e;let n=Cre.filter(a=>_p[a]==null);if(n.length>0)throw new Error(`There were no entries found for the following binaries: ${n.join(",")}. Please either call setWasmPaths with a map providing a path for each binary, or with a string indicating the directory where all the binaries can be found.`)}jv=t}var Are="2.8.5",Fre=2;oh("wasm",async()=>{let{wasm:e}=await Sre();return new Z2(e)},Fre);var bw={};dd(bw,{AnchorPosition:()=>lr,DrawBox:()=>nf,DrawBoxOptions:()=>ow,DrawFaceLandmarks:()=>yw,DrawFaceLandmarksOptions:()=>gw,DrawTextField:()=>fs,DrawTextFieldOptions:()=>Mp,drawContour:()=>_r,drawDetections:()=>Vre,drawFaceExpressions:()=>jre,drawFaceLandmarks:()=>qre});function _r(e,t,n=!1){if(e.beginPath(),t.slice(1).forEach(({x:a,y:r},s)=>{let i=t[s];e.moveTo(i.x,i.y),e.lineTo(a,r)}),n){let a=t[t.length-1],r=t[0];if(!a||!r)return;e.moveTo(a.x,a.y),e.lineTo(r.x,r.y)}e.stroke()}var qv={};dd(qv,{computeReshapedDimensions:()=>Yv,getCenterPoint:()=>Yi,isDimensions:()=>ef,isEven:()=>Qm,isFloat:()=>Xv,isTensor:()=>Ki,isTensor1D:()=>$re,isTensor2D:()=>Kv,isTensor3D:()=>Er,isTensor4D:()=>aa,isValidNumber:()=>za,isValidProbablitiy:()=>yu,range:()=>ir,round:()=>Xi});var yn=class{constructor(t,n){if(!za(t)||!za(n))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:n})}`);this._width=t,this._height=n}get width(){return this._width}get height(){return this._height}reverse(){return new yn(1/this.width,1/this.height)}};function Ki(e,t){return e instanceof z&&e.shape.length===t}function $re(e){return Ki(e,1)}function Kv(e){return Ki(e,2)}function Er(e){return Ki(e,3)}function aa(e){return Ki(e,4)}function Xv(e){return e%1!=0}function Qm(e){return e%2==0}function Xi(e,t=2){let n=10**t;return Math.floor(e*n)/n}function ef(e){return e&&e.width&&e.height}function Yv({width:e,height:t},n){let a=n/Math.max(t,e);return new yn(Math.round(e*a),Math.round(t*a))}function Yi(e){return e.reduce((t,n)=>t.add(n),new De(0,0)).div(new De(e.length,e.length))}function ir(e,t,n){return Array(e).fill(0).map((a,r)=>t+r*n)}function za(e){return!!e&&e!==Infinity&&e!==-Infinity&&!Number.isNaN(e)||e===0}function yu(e){return za(e)&&e>=0&&e<=1}var De=class{constructor(t,n){this._x=t,this._y=n}get x(){return this._x}get y(){return this._y}add(t){return new De(this.x+t.x,this.y+t.y)}sub(t){return new De(this.x-t.x,this.y-t.y)}mul(t){return new De(this.x*t.x,this.y*t.y)}div(t){return new De(this.x/t.x,this.y/t.y)}abs(){return new De(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new De(Math.floor(this.x),Math.floor(this.y))}};var ct=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(za)}static assertIsValidBox(t,n,a=!1){if(!ct.isRect(t))throw new Error(`${n} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!a&&(t.width<0||t.height<0))throw new Error(`${n} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,n=!0){let a=t||{},r=[a.left,a.top,a.right,a.bottom].every(za),s=[a.x,a.y,a.width,a.height].every(za);if(!s&&!r)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(a)}`);let[i,o,l,c]=s?[a.x,a.y,a.width,a.height]:[a.left,a.top,a.right-a.left,a.bottom-a.top];ct.assertIsValidBox({x:i,y:o,width:l,height:c},"Box.constructor",n),this._x=i,this._y=o,this._width=l,this._height=c}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new De(this.left,this.top)}get topRight(){return new De(this.right,this.top)}get bottomLeft(){return new De(this.left,this.bottom)}get bottomRight(){return new De(this.right,this.bottom)}round(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.round(s));return new ct({x:t,y:n,width:a,height:r})}floor(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.floor(s));return new ct({x:t,y:n,width:a,height:r})}toSquare(){let{x:t,y:n,width:a,height:r}=this,s=Math.abs(a-r);return an&&(o=-p+n+a,p=n),d>t&&(l=-d+t+r,d=t),c<1&&(l=2-c,c=1),u<1&&(l=2-u,u=1),{dy:i,edy:l,dx:s,edx:o,y:u,ey:d,x:c,ex:p,w:a,h:r}}calibrate(t){return new ct({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var bu=class extends ct{constructor(t,n,a,r,s=!1){super({left:t,top:n,right:a,bottom:r},s)}};var ms=class{constructor(t,n,a,r,s){this._imageDims=new yn(s.width,s.height),this._score=t,this._classScore=n,this._className=a,this._box=new ct(r).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new ct(this._box).rescale(this.imageDims.reverse())}forSize(t,n){return new ms(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:n})}};var vt=class extends ms{constructor(t,n,a){super(t,t,"",n,a)}forSize(t,n){let{score:a,relativeBox:r,imageDims:s}=super.forSize(t,n);return new vt(a,r,s)}};function Jv(e,t,n=!0){let a=Math.max(0,Math.min(e.right,t.right)-Math.max(e.left,t.left)),r=Math.max(0,Math.min(e.bottom,t.bottom)-Math.max(e.top,t.top)),s=a*r;return n?s/(e.area+t.area-s):s/Math.min(e.area,t.area)}function Zv(e){let t=e.map(o=>o.x),n=e.map(o=>o.y),a=t.reduce((o,l)=>lloo({score:i,boxIndex:o})).sort((i,o)=>i.score-o.score).map(i=>i.boxIndex),s=[];for(;r.length>0;){let i=r.pop();s.push(i);let o=r,l=[];for(let c=0;cl[u]<=n)}return s}function Ba(e,t){return D(()=>{let[n,a,r]=t,s=kn([...e.shape.slice(0,3),1],n,"float32"),i=kn([...e.shape.slice(0,3),1],a,"float32"),o=kn([...e.shape.slice(0,3),1],r,"float32"),l=Qe([s,i,o],3);return ge(e,l)})}function ew(e,t=!1){return D(()=>{let[n,a]=e.shape.slice(1);if(n===a)return e;let r=Math.abs(n-a),s=Math.round(r*(t?.5:1)),i=n>a?2:1,o=d=>{let h=e.shape.slice();return h[i]=d,kn(h,0,"float32")},l=o(s),c=r-l.shape[i],p=[t&&c?o(c):null,e,l].filter(d=>!!d).map(d=>pe(d,"float32"));return Qe(p,i)})}function Dre(e){let t=e.slice();for(let n=t.length-1;n>0;n--){let a=Math.floor(Math.random()*(n+1)),r=t[n];t[n]=t[a],t[a]=r}return t}function Fp(e){return 1/(1+Math.exp(-e))}function Mre(e){return Math.log(e/(1-e))}var xu=class extends ct{constructor(t,n,a,r,s=!1){super({x:t,y:n,width:a,height:r},s)}};var Rre=.5,Pre=.43,Ore=.45,ra=class{constructor(t,n,a=new De(0,0)){let{width:r,height:s}=n;this._imgDims=new yn(r,s),this._shift=a,this._positions=t.map(i=>i.mul(new De(r,s)).add(a))}get shift(){return new De(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new De(this.imageWidth,this.imageHeight)))}forSize(t,n){return new this.constructor(this.relativePositions,{width:t,height:n})}shiftBy(t,n){return new this.constructor(this.relativePositions,this._imgDims,new De(t,n))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,n={}){if(t){let s=t instanceof vt?t.box.floor():new ct(t);return this.shiftBy(s.x,s.y).align(null,n)}let{useDlibAlignment:a,minBoxPadding:r}={useDlibAlignment:!1,minBoxPadding:.2,...n};return a?this.alignDlib():this.alignMinBbox(r)}alignDlib(){let t=this.getRefPointsForAlignment(),[n,a,r]=t,s=p=>r.sub(p).magnitude(),i=(s(n)+s(a))/2,o=Math.floor(i/Ore),l=Yi(t),c=Math.floor(Math.max(0,l.x-Rre*o)),u=Math.floor(Math.max(0,l.y-Pre*o));return new xu(c,u,Math.min(o,this.imageWidth+c),Math.min(o,this.imageHeight+u))}alignMinBbox(t){let n=Zv(this.positions);return n.pad(n.width*t,n.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var eC=class extends ra{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Yi([t[3],t[4]])]}};var vu=class extends ra{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Yi)}};var $p=class{constructor(t,n){this._label=t,this._distance=n}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${Xi(this.distance)})`:""}`}};var Dp=class extends ct{static assertIsValidLabeledBox(t,n){if(ct.assertIsValidBox(t,n),!za(t.label))throw new Error(`${n} - expected property label (${t.label}) to be a number`)}constructor(t,n){super(t);this._label=n}get label(){return this._label}};var Ar=class{constructor(t,n){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(n)||n.some(a=>!(a instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=n}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let n=t.descriptors.map(a=>new Float32Array(a));return new Ar(t.label,n)}};var tC=class extends Dp{static assertIsValidPredictedBox(t,n){if(Dp.assertIsValidLabeledBox(t,n),!yu(t.score)||!yu(t.classScore))throw new Error(`${n} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,n,a,r){super(t,n);this._score=a,this._classScore=r}get score(){return this._score}get classScore(){return this._classScore}};function or(e){return e.detection instanceof vt}function Ji(e,t){return{...e,...{detection:t}}}function tw(){let e=window.fetch;if(!e)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:e,readFile:t}}function tf(e){let t="";if(!e)try{e=require("fs")}catch(a){t=a.toString()}return{readFile:e?a=>new Promise((r,s)=>{e.readFile(a,(i,o)=>i?s(i):r(o))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function nw(){let e=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,n=()=>{if(e)return new e;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},a=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},r=global.fetch,s=tf();return{Canvas:e||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:n,createImageElement:a,fetch:r,...s}}function aw(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var rw=dE(aC()),en;function Bre(){if(!en)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return en}function sw(e){en=e}function iw(){return aw()?sw(tw()):rw.isNodejs()?sw(nw()):null}function Wre(e){if(en||iw(),!en)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=en.Canvas,Image:n=en.Image}=e;en.Canvas=t,en.Image=n,en.createCanvasElement=e.createCanvasElement||(()=>new t),en.createImageElement=e.createImageElement||(()=>new n),en.ImageData=e.ImageData||en.ImageData,en.Video=e.Video||en.Video,en.fetch=e.fetch||en.fetch,en.readFile=e.readFile||en.readFile}var it={getEnv:Bre,setEnv:sw,initialize:iw,createBrowserEnv:tw,createFileSystem:tf,createNodejsEnv:nw,monkeyPatch:Wre,isBrowser:aw,isNodejs:rw.isNodejs};iw();function Zi(e){return!it.isNodejs()&&typeof e=="string"?document.getElementById(e):e}function Cn(e){let{Canvas:t,CanvasRenderingContext2D:n}=it.getEnv();if(e instanceof n)return e;let a=Zi(e);if(!(a instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let r=a.getContext("2d");if(!r)throw new Error("resolveContext2d - canvas 2d context is null");return r}var lr;(function(e){e.TOP_LEFT="TOP_LEFT",e.TOP_RIGHT="TOP_RIGHT",e.BOTTOM_LEFT="BOTTOM_LEFT",e.BOTTOM_RIGHT="BOTTOM_RIGHT"})(lr||(lr={}));var Mp=class{constructor(t={}){let{anchorPosition:n,backgroundColor:a,fontColor:r,fontSize:s,fontStyle:i,padding:o}=t;this.anchorPosition=n||lr.TOP_LEFT,this.backgroundColor=a||"rgba(0, 0, 0, 0.5)",this.fontColor=r||"rgba(255, 255, 255, 1)",this.fontSize=s||14,this.fontStyle=i||"Georgia",this.padding=o||4}},fs=class{constructor(t,n,a={}){this.text=typeof t=="string"?[t]:t instanceof fs?t.text:t,this.anchor=n,this.options=new Mp(a)}measureWidth(t){let{padding:n}=this.options;return this.text.map(a=>t.measureText(a).width).reduce((a,r)=>a{let m=l+p.x,f=l+p.y+(h+1)*i;a.fillText(d,m,f)})}};var ow=class{constructor(t={}){let{boxColor:n,lineWidth:a,label:r,drawLabelOptions:s}=t;this.boxColor=n||"rgba(0, 0, 255, 1)",this.lineWidth=a||2,this.label=r;let i={anchorPosition:lr.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Mp({...i,...s})}},nf=class{constructor(t,n={}){this.box=new ct(t),this.options=new ow(n)}draw(t){let n=Cn(t),{boxColor:a,lineWidth:r}=this.options,{x:s,y:i,width:o,height:l}=this.box;n.strokeStyle=a,n.lineWidth=r,n.strokeRect(s,i,o,l);let{label:c}=this.options;c&&new fs([c],{x:s-r/2,y:i},this.options.drawLabelOptions).draw(t)}};function Vre(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof vt?a.score:or(a)?a.detection.score:void 0,s=a instanceof vt?a.box:or(a)?a.detection.box:new ct(a),i=r?`${Xi(r)}`:void 0;new nf(s,{label:i}).draw(e)})}function Rp(e){let{Image:t,Video:n}=it.getEnv();return e instanceof t&&e.complete||e instanceof n&&e.readyState>=3}function lw(e){return new Promise((t,n)=>{if(e instanceof it.getEnv().Canvas||Rp(e))return t(null);function a(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),n(s))}function r(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),t(s))}e.addEventListener("load",r),e.addEventListener("error",a)})}function uw(e){return new Promise((t,n)=>{e instanceof Blob||n(new Error("bufferToImage - expected buf to be of type: Blob"));let a=new FileReader;a.onload=()=>{typeof a.result!="string"&&n(new Error("bufferToImage - expected reader.result to be a string, in onload"));let r=it.getEnv().createImageElement();r.onload=()=>t(r),r.onerror=n,r.src=a.result},a.onerror=n,a.readAsDataURL(e)})}function Qi(e){let{Image:t,Video:n}=it.getEnv();return e instanceof t?new yn(e.naturalWidth,e.naturalHeight):e instanceof n?new yn(e.videoWidth,e.videoHeight):new yn(e.width,e.height)}function wu({width:e,height:t}){let{createCanvasElement:n}=it.getEnv(),a=n();return a.width=e,a.height=t,a}function Pp(e,t){let{ImageData:n}=it.getEnv();if(!(e instanceof n)&&!Rp(e))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:a,height:r}=t||Qi(e),s=wu({width:a,height:r});return e instanceof n?Cn(s).putImageData(e,0,0):Cn(s).drawImage(e,0,0,a,r),s}async function cw(e,t){let n=t||it.getEnv().createCanvasElement(),[a,r,s]=e.shape.slice(aa(e)?1:0),i=D(()=>e.as3D(a,r,s).toInt());return await Ni.toPixels(i,n),i.dispose(),n}function af(e){let{Image:t,Canvas:n,Video:a}=it.getEnv();return e instanceof t||e instanceof n||e instanceof a}function pw(e,t,n=!1){let{Image:a,Canvas:r}=it.getEnv();if(!(e instanceof a||e instanceof r))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let s=Qi(e),i=t/Math.max(s.height,s.width),o=i*s.width,l=i*s.height,c=wu({width:t,height:t}),u=e instanceof r?e:Pp(e),p=Math.abs(o-l)/2,d=n&&o{if(Er(a)){this._imageTensors[r]=a,this._inputDimensions[r]=a.shape;return}if(aa(a)){let i=a.shape[0];if(i!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${i} passed, but not supported in input array`);this._imageTensors[r]=a,this._inputDimensions[r]=a.shape.slice(1);return}let s=a instanceof it.getEnv().Canvas?a:Pp(a);this._canvases[r]=s,this._inputDimensions[r]=[s.height,s.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ir(this.batchSize,0,1).map((t,n)=>this.getReshapedInputDimensions(n))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let n=this.getInputWidth(t),a=this.getInputHeight(t);return Yv({width:n,height:a},this.inputSize)}toBatchTensor(t,n=!0){return this._inputSize=t,D(()=>{let a=ir(this.batchSize,0,1).map(s=>{let i=this.getInput(s);if(i instanceof z){let o=aa(i)?i:i.expandDims();return o=ew(o,n),(o.shape[1]!==t||o.shape[2]!==t)&&(o=Ja.resizeBilinear(o,[t,t])),o.as3D(t,t,3)}if(i instanceof it.getEnv().Canvas)return Ni.fromPixels(pw(i,t,n));throw new Error(`toBatchTensor - at batchIdx ${s}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${i}`)});return Dt(a.map(s=>pe(s,"float32"))).as4D(this.batchSize,t,t,3)})}};async function yt(e){if(e instanceof Fr)return e;let t=Array.isArray(e)?e:[e];if(!t.length)throw new Error("toNetInput - empty array passed as input");let n=r=>Array.isArray(e)?` at input index ${r}:`:"",a=t.map(Zi);return a.forEach((r,s)=>{if(!af(r)&&!Er(r)&&!aa(r))throw typeof t[s]=="string"?new Error(`toNetInput -${n(s)} string passed, but could not resolve HTMLElement for element id ${t[s]}`):new Error(`toNetInput -${n(s)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(aa(r)){let i=r.shape[0];if(i!==1)throw new Error(`toNetInput -${n(s)} tf.Tensor4D with batchSize ${i} passed, but not supported in input array`)}}),await Promise.all(a.map(r=>af(r)&&lw(r))),new Fr(a,Array.isArray(e))}async function ku(e,t){let{Canvas:n}=it.getEnv(),a=e;if(!(e instanceof n)){let i=await yt(e);if(i.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let o=i.getInput(0);a=o instanceof n?o:await cw(o)}let r=Cn(a);return t.map(i=>i instanceof vt?i.forSize(a.width,a.height).box.floor():i).map(i=>i.clipAtImageBorders(a.width,a.height)).map(({x:i,y:o,width:l,height:c})=>{let u=wu({width:l,height:c});return Cn(u).putImageData(r.getImageData(i,o,l,c),0,0),u})}async function Iu(e,t){if(!Er(e)&&!aa(e))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(aa(e)&&e.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return D(()=>{let[n,a,r]=e.shape.slice(aa(e)?1:0);return t.map(o=>o instanceof vt?o.forSize(a,n).box:o).map(o=>o.clipAtImageBorders(a,n)).map(({x:o,y:l,width:c,height:u})=>Vl(e.as3D(n,a,r),[l,o,0],[u,c,r]))})}async function eo(e,t){let{fetch:n}=it.getEnv(),a=await n(e,t);if(!(a.status<400))throw new Error(`failed to fetch: (${a.status}) ${a.statusText}, from url: ${a.url}`);return a}async function Ure(e){let t=await eo(e),n=await t.blob();if(!n.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${n.type}, for url: ${t.url}`);return uw(n)}async function dw(e){return(await eo(e)).json()}async function Gre(e){return new Float32Array(await(await eo(e)).arrayBuffer())}function rf(e,t){let n=`${t}-weights_manifest.json`;if(!e)return{modelBaseUri:"",manifestUri:n};if(e==="/")return{modelBaseUri:"/",manifestUri:`/${n}`};let a=e.startsWith("http://")?"http://":e.startsWith("https://")?"https://":"";e=e.replace(a,"");let r=e.split("/").filter(o=>o),s=e.endsWith(".json")?r[r.length-1]:n,i=a+(e.endsWith(".json")?r.slice(0,r.length-1):r).join("/");return i=e.startsWith("/")?`/${i}`:i,{modelBaseUri:i,manifestUri:i==="/"?`/${s}`:`${i}/${s}`}}async function hw(e,t){let{manifestUri:n,modelBaseUri:a}=rf(e,t),r=await dw(n);return qt.loadWeights(r,a)}function Hre(e,t,n=!1){let{width:a,height:r}=n?Qi(t):t;return e.width=a,e.height=r,{width:a,height:r}}var sn=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:n,objProp:a}=this.traversePropertyPath(t);return n[a]}reassignParamFromPath(t,n){let{obj:a,objProp:r}=this.traversePropertyPath(t);a[r].dispose(),a[r]=n}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof Hr)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof Hr))}variable(){this.getFrozenParams().forEach(({path:t,tensor:n})=>{this.reassignParamFromPath(t,n.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:n})=>{let a=Kn(n.dataSync());n.dispose(),this.reassignParamFromPath(t,a)})}dispose(t=!0){this.getParamList().forEach(n=>{if(t&&n.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${n.path}`);n.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,n)=>t.concat(n)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let n=await hw(t,this.getDefaultModelName());this.loadFromWeightMap(n)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:n}=it.getEnv(),{manifestUri:a,modelBaseUri:r}=rf(t,this.getDefaultModelName()),s=c=>Promise.all(c.map(u=>n(u).then(p=>p.buffer))),i=qt.weightsLoaderFactory(s),o=JSON.parse((await n(a)).toString()),l=await i(o,r);this.loadFromWeightMap(l)}loadFromWeightMap(t){let{paramMappings:n,params:a}=this.extractParamsFromWeightMap(t);this._paramMappings=n,this._params=a}extractWeights(t){let{paramMappings:n,params:a}=this.extractParams(t);this._paramMappings=n,this._params=a}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let n=t.split("/").reduce((s,i)=>{if(!s.nextObj.hasOwnProperty(i))throw new Error(`traversePropertyPath - object does not have property ${i}, for path ${t}`);return{obj:s.nextObj,objProp:i,nextObj:s.nextObj[i]}},{nextObj:this.params}),{obj:a,objProp:r}=n;if(!a||!r||!(a[r]instanceof z))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:a,objProp:r}}};function _n(e,t,n){return D(()=>{let a=Ai(e,t.depthwise_filter,t.pointwise_filter,n,"same");return a=Z(a,t.bias),a})}function sf(e,t,n=!1){return D(()=>{let a=Ye(n?Z(Ft(e,t.conv0.filters,[2,2],"same"),t.conv0.bias):_n(e,t.conv0,[2,2])),r=_n(a,t.conv1,[1,1]),s=Ye(Z(a,r)),i=_n(s,t.conv2,[1,1]);return Ye(Z(a,Z(r,i)))})}function Op(e,t,n=!1,a=!0){return D(()=>{let r=Ye(n?Z(Ft(e,t.conv0.filters,a?[2,2]:[1,1],"same"),t.conv0.bias):_n(e,t.conv0,a?[2,2]:[1,1])),s=_n(r,t.conv1,[1,1]),i=Ye(Z(r,s)),o=_n(i,t.conv2,[1,1]),l=Ye(Z(r,Z(s,o))),c=_n(l,t.conv3,[1,1]);return Ye(Z(r,Z(s,Z(o,c))))})}function to(e,t,n="same",a=!1){return D(()=>{let r=Z(Ft(e,t.filters,[1,1],n),t.bias);return a?Ye(r):r})}function bn(e,t){Object.keys(e).forEach(n=>{t.some(a=>a.originalPath===n)||e[n].dispose()})}function Nu(e,t){return(n,a,r,s)=>{let i=Ea(e(n*a*r*r),[r,r,n,a]),o=tt(e(a));return t.push({paramPath:`${s}/filters`},{paramPath:`${s}/bias`}),{filters:i,bias:o}}}function of(e,t){return(n,a,r)=>{let s=_a(e(n*a),[n,a]),i=tt(e(a));return t.push({paramPath:`${r}/weights`},{paramPath:`${r}/bias`}),{weights:s,bias:i}}}var lf=class{constructor(t,n,a){this.depthwise_filter=t;this.pointwise_filter=n;this.bias=a}};function Tu(e,t){return(n,a,r)=>{let s=Ea(e(3*3*n),[3,3,n,1]),i=Ea(e(n*a),[1,1,n,a]),o=tt(e(a));return t.push({paramPath:`${r}/depthwise_filter`},{paramPath:`${r}/pointwise_filter`},{paramPath:`${r}/bias`}),new lf(s,i,o)}}function Su(e){return t=>{let n=e(`${t}/depthwise_filter`,4),a=e(`${t}/pointwise_filter`,4),r=e(`${t}/bias`,1);return new lf(n,a,r)}}function Gn(e,t){return(n,a,r)=>{let s=e[n];if(!Ki(s,a))throw new Error(`expected weightMap[${n}] to be a Tensor${a}D, instead have ${s}`);return t.push({originalPath:n,paramPath:r||n}),s}}function xn(e){let t=e;function n(r){let s=t.slice(0,r);return t=t.slice(r),s}function a(){return t}return{extractWeights:n,getRemainingWeights:a}}function uf(e,t){let n=Nu(e,t),a=Tu(e,t);function r(i,o,l,c=!1){let u=c?n(i,o,3,`${l}/conv0`):a(i,o,`${l}/conv0`),p=a(o,o,`${l}/conv1`),d=a(o,o,`${l}/conv2`);return{conv0:u,conv1:p,conv2:d}}function s(i,o,l,c=!1){let{conv0:u,conv1:p,conv2:d}=r(i,o,l,c),h=a(o,o,`${l}/conv3`);return{conv0:u,conv1:p,conv2:d,conv3:h}}return{extractDenseBlock3Params:r,extractDenseBlock4Params:s}}function rC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),{extractDenseBlock4Params:r}=uf(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2"),l=r(128,256,"dense3");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o,dense3:l}}}function cf(e){return t=>{let n=e(`${t}/filters`,4),a=e(`${t}/bias`,1);return{filters:n,bias:a}}}function pf(e,t){let n=Gn(e,t),a=cf(n),r=Su(n);function s(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`);return{conv0:c,conv1:u,conv2:p}}function i(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`),d=r(`${o}/conv3`);return{conv0:c,conv1:u,conv2:p,conv3:d}}return{extractDenseBlock3Params:s,extractDenseBlock4Params:i}}function sC(e){let t=[],{extractDenseBlock4Params:n}=pf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2"),dense3:n("dense3")};return bn(e,t),{params:a,paramMappings:t}}var Lp=class extends sn{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(255)),i=Op(s,n.dense0,!0);return i=Op(i,n.dense1),i=Op(i,n.dense2),i=Op(i,n.dense3),i=Yn(i,[7,7],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return sC(t)}extractParams(t){return rC(t)}};function zp(e,t){return D(()=>Z(ze(e,t.weights),t.bias))}function iC(e,t,n){let a=[],{extractWeights:r,getRemainingWeights:s}=xn(e),o=of(r,a)(t,n,"fc");if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{paramMappings:a,params:{fc:o}}}function oC(e){let t=[],n=Gn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:a("fc")};return bn(e,t),{params:r,paramMappings:t}}function df(e){let t={},n={};return Object.keys(e).forEach(a=>{let r=a.startsWith("fc")?n:t;r[a]=e[a]}),{featureExtractorMap:t,classifierMap:n}}var Bp=class extends sn{constructor(t,n){super(t);this._faceFeatureExtractor=n}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof Fr?this.faceFeatureExtractor.forwardInput(t):t;return zp(a.as2D(a.shape[0],-1),n.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return iC(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=df(t);return this.faceFeatureExtractor.loadFromWeightMap(n),oC(a)}extractParams(t){let n=this.getClassifierChannelsIn(),a=this.getClassifierChannelsOut(),r=a*n+a,s=t.slice(0,t.length-r),i=t.slice(t.length-r);return this.faceFeatureExtractor.extractWeights(s),this.extractClassifierParams(i)}};var mw=["neutral","happy","sad","angry","fearful","disgusted","surprised"],gs=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);mw.forEach((n,a)=>{this[n]=t[a]})}asSortedArray(){return mw.map(t=>({expression:t,probability:this[t]})).sort((t,n)=>n.probability-t.probability)}};var hf=class extends Bp{constructor(t=new Lp){super("FaceExpressionNet",t)}forwardInput(t){return D(()=>Ca(this.runNet(t)))}async forward(t){return this.forwardInput(await yt(t))}async predictExpressions(t){let n=await yt(t),a=await this.forwardInput(n),r=await Promise.all(ht(a).map(async i=>{let o=await i.data();return i.dispose(),o}));a.dispose();let s=r.map(i=>new gs(i));return n.isBatchInput?s:s[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function fw(e){return e.expressions instanceof gs}function mf(e,t){return{...e,...{expressions:t}}}function jre(e,t,n=.1,a){(Array.isArray(t)?t:[t]).forEach(s=>{let i=s instanceof gs?s:fw(s)?s.expressions:void 0;if(!i)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let l=i.asSortedArray().filter(p=>p.probability>n),c=or(s)?s.detection.box.bottomLeft:a||new De(0,0);new fs(l.map(p=>`${p.expression} (${Xi(p.probability)})`),c).draw(e)})}function no(e){return or(e)&&e.landmarks instanceof ra&&e.unshiftedLandmarks instanceof ra&&e.alignedRect instanceof vt}function Cu(e,t){let{box:n}=e.detection,a=t.shiftBy(n.x,n.y),r=a.align(),{imageDims:s}=e.detection,i=new vt(e.detection.score,r.rescale(s.reverse()),s);return{...e,...{landmarks:a,unshiftedLandmarks:t,alignedRect:i}}}var gw=class{constructor(t={}){let{drawLines:n=!0,drawPoints:a=!0,lineWidth:r,lineColor:s,pointSize:i,pointColor:o}=t;this.drawLines=n,this.drawPoints=a,this.lineWidth=r||1,this.pointSize=i||2,this.lineColor=s||"rgba(0, 255, 255, 1)",this.pointColor=o||"rgba(255, 0, 255, 1)"}},yw=class{constructor(t,n={}){this.faceLandmarks=t,this.options=new gw(n)}draw(t){let n=Cn(t),{drawLines:a,drawPoints:r,lineWidth:s,lineColor:i,pointSize:o,pointColor:l}=this.options;if(a&&this.faceLandmarks instanceof vu&&(n.strokeStyle=i,n.lineWidth=s,_r(n,this.faceLandmarks.getJawOutline()),_r(n,this.faceLandmarks.getLeftEyeBrow()),_r(n,this.faceLandmarks.getRightEyeBrow()),_r(n,this.faceLandmarks.getNose()),_r(n,this.faceLandmarks.getLeftEye(),!0),_r(n,this.faceLandmarks.getRightEye(),!0),_r(n,this.faceLandmarks.getMouth(),!0)),r){n.strokeStyle=l,n.fillStyle=l;let c=u=>{n.beginPath(),n.arc(u.x,u.y,o,0,2*Math.PI),n.fill()};this.faceLandmarks.positions.forEach(c)}}};function qre(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof ra?a:no(a)?a.landmarks:void 0;if(!r)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new yw(r).draw(e)})}var lC="0.11.5";function Kre(e,t){let n=Nu(e,t),a=Tu(e,t);function r(i,o,l){let c=a(i,o,`${l}/separable_conv0`),u=a(o,o,`${l}/separable_conv1`),p=n(i,o,1,`${l}/expansion_conv`);return{separable_conv0:c,separable_conv1:u,expansion_conv:p}}function s(i,o){let l=a(i,i,`${o}/separable_conv0`),c=a(i,i,`${o}/separable_conv1`),u=a(i,i,`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:n,extractSeparableConvParams:a,extractReductionBlockParams:r,extractMainBlockParams:s}}function uC(e,t){let n=[],{extractWeights:a,getRemainingWeights:r}=xn(e),{extractConvParams:s,extractSeparableConvParams:i,extractReductionBlockParams:o,extractMainBlockParams:l}=Kre(a,n),c=s(3,32,3,"entry_flow/conv_in"),u=o(32,64,"entry_flow/reduction_block_0"),p=o(64,128,"entry_flow/reduction_block_1"),d={conv_in:c,reduction_block_0:u,reduction_block_1:p},h={};ir(t,0,1).forEach(y=>{h[`main_block_${y}`]=l(128,`middle_flow/main_block_${y}`)});let m=o(128,256,"exit_flow/reduction_block"),f=i(256,512,"exit_flow/separable_conv"),g={reduction_block:m,separable_conv:f};if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:n,params:{entry_flow:d,middle_flow:h,exit_flow:g}}}function Xre(e,t){let n=Gn(e,t),a=cf(n),r=Su(n);function s(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=a(`${o}/expansion_conv`);return{separable_conv0:l,separable_conv1:c,expansion_conv:u}}function i(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=r(`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}}function cC(e,t){let n=[],{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}=Xre(e,n),o=a("entry_flow/conv_in"),l=s("entry_flow/reduction_block_0"),c=s("entry_flow/reduction_block_1"),u={conv_in:o,reduction_block_0:l,reduction_block_1:c},p={};ir(t,0,1).forEach(f=>{p[`main_block_${f}`]=i(`middle_flow/main_block_${f}`)});let d=s("exit_flow/reduction_block"),h=r("exit_flow/separable_conv"),m={reduction_block:d,separable_conv:h};return bn(e,n),{params:{entry_flow:u,middle_flow:p,exit_flow:m},paramMappings:n}}function pC(e,t,n){return Z(Ft(e,t.filters,n,"same"),t.bias)}function xw(e,t,n=!0){let a=n?Ye(e):e;return a=_n(a,t.separable_conv0,[1,1]),a=_n(Ye(a),t.separable_conv1,[1,1]),a=$t(a,[3,3],[2,2],"same"),a=Z(a,pC(e,t.expansion_conv,[2,2])),a}function Yre(e,t){let n=_n(Ye(e),t.separable_conv0,[1,1]);return n=_n(Ye(n),t.separable_conv1,[1,1]),n=_n(Ye(n),t.separable_conv2,[1,1]),n=Z(n,e),n}var vw=class extends sn{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyXception - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(256)),i=Ye(pC(s,n.entry_flow.conv_in,[2,2]));return i=xw(i,n.entry_flow.reduction_block_0,!1),i=xw(i,n.entry_flow.reduction_block_1),ir(this._numMainBlocks,0,1).forEach(o=>{i=Yre(i,n.middle_flow[`main_block_${o}`])}),i=xw(i,n.exit_flow.reduction_block),i=Ye(_n(i,n.exit_flow.separable_conv,[1,1])),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return cC(t,this._numMainBlocks)}extractParams(t){return uC(t,this._numMainBlocks)}};function dC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),r=of(n,t),s=r(512,1,"fc/age"),i=r(512,2,"fc/gender");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{fc:{age:s,gender:i}}}}function hC(e){let t=[],n=Gn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:{age:a("fc/age"),gender:a("fc/gender")}};return bn(e,t),{params:r,paramMappings:t}}var $r;(function(e){e.FEMALE="female",e.MALE="male"})($r||($r={}));var ff=class extends sn{constructor(t=new vw(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof Fr?this.faceFeatureExtractor.forwardInput(t):t,r=Yn(a,[7,7],[2,2],"valid").as2D(a.shape[0],-1),s=zp(r,n.fc.age).as1D(),i=zp(r,n.fc.gender);return{age:s,gender:i}})}forwardInput(t){return D(()=>{let{age:n,gender:a}=this.runNet(t);return{age:n,gender:Ca(a)}})}async forward(t){return this.forwardInput(await yt(t))}async predictAgeAndGender(t){let n=await yt(t),a=await this.forwardInput(n),r=ht(a.age),s=ht(a.gender),i=r.map((l,c)=>({ageTensor:l,genderTensor:s[c]})),o=await Promise.all(i.map(async({ageTensor:l,genderTensor:c})=>{let u=(await l.data())[0],p=(await c.data())[0],d=p>.5,h=d?$r.MALE:$r.FEMALE,m=d?p:1-p;return l.dispose(),c.dispose(),{age:u,gender:h,genderProbability:m}}));return a.age.dispose(),a.gender.dispose(),n.isBatchInput?o:o[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return dC(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=df(t);return this.faceFeatureExtractor.loadFromWeightMap(n),hC(a)}extractParams(t){let n=512*1+1+(512*2+2),a=t.slice(0,t.length-n),r=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(r)}};var Wp=class extends Bp{postProcess(t,n,a){let r=a.map(({width:i,height:o})=>{let l=n/Math.max(o,i);return{width:i*l,height:o*l}}),s=r.length;return D(()=>{let i=(p,d)=>Dt([kn([68],p,"float32"),kn([68],d,"float32")],1).as2D(1,136).as1D(),o=(p,d)=>{let{width:h,height:m}=r[p];return d(h,m)?Math.abs(h-m)/2:0},l=p=>o(p,(d,h)=>do(p,(d,h)=>hi(l(d),c(d))))).div(Dt(Array.from(Array(s),(p,d)=>i(r[d].width,r[d].height))))})}forwardInput(t){return D(()=>{let n=this.runNet(t);return this.postProcess(n,t.inputSize,t.inputDimensions.map(([a,r])=>({height:a,width:r})))})}async forward(t){return this.forwardInput(await yt(t))}async detectLandmarks(t){let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(async(s,i)=>{let o=Array.from(await s.data()),l=o.filter((u,p)=>Qm(p)),c=o.filter((u,p)=>!Qm(p));return new vu(Array(68).fill(0).map((u,p)=>new De(l[p],c[p])),{height:n.getInputHeight(i),width:n.getInputWidth(i)})}));return a.forEach(s=>s.dispose()),n.isBatchInput?r:r[0]}getClassifierChannelsOut(){return 136}};var _u=class extends Wp{constructor(t=new Lp){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};function mC(e){let t=[],{extractDenseBlock3Params:n}=pf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2")};return bn(e,t),{params:a,paramMappings:t}}function fC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),{extractDenseBlock3Params:r}=uf(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o}}}var ww=class extends sn{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyFaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(255)),i=sf(s,n.dense0,!0);return i=sf(i,n.dense1),i=sf(i,n.dense2),i=Yn(i,[14,14],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return mC(t)}extractParams(t){return fC(t)}};var gf=class extends Wp{constructor(t=new ww){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var gC=class extends _u{};function yC(e,t){return Z(L(e,t.weights),t.biases)}function kw(e,t,n,a,r="same"){let{filters:s,bias:i}=t.conv,o=Ft(e,s,n,r);return o=Z(o,i),o=yC(o,t.scale),a?Ye(o):o}function bC(e,t){return kw(e,t,[1,1],!0)}function Iw(e,t){return kw(e,t,[1,1],!1)}function yf(e,t){return kw(e,t,[2,2],!0,"valid")}function Jre(e,t){function n(o,l,c){let u=e(o),p=u.length/(l*c*c);if(Xv(p))throw new Error(`depth has to be an integer: ${p}, weights.length: ${u.length}, numFilters: ${l}, filterSize: ${c}`);return D(()=>Ue(Ea(u,[l,p,c,c]),[2,3,1,0]))}function a(o,l,c,u){let p=n(o,l,c),d=tt(e(l));return t.push({paramPath:`${u}/filters`},{paramPath:`${u}/bias`}),{filters:p,bias:d}}function r(o,l){let c=tt(e(o)),u=tt(e(o));return t.push({paramPath:`${l}/weights`},{paramPath:`${l}/biases`}),{weights:c,biases:u}}function s(o,l,c,u){let p=a(o,l,c,`${u}/conv`),d=r(l,`${u}/scale`);return{conv:p,scale:d}}function i(o,l,c,u,p=!1){let d=s((p?.5:1)*o,l,c,`${u}/conv1`),h=s(o,l,c,`${u}/conv2`);return{conv1:d,conv2:h}}return{extractConvLayerParams:s,extractResidualLayerParams:i}}function xC(e){let{extractWeights:t,getRemainingWeights:n}=xn(e),a=[],{extractConvLayerParams:r,extractResidualLayerParams:s}=Jre(t,a),i=r(4704,32,7,"conv32_down"),o=s(9216,32,3,"conv32_1"),l=s(9216,32,3,"conv32_2"),c=s(9216,32,3,"conv32_3"),u=s(36864,64,3,"conv64_down",!0),p=s(36864,64,3,"conv64_1"),d=s(36864,64,3,"conv64_2"),h=s(36864,64,3,"conv64_3"),m=s(147456,128,3,"conv128_down",!0),f=s(147456,128,3,"conv128_1"),g=s(147456,128,3,"conv128_2"),y=s(589824,256,3,"conv256_down",!0),b=s(589824,256,3,"conv256_1"),v=s(589824,256,3,"conv256_2"),x=s(589824,256,3,"conv256_down_out"),N=D(()=>Ue(_a(t(256*128),[128,256]),[1,0]));if(a.push({paramPath:"fc"}),n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{params:{conv32_down:i,conv32_1:o,conv32_2:l,conv32_3:c,conv64_down:u,conv64_1:p,conv64_2:d,conv64_3:h,conv128_down:m,conv128_1:f,conv128_2:g,conv256_down:y,conv256_1:b,conv256_2:v,conv256_down_out:x,fc:N},paramMappings:a}}function Zre(e,t){let n=Gn(e,t);function a(i){let o=n(`${i}/scale/weights`,1),l=n(`${i}/scale/biases`,1);return{weights:o,biases:l}}function r(i){let o=n(`${i}/conv/filters`,4),l=n(`${i}/conv/bias`,1),c=a(i);return{conv:{filters:o,bias:l},scale:c}}function s(i){return{conv1:r(`${i}/conv1`),conv2:r(`${i}/conv2`)}}return{extractConvLayerParams:r,extractResidualLayerParams:s}}function vC(e){let t=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=Zre(e,t),r=n("conv32_down"),s=a("conv32_1"),i=a("conv32_2"),o=a("conv32_3"),l=a("conv64_down"),c=a("conv64_1"),u=a("conv64_2"),p=a("conv64_3"),d=a("conv128_down"),h=a("conv128_1"),m=a("conv128_2"),f=a("conv256_down"),g=a("conv256_1"),y=a("conv256_2"),b=a("conv256_down_out"),{fc:v}=e;if(t.push({originalPath:"fc",paramPath:"fc"}),!Kv(v))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${v}`);let x={conv32_down:r,conv32_1:s,conv32_2:i,conv32_3:o,conv64_down:l,conv64_1:c,conv64_2:u,conv64_3:p,conv128_down:d,conv128_1:h,conv128_2:m,conv256_down:f,conv256_1:g,conv256_2:y,conv256_down_out:b,fc:v};return bn(e,t),{params:x,paramMappings:t}}function Wa(e,t){let n=bC(e,t.conv1);return n=Iw(n,t.conv2),n=Z(n,e),n=Ye(n),n}function Vp(e,t){let n=yf(e,t.conv1);n=Iw(n,t.conv2);let a=Yn(e,2,2,"valid"),r=bt(a.shape),s=a.shape[3]!==n.shape[3];if(a.shape[1]!==n.shape[1]||a.shape[2]!==n.shape[2]){let o=[...n.shape];o[1]=1;let l=bt(o);n=Qe([n,l],1);let c=[...n.shape];c[2]=1;let u=bt(c);n=Qe([n,u],2)}return a=s?Qe([a,r],3):a,n=Z(a,n),n=Ye(n),n}var Eu=class extends sn{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceRecognitionNet - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(150,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(256)),i=yf(s,n.conv32_down);i=$t(i,3,2,"valid"),i=Wa(i,n.conv32_1),i=Wa(i,n.conv32_2),i=Wa(i,n.conv32_3),i=Vp(i,n.conv64_down),i=Wa(i,n.conv64_1),i=Wa(i,n.conv64_2),i=Wa(i,n.conv64_3),i=Vp(i,n.conv128_down),i=Wa(i,n.conv128_1),i=Wa(i,n.conv128_2),i=Vp(i,n.conv256_down),i=Wa(i,n.conv256_1),i=Wa(i,n.conv256_2),i=Vp(i,n.conv256_down_out);let o=i.mean([1,2]);return ze(o,n.fc)})}async forward(t){return this.forwardInput(await yt(t))}async computeFaceDescriptor(t){var s;if((s=t==null?void 0:t.shape)==null?void 0:s.some(i=>i<=0))return new Float32Array(128);let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(i=>i.data()));return a.forEach(i=>i.dispose()),n.isBatchInput?r:r[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return vC(t)}extractParams(t){return xC(t)}};function Qre(e){let t=new Eu;return t.extractWeights(e),t}function bf(e,t){return{...e,...{descriptor:t}}}function ese(e){return typeof e.age=="number"}function xf(e,t){return{...e,...{age:t}}}function tse(e){return(e.gender===$r.MALE||e.gender===$r.FEMALE)&&yu(e.genderProbability)}function vf(e,t,n){return{...e,...{gender:t,genderProbability:n}}}function nse(e,t){function n(l,c){let u=Ea(e(3*3*l),[3,3,l,1]),p=tt(e(l)),d=tt(e(l)),h=tt(e(l)),m=tt(e(l));return t.push({paramPath:`${c}/filters`},{paramPath:`${c}/batch_norm_scale`},{paramPath:`${c}/batch_norm_offset`},{paramPath:`${c}/batch_norm_mean`},{paramPath:`${c}/batch_norm_variance`}),{filters:u,batch_norm_scale:p,batch_norm_offset:d,batch_norm_mean:h,batch_norm_variance:m}}function a(l,c,u,p,d){let h=Ea(e(l*c*u*u),[u,u,l,c]),m=tt(e(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/${d?"batch_norm_offset":"bias"}`}),{filters:h,bias:m}}function r(l,c,u,p){let{filters:d,bias:h}=a(l,c,u,p,!0);return{filters:d,batch_norm_offset:h}}function s(l,c,u){let p=n(l,`${u}/depthwise_conv`),d=r(l,c,1,`${u}/pointwise_conv`);return{depthwise_conv:p,pointwise_conv:d}}function i(){let l=r(3,32,3,"mobilenetv1/conv_0"),c=s(32,64,"mobilenetv1/conv_1"),u=s(64,128,"mobilenetv1/conv_2"),p=s(128,128,"mobilenetv1/conv_3"),d=s(128,256,"mobilenetv1/conv_4"),h=s(256,256,"mobilenetv1/conv_5"),m=s(256,512,"mobilenetv1/conv_6"),f=s(512,512,"mobilenetv1/conv_7"),g=s(512,512,"mobilenetv1/conv_8"),y=s(512,512,"mobilenetv1/conv_9"),b=s(512,512,"mobilenetv1/conv_10"),v=s(512,512,"mobilenetv1/conv_11"),x=s(512,1024,"mobilenetv1/conv_12"),N=s(1024,1024,"mobilenetv1/conv_13");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,conv_8:g,conv_9:y,conv_10:b,conv_11:v,conv_12:x,conv_13:N}}function o(){let l=r(1024,256,1,"prediction_layer/conv_0"),c=r(256,512,3,"prediction_layer/conv_1"),u=r(512,128,1,"prediction_layer/conv_2"),p=r(128,256,3,"prediction_layer/conv_3"),d=r(256,128,1,"prediction_layer/conv_4"),h=r(128,256,3,"prediction_layer/conv_5"),m=r(256,64,1,"prediction_layer/conv_6"),f=r(64,128,3,"prediction_layer/conv_7"),g=a(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=a(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),b=a(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),v=a(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),x=a(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),N=a(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),T=a(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),C=a(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),$=a(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),F=a(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),O=a(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),W=a(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,box_predictor_0:{box_encoding_predictor:g,class_predictor:y},box_predictor_1:{box_encoding_predictor:b,class_predictor:v},box_predictor_2:{box_encoding_predictor:x,class_predictor:N},box_predictor_3:{box_encoding_predictor:T,class_predictor:C},box_predictor_4:{box_encoding_predictor:$,class_predictor:F},box_predictor_5:{box_encoding_predictor:O,class_predictor:W}}}return{extractMobilenetV1Params:i,extractPredictionLayerParams:o}}function wC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),{extractMobilenetV1Params:r,extractPredictionLayerParams:s}=nse(n,t),i=r(),o=s(),c={extra_dim:rh(n(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:{mobilenetv1:i,prediction_layer:o,output_layer:c},paramMappings:t}}function ase(e,t){let n=Gn(e,t);function a(c,u,p){let d=n(`${c}/Conv2d_${u}_pointwise/weights`,4,`${p}/filters`),h=n(`${c}/Conv2d_${u}_pointwise/convolution_bn_offset`,1,`${p}/batch_norm_offset`);return{filters:d,batch_norm_offset:h}}function r(c){let u=`mobilenetv1/conv_${c}`,p=`MobilenetV1/Conv2d_${c}_depthwise`,d=`${u}/depthwise_conv`,h=`${u}/pointwise_conv`,m=n(`${p}/depthwise_weights`,4,`${d}/filters`),f=n(`${p}/BatchNorm/gamma`,1,`${d}/batch_norm_scale`),g=n(`${p}/BatchNorm/beta`,1,`${d}/batch_norm_offset`),y=n(`${p}/BatchNorm/moving_mean`,1,`${d}/batch_norm_mean`),b=n(`${p}/BatchNorm/moving_variance`,1,`${d}/batch_norm_variance`);return{depthwise_conv:{filters:m,batch_norm_scale:f,batch_norm_offset:g,batch_norm_mean:y,batch_norm_variance:b},pointwise_conv:a("MobilenetV1",c,h)}}function s(){return{conv_0:a("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:r(1),conv_2:r(2),conv_3:r(3),conv_4:r(4),conv_5:r(5),conv_6:r(6),conv_7:r(7),conv_8:r(8),conv_9:r(9),conv_10:r(10),conv_11:r(11),conv_12:r(12),conv_13:r(13)}}function i(c,u){let p=n(`${c}/weights`,4,`${u}/filters`),d=n(`${c}/biases`,1,`${u}/bias`);return{filters:p,bias:d}}function o(c){let u=i(`Prediction/BoxPredictor_${c}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${c}/box_encoding_predictor`),p=i(`Prediction/BoxPredictor_${c}/ClassPredictor`,`prediction_layer/box_predictor_${c}/class_predictor`);return{box_encoding_predictor:u,class_predictor:p}}function l(){return{conv_0:a("Prediction",0,"prediction_layer/conv_0"),conv_1:a("Prediction",1,"prediction_layer/conv_1"),conv_2:a("Prediction",2,"prediction_layer/conv_2"),conv_3:a("Prediction",3,"prediction_layer/conv_3"),conv_4:a("Prediction",4,"prediction_layer/conv_4"),conv_5:a("Prediction",5,"prediction_layer/conv_5"),conv_6:a("Prediction",6,"prediction_layer/conv_6"),conv_7:a("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:o(0),box_predictor_1:o(1),box_predictor_2:o(2),box_predictor_3:o(3),box_predictor_4:o(4),box_predictor_5:o(5)}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:l}}function kC(e){let t=[],{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=ase(e,t),r=e["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!Er(r))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${r}`);let s={mobilenetv1:n(),prediction_layer:a(),output_layer:{extra_dim:r}};return bn(e,t),{params:s,paramMappings:t}}function va(e,t,n){return D(()=>{let a=Ft(e,t.filters,n,"same");return a=Z(a,t.batch_norm_offset),Xt(a,0,6)})}var rse=.0010000000474974513;function sse(e,t,n){return D(()=>{let a=yr(e,t.filters,n,"same");return a=gr(a,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,rse),Xt(a,0,6)})}function ise(e){return[2,4,6,12].some(t=>t===e)?[2,2]:[1,1]}function IC(e,t){return D(()=>{let n,a=va(e,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((s,i)=>{let o=i+1,l=ise(o);a=sse(a,s.depthwise_conv,l),a=va(a,s.pointwise_conv,[1,1]),o===11&&(n=a)}),n===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:a,conv11:n}})}function ose(e,t,n){let a=e.arraySync(),r=Math.min(a[t][0],a[t][2]),s=Math.min(a[t][1],a[t][3]),i=Math.max(a[t][0],a[t][2]),o=Math.max(a[t][1],a[t][3]),l=Math.min(a[n][0],a[n][2]),c=Math.min(a[n][1],a[n][3]),u=Math.max(a[n][0],a[n][2]),p=Math.max(a[n][1],a[n][3]),d=(i-r)*(o-s),h=(u-l)*(p-c);if(d<=0||h<=0)return 0;let m=Math.max(r,l),f=Math.max(s,c),g=Math.min(i,u),y=Math.min(o,p),b=Math.max(g-m,0)*Math.max(y-f,0);return b/(d+h-b)}function NC(e,t,n,a,r){let s=e.shape[0],i=Math.min(n,s),o=t.map((u,p)=>({score:u,boxIndex:p})).filter(u=>u.score>r).sort((u,p)=>p.score-u.score),l=u=>u<=a?1:0,c=[];return o.forEach(u=>{if(c.length>=i)return;let p=u.score;for(let d=c.length-1;d>=0;--d){let h=ose(e,u.boxIndex,c[d]);if(h!==0&&(u.score*=l(h),u.score<=r))break}p===u.score&&c.push(u.boxIndex)}),c}function lse(e){let t=ht(Ue(e,[1,0])),n=[ge(t[2],t[0]),ge(t[3],t[1])],a=[Z(t[0],we(n[0],he(2))),Z(t[1],we(n[1],he(2)))];return{sizes:n,centers:a}}function use(e,t){let{sizes:n,centers:a}=lse(e),r=ht(Ue(t,[1,0])),s=we(L(dn(we(r[2],he(5))),n[0]),he(2)),i=Z(L(we(r[0],he(10)),n[0]),a[0]),o=we(L(dn(we(r[3],he(5))),n[1]),he(2)),l=Z(L(we(r[1],he(10)),n[1]),a[1]);return Ue(Dt([ge(i,s),ge(l,o),Z(i,s),Z(l,o)]),[1,0])}function TC(e,t,n){return D(()=>{let a=e.shape[0],r=use(q(qa(n.extra_dim,[a,1,1]),[-1,4]),q(e,[-1,4]));r=q(r,[a,r.shape[0]/a,4]);let s=da(We(t,[0,0,1],[-1,-1,-1])),i=We(s,[0,0,0],[-1,-1,1]);i=q(i,[a,i.shape[1]]);let o=ht(r),l=ht(i);return{boxes:o,scores:l}})}function ao(e,t){return D(()=>{let n=e.shape[0],a=q(to(e,t.box_encoding_predictor),[n,-1,1,4]),r=q(to(e,t.class_predictor),[n,-1,3]);return{boxPredictionEncoding:a,classPrediction:r}})}function SC(e,t,n){return D(()=>{let a=va(e,n.conv_0,[1,1]),r=va(a,n.conv_1,[2,2]),s=va(r,n.conv_2,[1,1]),i=va(s,n.conv_3,[2,2]),o=va(i,n.conv_4,[1,1]),l=va(o,n.conv_5,[2,2]),c=va(l,n.conv_6,[1,1]),u=va(c,n.conv_7,[2,2]),p=ao(t,n.box_predictor_0),d=ao(e,n.box_predictor_1),h=ao(r,n.box_predictor_2),m=ao(i,n.box_predictor_3),f=ao(l,n.box_predictor_4),g=ao(u,n.box_predictor_5),y=Qe([p.boxPredictionEncoding,d.boxPredictionEncoding,h.boxPredictionEncoding,m.boxPredictionEncoding,f.boxPredictionEncoding,g.boxPredictionEncoding],1),b=Qe([p.classPrediction,d.classPrediction,h.classPrediction,m.classPrediction,f.classPrediction,g.classPrediction],1);return{boxPredictions:y,classPredictions:b}})}var wa=class{constructor({minConfidence:t,maxResults:n}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=n||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var ro=class extends sn{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("SsdMobilenetv1 - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(512,!1),"float32"),r=ge(L(a,he(.007843137718737125)),he(1)),s=IC(r,n.mobilenetv1),{boxPredictions:i,classPredictions:o}=SC(s.out,s.conv11,n.prediction_layer);return TC(i,o,n.output_layer)})}async forward(t){return this.forwardInput(await yt(t))}async locateFaces(t,n={}){let{maxResults:a,minConfidence:r}=new wa(n),s=await yt(t),{boxes:i,scores:o}=this.forwardInput(s),l=i[0],c=o[0];for(let v=1;v{let[x,N]=[Math.max(0,y[v][0]),Math.min(1,y[v][2])].map($=>$*g),[T,C]=[Math.max(0,y[v][1]),Math.min(1,y[v][3])].map($=>$*f);return new vt(u[v],new xu(T,x,C-T,N-x),{height:s.getInputHeight(0),width:s.getInputWidth(0)})});return l.dispose(),c.dispose(),b}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return kC(t)}extractParams(t){return wC(t)}};function CC(e){let t=new ro;return t.extractWeights(e),t}function cse(e){return CC(e)}var _C=class extends ro{};var EC=.4,AC=[new De(.738768,.874946),new De(2.42204,2.65704),new De(4.30971,7.04493),new De(10.246,4.59428),new De(12.6868,11.8741)],FC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],$C=[117.001,114.697,97.404],DC="tiny_yolov2_model",MC="tiny_yolov2_separable_conv_model";var wf=e=>typeof e=="number";function Nw(e){if(!e)throw new Error(`invalid config: ${e}`);if(typeof e.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${e.withSeparableConvs}`);if(!wf(e.iouThreshold)||e.iouThreshold<0||e.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${e.iouThreshold}`);if(!Array.isArray(e.classes)||!e.classes.length||!e.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(e.classes)}`);if(!Array.isArray(e.anchors)||!e.anchors.length||!e.anchors.map(t=>t||{}).every(t=>wf(t.x)&&wf(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(e.anchors)}`);if(e.meanRgb&&(!Array.isArray(e.meanRgb)||e.meanRgb.length!==3||!e.meanRgb.every(wf)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(e.meanRgb)}`)}function Au(e){return D(()=>{let t=L(e,he(.10000000149011612));return Z(Ye(ge(e,t)),t)})}function Dr(e,t){return D(()=>{let n=ea(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Ft(n,t.conv.filters,[1,1],"valid"),n=ge(n,t.bn.sub),n=L(n,t.bn.truediv),n=Z(n,t.conv.bias),Au(n)})}function Mr(e,t){return D(()=>{let n=ea(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Ai(n,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),n=Z(n,t.bias),Au(n)})}function pse(e,t){let n=Nu(e,t);function a(i,o){let l=tt(e(i)),c=tt(e(i));return t.push({paramPath:`${o}/sub`},{paramPath:`${o}/truediv`}),{sub:l,truediv:c}}function r(i,o,l){let c=n(i,o,3,`${l}/conv`),u=a(o,`${l}/bn`);return{conv:c,bn:u}}let s=Tu(e,t);return{extractConvParams:n,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}}function RC(e,t,n,a){let{extractWeights:r,getRemainingWeights:s}=xn(e),i=[],{extractConvParams:o,extractConvWithBatchNormParams:l,extractSeparableConvParams:c}=pse(r,i),u;if(t.withSeparableConvs){let[p,d,h,m,f,g,y,b,v]=a,x=t.isFirstLayerConv2d?o(p,d,3,"conv0"):c(p,d,"conv0"),N=c(d,h,"conv1"),T=c(h,m,"conv2"),C=c(m,f,"conv3"),$=c(f,g,"conv4"),F=c(g,y,"conv5"),O=b?c(y,b,"conv6"):void 0,W=v?c(b,v,"conv7"):void 0,V=o(v||b||y,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}else{let[p,d,h,m,f,g,y,b,v]=a,x=l(p,d,"conv0"),N=l(d,h,"conv1"),T=l(h,m,"conv2"),C=l(m,f,"conv3"),$=l(f,g,"conv4"),F=l(g,y,"conv5"),O=l(y,b,"conv6"),W=l(b,v,"conv7"),V=o(v,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{params:u,paramMappings:i}}function dse(e,t){let n=Gn(e,t);function a(o){let l=n(`${o}/sub`,1),c=n(`${o}/truediv`,1);return{sub:l,truediv:c}}function r(o){let l=n(`${o}/filters`,4),c=n(`${o}/bias`,1);return{filters:l,bias:c}}function s(o){let l=r(`${o}/conv`),c=a(`${o}/bn`);return{conv:l,bn:c}}let i=Su(n);return{extractConvParams:r,extractConvWithBatchNormParams:s,extractSeparableConvParams:i}}function PC(e,t){let n=[],{extractConvParams:a,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}=dse(e,n),i;if(t.withSeparableConvs){let o=t.filterSizes&&t.filterSizes.length||9;i={conv0:t.isFirstLayerConv2d?a("conv0"):s("conv0"),conv1:s("conv1"),conv2:s("conv2"),conv3:s("conv3"),conv4:s("conv4"),conv5:s("conv5"),conv6:o>7?s("conv6"):void 0,conv7:o>8?s("conv7"):void 0,conv8:a("conv8")}}else i={conv0:r("conv0"),conv1:r("conv1"),conv2:r("conv2"),conv3:r("conv3"),conv4:r("conv4"),conv5:r("conv5"),conv6:r("conv6"),conv7:r("conv7"),conv8:a("conv8")};return bn(e,n),{params:i,paramMappings:n}}var ur=class{constructor({inputSize:t,scoreThreshold:n}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=n||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var Tw=class extends sn{constructor(t){super("TinyYolov2");Nw(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,n){let a=Dr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=Dr(a,n.conv6),a=Dr(a,n.conv7),to(a,n.conv8,"valid",!1)}runMobilenet(t,n){let a=this.config.isFirstLayerConv2d?Au(to(t,n.conv0,"valid",!1)):Mr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=n.conv6?Mr(a,n.conv6):a,a=n.conv7?Mr(a,n.conv7):a,to(a,n.conv8,"valid",!1)}forwardInput(t,n){let{params:a}=this;if(!a)throw new Error("TinyYolov2 - load model before inference");return D(()=>{let r=pe(t.toBatchTensor(n,!1),"float32");return r=this.config.meanRgb?Ba(r,this.config.meanRgb):r,r=r.div(he(256)),this.config.withSeparableConvs?this.runMobilenet(r,a):this.runTinyYolov2(r,a)})}async forward(t,n){return this.forwardInput(await yt(t),n)}async detect(t,n={}){let{inputSize:a,scoreThreshold:r}=new ur(n),s=await yt(t),i=await this.forwardInput(s,a),o=D(()=>ht(i)[0].expandDims()),l={width:s.getInputWidth(0),height:s.getInputHeight(0)},c=await this.extractBoxes(o,s.getReshapedInputDimensions(0),r);i.dispose(),o.dispose();let u=c.map(g=>g.box),p=c.map(g=>g.score),d=c.map(g=>g.classScore),h=c.map(g=>this.config.classes[g.label]);return Qv(u.map(g=>g.rescale(a)),p,this.config.iouThreshold,!0).map(g=>new ms(p[g],d[g],h[g],u[g],l))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return PC(t,this.config)}extractParams(t){let n=this.config.filterSizes||Tw.DEFAULT_FILTER_SIZES,a=n?n.length:void 0;if(a!==7&&a!==8&&a!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${a} filterSizes in config`);return RC(t,this.config,this.boxEncodingSize,n)}async extractBoxes(t,n,a){let{width:r,height:s}=n,i=Math.max(r,s),o=i/r,l=i/s,c=t.shape[1],u=this.config.anchors.length,[p,d,h]=D(()=>{let y=t.reshape([c,c,u,this.boxEncodingSize]),b=y.slice([0,0,0,0],[c,c,u,4]),v=y.slice([0,0,0,4],[c,c,u,1]),x=this.withClassScores?Ca(y.slice([0,0,0,5],[c,c,u,this.config.classes.length]),3):he(0);return[b,v,x]}),m=[],f=await d.array(),g=await p.array();for(let y=0;ya){let N=(b+Fp(g[y][b][v][0]))/c*o,T=(y+Fp(g[y][b][v][1]))/c*l,C=Math.exp(g[y][b][v][2])*this.config.anchors[v].x/c*o,$=Math.exp(g[y][b][v][3])*this.config.anchors[v].y/c*l,F=N-C/2,O=T-$/2,W={row:y,col:b,anchor:v},{classScore:V,label:H}=this.withClassScores?await this.extractPredictedClass(h,W):{classScore:1,label:0};m.push({box:new bu(F,O,F+C,O+$),score:x,classScore:x*V,label:H,...W})}}return p.dispose(),d.dispose(),h.dispose(),m}async extractPredictedClass(t,n){let{row:a,col:r,anchor:s}=n,i=await t.array();return Array(this.config.classes.length).fill(0).map((o,l)=>i[a][r][s][l]).map((o,l)=>({classScore:o,label:l})).reduce((o,l)=>o.classScore>l.classScore?o:l)}},Fu=Tw;Fu.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var $u=class extends Fu{constructor(t=!0){let n={withSeparableConvs:t,iouThreshold:EC,classes:["face"],...t?{anchors:FC,meanRgb:$C}:{anchors:AC,withClassScores:!0}};super(n)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new vt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?MC:DC}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function hse(e,t=!0){let n=new $u(t);return n.extractWeights(e),n}var kf=class extends ur{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var ka=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};async function so(e,t,n,a,r=({alignedRect:s})=>s){let s=e.map(l=>no(l)?r(l):l.detection),i=a||(t instanceof z?await Iu(t,s):await ku(t,s)),o=await n(i);return i.forEach(l=>l instanceof z&&l.dispose()),o}async function Du(e,t,n,a,r){return so([e],t,async s=>n(s[0]),a,r)}var OC=.4,LC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],zC=[117.001,114.697,97.404];var Mu=class extends Fu{constructor(){let t={withSeparableConvs:!0,iouThreshold:OC,classes:["face"],anchors:LC,meanRgb:zC,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new vt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var nt={ssdMobilenetv1:new ro,tinyFaceDetector:new Mu,tinyYolov2:new $u,faceLandmark68Net:new _u,faceLandmark68TinyNet:new gf,faceRecognitionNet:new Eu,faceExpressionNet:new hf,ageGenderNet:new ff},BC=(e,t)=>nt.ssdMobilenetv1.locateFaces(e,t),mse=(e,t)=>nt.tinyFaceDetector.locateFaces(e,t),fse=(e,t)=>nt.tinyYolov2.locateFaces(e,t),WC=e=>nt.faceLandmark68Net.detectLandmarks(e),gse=e=>nt.faceLandmark68TinyNet.detectLandmarks(e),yse=e=>nt.faceRecognitionNet.computeFaceDescriptor(e),bse=e=>nt.faceExpressionNet.predictExpressions(e),xse=e=>nt.ageGenderNet.predictAgeAndGender(e),VC=e=>nt.ssdMobilenetv1.load(e),vse=e=>nt.tinyFaceDetector.load(e),wse=e=>nt.tinyYolov2.load(e),kse=e=>nt.faceLandmark68Net.load(e),Ise=e=>nt.faceLandmark68TinyNet.load(e),Nse=e=>nt.faceRecognitionNet.load(e),Tse=e=>nt.faceExpressionNet.load(e),Sse=e=>nt.ageGenderNet.load(e),Cse=VC,_se=BC,Ese=WC;var Sw=class extends ka{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Ou=class extends Sw{async run(){let t=await this.parentTask,n=await so(t,this.input,async a=>Promise.all(a.map(r=>nt.faceExpressionNet.predictExpressions(r))),this.extractedFaces);return t.map((a,r)=>mf(a,n[r]))}withAgeAndGender(){return new Ru(this,this.input)}},Lu=class extends Sw{async run(){let t=await this.parentTask;if(!t)return;let n=await Du(t,this.input,a=>nt.faceExpressionNet.predictExpressions(a),this.extractedFaces);return mf(t,n)}withAgeAndGender(){return new Pu(this,this.input)}},lo=class extends Ou{withAgeAndGender(){return new io(this,this.input)}withFaceDescriptors(){return new ys(this,this.input)}},uo=class extends Lu{withAgeAndGender(){return new oo(this,this.input)}withFaceDescriptor(){return new bs(this,this.input)}};var Cw=class extends ka{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Ru=class extends Cw{async run(){let t=await this.parentTask,n=await so(t,this.input,async a=>Promise.all(a.map(r=>nt.ageGenderNet.predictAgeAndGender(r))),this.extractedFaces);return t.map((a,r)=>{let{age:s,gender:i,genderProbability:o}=n[r];return xf(vf(a,i,o),s)})}withFaceExpressions(){return new Ou(this,this.input)}},Pu=class extends Cw{async run(){let t=await this.parentTask;if(!t)return;let{age:n,gender:a,genderProbability:r}=await Du(t,this.input,s=>nt.ageGenderNet.predictAgeAndGender(s),this.extractedFaces);return xf(vf(t,a,r),n)}withFaceExpressions(){return new Lu(this,this.input)}},io=class extends Ru{withFaceExpressions(){return new lo(this,this.input)}withFaceDescriptors(){return new ys(this,this.input)}},oo=class extends Pu{withFaceExpressions(){return new uo(this,this.input)}withFaceDescriptor(){return new bs(this,this.input)}};var If=class extends ka{constructor(t,n){super();this.parentTask=t;this.input=n}},ys=class extends If{async run(){let t=await this.parentTask;return(await so(t,this.input,a=>Promise.all(a.map(r=>nt.faceRecognitionNet.computeFaceDescriptor(r))),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}))).map((a,r)=>bf(t[r],a))}withFaceExpressions(){return new lo(this,this.input)}withAgeAndGender(){return new io(this,this.input)}},bs=class extends If{async run(){let t=await this.parentTask;if(!t)return;let n=await Du(t,this.input,a=>nt.faceRecognitionNet.computeFaceDescriptor(a),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}));return bf(t,n)}withFaceExpressions(){return new uo(this,this.input)}withAgeAndGender(){return new oo(this,this.input)}};var Nf=class extends ka{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.useTinyLandmarkNet=a}get landmarkNet(){return this.useTinyLandmarkNet?nt.faceLandmark68TinyNet:nt.faceLandmark68Net}},Tf=class extends Nf{async run(){let t=await this.parentTask,n=t.map(s=>s.detection),a=this.input instanceof z?await Iu(this.input,n):await ku(this.input,n),r=await Promise.all(a.map(s=>this.landmarkNet.detectLandmarks(s)));return a.forEach(s=>s instanceof z&&s.dispose()),t.map((s,i)=>Cu(s,r[i]))}withFaceExpressions(){return new lo(this,this.input)}withAgeAndGender(){return new io(this,this.input)}withFaceDescriptors(){return new ys(this,this.input)}},Sf=class extends Nf{async run(){let t=await this.parentTask;if(!t)return;let{detection:n}=t,a=this.input instanceof z?await Iu(this.input,[n]):await ku(this.input,[n]),r=await this.landmarkNet.detectLandmarks(a[0]);return a.forEach(s=>s instanceof z&&s.dispose()),Cu(t,r)}withFaceExpressions(){return new uo(this,this.input)}withAgeAndGender(){return new oo(this,this.input)}withFaceDescriptor(){return new bs(this,this.input)}};var Cf=class extends ka{constructor(t,n=new wa){super();this.input=t;this.options=n}},Up=class extends Cf{async run(){let{input:t,options:n}=this,a=n instanceof kf?r=>nt.tinyFaceDetector.locateFaces(r,n):n instanceof wa?r=>nt.ssdMobilenetv1.locateFaces(r,n):n instanceof ur?r=>nt.tinyYolov2.locateFaces(r,n):null;if(!a)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return a(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let n=await this.run();t(n.map(a=>Ji({},a)))})}withFaceLandmarks(t=!1){return new Tf(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new Ou(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Ru(this.runAndExtendWithFaceDetections(),this.input)}},_f=class extends Cf{async run(){let t=await new Up(this.input,this.options),n=t[0];return t.forEach(a=>{a.score>n.score&&(n=a)}),n}runAndExtendWithFaceDetection(){return new Promise(async t=>{let n=await this.run();t(n?Ji({},n):void 0)})}withFaceLandmarks(t=!1){return new Sf(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new Lu(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Pu(this.runAndExtendWithFaceDetection(),this.input)}};function Ase(e,t=new wa){return new _f(e,t)}function Ef(e,t=new wa){return new Up(e,t)}async function UC(e,t){return Ef(e,new wa(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function Fse(e,t={}){return Ef(e,new ur(t)).withFaceLandmarks().withFaceDescriptors()}var $se=UC;function _w(e,t){if(e.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let n=Array.from(e),a=Array.from(t);return Math.sqrt(n.map((r,s)=>r-a[s]).reduce((r,s)=>r+s**2,0))}var Af=class{constructor(t,n=.6){this._distanceThreshold=n;let a=Array.isArray(t)?t:[t];if(!a.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let r=1,s=()=>`person ${r++}`;this._labeledDescriptors=a.map(i=>{if(i instanceof Ar)return i;if(i instanceof Float32Array)return new Ar(s(),[i]);if(i.descriptor&&i.descriptor instanceof Float32Array)return new Ar(s(),[i.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,n){return n.map(a=>_w(a,t)).reduce((a,r)=>a+r,0)/(n.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:n,label:a})=>new $p(a,this.computeMeanDistance(t,n))).reduce((n,a)=>n.distancet.toJSON())}}static fromJSON(t){let n=t.labeledDescriptors.map(a=>Ar.fromJSON(a));return new Af(n,t.distanceThreshold)}};function Dse(e){let t=new Mu;return t.extractWeights(e),t}function GC(e,t){let{width:n,height:a}=new yn(t.width,t.height);if(n<=0||a<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:n,height:a})}`);if(Array.isArray(e))return e.map(r=>GC(r,{width:n,height:a}));if(no(e)){let r=e.detection.forSize(n,a),s=e.unshiftedLandmarks.forSize(r.box.width,r.box.height);return Cu(Ji(e,r),s)}return or(e)?Ji(e,e.detection.forSize(n,a)):e instanceof ra||e instanceof vt?e.forSize(n,a):e}var Mse=typeof process!="undefined",Rse=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Pse={faceapi:lC,node:Mse,browser:Rse};export{ff as AgeGenderNet,bu as BoundingBox,ct as Box,ka as ComposableTask,ys as ComputeAllFaceDescriptorsTask,If as ComputeFaceDescriptorsTaskBase,bs as ComputeSingleFaceDescriptorTask,Tf as DetectAllFaceLandmarksTask,Up as DetectAllFacesTask,Nf as DetectFaceLandmarksTaskBase,Cf as DetectFacesTaskBase,Sf as DetectSingleFaceLandmarksTask,_f as DetectSingleFaceTask,yn as Dimensions,mw as FACE_EXPRESSION_LABELS,vt as FaceDetection,_C as FaceDetectionNet,hf as FaceExpressionNet,gs as FaceExpressions,_u as FaceLandmark68Net,gf as FaceLandmark68TinyNet,gC as FaceLandmarkNet,ra as FaceLandmarks,eC as FaceLandmarks5,vu as FaceLandmarks68,$p as FaceMatch,Af as FaceMatcher,Eu as FaceRecognitionNet,$r as Gender,Dp as LabeledBox,Ar as LabeledFaceDescriptors,Fr as NetInput,sn as NeuralNetwork,ms as ObjectDetection,De as Point,tC as PredictedBox,xu as Rect,ro as SsdMobilenetv1,wa as SsdMobilenetv1Options,Mu as TinyFaceDetector,kf as TinyFaceDetectorOptions,$u as TinyYolov2,ur as TinyYolov2Options,$se as allFaces,UC as allFacesSsdMobilenetv1,Fse as allFacesTinyYolov2,lw as awaitMediaLoaded,uw as bufferToImage,yse as computeFaceDescriptor,wu as createCanvas,Pp as createCanvasFromMedia,cse as createFaceDetectionNet,Qre as createFaceRecognitionNet,CC as createSsdMobilenetv1,Dse as createTinyFaceDetector,hse as createTinyYolov2,Ef as detectAllFaces,WC as detectFaceLandmarks,gse as detectFaceLandmarksTiny,Ese as detectLandmarks,Ase as detectSingleFace,bw as draw,it as env,_w as euclideanDistance,xf as extendWithAge,bf as extendWithFaceDescriptor,Ji as extendWithFaceDetection,mf as extendWithFaceExpressions,Cu as extendWithFaceLandmarks,vf as extendWithGender,Iu as extractFaceTensors,ku as extractFaces,Ure as fetchImage,dw as fetchJson,Gre as fetchNetWeights,eo as fetchOrThrow,Cn as getContext2dOrThrow,Qi as getMediaDimensions,cw as imageTensorToCanvas,pw as imageToSquare,Mre as inverseSigmoid,Jv as iou,af as isMediaElement,Rp as isMediaLoaded,ese as isWithAge,or as isWithFaceDetection,fw as isWithFaceExpressions,no as isWithFaceLandmarks,tse as isWithGender,Sse as loadAgeGenderModel,Cse as loadFaceDetectionModel,Tse as loadFaceExpressionModel,kse as loadFaceLandmarkModel,Ise as loadFaceLandmarkTinyModel,Nse as loadFaceRecognitionModel,VC as loadSsdMobilenetv1Model,vse as loadTinyFaceDetectorModel,wse as loadTinyYolov2Model,hw as loadWeightMap,_se as locateFaces,Hre as matchDimensions,Zv as minBbox,nt as nets,Qv as nonMaxSuppression,Ba as normalize,ew as padToSquare,xse as predictAgeAndGender,bse as recognizeFaceExpressions,GC as resizeResults,Zi as resolveInput,Dre as shuffleArray,Fp as sigmoid,BC as ssdMobilenetv1,Bg as tf,mse as tinyFaceDetector,fse as tinyYolov2,yt as toNetInput,qv as utils,Nw as validateConfig,Pse as version}; + `}};function Dee(e){let{inputs:t,backend:n,attrs:a}=e,{x:r,segmentIds:s}=t,{numSegments:i}=a,o=r.shape.length,l=[],c=0,u=E.getAxesPermutation([c],o),p=r;u!=null&&(p=Sn({inputs:{x:r},backend:n,attrs:{perm:u}}),l.push(p),c=E.getInnerMostAxes(1,o)[0]);let d=E.segment_util.computeOutShape(p.shape,c,i),h=k.sizeFromShape([p.shape[c]]),m=ve({inputs:{x:p},backend:n,attrs:{shape:[-1,h]}});l.push(m);let f=eh(r.dtype),g=(x,N,T,C,$)=>{let F=x.shape[0],O=x.shape[1],W=E.segment_util.segOpComputeOptimalWindowSize(O,$),V={windowSize:W,inSize:O,batchSize:F,numSegments:$},H=new $ee(V,N),K=n.compileAndRun(H,[x,T],C);if(l.push(K),K.shape[1]===$)return K;let j=a2({backend:n,attrs:{start:0,stop:$,step:1,dtype:"float32"}}),Y=i2({inputs:{x:j},backend:n,attrs:{reps:[O/W]}});return l.push(j),l.push(Y),g(K,N,Y,C,$)},y=g(m,"unsortedSegmentSum",s,f,i),b=ve({inputs:{x:y},backend:n,attrs:{shape:d}}),v=b;if(u!=null){l.push(b);let x=E.getUndoAxesPermutation(u);v=Sn({inputs:{x:v},backend:n,attrs:{perm:x}})}return l.forEach(x=>n.disposeIntermediateTensorInfo(x)),v}var Mee={kernelName:Nc,backendName:"webgl",kernelFunc:Dee},Ree=[C9,A9,fX,yX,vX,IX,TX,_X,AX,$X,PX,LX,WX,GX,JX,qX,eY,rY,nY,lY,cY,dY,gY,IY,TY,FY,DY,OY,BY,YK,GY,e7,n7,KY,i7,l7,r7,p7,m7,y7,x7,w7,N7,A7,$7,S7,R7,L7,V7,j7,Y7,Q7,eJ,tJ,aJ,sJ,oJ,uJ,pJ,fJ,xJ,wJ,IJ,SJ,AJ,MJ,LJ,XK,BJ,UY,UJ,jJ,XJ,ZK,QJ,a9,s9,d9,u9,g9,x9,I9,$9,B9,L9,G9,j9,K9,P9,Y9,Z9,nZ,iZ,cZ,bZ,aX,vZ,IZ,SZ,EZ,CY,$Z,MZ,PZ,zZ,UZ,eX,HZ,jZ,_Y,mZ,XZ,aQ,QZ,sX,oQ,cQ,hQ,gQ,vQ,kQ,TQ,_Q,AQ,DQ,PQ,zQ,VQ,HQ,KQ,wY,gZ,JQ,QQ,tee,aee,iee,uee,pee,hee,gee,fZ,dX,xee,kee,Tee,Cee,hX,Eee,Fee,Mee,DZ];for(let e of Ree)Sc(e);var Pee="2.8.5",Oee={"tfjs-core":X0,"tfjs-backend-cpu":hG,"tfjs-backend-webgl":KK,"tfjs-data":PN,"tfjs-layers":mm,"tfjs-converter":AN,tfjs:Pee},Vn;(function(e){e[e.float32=0]="float32",e[e.int32=1]="int32",e[e.bool=2]="bool",e[e.string=3]="string",e[e.complex64=4]="complex64"})(Vn||(Vn={}));var Cp;(function(e){e[e.linear=0]="linear",e[e.relu=1]="relu",e[e.relu6=2]="relu6",e[e.prelu=3]="prelu",e[e.leakyrelu=4]="leakyrelu"})(Cp||(Cp={}));var o2;function Lee(e){o2=e.wasm.cwrap(bi,null,["number","array","number","number","array","number","number","number","number","number","number","number","number"])}function zee(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s,bias:i,preluActivationWeights:o}=t;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("_FusedMatMul for non non-float32 tensors not yet supported.");let{transposeA:l,transposeB:c,activation:u,leakyreluAlpha:p}=a,d=n.dataIdMap.get(r.dataId).id,h=n.dataIdMap.get(s.dataId).id,m=0;if(i!=null){let $=n.dataIdMap.get(i.dataId);if($.shape.length!==1)throw new Error(`_FusedMatMul only supports rank-1 bias but got rank ${$.shape.length}.`);m=$.id}let f=o==null?0:n.dataIdMap.get(o.dataId).id,g=Cp[u];if(g==null)throw new Error(`${u} activation not yet supported for FusedConv2D in the wasm backend.`);let y=l?r.shape[2]:r.shape[1],b=c?s.shape[1]:s.shape[2],v=r.shape[0],x=n.makeOutput([v,y,b],r.dtype),N=n.dataIdMap.get(x.dataId).id,T=new Uint8Array(new Int32Array(r.shape).buffer),C=new Uint8Array(new Int32Array(s.shape).buffer);return o2(d,T,r.shape.length,h,C,s.shape.length,l,c,g,m,f,p||0,N),x}var Bee={kernelName:bi,backendName:"wasm",setupFunc:Lee,kernelFunc:zee};function Un(e){let t;function n(r){t=r.wasm.cwrap(e,null,["number","number"])}function a(r){let{backend:s,inputs:{x:i}}=r,o=s.dataIdMap.get(i.dataId).id,l=s.makeOutput(i.shape,i.dtype),c=s.dataIdMap.get(l.dataId).id;return k.sizeFromShape(l.shape)===0||t(o,c),l}return{kernelName:e,backendName:"wasm",setupFunc:n,kernelFunc:a}}var Wee=Un(Co);function gn(e,t,n){let a;function r(i){a=i.wasm.cwrap(e,null,["number","array","number","number","array","number","number","number"])}function s(i){let{backend:o,inputs:l}=i,{a:c,b:u}=l,p=o.dataIdMap.get(c.dataId).id,d=o.dataIdMap.get(u.dataId).id,h=n!=null?n:c.dtype,m=E.assertAndGetBroadcastShape(c.shape,u.shape),f=o.makeOutput(m,h);if(k.sizeFromShape(m)===0)return f;let g=new Uint8Array(new Int32Array(c.shape).buffer),y=new Uint8Array(new Int32Array(u.shape).buffer),b=o.dataIdMap.get(f.dataId).id,v=()=>a(p,g,c.shape.length,d,y,u.shape.length,Vn[c.dtype],b);if(t&&c.dtype==="float32")return v(),f;let x=E.getBroadcastDims(c.shape,m),N=E.getBroadcastDims(u.shape,m),T=x.every(($,F)=>$===F),C=N.every(($,F)=>$===F);if(T&&C)return v(),f;throw new Error(`Broadcasting along outer dims is not yet supported for ${c.dtype} ${e}.`)}return{kernelName:e,backendName:"wasm",setupFunc:r,kernelFunc:s}}var Vee=!0,Uee=gn(Wr,Vee),l2;function Gee(e){l2=e.wasm.cwrap(_s,null,["array","number","number","number"])}function Hee(e){let{inputs:t,backend:n}=e,a=n.makeOutput(t[0].shape,t[0].dtype);if(k.sizeFromShape(a.shape)===0)return a;let r=t.map(o=>n.dataIdMap.get(o.dataId).id),s=new Uint8Array(new Int32Array(r).buffer),i=n.dataIdMap.get(a.dataId).id;return l2(s,r.length,Vn[a.dtype],i),a}var jee={kernelName:_s,backendName:"wasm",setupFunc:Gee,kernelFunc:Hee};function Km(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype),r=n.typedArrayFromHeap(t);return n.typedArrayFromHeap(a).set(r),a}var qee={kernelName:Xo,backendName:"wasm",kernelFunc:Km},u2;function Kee(e){u2=e.wasm.cwrap(yi,null,["number","array","number","number","number","array","number"])}function Xm(e){let{inputs:t,backend:n,attrs:a}=e,[r,s]=Yee(t.x.shape,a.perm),i=!0;for(let m=0;m=r&&(s===-1||a[s]>a[i])&&(s=i);a[s]=r}return[n,a]}var Jee={kernelName:yi,backendName:"wasm",kernelFunc:Xm,setupFunc:Kee};function gu(e,t,n){let a=e.shape,r=e.shape.length,s=k.parseAxisParam(t,a),i=s,o=E.getAxesPermutation(i,r),l=null,c=!1;if(o!=null){let u=new Array(r);for(let d=0;d`new shape: ${i}, old shape: ${a.shape}. New shape and old shape must have the same number of elements.`),{dataId:a.dataId,shape:i,dtype:a.dtype}}var rte={kernelName:hl,backendName:"wasm",kernelFunc:La},d2;function ste(e){d2=e.wasm.cwrap(Fs,null,["number","array","number","number","array","number","number","number","number"])}function ite(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s}=t,{transposeA:i,transposeB:o}=a;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("BatchMatMul for non non-float32 tensors not yet supported.");let l=r.shape.length,c=s.shape.length,u=i?r.shape[l-2]:r.shape[l-1],p=o?s.shape[c-1]:s.shape[c-2],d=i?r.shape[l-1]:r.shape[l-2],h=o?s.shape[c-2]:s.shape[c-1],m=r.shape.slice(0,-2),f=s.shape.slice(0,-2),g=k.sizeFromShape(m),y=k.sizeFromShape(f),b=g===y||g===1||y===1;k.assert(l>=2&&c>=2&&b,()=>`Error in matMul: the input batch dimensions must either be the same or at least one input batch dimension must be 1. Got input batch dimensions of (${m}) and (${f}).`);let v=(g>y?r.shape.slice(0,-2):s.shape.slice(0,-2)).concat([d,h]);k.assert(u===p,()=>`Error in matMul: inner shapes (${u}) and (${p}) of Tensors with shapes ${r.shape} and ${s.shape} and transposeA=${i} and transposeB=${o} must match.`);let x=i?[g,u,d]:[g,d,u],N=o?[y,h,p]:[y,p,h],T=La({inputs:{x:r},backend:n,attrs:{shape:x}}),C=La({inputs:{x:s},backend:n,attrs:{shape:N}}),$=n.dataIdMap.get(T.dataId).id,F=n.dataIdMap.get(C.dataId).id,O=i?T.shape[2]:T.shape[1],W=o?C.shape[1]:C.shape[2],V=Math.max(g,y),H=n.makeOutput([V,O,W],T.dtype),K=n.dataIdMap.get(H.dataId).id,j=new Uint8Array(new Int32Array(T.shape).buffer),Y=new Uint8Array(new Int32Array(C.shape).buffer);return d2($,j,T.shape.length,F,Y,C.shape.length,i,o,K),H.shape=v,H}var ote={kernelName:Fs,backendName:"wasm",setupFunc:ste,kernelFunc:ite};function Ym(e){let{inputs:{x:t},attrs:{dtype:n},backend:a}=e,r=a.makeOutput(t.shape,n),s=a.typedArrayFromHeap(t);return a.typedArrayFromHeap(r).set(s),r}var lte={kernelName:$s,backendName:"wasm",kernelFunc:Ym},h2;function ute(e){h2=e.wasm.cwrap(Vr,null,["number","number","number","number"])}function cte(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{clipValueMin:s,clipValueMax:i}=a,o=n.dataIdMap.get(r.dataId).id,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(l.dataId).id;return h2(o,s,i,c),l}var pte={kernelName:Vr,backendName:"wasm",setupFunc:ute,kernelFunc:cte};function m2(e){let{inputs:t,backend:n}=e,a=k.parseAxisParam(e.attrs.axis,t[0].shape)[0],r=E.computeOutShape(t.map(h=>h.shape),a),s=t.filter(h=>k.sizeFromShape(h.shape)>0);if(s.length===1)return Km({inputs:{x:s[0]},backend:n});let i=n.makeOutput(r,t[0].dtype);if(k.sizeFromShape(r)===0)return i;let o=s.map(h=>h.shape);if(E.assertParamsConsistent(o,a),s[0].dtype==="string"){let h=s.map(v=>{let x=k.sizeFromShape(v.shape.slice(a));return La({inputs:{x:v},backend:n,attrs:{shape:[-1,x]}})}),m=h.map(v=>({vals:n.readSync(v.dataId),shape:v.shape}));r=E.computeOutShape(h.map(v=>v.shape),1);let f=h[0].shape[0]===1,g=dv(m,r,t[0].dtype,f),y=E.computeOutShape(s.map(v=>v.shape),a);i.shape=y;let b=n.dataIdMap.get(i.dataId);return b.stringBytes=E.fromStringArrayToUint8(g),i}let l=k.sizeFromShape(s[0].shape.slice(0,a)),c=0,u=s.map(h=>{let m=k.sizeFromShape(h.shape.slice(a));return c+=m,m}),p=s.map(h=>n.typedArrayFromHeap(h)),d=n.typedArrayFromHeap(i);for(let h=0;h`cumsum does not support ${r.dtype} tensors in the WASM backend`);let c=E.getAxesPermutation([s],l),u=r;c!==null&&(u=Xm({inputs:{x:r},attrs:{perm:c},backend:n}));let p=E.getInnerMostAxes(1,l)[0];E.assertAxesAreInnerMostDims("cumsum",[p],l);let d=n.makeOutput(u.shape,u.dtype),h=u.shape[p],m=n.dataIdMap.get(u.dataId).id,f=n.dataIdMap.get(d.dataId).id;b2(m,i?1:0,o?1:0,h,f,Vn[r.dtype]);let g=d;if(c!==null){let y=E.getUndoAxesPermutation(c);g=Xm({inputs:{x:d},attrs:{perm:y},backend:n}),n.disposeData(u.dataId),n.disposeData(d.dataId)}return g}var Tte={kernelName:Ps,backendName:"wasm",setupFunc:Ite,kernelFunc:Nte},x2;function Ste(e){x2=e.wasm.cwrap(zo,null,["number","number","number","array","number","array","array","number","number"])}function Cte(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{blockSize:s,dataFormat:i}=a;k.assert(s>1,()=>`blockSize should be > 1 for depthToSpace, but was: ${s}`);let o=r.shape[0],l=i==="NHWC"?r.shape[1]:r.shape[2],c=i==="NHWC"?r.shape[2]:r.shape[3],u=i==="NHWC"?r.shape[3]:r.shape[1],p=l*s,d=c*s,h=u/(s*s),m=i==="NHWC"?[o,p,d,h]:[o,h,p,d],f=t.makeOutput(m,"float32"),g=t.dataIdMap.get(r.dataId).id,y=new Uint8Array(new Int32Array(k.computeStrides(r.shape)).buffer),b=new Uint8Array(new Int32Array(m).buffer),v=new Uint8Array(new Int32Array(k.computeStrides(m)).buffer),x=t.dataIdMap.get(f.dataId).id;return x2(g,s,i==="NHWC"?1:0,y,r.shape.length-1,b,v,m.length,x),f}var _te={kernelName:zo,backendName:"wasm",setupFunc:Ste,kernelFunc:Cte},v2;function Ete(e){v2=e.wasm.cwrap(Os,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Ate(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s}=t,i=a.dataIdMap.get(r.dataId).id,o=a.dataIdMap.get(s.dataId).id,{strides:l,dilations:c,pad:u,dimRoundingMode:p}=n,d=c==null?[1,1]:c,h=E.computeConv2DInfo(r.shape,s.shape,l,d,u,p,!0),m=h.filterHeight,f=h.filterWidth,g=h.padInfo.top,y=h.padInfo.right,b=h.padInfo.bottom,v=h.padInfo.left,x=h.dilationHeight,N=h.dilationWidth,T=h.strideHeight,C=h.strideWidth,$=h.inChannels,F=h.outChannels,O=h.padInfo.type==="SAME"?1:0;if(h.dataFormat!=="channelsLast")throw new Error(`wasm backend DepthwiseConv2dNative does not support dataFormat:'${h.dataFormat}'. Please use 'channelsLast'.`);let W=a.makeOutput(h.outShape,"float32"),V=a.dataIdMap.get(W.dataId).id;return v2(i,r.shape[0],r.shape[1],r.shape[2],o,m,f,g,y,b,v,O,x,N,T,C,$,F,V),W}var Fte={kernelName:Os,backendName:"wasm",setupFunc:Ete,kernelFunc:Ate},$te=!1,Dte=gn(Vo,$te,"bool"),Mte=Un(zs);function Uv(e){let{inputs:t,attrs:n,backend:a}=e,{input:r}=t,{dim:s}=n,i=r.shape.length,o=r.shape.slice(),l=s;return s<0&&(k.assert(-(i+1)<=s,()=>`Axis must be in the interval [${-(i+1)}, ${i}]`),l=i+s+1),o.splice(l,0,1),La({inputs:{x:r},backend:a,attrs:{shape:o}})}var Rte={kernelName:Uo,backendName:"wasm",kernelFunc:Uv};function Pte(e){let{attrs:{shape:t,value:n,dtype:a},backend:r}=e,s=r.makeOutput(t,a);return r.typedArrayFromHeap(s).fill(n),s}var Ote={kernelName:mc,backendName:"wasm",kernelFunc:Pte},w2;function Lte(e){w2=e.wasm.cwrap(Ho,null,["number","number","number","number","number","number"])}function zte(e){let{inputs:t,backend:n}=e,{image:a}=t,r=n.makeOutput(a.shape,a.dtype),s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,[o,l,c,u]=a.shape;return w2(s,o,l,c,u,i),r}var Bte={kernelName:Ho,backendName:"wasm",kernelFunc:zte,setupFunc:Lte},Wte=Un(Bs),Vte=!1,Ute=gn(Ws,Vte),k2;function Gte(e){k2=e.wasm.cwrap(Vs,null,["number","number","number","number","number","number","number"])}function Hte(e){let{backend:t,inputs:n,attrs:a}=e,{varianceEpsilon:r}=a,{x:s,mean:i,variance:o,offset:l,scale:c}=n,u=t.dataIdMap.get(s.dataId).id,p=t.dataIdMap.get(i.dataId).id,d=t.dataIdMap.get(o.dataId).id,h=l!=null?t.dataIdMap.get(l.dataId).id:0,m=c!=null?t.dataIdMap.get(c.dataId).id:0,f=t.makeOutput(s.shape,s.dtype);if(k.sizeFromShape(s.shape)===0)return f;let g=t.dataIdMap.get(f.dataId).id;return k2(u,p,d,h,m,r,g),f}var jte={kernelName:Vs,backendName:"wasm",setupFunc:Gte,kernelFunc:Hte},I2;function qte(e){I2=e.wasm.cwrap(xi,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Kte(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d),g=Cp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return I2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Xte={kernelName:xi,backendName:"wasm",setupFunc:qte,kernelFunc:Kte},N2;function Yte(e){N2=e.wasm.cwrap(vi,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Jte(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d,!0),g=Cp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedDepthwiseConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedDepthwiseConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedDepthwiseConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedDepthwiseConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return N2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Zte={kernelName:vi,backendName:"wasm",setupFunc:Yte,kernelFunc:Jte},T2;function Qte(e){T2=e.wasm.cwrap(qo,null,["number","number","number","number","number","number","array","number"])}function ene(e){let{backend:t,inputs:n}=e,{params:a,indices:r}=n,[s,i,o,l]=my.prepareAndValidate(a,r),c=t.makeOutput(s,a.dtype);if(i===0)return c;let u=r.shape,p=u[u.length-1],d=t.dataIdMap.get(a.dataId).id,h=t.dataIdMap.get(r.dataId).id,m=new Uint8Array(new Int32Array(l).buffer),f=t.dataIdMap.get(c.dataId).id;return T2(d,Vn[a.dtype],h,i,p,o,m,f),c}var tne={kernelName:qo,backendName:"wasm",setupFunc:Qte,kernelFunc:ene},S2;function nne(e){S2=e.wasm.cwrap("Gather",null,["number","number","array","number","number","number","array","number"])}function ane(e){let{backend:t,inputs:n,attrs:a}=e,{x:r,indices:s}=n,{axis:i,batchDims:o}=a,l=k.parseAxisParam(i,r.shape)[0],c=E.segment_util.collectGatherOpShapeInfo(r,s,l,o),u=La({inputs:{x:r},attrs:{shape:[c.batchSize,c.outerSize,c.dimSize,c.sliceSize]},backend:t}),p=k.sizeFromShape(s.shape),d=La({inputs:{x:s},attrs:{shape:[c.batchSize,p/c.batchSize]},backend:t}),h=[c.batchSize,c.outerSize,p/c.batchSize,c.sliceSize],m=t.makeOutput(h,r.dtype);if(k.sizeFromShape(r.shape)===0)return m;let f=u.shape.length-1,g=t.dataIdMap.get(u.dataId).id,y=t.dataIdMap.get(d.dataId).id,b=t.dataIdMap.get(m.dataId).id,v=new Uint8Array(new Int32Array(k.computeStrides(u.shape)).buffer),x=new Uint8Array(new Int32Array(k.computeStrides(h)).buffer);return S2(g,Vn[r.dtype],v,f,y,c.batchSize,x,b),m.shape=c.outputShape,m}var rne={kernelName:jo,backendName:"wasm",setupFunc:nne,kernelFunc:ane},sne=!1,ine=gn(Ko,sne,"bool"),one=!1,lne=gn(Us,one,"bool"),C2;function une(e){C2=e.wasm.cwrap(Gs,null,["number","number","number"])}function cne(e){let{inputs:{x:t},attrs:{alpha:n},backend:a}=e,r=a.dataIdMap.get(t.dataId).id,s=a.makeOutput(t.shape,t.dtype);if(k.sizeFromShape(t.shape)!==0){let i=a.dataIdMap.get(s.dataId).id;C2(r,n,i)}return s}var pne={kernelName:Gs,backendName:"wasm",setupFunc:une,kernelFunc:cne},dne=!1,hne=gn(Qo,dne,"bool"),mne=!1,fne=gn(el,mne,"bool"),gne=Un(Hs),yne=!1,bne=gn(nl,yne,"bool"),_2;function xne(e){_2=e.wasm.cwrap(js,null,["number, number, number"])}function vne(e){let{backend:t,inputs:n,attrs:a}=e,{reductionIndices:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=i,{transposed:c,axes:u,originalAxes:p,inputWasTransposed:d}=gu(i,r,t);if(d){let b=t.dataIdMap.get(c.dataId).id;l=c,o=b}let h=l.shape.length;E.assertAxesAreInnerMostDims("max",u,h);let[m,f]=E.computeOutAndReduceShapes(l.shape,u),g=k.sizeFromShape(f),y=t.makeOutput(m,i.dtype);if(k.sizeFromShape(l.shape)!==0){let b=t.dataIdMap.get(y.dataId).id;_2(o,g,b)}if(d&&t.disposeData(c.dataId),s){let b=E.expandShapeToKeepDim(y.shape,p);y.shape=b}return y}var wne={kernelName:js,backendName:"wasm",setupFunc:xne,kernelFunc:vne},kne=!1,Ine=gn(qs,kne),E2;function Nne(e){E2=e.wasm.cwrap(Ks,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Tne(e){let{inputs:t,attrs:n,backend:a}=e,r=t.x,s=a.dataIdMap.get(r.dataId).id,{filterSize:i,strides:o,pad:l,dimRoundingMode:c}=n,u=E.computePool2DInfo(r.shape,i,o,1,l,c),p=u.filterHeight,d=u.filterWidth,h=u.padInfo.top,m=u.padInfo.right,f=u.padInfo.bottom,g=u.padInfo.left,y=u.dilationHeight,b=u.dilationWidth,v=u.strideHeight,x=u.strideWidth,N=u.inChannels,T=u.outChannels;if(u.dataFormat!=="channelsLast")throw new Error(`wasm backend does not support dataFormat:'${u.dataFormat}'. Please use 'channelsLast'.`);let C=a.makeOutput(u.outShape,"float32"),$=a.dataIdMap.get(C.dataId).id;return E2(s,r.shape[0],r.shape[1],r.shape[2],p,d,h,m,f,g,y,b,v,x,N,T,$),C}var Sne={kernelName:Ks,backendName:"wasm",setupFunc:Nne,kernelFunc:Tne},A2;function Cne(e){A2=e.wasm.cwrap(Xs,null,["number, number, number"])}function _ne(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t),m=p;if(h){let x=t.dataIdMap.get(u.dataId).id;x!==o&&(c=u,l=x,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("mean",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=c;c.dtype!=="float32"&&(b=Ym({backend:t,inputs:{x:c},attrs:{dtype:"float32"}}),l=t.dataIdMap.get(b.dataId).id);let v=t.makeOutput(f,"float32");if(k.sizeFromShape(c.shape)!==0){let x=t.dataIdMap.get(v.dataId).id;A2(l,y,x)}if(h&&t.disposeData(u.dataId),s){let x=E.expandShapeToKeepDim(v.shape,d);v.shape=x}return c.dtype!=="float32"&&t.disposeData(b.dataId),v}var Ene={kernelName:Xs,backendName:"wasm",setupFunc:Cne,kernelFunc:_ne},F2;function Ane(e){F2=e.wasm.cwrap(Ys,null,["number, number, number"])}function Fne(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t);if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v)}let m=c.shape.length;E.assertAxesAreInnerMostDims("min",p,m);let[f,g]=E.computeOutAndReduceShapes(c.shape,p),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;F2(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var $ne={kernelName:Ys,backendName:"wasm",setupFunc:Ane,kernelFunc:Fne},Dne=!1,Mne=gn(Js,Dne),Rne=!0,Pne=gn(Zs,Rne),One=Un(rl);function Gv(e,t){let n=new Int32Array(e.wasm.HEAPU8.buffer,t,4),a=n[0],r=n[1],s=n[2],i=n[3];return e.wasm._free(t),{pSelectedIndices:a,selectedSize:r,pSelectedScores:s,pValidOutputs:i}}var $2;function Lne(e){$2=e.wasm.cwrap(il,"number",["number","number","number","number","number"])}function zne(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i}=a,{boxes:o,scores:l}=n,c=t.dataIdMap.get(o.dataId).id,u=t.dataIdMap.get(l.dataId).id,p=$2(c,u,s,r,i),{pSelectedIndices:d,selectedSize:h,pSelectedScores:m,pValidOutputs:f}=Gv(t,p);return t.wasm._free(m),t.wasm._free(f),t.makeOutput([h],"int32",d)}var Bne={kernelName:il,backendName:"wasm",setupFunc:Lne,kernelFunc:zne},D2;function Wne(e){D2=e.wasm.cwrap(ol,"number",["number","number","number","number","number","bool"])}function Vne(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,padToMaxOutputSize:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=D2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=Gv(t,d);t.wasm._free(f);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([],"int32",g);return[y,b]}var Une={kernelName:ol,backendName:"wasm",setupFunc:Wne,kernelFunc:Vne},M2;function Gne(e){M2=e.wasm.cwrap(ll,"number",["number","number","number","number","number","number"])}function Hne(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,softNmsSigma:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=M2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=Gv(t,d);t.wasm._free(g);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([m],"float32",f);return[y,b]}var jne={kernelName:ll,backendName:"wasm",setupFunc:Gne,kernelFunc:Hne},qne=!1,Kne=gn(sl,qne,"bool"),R2;function Xne(e){R2=e.wasm.cwrap(Qs,null,["number","number","number","number","number"])}function Yne(e){let{inputs:t,backend:n,attrs:a}=e,{indices:r}=t,{depth:s,onValue:i,offValue:o}=a,l=n.makeOutput([...r.shape,s],"int32"),c=n.dataIdMap.get(l.dataId).id,u=n.dataIdMap.get(r.dataId).id;return R2(u,s,i,o,c),l}var Jne={kernelName:Qs,backendName:"wasm",setupFunc:Xne,kernelFunc:Yne};function Zne(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(1),a}var Qne={kernelName:ul,backendName:"wasm",kernelFunc:Zne};function eae(e){let{inputs:t,backend:n,attrs:a}=e,{axis:r}=a;if(t.length===1)return Uv({inputs:{input:t[0]},backend:n,attrs:{dim:r}});let s=t[0].shape,i=t[0].dtype;t.forEach(l=>{k.assertShapesMatch(s,l.shape,"All tensors passed to stack must have matching shapes"),k.assert(i===l.dtype,()=>"All tensors passed to stack must have matching dtypes")});let o=t.map(l=>Uv({inputs:{input:l},backend:n,attrs:{dim:r}}));return m2({inputs:o,backend:n,attrs:{axis:r}})}var tae={kernelName:cl,backendName:"wasm",kernelFunc:eae},P2;function nae(e){P2=e.wasm.cwrap(ei,null,["number","array","number","number","array","array","number","number"])}function aae(e){let{inputs:{x:t},backend:n,attrs:{paddings:a,constantValue:r}}=e,s=a.map((m,f)=>m[0]+t.shape[f]+m[1]),i=n.dataIdMap.get(t.dataId).id,o=n.makeOutput(s,t.dtype),l=n.dataIdMap.get(o.dataId).id,c=new Uint8Array(new Int32Array(t.shape).buffer),u=a.map(m=>m[0]),p=a.map(m=>m[1]),d=new Uint8Array(new Int32Array(u).buffer),h=new Uint8Array(new Int32Array(p).buffer);return P2(i,c,t.shape.length,Vn[t.dtype],d,h,r,l),o}var rae={kernelName:ei,backendName:"wasm",kernelFunc:aae,setupFunc:nae},sae=!1,iae=gn(ti,sae),O2;function oae(e){O2=e.wasm.cwrap(ni,null,["number","number","number"])}function lae(e){let{inputs:t,backend:n}=e,{x:a,alpha:r}=t,s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,o=n.makeOutput(a.shape,"float32"),l=n.dataIdMap.get(o.dataId).id;return O2(s,i,l),o}var uae={kernelName:ni,backendName:"wasm",setupFunc:oae,kernelFunc:lae},L2;function cae(e){L2=e.wasm.cwrap(pl,null,["number","number","number","number"])}function pae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("prod",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;L2(l,y,Vn[b.dtype],v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var dae={kernelName:pl,backendName:"wasm",setupFunc:cae,kernelFunc:pae},hae=e=>{let{backend:t,attrs:n}=e,{start:a,stop:r,step:s,dtype:i}=n,o=fv(a,r,s,i),l=t.makeOutput([o.length],i);return t.typedArrayFromHeap(l).set(o),l},mae={kernelName:vc,backendName:"wasm",kernelFunc:hae},fae=!0,gae=gn(Ls,fae),yae=Un(ai),bae=Un(si),z2;function xae(e){z2=e.wasm.cwrap(ri,null,["number","number","number","number","number","number","number","number","number","number"])}function vae(e){let{backend:t,inputs:n,attrs:a}=e,{images:r}=n,{alignCorners:s,halfPixelCenters:i,size:o}=a,[l,c]=o,[u,p,d,h]=r.shape,m=[u,l,c,h],f=t.dataIdMap.get(r.dataId),g;f.dtype!=="float32"&&(g=Ym({backend:t,inputs:{x:r},attrs:{dtype:"float32"}}),f=t.dataIdMap.get(g.dataId));let y=f.id,b=t.makeOutput(m,"float32");if(k.sizeFromShape(r.shape)===0)return b;let v=t.dataIdMap.get(b.dataId).id;return z2(y,u,p,d,h,l,c,s?1:0,i?1:0,v),g!=null&&t.disposeData(g.dataId),b}var wae={kernelName:ri,backendName:"wasm",setupFunc:xae,kernelFunc:vae},B2;function kae(e){B2=e.wasm.cwrap(ii,null,["number","array","number","array","number","number"])}function Iae(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{dims:s}=a,i=k.parseAxisParam(s,r.shape);if(r.shape.length===0)return Km({inputs:{x:r},backend:n});let o=n.makeOutput(r.shape,r.dtype),l=n.dataIdMap.get(r.dataId).id,c=n.dataIdMap.get(o.dataId).id,u=new Uint8Array(new Int32Array(i).buffer),p=new Uint8Array(new Int32Array(r.shape).buffer);return B2(l,u,i.length,p,r.shape.length,c),La({inputs:{x:o},attrs:{shape:r.shape},backend:n})}var Nae={kernelName:ii,backendName:"wasm",kernelFunc:Iae,setupFunc:kae},W2;function Tae(e){W2=e.wasm.cwrap(Cl,null,["number","number","number","number","number","number","number","number","array","number","number"])}function Sae(e){let{inputs:t,backend:n,attrs:a}=e,{image:r}=t,{radians:s,fillValue:i,center:o}=a,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(r.dataId).id,u=n.dataIdMap.get(l.dataId).id,[p,d,h,m]=r.shape,[f,g]=E.getImageCenter(o,d,h),y=i===0,b=255,v=typeof i=="number"?[i,i,i,y?0:b]:[...i,b],x=new Uint8Array(new Int32Array(v).buffer);return W2(c,p,d,h,m,s,f,g,x,v.length,u),l}var Cae={kernelName:Cl,backendName:"wasm",kernelFunc:Sae,setupFunc:Tae},_ae=Un(oi),Eae=Un(li),V2;function Aae(e){V2=e.wasm.cwrap(ml,null,["number","number","number","number","number","number","array","number","number"])}function Fae(e){let{backend:t,inputs:n,attrs:a}=e,{indices:r,updates:s}=n,{shape:i}=a,o=t.makeOutput(i,s.dtype);if(k.sizeFromShape(i)===0)return o;let{sliceRank:l,numUpdates:c,sliceSize:u,strides:p,outputSize:d}=fy.calculateShapes(s,r,i),h=t.dataIdMap.get(r.dataId).id,m=t.dataIdMap.get(s.dataId).id,f=new Uint8Array(new Int32Array(p).buffer),g=t.dataIdMap.get(o.dataId).id;return V2(h,m,Vn[s.dtype],l,c,u,f,d,g),o}var $ae={kernelName:ml,backendName:"wasm",setupFunc:Aae,kernelFunc:Fae},U2;function Dae(e){U2=e.wasm.cwrap("SelectV2",null,["number","number","number","number","number"])}function Mae(e){let{inputs:t,backend:n}=e,{condition:a,t:r,e:s}=t,i=n.dataIdMap.get(a.dataId).id,o=n.dataIdMap.get(r.dataId).id,l=n.dataIdMap.get(s.dataId).id,c=n.makeOutput(r.shape,r.dtype),u=n.dataIdMap.get(c.dataId).id,p=a.shape.length,d=r.shape.length,h=p===0||p>1||d===1?1:k.sizeFromShape(r.shape.slice(1));return U2(i,o,l,h,u),c}var Rae={kernelName:fl,backendName:"wasm",kernelFunc:Mae,setupFunc:Dae},G2;function Pae(e){G2=e.wasm.cwrap(ci,null,["number","number"])}function Oae(e){let{backend:t,inputs:{x:n}}=e,a=t.dataIdMap.get(n.dataId).id,r=t.makeOutput(n.shape,n.dtype),s=t.dataIdMap.get(r.dataId).id;return k.sizeFromShape(r.shape)===0||G2(a,s),r}var Lae={kernelName:"Sigmoid",backendName:"wasm",setupFunc:Pae,kernelFunc:Oae},zae=Un(ui);function Jm(e){let{inputs:{x:t},attrs:{begin:n,size:a},backend:r}=e,[s,i]=pn.parseSliceParams(t,n,a),o=pn.isSliceContinous(t.shape,s,i),l=r.readSync(t.dataId),c=r.makeOutput(i,t.dtype),u=k.computeStrides(t.shape),p=r.dataIdMap.get(c.dataId);if(o){let m=pn.computeFlatOffset(s,u);return t.dtype==="string"?p.stringBytes=l.slice(m,m+k.sizeFromShape(i)):r.typedArrayFromHeap(c).set(l.subarray(m,m+k.sizeFromShape(i))),c}if(t.dtype==="string"){let m=Am(l,s,i,t.shape,t.dtype);return p.stringBytes=m,c}let d=r.typedArrayFromHeap(c),h=t.shape.length;if(h===2)Bae(l,u[0],d,s,i);else if(h===3)Wae(l,u[0],u[1],d,s,i);else if(h===4)Vae(l,u[0],u[1],u[2],d,s,i);else{let m=Am(l,s,i,t.shape,t.dtype);d.set(m)}return c}function Bae(e,t,n,a,r){let s=0,i=a[0],o=a[1],l=i+r[0];for(let c=i;c{let d=[...u];d[o]=p;let h=Jm({inputs:{x:r},attrs:{begin:c,size:d},backend:a});return c[o]+=p,h})}var Kae={kernelName:wl,backendName:"wasm",kernelFunc:qae},Xae=Un(pi),Yae=Un(Ic),Jae=!0,Zae=gn(mi,Jae),j2;function Qae(e){j2=e.wasm.cwrap(Gr,null,["number","number","number"])}function ere(e){let{backend:t,inputs:n,attrs:a}=e,{alpha:r}=a,{x:s}=n,i=t.dataIdMap.get(s.dataId).id,o=t.makeOutput(s.shape,s.dtype),l=t.dataIdMap.get(o.dataId).id;return j2(i,r,l),o}var tre={kernelName:Gr,backendName:"wasm",setupFunc:Qae,kernelFunc:ere},q2;function nre(e){q2=e.wasm.cwrap(kl,null,["number","array","number","array","array","array","array","array","number","number"])}function are(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{begin:s,end:i,strides:o}=a;o==null&&(o=new Array(s.length));let{beginMask:l,endMask:c,ellipsisMask:u,newAxisMask:p,shrinkAxisMask:d}=a,h=E.slice_util.maskToAxes(u);if(h.length>1)throw new Error("Multiple ellipses in slice is not allowed.");if(u!==0&&p!==0)throw new Error("Using both ellipsisMask and newAxisMask is not yet supported.");if(u!==0&&d!==0)throw new Error("Using both ellipsisMask and shrinkAxisMask is not yet supported.");let m=r.shape.length-s.length,f=E.slice_util.maskToAxes(p),g=r.shape.slice();f.forEach(F=>{s[F]=0,i[F]=1,g.splice(F,0,1)});let y=La({inputs:{x:r},attrs:{shape:g},backend:t}),{begin:b,end:v,strides:x}=E.slice_util.getNormalizedAxes(y.shape,h,m,s,i,o,l,c,u);s=b,i=v,o=x;let N=E.slice_util.maskToAxes(d);N.forEach(F=>{i[F]=s[F]+1,o[F]=1});let T=E.slice_util.computeOutShape(s,i,o),C=T.filter((F,O)=>N.indexOf(O)===-1);if(o.every(F=>F===1)){let F=Jm({inputs:{x:r},attrs:{begin:s,size:T},backend:t});return La({inputs:{x:F},attrs:{shape:C},backend:t})}let $=t.makeOutput(C,"float32");if(!C.some(F=>F===0)){let F=t.dataIdMap.get(y.dataId).id,O=new Uint8Array(new Int32Array(k.computeStrides(y.shape)).buffer),W=new Uint8Array(new Int32Array(s).buffer),V=new Uint8Array(new Int32Array(i).buffer),H=new Uint8Array(new Int32Array(o).buffer),K=new Uint8Array(new Int32Array(C).buffer),j=new Uint8Array(new Int32Array(k.computeStrides(C)).buffer),Y=t.dataIdMap.get($.dataId).id;q2(F,O,y.shape.length,W,V,H,K,j,C.length,Y)}return La({inputs:{x:$},attrs:{shape:C},backend:t})}var rre={kernelName:kl,backendName:"wasm",setupFunc:nre,kernelFunc:are},sre=!0,ire=gn(fi,sre),K2;function ore(e){K2=e.wasm.cwrap(di,null,["number, number, number"])}function lre(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=gu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("sum",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;K2(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var ure={kernelName:di,backendName:"wasm",setupFunc:ore,kernelFunc:lre},cre=Un(gi),X2;function pre(e){X2=e.wasm.cwrap(Ur,null,["number","array","number","array","number","number"])}function dre(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,s=n.dataIdMap.get(r.dataId).id,{reps:i}=a,o=new Array(r.shape.length);for(let d=0;d{let{x:a}=e,{k:r,sorted:s}=n,i=t.dataIdMap.get(a.dataId).id,o=new Uint8Array(new Int32Array(a.shape).buffer),l=a.shape.slice();l[l.length-1]=r;let c=t.makeOutput(l,a.dtype),u=t.dataIdMap.get(c.dataId).id,p=t.makeOutput(l,"int32"),d=t.dataIdMap.get(p.dataId).id;return Y2(i,o,a.shape.length,Vn[a.dtype],r,s,u,d),[c,p]},gre={kernelName:Nl,backendName:"wasm",setupFunc:mre,kernelFunc:fre};function yre(e){let{inputs:t,backend:n,attrs:a}=e,{value:r}=t,{axis:s}=a;s<0&&(s+=r.shape.length);let i=r.shape[s],o=r.shape.length,l=new Array(o-1),c=0;for(let h=0;h({dataId:h,dtype:m,shape:l}))}var bre={kernelName:Tl,backendName:"wasm",kernelFunc:yre};function xre(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(0),a}var vre={kernelName:Sl,backendName:"wasm",kernelFunc:xre},wre=[Wee,Uee,jee,ete,ate,ote,lte,pte,dte,fte,bte,xte,kte,Tte,_te,Fte,Dte,Mte,Rte,Ote,Bte,Wte,Ute,Bee,jte,Xte,Zte,tne,rne,ine,lne,qee,pne,hne,fne,gne,bne,wne,Ine,Sne,Ene,$ne,Mne,Pne,One,Bne,Une,jne,Kne,Jne,Qne,tae,rae,iae,uae,dae,mae,gae,yae,bae,rte,wae,Nae,Cae,Eae,_ae,$ae,Rae,Lae,zae,Uae,jae,Kae,Xae,Yae,Zae,tre,rre,ire,ure,cre,hre,gre,Jee,bre,vre];for(let e of wre)Sc(e);var Hv=te();Hv.registerFlag("WASM_HAS_SIMD_SUPPORT",async()=>WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,10,9,1,7,0,65,0,253,15,26,11])));Hv.registerFlag("WASM_HAS_MULTITHREAD_SUPPORT",async()=>{if(Hv.get("IS_NODE"))return!1;try{return new MessageChannel().port1.postMessage(new SharedArrayBuffer(1)),WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,5,4,1,3,1,1,10,11,1,9,0,65,0,254,16,2,0,26,11]))}catch(e){return!1}});var J2=No(FE()),kre='var threadInfoStruct=0;var selfThreadId=0;var parentThreadId=0;var Module={};function threadPrintErr(){var text=Array.prototype.slice.call(arguments).join(" ");console.error(text)}function threadAlert(){var text=Array.prototype.slice.call(arguments).join(" ");postMessage({cmd:"alert",text:text,threadId:selfThreadId})}var err=threadPrintErr;this.alert=threadAlert;Module["instantiateWasm"]=function(info,receiveInstance){var instance=new WebAssembly.Instance(Module["wasmModule"],info);Module["wasmModule"]=null;receiveInstance(instance);return instance.exports};this.onmessage=function(e){try{if(e.data.cmd==="load"){Module["DYNAMIC_BASE"]=e.data.DYNAMIC_BASE;Module["DYNAMICTOP_PTR"]=e.data.DYNAMICTOP_PTR;Module["wasmModule"]=e.data.wasmModule;Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;Module["ENVIRONMENT_IS_PTHREAD"]=true;if(typeof e.data.urlOrBlob==="string"){importScripts(e.data.urlOrBlob)}else{var objectUrl=URL.createObjectURL(e.data.urlOrBlob);importScripts(objectUrl);URL.revokeObjectURL(objectUrl)}Module=WasmBackendModuleThreadedSimd(Module);postMessage({"cmd":"loaded"})}else if(e.data.cmd==="objectTransfer"){Module["PThread"].receiveObjectTransfer(e.data)}else if(e.data.cmd==="run"){Module["__performance_now_clock_drift"]=performance.now()-e.data.time;threadInfoStruct=e.data.threadInfoStruct;Module["__register_pthread_ptr"](threadInfoStruct,0,0);selfThreadId=e.data.selfThreadId;parentThreadId=e.data.parentThreadId;var max=e.data.stackBase;var top=e.data.stackBase+e.data.stackSize;Module["establishStackSpace"](top,max);Module["_emscripten_tls_init"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].setThreadStatus(Module["_pthread_self"](),1);try{var result=Module["dynCall_ii"](e.data.start_routine,e.data.arg);if(!Module["getNoExitRuntime"]())Module["PThread"].threadExit(result)}catch(ex){if(ex==="Canceled!"){Module["PThread"].threadCancel()}else if(ex!="unwind"){Atomics.store(Module["HEAPU32"],threadInfoStruct+4>>2,ex instanceof Module["ExitStatus"]?ex.status:-2);Atomics.store(Module["HEAPU32"],threadInfoStruct+0>>2,1);Module["_emscripten_futex_wake"](threadInfoStruct+0,2147483647);if(!(ex instanceof Module["ExitStatus"]))throw ex}}}else if(e.data.cmd==="cancel"){if(threadInfoStruct){Module["PThread"].threadCancel()}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="processThreadQueue"){if(threadInfoStruct){Module["_emscripten_current_thread_process_queued_calls"]()}}else{err("worker.js received unknown command "+e.data.cmd);err(e.data)}}catch(ex){err("worker.js onmessage() captured an uncaught exception: "+ex);if(ex.stack)err(ex.stack);throw ex}};if(typeof process==="object"&&typeof process.versions==="object"&&typeof process.versions.node==="string"){self={location:{href:__filename}};var onmessage=this.onmessage;var nodeWorkerThreads=require("worker_threads");Worker=nodeWorkerThreads.Worker;var parentPort=nodeWorkerThreads.parentPort;parentPort.on("message",function(data){onmessage({data:data})});var nodeFS=require("fs");var nodeRead=function(filename){return nodeFS.readFileSync(filename,"utf8")};function globalEval(x){global.require=require;global.Module=Module;eval.call(null,x)}importScripts=function(f){globalEval(nodeRead(f))};postMessage=function(msg){parentPort.postMessage(msg)};if(typeof performance==="undefined"){performance={now:function(){return Date.now()}}}}',Ire=No($E()),Z2=class extends sc{constructor(e){super();this.wasm=e,this.dataIdNextNumber=1,this.wasm.tfjs.init(),this.dataIdMap=new fd(this,Jr())}write(e,t,n){let a={};return this.move(a,e,t,n),a}numDataIds(){return this.dataIdMap.numDataIds()}async time(e){let t=k.now();return e(),{kernelMs:k.now()-t}}move(e,t,n,a){let r=this.dataIdNextNumber++;if(a==="string"){let l=t;this.dataIdMap.set(e,{id:r,stringBytes:l,shape:n,dtype:a,memoryOffset:null});return}let s=k.sizeFromShape(n),i=s*k.bytesPerElement(a),o=this.wasm._malloc(i);this.dataIdMap.set(e,{id:r,memoryOffset:o,shape:n,dtype:a}),this.wasm.tfjs.registerTensor(r,s,o),t!=null&&this.wasm.HEAPU8.set(new Uint8Array(t.buffer,t.byteOffset,i),o)}async read(e){return this.readSync(e)}readSync(e){let{memoryOffset:t,dtype:n,shape:a,stringBytes:r}=this.dataIdMap.get(e);if(n==="string")return r;let s=this.wasm.HEAPU8.slice(t,t+k.sizeFromShape(a)*k.bytesPerElement(n));return Nre(s.buffer,n)}disposeData(e){let t=this.dataIdMap.get(e);this.wasm._free(t.memoryOffset),this.wasm.tfjs.disposeData(t.id),this.dataIdMap.delete(e)}floatPrecision(){return 32}getMemoryOffset(e){return this.dataIdMap.get(e).memoryOffset}dispose(){this.wasm.tfjs.dispose(),this.wasm=null}memory(){return{unreliable:!1}}makeOutput(e,t,n){let a;if(n==null)a=this.write(null,e,t);else{a={};let r=this.dataIdNextNumber++;this.dataIdMap.set(a,{id:r,memoryOffset:n,shape:e,dtype:t});let s=k.sizeFromShape(e);this.wasm.tfjs.registerTensor(r,s,n)}return{dataId:a,shape:e,dtype:t}}typedArrayFromHeap({shape:e,dtype:t,dataId:n}){let a=this.wasm.HEAPU8.buffer,{memoryOffset:r}=this.dataIdMap.get(n),s=k.sizeFromShape(e);switch(t){case"float32":return new Float32Array(a,r,s);case"int32":return new Int32Array(a,r,s);case"bool":return new Uint8Array(a,r,s);default:throw new Error(`Unknown dtype ${t}`)}}};function Tre(e){return(t,n)=>(k.fetch(e,{credentials:"same-origin"}).then(a=>{a.ok||t.env.a(`failed to load wasm binary file at '${e}'`),a.arrayBuffer().then(r=>{WebAssembly.instantiate(r,t).then(s=>{n(s.instance)})})}),{})}function Q2(e,t,n){if(Zm!=null)return Zm;let a="tfjs-backend-wasm.wasm";return e&&t?a="tfjs-backend-wasm-threaded-simd.wasm":e&&(a="tfjs-backend-wasm-simd.wasm"),_p!=null&&_p[a]!=null?_p[a]:n+a}async function Sre(){let[e,t]=await Promise.all([te().getAsync("WASM_HAS_SIMD_SUPPORT"),te().getAsync("WASM_HAS_MULTITHREAD_SUPPORT")]);return new Promise((n,a)=>{let r={};r.locateFile=(l,c)=>{if(l.endsWith(".worker.js")){let u=kre,p=new Blob([u],{type:"application/javascript"});return URL.createObjectURL(p)}return l.endsWith(".wasm")?Q2(e,t,Ep!=null?Ep:c):c+l},jv&&(r.instantiateWasm=Tre(Q2(e,t,Ep!=null?Ep:"")));let s;t&&e&&Zm==null?(s=J2.default(r),s.mainScriptUrlOrBlob=new Blob(["var WasmBackendModuleThreadedSimd = "+J2.default.toString()],{type:"text/javascript"})):s=Ire.default(r);let i=null;s.tfjs={init:s.cwrap("init",null,[]),registerTensor:s.cwrap("register_tensor",null,["number","number","number"]),disposeData:s.cwrap("dispose_data",i,["number"]),dispose:s.cwrap("dispose",i,[])};let o=!1;s.onRuntimeInitialized=()=>{o=!0,Ap=!1,n({wasm:s})},s.onAbort=()=>{o||Ap||(Ap=!0,a({message:"Make sure the server can serve the `.wasm` file relative to the bundled js file. For more details see https://github.com/tensorflow/tfjs/blob/master/tfjs-backend-wasm/README.md#using-bundlers"}))}})}function Nre(e,t){switch(t){case"float32":return new Float32Array(e);case"int32":return new Int32Array(e);case"bool":return new Uint8Array(e);default:throw new Error(`Unknown dtype ${t}`)}}var Cre=["tfjs-backend-wasm.wasm","tfjs-backend-wasm-simd.wasm","tfjs-backend-wasm-threaded-simd.wasm"],Zm=null,Ep=null,_p={},Ap=!1,jv=!1;function _re(e,t=!1){if(Rt("setWasmPath has been deprecated in favor of setWasmPaths and will be removed in a future release."),Ap)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPath()` before you call `tf.setBackend()` or `tf.ready()`");Zm=e,jv=t}function Ere(e,t=!1){if(Ap)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPaths()` before you call `tf.setBackend()` or `tf.ready()`");if(typeof e=="string")Ep=e;else{_p=e;let n=Cre.filter(a=>_p[a]==null);if(n.length>0)throw new Error(`There were no entries found for the following binaries: ${n.join(",")}. Please either call setWasmPaths with a map providing a path for each binary, or with a string indicating the directory where all the binaries can be found.`)}jv=t}var Are="2.8.5",Fre=2;oh("wasm",async()=>{let{wasm:e}=await Sre();return new Z2(e)},Fre);var bw={};dd(bw,{AnchorPosition:()=>lr,DrawBox:()=>nf,DrawBoxOptions:()=>ow,DrawFaceLandmarks:()=>yw,DrawFaceLandmarksOptions:()=>gw,DrawTextField:()=>fs,DrawTextFieldOptions:()=>Mp,drawContour:()=>_r,drawDetections:()=>Vre,drawFaceExpressions:()=>jre,drawFaceLandmarks:()=>qre});function _r(e,t,n=!1){if(e.beginPath(),t.slice(1).forEach(({x:a,y:r},s)=>{let i=t[s];e.moveTo(i.x,i.y),e.lineTo(a,r)}),n){let a=t[t.length-1],r=t[0];if(!a||!r)return;e.moveTo(a.x,a.y),e.lineTo(r.x,r.y)}e.stroke()}var qv={};dd(qv,{computeReshapedDimensions:()=>Yv,getCenterPoint:()=>Yi,isDimensions:()=>ef,isEven:()=>Qm,isFloat:()=>Xv,isTensor:()=>Ki,isTensor1D:()=>$re,isTensor2D:()=>Kv,isTensor3D:()=>Er,isTensor4D:()=>aa,isValidNumber:()=>za,isValidProbablitiy:()=>yu,range:()=>ir,round:()=>Xi});var yn=class{constructor(t,n){if(!za(t)||!za(n))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:n})}`);this._width=t,this._height=n}get width(){return this._width}get height(){return this._height}reverse(){return new yn(1/this.width,1/this.height)}};function Ki(e,t){return e instanceof z&&e.shape.length===t}function $re(e){return Ki(e,1)}function Kv(e){return Ki(e,2)}function Er(e){return Ki(e,3)}function aa(e){return Ki(e,4)}function Xv(e){return e%1!=0}function Qm(e){return e%2==0}function Xi(e,t=2){let n=10**t;return Math.floor(e*n)/n}function ef(e){return e&&e.width&&e.height}function Yv({width:e,height:t},n){let a=n/Math.max(t,e);return new yn(Math.round(e*a),Math.round(t*a))}function Yi(e){return e.reduce((t,n)=>t.add(n),new De(0,0)).div(new De(e.length,e.length))}function ir(e,t,n){return Array(e).fill(0).map((a,r)=>t+r*n)}function za(e){return!!e&&e!==Infinity&&e!==-Infinity&&!Number.isNaN(e)||e===0}function yu(e){return za(e)&&e>=0&&e<=1}var De=class{constructor(t,n){this._x=t,this._y=n}get x(){return this._x}get y(){return this._y}add(t){return new De(this.x+t.x,this.y+t.y)}sub(t){return new De(this.x-t.x,this.y-t.y)}mul(t){return new De(this.x*t.x,this.y*t.y)}div(t){return new De(this.x/t.x,this.y/t.y)}abs(){return new De(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new De(Math.floor(this.x),Math.floor(this.y))}};var ct=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(za)}static assertIsValidBox(t,n,a=!1){if(!ct.isRect(t))throw new Error(`${n} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!a&&(t.width<0||t.height<0))throw new Error(`${n} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,n=!0){let a=t||{},r=[a.left,a.top,a.right,a.bottom].every(za),s=[a.x,a.y,a.width,a.height].every(za);if(!s&&!r)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(a)}`);let[i,o,l,c]=s?[a.x,a.y,a.width,a.height]:[a.left,a.top,a.right-a.left,a.bottom-a.top];ct.assertIsValidBox({x:i,y:o,width:l,height:c},"Box.constructor",n),this._x=i,this._y=o,this._width=l,this._height=c}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new De(this.left,this.top)}get topRight(){return new De(this.right,this.top)}get bottomLeft(){return new De(this.left,this.bottom)}get bottomRight(){return new De(this.right,this.bottom)}round(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.round(s));return new ct({x:t,y:n,width:a,height:r})}floor(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.floor(s));return new ct({x:t,y:n,width:a,height:r})}toSquare(){let{x:t,y:n,width:a,height:r}=this,s=Math.abs(a-r);return an&&(o=-p+n+a,p=n),d>t&&(l=-d+t+r,d=t),c<1&&(l=2-c,c=1),u<1&&(l=2-u,u=1),{dy:i,edy:l,dx:s,edx:o,y:u,ey:d,x:c,ex:p,w:a,h:r}}calibrate(t){return new ct({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var bu=class extends ct{constructor(t,n,a,r,s=!1){super({left:t,top:n,right:a,bottom:r},s)}};var ms=class{constructor(t,n,a,r,s){this._imageDims=new yn(s.width,s.height),this._score=t,this._classScore=n,this._className=a,this._box=new ct(r).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new ct(this._box).rescale(this.imageDims.reverse())}forSize(t,n){return new ms(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:n})}};var vt=class extends ms{constructor(t,n,a){super(t,t,"",n,a)}forSize(t,n){let{score:a,relativeBox:r,imageDims:s}=super.forSize(t,n);return new vt(a,r,s)}};function Jv(e,t,n=!0){let a=Math.max(0,Math.min(e.right,t.right)-Math.max(e.left,t.left)),r=Math.max(0,Math.min(e.bottom,t.bottom)-Math.max(e.top,t.top)),s=a*r;return n?s/(e.area+t.area-s):s/Math.min(e.area,t.area)}function Zv(e){let t=e.map(o=>o.x),n=e.map(o=>o.y),a=t.reduce((o,l)=>lloo({score:i,boxIndex:o})).sort((i,o)=>i.score-o.score).map(i=>i.boxIndex),s=[];for(;r.length>0;){let i=r.pop();s.push(i);let o=r,l=[];for(let c=0;cl[u]<=n)}return s}function Ba(e,t){return D(()=>{let[n,a,r]=t,s=kn([...e.shape.slice(0,3),1],n,"float32"),i=kn([...e.shape.slice(0,3),1],a,"float32"),o=kn([...e.shape.slice(0,3),1],r,"float32"),l=Qe([s,i,o],3);return ge(e,l)})}function ew(e,t=!1){return D(()=>{let[n,a]=e.shape.slice(1);if(n===a)return e;let r=Math.abs(n-a),s=Math.round(r*(t?.5:1)),i=n>a?2:1,o=d=>{let h=e.shape.slice();return h[i]=d,kn(h,0,"float32")},l=o(s),c=r-l.shape[i],p=[t&&c?o(c):null,e,l].filter(d=>!!d).map(d=>pe(d,"float32"));return Qe(p,i)})}function Dre(e){let t=e.slice();for(let n=t.length-1;n>0;n--){let a=Math.floor(Math.random()*(n+1)),r=t[n];t[n]=t[a],t[a]=r}return t}function Fp(e){return 1/(1+Math.exp(-e))}function Mre(e){return Math.log(e/(1-e))}var xu=class extends ct{constructor(t,n,a,r,s=!1){super({x:t,y:n,width:a,height:r},s)}};var Rre=.5,Pre=.43,Ore=.45,ra=class{constructor(t,n,a=new De(0,0)){let{width:r,height:s}=n;this._imgDims=new yn(r,s),this._shift=a,this._positions=t.map(i=>i.mul(new De(r,s)).add(a))}get shift(){return new De(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new De(this.imageWidth,this.imageHeight)))}forSize(t,n){return new this.constructor(this.relativePositions,{width:t,height:n})}shiftBy(t,n){return new this.constructor(this.relativePositions,this._imgDims,new De(t,n))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,n={}){if(t){let s=t instanceof vt?t.box.floor():new ct(t);return this.shiftBy(s.x,s.y).align(null,n)}let{useDlibAlignment:a,minBoxPadding:r}={useDlibAlignment:!1,minBoxPadding:.2,...n};return a?this.alignDlib():this.alignMinBbox(r)}alignDlib(){let t=this.getRefPointsForAlignment(),[n,a,r]=t,s=p=>r.sub(p).magnitude(),i=(s(n)+s(a))/2,o=Math.floor(i/Ore),l=Yi(t),c=Math.floor(Math.max(0,l.x-Rre*o)),u=Math.floor(Math.max(0,l.y-Pre*o));return new xu(c,u,Math.min(o,this.imageWidth+c),Math.min(o,this.imageHeight+u))}alignMinBbox(t){let n=Zv(this.positions);return n.pad(n.width*t,n.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var eC=class extends ra{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Yi([t[3],t[4]])]}};var vu=class extends ra{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Yi)}};var $p=class{constructor(t,n){this._label=t,this._distance=n}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${Xi(this.distance)})`:""}`}};var Dp=class extends ct{static assertIsValidLabeledBox(t,n){if(ct.assertIsValidBox(t,n),!za(t.label))throw new Error(`${n} - expected property label (${t.label}) to be a number`)}constructor(t,n){super(t);this._label=n}get label(){return this._label}};var Ar=class{constructor(t,n){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(n)||n.some(a=>!(a instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=n}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let n=t.descriptors.map(a=>new Float32Array(a));return new Ar(t.label,n)}};var tC=class extends Dp{static assertIsValidPredictedBox(t,n){if(Dp.assertIsValidLabeledBox(t,n),!yu(t.score)||!yu(t.classScore))throw new Error(`${n} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,n,a,r){super(t,n);this._score=a,this._classScore=r}get score(){return this._score}get classScore(){return this._classScore}};function or(e){return e.detection instanceof vt}function Ji(e,t){return{...e,...{detection:t}}}function tw(){let e=window.fetch;if(!e)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:e,readFile:t}}function tf(e){let t="";if(!e)try{e=require("fs")}catch(a){t=a.toString()}return{readFile:e?a=>new Promise((r,s)=>{e.readFile(a,(i,o)=>i?s(i):r(o))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function nw(){let e=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,n=()=>{if(e)return new e;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},a=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},r=global.fetch,s=tf();return{Canvas:e||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:n,createImageElement:a,fetch:r,...s}}function aw(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var rw=dE(aC()),en;function Bre(){if(!en)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return en}function sw(e){en=e}function iw(){return aw()?sw(tw()):rw.isNodejs()?sw(nw()):null}function Wre(e){if(en||iw(),!en)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=en.Canvas,Image:n=en.Image}=e;en.Canvas=t,en.Image=n,en.createCanvasElement=e.createCanvasElement||(()=>new t),en.createImageElement=e.createImageElement||(()=>new n),en.ImageData=e.ImageData||en.ImageData,en.Video=e.Video||en.Video,en.fetch=e.fetch||en.fetch,en.readFile=e.readFile||en.readFile}var it={getEnv:Bre,setEnv:sw,initialize:iw,createBrowserEnv:tw,createFileSystem:tf,createNodejsEnv:nw,monkeyPatch:Wre,isBrowser:aw,isNodejs:rw.isNodejs};iw();function Zi(e){return!it.isNodejs()&&typeof e=="string"?document.getElementById(e):e}function Cn(e){let{Canvas:t,CanvasRenderingContext2D:n}=it.getEnv();if(e instanceof n)return e;let a=Zi(e);if(!(a instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let r=a.getContext("2d");if(!r)throw new Error("resolveContext2d - canvas 2d context is null");return r}var lr;(function(e){e.TOP_LEFT="TOP_LEFT",e.TOP_RIGHT="TOP_RIGHT",e.BOTTOM_LEFT="BOTTOM_LEFT",e.BOTTOM_RIGHT="BOTTOM_RIGHT"})(lr||(lr={}));var Mp=class{constructor(t={}){let{anchorPosition:n,backgroundColor:a,fontColor:r,fontSize:s,fontStyle:i,padding:o}=t;this.anchorPosition=n||lr.TOP_LEFT,this.backgroundColor=a||"rgba(0, 0, 0, 0.5)",this.fontColor=r||"rgba(255, 255, 255, 1)",this.fontSize=s||14,this.fontStyle=i||"Georgia",this.padding=o||4}},fs=class{constructor(t,n,a={}){this.text=typeof t=="string"?[t]:t instanceof fs?t.text:t,this.anchor=n,this.options=new Mp(a)}measureWidth(t){let{padding:n}=this.options;return this.text.map(a=>t.measureText(a).width).reduce((a,r)=>a{let m=l+p.x,f=l+p.y+(h+1)*i;a.fillText(d,m,f)})}};var ow=class{constructor(t={}){let{boxColor:n,lineWidth:a,label:r,drawLabelOptions:s}=t;this.boxColor=n||"rgba(0, 0, 255, 1)",this.lineWidth=a||2,this.label=r;let i={anchorPosition:lr.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Mp({...i,...s})}},nf=class{constructor(t,n={}){this.box=new ct(t),this.options=new ow(n)}draw(t){let n=Cn(t),{boxColor:a,lineWidth:r}=this.options,{x:s,y:i,width:o,height:l}=this.box;n.strokeStyle=a,n.lineWidth=r,n.strokeRect(s,i,o,l);let{label:c}=this.options;c&&new fs([c],{x:s-r/2,y:i},this.options.drawLabelOptions).draw(t)}};function Vre(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof vt?a.score:or(a)?a.detection.score:void 0,s=a instanceof vt?a.box:or(a)?a.detection.box:new ct(a),i=r?`${Xi(r)}`:void 0;new nf(s,{label:i}).draw(e)})}function Rp(e){let{Image:t,Video:n}=it.getEnv();return e instanceof t&&e.complete||e instanceof n&&e.readyState>=3}function lw(e){return new Promise((t,n)=>{if(e instanceof it.getEnv().Canvas||Rp(e))return t(null);function a(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),n(s))}function r(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),t(s))}e.addEventListener("load",r),e.addEventListener("error",a)})}function uw(e){return new Promise((t,n)=>{e instanceof Blob||n(new Error("bufferToImage - expected buf to be of type: Blob"));let a=new FileReader;a.onload=()=>{typeof a.result!="string"&&n(new Error("bufferToImage - expected reader.result to be a string, in onload"));let r=it.getEnv().createImageElement();r.onload=()=>t(r),r.onerror=n,r.src=a.result},a.onerror=n,a.readAsDataURL(e)})}function Qi(e){let{Image:t,Video:n}=it.getEnv();return e instanceof t?new yn(e.naturalWidth,e.naturalHeight):e instanceof n?new yn(e.videoWidth,e.videoHeight):new yn(e.width,e.height)}function wu({width:e,height:t}){let{createCanvasElement:n}=it.getEnv(),a=n();return a.width=e,a.height=t,a}function Pp(e,t){let{ImageData:n}=it.getEnv();if(!(e instanceof n)&&!Rp(e))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:a,height:r}=t||Qi(e),s=wu({width:a,height:r});return e instanceof n?Cn(s).putImageData(e,0,0):Cn(s).drawImage(e,0,0,a,r),s}async function cw(e,t){let n=t||it.getEnv().createCanvasElement(),[a,r,s]=e.shape.slice(aa(e)?1:0),i=D(()=>e.as3D(a,r,s).toInt());return await Ni.toPixels(i,n),i.dispose(),n}function af(e){let{Image:t,Canvas:n,Video:a}=it.getEnv();return e instanceof t||e instanceof n||e instanceof a}function pw(e,t,n=!1){let{Image:a,Canvas:r}=it.getEnv();if(!(e instanceof a||e instanceof r))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let s=Qi(e),i=t/Math.max(s.height,s.width),o=i*s.width,l=i*s.height,c=wu({width:t,height:t}),u=e instanceof r?e:Pp(e),p=Math.abs(o-l)/2,d=n&&o{if(Er(a)){this._imageTensors[r]=a,this._inputDimensions[r]=a.shape;return}if(aa(a)){let i=a.shape[0];if(i!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${i} passed, but not supported in input array`);this._imageTensors[r]=a,this._inputDimensions[r]=a.shape.slice(1);return}let s=a instanceof it.getEnv().Canvas?a:Pp(a);this._canvases[r]=s,this._inputDimensions[r]=[s.height,s.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ir(this.batchSize,0,1).map((t,n)=>this.getReshapedInputDimensions(n))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let n=this.getInputWidth(t),a=this.getInputHeight(t);return Yv({width:n,height:a},this.inputSize)}toBatchTensor(t,n=!0){return this._inputSize=t,D(()=>{let a=ir(this.batchSize,0,1).map(s=>{let i=this.getInput(s);if(i instanceof z){let o=aa(i)?i:i.expandDims();return o=ew(o,n),(o.shape[1]!==t||o.shape[2]!==t)&&(o=Ja.resizeBilinear(o,[t,t])),o.as3D(t,t,3)}if(i instanceof it.getEnv().Canvas)return Ni.fromPixels(pw(i,t,n));throw new Error(`toBatchTensor - at batchIdx ${s}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${i}`)});return Dt(a.map(s=>pe(s,"float32"))).as4D(this.batchSize,t,t,3)})}};async function yt(e){if(e instanceof Fr)return e;let t=Array.isArray(e)?e:[e];if(!t.length)throw new Error("toNetInput - empty array passed as input");let n=r=>Array.isArray(e)?` at input index ${r}:`:"",a=t.map(Zi);return a.forEach((r,s)=>{if(!af(r)&&!Er(r)&&!aa(r))throw typeof t[s]=="string"?new Error(`toNetInput -${n(s)} string passed, but could not resolve HTMLElement for element id ${t[s]}`):new Error(`toNetInput -${n(s)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(aa(r)){let i=r.shape[0];if(i!==1)throw new Error(`toNetInput -${n(s)} tf.Tensor4D with batchSize ${i} passed, but not supported in input array`)}}),await Promise.all(a.map(r=>af(r)&&lw(r))),new Fr(a,Array.isArray(e))}async function ku(e,t){let{Canvas:n}=it.getEnv(),a=e;if(!(e instanceof n)){let i=await yt(e);if(i.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let o=i.getInput(0);a=o instanceof n?o:await cw(o)}let r=Cn(a);return t.map(i=>i instanceof vt?i.forSize(a.width,a.height).box.floor():i).map(i=>i.clipAtImageBorders(a.width,a.height)).map(({x:i,y:o,width:l,height:c})=>{let u=wu({width:l,height:c});return Cn(u).putImageData(r.getImageData(i,o,l,c),0,0),u})}async function Iu(e,t){if(!Er(e)&&!aa(e))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(aa(e)&&e.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return D(()=>{let[n,a,r]=e.shape.slice(aa(e)?1:0);return t.map(o=>o instanceof vt?o.forSize(a,n).box:o).map(o=>o.clipAtImageBorders(a,n)).map(({x:o,y:l,width:c,height:u})=>Vl(e.as3D(n,a,r),[l,o,0],[u,c,r]))})}async function eo(e,t){let{fetch:n}=it.getEnv(),a=await n(e,t);if(!(a.status<400))throw new Error(`failed to fetch: (${a.status}) ${a.statusText}, from url: ${a.url}`);return a}async function Ure(e){let t=await eo(e),n=await t.blob();if(!n.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${n.type}, for url: ${t.url}`);return uw(n)}async function dw(e){return(await eo(e)).json()}async function Gre(e){return new Float32Array(await(await eo(e)).arrayBuffer())}function rf(e,t){let n=`${t}-weights_manifest.json`;if(!e)return{modelBaseUri:"",manifestUri:n};if(e==="/")return{modelBaseUri:"/",manifestUri:`/${n}`};let a=e.startsWith("http://")?"http://":e.startsWith("https://")?"https://":"";e=e.replace(a,"");let r=e.split("/").filter(o=>o),s=e.endsWith(".json")?r[r.length-1]:n,i=a+(e.endsWith(".json")?r.slice(0,r.length-1):r).join("/");return i=e.startsWith("/")?`/${i}`:i,{modelBaseUri:i,manifestUri:i==="/"?`/${s}`:`${i}/${s}`}}async function hw(e,t){let{manifestUri:n,modelBaseUri:a}=rf(e,t),r=await dw(n);return qt.loadWeights(r,a)}function Hre(e,t,n=!1){let{width:a,height:r}=n?Qi(t):t;return e.width=a,e.height=r,{width:a,height:r}}var sn=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:n,objProp:a}=this.traversePropertyPath(t);return n[a]}reassignParamFromPath(t,n){let{obj:a,objProp:r}=this.traversePropertyPath(t);a[r].dispose(),a[r]=n}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof Hr)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof Hr))}variable(){this.getFrozenParams().forEach(({path:t,tensor:n})=>{this.reassignParamFromPath(t,n.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:n})=>{let a=Kn(n.dataSync());n.dispose(),this.reassignParamFromPath(t,a)})}dispose(t=!0){this.getParamList().forEach(n=>{if(t&&n.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${n.path}`);n.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,n)=>t.concat(n)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let n=await hw(t,this.getDefaultModelName());this.loadFromWeightMap(n)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:n}=it.getEnv(),{manifestUri:a,modelBaseUri:r}=rf(t,this.getDefaultModelName()),s=c=>Promise.all(c.map(u=>n(u).then(p=>p.buffer))),i=qt.weightsLoaderFactory(s),o=JSON.parse((await n(a)).toString()),l=await i(o,r);this.loadFromWeightMap(l)}loadFromWeightMap(t){let{paramMappings:n,params:a}=this.extractParamsFromWeightMap(t);this._paramMappings=n,this._params=a}extractWeights(t){let{paramMappings:n,params:a}=this.extractParams(t);this._paramMappings=n,this._params=a}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let n=t.split("/").reduce((s,i)=>{if(!s.nextObj.hasOwnProperty(i))throw new Error(`traversePropertyPath - object does not have property ${i}, for path ${t}`);return{obj:s.nextObj,objProp:i,nextObj:s.nextObj[i]}},{nextObj:this.params}),{obj:a,objProp:r}=n;if(!a||!r||!(a[r]instanceof z))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:a,objProp:r}}};function _n(e,t,n){return D(()=>{let a=Ai(e,t.depthwise_filter,t.pointwise_filter,n,"same");return a=Z(a,t.bias),a})}function sf(e,t,n=!1){return D(()=>{let a=Ye(n?Z(Ft(e,t.conv0.filters,[2,2],"same"),t.conv0.bias):_n(e,t.conv0,[2,2])),r=_n(a,t.conv1,[1,1]),s=Ye(Z(a,r)),i=_n(s,t.conv2,[1,1]);return Ye(Z(a,Z(r,i)))})}function Op(e,t,n=!1,a=!0){return D(()=>{let r=Ye(n?Z(Ft(e,t.conv0.filters,a?[2,2]:[1,1],"same"),t.conv0.bias):_n(e,t.conv0,a?[2,2]:[1,1])),s=_n(r,t.conv1,[1,1]),i=Ye(Z(r,s)),o=_n(i,t.conv2,[1,1]),l=Ye(Z(r,Z(s,o))),c=_n(l,t.conv3,[1,1]);return Ye(Z(r,Z(s,Z(o,c))))})}function to(e,t,n="same",a=!1){return D(()=>{let r=Z(Ft(e,t.filters,[1,1],n),t.bias);return a?Ye(r):r})}function bn(e,t){Object.keys(e).forEach(n=>{t.some(a=>a.originalPath===n)||e[n].dispose()})}function Nu(e,t){return(n,a,r,s)=>{let i=Ea(e(n*a*r*r),[r,r,n,a]),o=tt(e(a));return t.push({paramPath:`${s}/filters`},{paramPath:`${s}/bias`}),{filters:i,bias:o}}}function of(e,t){return(n,a,r)=>{let s=_a(e(n*a),[n,a]),i=tt(e(a));return t.push({paramPath:`${r}/weights`},{paramPath:`${r}/bias`}),{weights:s,bias:i}}}var lf=class{constructor(t,n,a){this.depthwise_filter=t;this.pointwise_filter=n;this.bias=a}};function Tu(e,t){return(n,a,r)=>{let s=Ea(e(3*3*n),[3,3,n,1]),i=Ea(e(n*a),[1,1,n,a]),o=tt(e(a));return t.push({paramPath:`${r}/depthwise_filter`},{paramPath:`${r}/pointwise_filter`},{paramPath:`${r}/bias`}),new lf(s,i,o)}}function Su(e){return t=>{let n=e(`${t}/depthwise_filter`,4),a=e(`${t}/pointwise_filter`,4),r=e(`${t}/bias`,1);return new lf(n,a,r)}}function Gn(e,t){return(n,a,r)=>{let s=e[n];if(!Ki(s,a))throw new Error(`expected weightMap[${n}] to be a Tensor${a}D, instead have ${s}`);return t.push({originalPath:n,paramPath:r||n}),s}}function xn(e){let t=e;function n(r){let s=t.slice(0,r);return t=t.slice(r),s}function a(){return t}return{extractWeights:n,getRemainingWeights:a}}function uf(e,t){let n=Nu(e,t),a=Tu(e,t);function r(i,o,l,c=!1){let u=c?n(i,o,3,`${l}/conv0`):a(i,o,`${l}/conv0`),p=a(o,o,`${l}/conv1`),d=a(o,o,`${l}/conv2`);return{conv0:u,conv1:p,conv2:d}}function s(i,o,l,c=!1){let{conv0:u,conv1:p,conv2:d}=r(i,o,l,c),h=a(o,o,`${l}/conv3`);return{conv0:u,conv1:p,conv2:d,conv3:h}}return{extractDenseBlock3Params:r,extractDenseBlock4Params:s}}function rC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),{extractDenseBlock4Params:r}=uf(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2"),l=r(128,256,"dense3");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o,dense3:l}}}function cf(e){return t=>{let n=e(`${t}/filters`,4),a=e(`${t}/bias`,1);return{filters:n,bias:a}}}function pf(e,t){let n=Gn(e,t),a=cf(n),r=Su(n);function s(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`);return{conv0:c,conv1:u,conv2:p}}function i(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`),d=r(`${o}/conv3`);return{conv0:c,conv1:u,conv2:p,conv3:d}}return{extractDenseBlock3Params:s,extractDenseBlock4Params:i}}function sC(e){let t=[],{extractDenseBlock4Params:n}=pf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2"),dense3:n("dense3")};return bn(e,t),{params:a,paramMappings:t}}var Lp=class extends sn{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(255)),i=Op(s,n.dense0,!0);return i=Op(i,n.dense1),i=Op(i,n.dense2),i=Op(i,n.dense3),i=Yn(i,[7,7],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return sC(t)}extractParams(t){return rC(t)}};function zp(e,t){return D(()=>Z(ze(e,t.weights),t.bias))}function iC(e,t,n){let a=[],{extractWeights:r,getRemainingWeights:s}=xn(e),o=of(r,a)(t,n,"fc");if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{paramMappings:a,params:{fc:o}}}function oC(e){let t=[],n=Gn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:a("fc")};return bn(e,t),{params:r,paramMappings:t}}function df(e){let t={},n={};return Object.keys(e).forEach(a=>{let r=a.startsWith("fc")?n:t;r[a]=e[a]}),{featureExtractorMap:t,classifierMap:n}}var Bp=class extends sn{constructor(t,n){super(t);this._faceFeatureExtractor=n}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof Fr?this.faceFeatureExtractor.forwardInput(t):t;return zp(a.as2D(a.shape[0],-1),n.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return iC(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=df(t);return this.faceFeatureExtractor.loadFromWeightMap(n),oC(a)}extractParams(t){let n=this.getClassifierChannelsIn(),a=this.getClassifierChannelsOut(),r=a*n+a,s=t.slice(0,t.length-r),i=t.slice(t.length-r);return this.faceFeatureExtractor.extractWeights(s),this.extractClassifierParams(i)}};var mw=["neutral","happy","sad","angry","fearful","disgusted","surprised"],gs=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);mw.forEach((n,a)=>{this[n]=t[a]})}asSortedArray(){return mw.map(t=>({expression:t,probability:this[t]})).sort((t,n)=>n.probability-t.probability)}};var hf=class extends Bp{constructor(t=new Lp){super("FaceExpressionNet",t)}forwardInput(t){return D(()=>Ca(this.runNet(t)))}async forward(t){return this.forwardInput(await yt(t))}async predictExpressions(t){let n=await yt(t),a=await this.forwardInput(n),r=await Promise.all(ht(a).map(async i=>{let o=await i.data();return i.dispose(),o}));a.dispose();let s=r.map(i=>new gs(i));return n.isBatchInput?s:s[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function fw(e){return e.expressions instanceof gs}function mf(e,t){return{...e,...{expressions:t}}}function jre(e,t,n=.1,a){(Array.isArray(t)?t:[t]).forEach(s=>{let i=s instanceof gs?s:fw(s)?s.expressions:void 0;if(!i)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let l=i.asSortedArray().filter(p=>p.probability>n),c=or(s)?s.detection.box.bottomLeft:a||new De(0,0);new fs(l.map(p=>`${p.expression} (${Xi(p.probability)})`),c).draw(e)})}function no(e){return or(e)&&e.landmarks instanceof ra&&e.unshiftedLandmarks instanceof ra&&e.alignedRect instanceof vt}function Cu(e,t){let{box:n}=e.detection,a=t.shiftBy(n.x,n.y),r=a.align(),{imageDims:s}=e.detection,i=new vt(e.detection.score,r.rescale(s.reverse()),s);return{...e,...{landmarks:a,unshiftedLandmarks:t,alignedRect:i}}}var gw=class{constructor(t={}){let{drawLines:n=!0,drawPoints:a=!0,lineWidth:r,lineColor:s,pointSize:i,pointColor:o}=t;this.drawLines=n,this.drawPoints=a,this.lineWidth=r||1,this.pointSize=i||2,this.lineColor=s||"rgba(0, 255, 255, 1)",this.pointColor=o||"rgba(255, 0, 255, 1)"}},yw=class{constructor(t,n={}){this.faceLandmarks=t,this.options=new gw(n)}draw(t){let n=Cn(t),{drawLines:a,drawPoints:r,lineWidth:s,lineColor:i,pointSize:o,pointColor:l}=this.options;if(a&&this.faceLandmarks instanceof vu&&(n.strokeStyle=i,n.lineWidth=s,_r(n,this.faceLandmarks.getJawOutline()),_r(n,this.faceLandmarks.getLeftEyeBrow()),_r(n,this.faceLandmarks.getRightEyeBrow()),_r(n,this.faceLandmarks.getNose()),_r(n,this.faceLandmarks.getLeftEye(),!0),_r(n,this.faceLandmarks.getRightEye(),!0),_r(n,this.faceLandmarks.getMouth(),!0)),r){n.strokeStyle=l,n.fillStyle=l;let c=u=>{n.beginPath(),n.arc(u.x,u.y,o,0,2*Math.PI),n.fill()};this.faceLandmarks.positions.forEach(c)}}};function qre(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof ra?a:no(a)?a.landmarks:void 0;if(!r)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new yw(r).draw(e)})}var lC="0.11.6";function Kre(e,t){let n=Nu(e,t),a=Tu(e,t);function r(i,o,l){let c=a(i,o,`${l}/separable_conv0`),u=a(o,o,`${l}/separable_conv1`),p=n(i,o,1,`${l}/expansion_conv`);return{separable_conv0:c,separable_conv1:u,expansion_conv:p}}function s(i,o){let l=a(i,i,`${o}/separable_conv0`),c=a(i,i,`${o}/separable_conv1`),u=a(i,i,`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:n,extractSeparableConvParams:a,extractReductionBlockParams:r,extractMainBlockParams:s}}function uC(e,t){let n=[],{extractWeights:a,getRemainingWeights:r}=xn(e),{extractConvParams:s,extractSeparableConvParams:i,extractReductionBlockParams:o,extractMainBlockParams:l}=Kre(a,n),c=s(3,32,3,"entry_flow/conv_in"),u=o(32,64,"entry_flow/reduction_block_0"),p=o(64,128,"entry_flow/reduction_block_1"),d={conv_in:c,reduction_block_0:u,reduction_block_1:p},h={};ir(t,0,1).forEach(y=>{h[`main_block_${y}`]=l(128,`middle_flow/main_block_${y}`)});let m=o(128,256,"exit_flow/reduction_block"),f=i(256,512,"exit_flow/separable_conv"),g={reduction_block:m,separable_conv:f};if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:n,params:{entry_flow:d,middle_flow:h,exit_flow:g}}}function Xre(e,t){let n=Gn(e,t),a=cf(n),r=Su(n);function s(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=a(`${o}/expansion_conv`);return{separable_conv0:l,separable_conv1:c,expansion_conv:u}}function i(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=r(`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}}function cC(e,t){let n=[],{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}=Xre(e,n),o=a("entry_flow/conv_in"),l=s("entry_flow/reduction_block_0"),c=s("entry_flow/reduction_block_1"),u={conv_in:o,reduction_block_0:l,reduction_block_1:c},p={};ir(t,0,1).forEach(f=>{p[`main_block_${f}`]=i(`middle_flow/main_block_${f}`)});let d=s("exit_flow/reduction_block"),h=r("exit_flow/separable_conv"),m={reduction_block:d,separable_conv:h};return bn(e,n),{params:{entry_flow:u,middle_flow:p,exit_flow:m},paramMappings:n}}function pC(e,t,n){return Z(Ft(e,t.filters,n,"same"),t.bias)}function xw(e,t,n=!0){let a=n?Ye(e):e;return a=_n(a,t.separable_conv0,[1,1]),a=_n(Ye(a),t.separable_conv1,[1,1]),a=$t(a,[3,3],[2,2],"same"),a=Z(a,pC(e,t.expansion_conv,[2,2])),a}function Yre(e,t){let n=_n(Ye(e),t.separable_conv0,[1,1]);return n=_n(Ye(n),t.separable_conv1,[1,1]),n=_n(Ye(n),t.separable_conv2,[1,1]),n=Z(n,e),n}var vw=class extends sn{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyXception - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(256)),i=Ye(pC(s,n.entry_flow.conv_in,[2,2]));return i=xw(i,n.entry_flow.reduction_block_0,!1),i=xw(i,n.entry_flow.reduction_block_1),ir(this._numMainBlocks,0,1).forEach(o=>{i=Yre(i,n.middle_flow[`main_block_${o}`])}),i=xw(i,n.exit_flow.reduction_block),i=Ye(_n(i,n.exit_flow.separable_conv,[1,1])),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return cC(t,this._numMainBlocks)}extractParams(t){return uC(t,this._numMainBlocks)}};function dC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),r=of(n,t),s=r(512,1,"fc/age"),i=r(512,2,"fc/gender");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{fc:{age:s,gender:i}}}}function hC(e){let t=[],n=Gn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:{age:a("fc/age"),gender:a("fc/gender")}};return bn(e,t),{params:r,paramMappings:t}}var $r;(function(e){e.FEMALE="female",e.MALE="male"})($r||($r={}));var ff=class extends sn{constructor(t=new vw(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof Fr?this.faceFeatureExtractor.forwardInput(t):t,r=Yn(a,[7,7],[2,2],"valid").as2D(a.shape[0],-1),s=zp(r,n.fc.age).as1D(),i=zp(r,n.fc.gender);return{age:s,gender:i}})}forwardInput(t){return D(()=>{let{age:n,gender:a}=this.runNet(t);return{age:n,gender:Ca(a)}})}async forward(t){return this.forwardInput(await yt(t))}async predictAgeAndGender(t){let n=await yt(t),a=await this.forwardInput(n),r=ht(a.age),s=ht(a.gender),i=r.map((l,c)=>({ageTensor:l,genderTensor:s[c]})),o=await Promise.all(i.map(async({ageTensor:l,genderTensor:c})=>{let u=(await l.data())[0],p=(await c.data())[0],d=p>.5,h=d?$r.MALE:$r.FEMALE,m=d?p:1-p;return l.dispose(),c.dispose(),{age:u,gender:h,genderProbability:m}}));return a.age.dispose(),a.gender.dispose(),n.isBatchInput?o:o[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return dC(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=df(t);return this.faceFeatureExtractor.loadFromWeightMap(n),hC(a)}extractParams(t){let n=512*1+1+(512*2+2),a=t.slice(0,t.length-n),r=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(r)}};var Wp=class extends Bp{postProcess(t,n,a){let r=a.map(({width:i,height:o})=>{let l=n/Math.max(o,i);return{width:i*l,height:o*l}}),s=r.length;return D(()=>{let i=(p,d)=>Dt([kn([68],p,"float32"),kn([68],d,"float32")],1).as2D(1,136).as1D(),o=(p,d)=>{let{width:h,height:m}=r[p];return d(h,m)?Math.abs(h-m)/2:0},l=p=>o(p,(d,h)=>do(p,(d,h)=>hi(l(d),c(d))))).div(Dt(Array.from(Array(s),(p,d)=>i(r[d].width,r[d].height))))})}forwardInput(t){return D(()=>{let n=this.runNet(t);return this.postProcess(n,t.inputSize,t.inputDimensions.map(([a,r])=>({height:a,width:r})))})}async forward(t){return this.forwardInput(await yt(t))}async detectLandmarks(t){let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(async(s,i)=>{let o=Array.from(await s.data()),l=o.filter((u,p)=>Qm(p)),c=o.filter((u,p)=>!Qm(p));return new vu(Array(68).fill(0).map((u,p)=>new De(l[p],c[p])),{height:n.getInputHeight(i),width:n.getInputWidth(i)})}));return a.forEach(s=>s.dispose()),n.isBatchInput?r:r[0]}getClassifierChannelsOut(){return 136}};var _u=class extends Wp{constructor(t=new Lp){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};function mC(e){let t=[],{extractDenseBlock3Params:n}=pf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2")};return bn(e,t),{params:a,paramMappings:t}}function fC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),{extractDenseBlock3Params:r}=uf(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o}}}var ww=class extends sn{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyFaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(255)),i=sf(s,n.dense0,!0);return i=sf(i,n.dense1),i=sf(i,n.dense2),i=Yn(i,[14,14],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return mC(t)}extractParams(t){return fC(t)}};var gf=class extends Wp{constructor(t=new ww){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var gC=class extends _u{};function yC(e,t){return Z(L(e,t.weights),t.biases)}function kw(e,t,n,a,r="same"){let{filters:s,bias:i}=t.conv,o=Ft(e,s,n,r);return o=Z(o,i),o=yC(o,t.scale),a?Ye(o):o}function bC(e,t){return kw(e,t,[1,1],!0)}function Iw(e,t){return kw(e,t,[1,1],!1)}function yf(e,t){return kw(e,t,[2,2],!0,"valid")}function Jre(e,t){function n(o,l,c){let u=e(o),p=u.length/(l*c*c);if(Xv(p))throw new Error(`depth has to be an integer: ${p}, weights.length: ${u.length}, numFilters: ${l}, filterSize: ${c}`);return D(()=>Ue(Ea(u,[l,p,c,c]),[2,3,1,0]))}function a(o,l,c,u){let p=n(o,l,c),d=tt(e(l));return t.push({paramPath:`${u}/filters`},{paramPath:`${u}/bias`}),{filters:p,bias:d}}function r(o,l){let c=tt(e(o)),u=tt(e(o));return t.push({paramPath:`${l}/weights`},{paramPath:`${l}/biases`}),{weights:c,biases:u}}function s(o,l,c,u){let p=a(o,l,c,`${u}/conv`),d=r(l,`${u}/scale`);return{conv:p,scale:d}}function i(o,l,c,u,p=!1){let d=s((p?.5:1)*o,l,c,`${u}/conv1`),h=s(o,l,c,`${u}/conv2`);return{conv1:d,conv2:h}}return{extractConvLayerParams:s,extractResidualLayerParams:i}}function xC(e){let{extractWeights:t,getRemainingWeights:n}=xn(e),a=[],{extractConvLayerParams:r,extractResidualLayerParams:s}=Jre(t,a),i=r(4704,32,7,"conv32_down"),o=s(9216,32,3,"conv32_1"),l=s(9216,32,3,"conv32_2"),c=s(9216,32,3,"conv32_3"),u=s(36864,64,3,"conv64_down",!0),p=s(36864,64,3,"conv64_1"),d=s(36864,64,3,"conv64_2"),h=s(36864,64,3,"conv64_3"),m=s(147456,128,3,"conv128_down",!0),f=s(147456,128,3,"conv128_1"),g=s(147456,128,3,"conv128_2"),y=s(589824,256,3,"conv256_down",!0),b=s(589824,256,3,"conv256_1"),v=s(589824,256,3,"conv256_2"),x=s(589824,256,3,"conv256_down_out"),N=D(()=>Ue(_a(t(256*128),[128,256]),[1,0]));if(a.push({paramPath:"fc"}),n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{params:{conv32_down:i,conv32_1:o,conv32_2:l,conv32_3:c,conv64_down:u,conv64_1:p,conv64_2:d,conv64_3:h,conv128_down:m,conv128_1:f,conv128_2:g,conv256_down:y,conv256_1:b,conv256_2:v,conv256_down_out:x,fc:N},paramMappings:a}}function Zre(e,t){let n=Gn(e,t);function a(i){let o=n(`${i}/scale/weights`,1),l=n(`${i}/scale/biases`,1);return{weights:o,biases:l}}function r(i){let o=n(`${i}/conv/filters`,4),l=n(`${i}/conv/bias`,1),c=a(i);return{conv:{filters:o,bias:l},scale:c}}function s(i){return{conv1:r(`${i}/conv1`),conv2:r(`${i}/conv2`)}}return{extractConvLayerParams:r,extractResidualLayerParams:s}}function vC(e){let t=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=Zre(e,t),r=n("conv32_down"),s=a("conv32_1"),i=a("conv32_2"),o=a("conv32_3"),l=a("conv64_down"),c=a("conv64_1"),u=a("conv64_2"),p=a("conv64_3"),d=a("conv128_down"),h=a("conv128_1"),m=a("conv128_2"),f=a("conv256_down"),g=a("conv256_1"),y=a("conv256_2"),b=a("conv256_down_out"),{fc:v}=e;if(t.push({originalPath:"fc",paramPath:"fc"}),!Kv(v))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${v}`);let x={conv32_down:r,conv32_1:s,conv32_2:i,conv32_3:o,conv64_down:l,conv64_1:c,conv64_2:u,conv64_3:p,conv128_down:d,conv128_1:h,conv128_2:m,conv256_down:f,conv256_1:g,conv256_2:y,conv256_down_out:b,fc:v};return bn(e,t),{params:x,paramMappings:t}}function Wa(e,t){let n=bC(e,t.conv1);return n=Iw(n,t.conv2),n=Z(n,e),n=Ye(n),n}function Vp(e,t){let n=yf(e,t.conv1);n=Iw(n,t.conv2);let a=Yn(e,2,2,"valid"),r=bt(a.shape),s=a.shape[3]!==n.shape[3];if(a.shape[1]!==n.shape[1]||a.shape[2]!==n.shape[2]){let o=[...n.shape];o[1]=1;let l=bt(o);n=Qe([n,l],1);let c=[...n.shape];c[2]=1;let u=bt(c);n=Qe([n,u],2)}return a=s?Qe([a,r],3):a,n=Z(a,n),n=Ye(n),n}var Eu=class extends sn{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceRecognitionNet - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(150,!0),"float32"),s=Ba(a,[122.782,117.001,104.298]).div(he(256)),i=yf(s,n.conv32_down);i=$t(i,3,2,"valid"),i=Wa(i,n.conv32_1),i=Wa(i,n.conv32_2),i=Wa(i,n.conv32_3),i=Vp(i,n.conv64_down),i=Wa(i,n.conv64_1),i=Wa(i,n.conv64_2),i=Wa(i,n.conv64_3),i=Vp(i,n.conv128_down),i=Wa(i,n.conv128_1),i=Wa(i,n.conv128_2),i=Vp(i,n.conv256_down),i=Wa(i,n.conv256_1),i=Wa(i,n.conv256_2),i=Vp(i,n.conv256_down_out);let o=i.mean([1,2]);return ze(o,n.fc)})}async forward(t){return this.forwardInput(await yt(t))}async computeFaceDescriptor(t){var s;if((s=t==null?void 0:t.shape)==null?void 0:s.some(i=>i<=0))return new Float32Array(128);let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(i=>i.data()));return a.forEach(i=>i.dispose()),n.isBatchInput?r:r[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return vC(t)}extractParams(t){return xC(t)}};function Qre(e){let t=new Eu;return t.extractWeights(e),t}function bf(e,t){return{...e,...{descriptor:t}}}function ese(e){return typeof e.age=="number"}function xf(e,t){return{...e,...{age:t}}}function tse(e){return(e.gender===$r.MALE||e.gender===$r.FEMALE)&&yu(e.genderProbability)}function vf(e,t,n){return{...e,...{gender:t,genderProbability:n}}}function nse(e,t){function n(l,c){let u=Ea(e(3*3*l),[3,3,l,1]),p=tt(e(l)),d=tt(e(l)),h=tt(e(l)),m=tt(e(l));return t.push({paramPath:`${c}/filters`},{paramPath:`${c}/batch_norm_scale`},{paramPath:`${c}/batch_norm_offset`},{paramPath:`${c}/batch_norm_mean`},{paramPath:`${c}/batch_norm_variance`}),{filters:u,batch_norm_scale:p,batch_norm_offset:d,batch_norm_mean:h,batch_norm_variance:m}}function a(l,c,u,p,d){let h=Ea(e(l*c*u*u),[u,u,l,c]),m=tt(e(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/${d?"batch_norm_offset":"bias"}`}),{filters:h,bias:m}}function r(l,c,u,p){let{filters:d,bias:h}=a(l,c,u,p,!0);return{filters:d,batch_norm_offset:h}}function s(l,c,u){let p=n(l,`${u}/depthwise_conv`),d=r(l,c,1,`${u}/pointwise_conv`);return{depthwise_conv:p,pointwise_conv:d}}function i(){let l=r(3,32,3,"mobilenetv1/conv_0"),c=s(32,64,"mobilenetv1/conv_1"),u=s(64,128,"mobilenetv1/conv_2"),p=s(128,128,"mobilenetv1/conv_3"),d=s(128,256,"mobilenetv1/conv_4"),h=s(256,256,"mobilenetv1/conv_5"),m=s(256,512,"mobilenetv1/conv_6"),f=s(512,512,"mobilenetv1/conv_7"),g=s(512,512,"mobilenetv1/conv_8"),y=s(512,512,"mobilenetv1/conv_9"),b=s(512,512,"mobilenetv1/conv_10"),v=s(512,512,"mobilenetv1/conv_11"),x=s(512,1024,"mobilenetv1/conv_12"),N=s(1024,1024,"mobilenetv1/conv_13");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,conv_8:g,conv_9:y,conv_10:b,conv_11:v,conv_12:x,conv_13:N}}function o(){let l=r(1024,256,1,"prediction_layer/conv_0"),c=r(256,512,3,"prediction_layer/conv_1"),u=r(512,128,1,"prediction_layer/conv_2"),p=r(128,256,3,"prediction_layer/conv_3"),d=r(256,128,1,"prediction_layer/conv_4"),h=r(128,256,3,"prediction_layer/conv_5"),m=r(256,64,1,"prediction_layer/conv_6"),f=r(64,128,3,"prediction_layer/conv_7"),g=a(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=a(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),b=a(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),v=a(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),x=a(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),N=a(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),T=a(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),C=a(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),$=a(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),F=a(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),O=a(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),W=a(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,box_predictor_0:{box_encoding_predictor:g,class_predictor:y},box_predictor_1:{box_encoding_predictor:b,class_predictor:v},box_predictor_2:{box_encoding_predictor:x,class_predictor:N},box_predictor_3:{box_encoding_predictor:T,class_predictor:C},box_predictor_4:{box_encoding_predictor:$,class_predictor:F},box_predictor_5:{box_encoding_predictor:O,class_predictor:W}}}return{extractMobilenetV1Params:i,extractPredictionLayerParams:o}}function wC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=xn(e),{extractMobilenetV1Params:r,extractPredictionLayerParams:s}=nse(n,t),i=r(),o=s(),c={extra_dim:rh(n(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:{mobilenetv1:i,prediction_layer:o,output_layer:c},paramMappings:t}}function ase(e,t){let n=Gn(e,t);function a(c,u,p){let d=n(`${c}/Conv2d_${u}_pointwise/weights`,4,`${p}/filters`),h=n(`${c}/Conv2d_${u}_pointwise/convolution_bn_offset`,1,`${p}/batch_norm_offset`);return{filters:d,batch_norm_offset:h}}function r(c){let u=`mobilenetv1/conv_${c}`,p=`MobilenetV1/Conv2d_${c}_depthwise`,d=`${u}/depthwise_conv`,h=`${u}/pointwise_conv`,m=n(`${p}/depthwise_weights`,4,`${d}/filters`),f=n(`${p}/BatchNorm/gamma`,1,`${d}/batch_norm_scale`),g=n(`${p}/BatchNorm/beta`,1,`${d}/batch_norm_offset`),y=n(`${p}/BatchNorm/moving_mean`,1,`${d}/batch_norm_mean`),b=n(`${p}/BatchNorm/moving_variance`,1,`${d}/batch_norm_variance`);return{depthwise_conv:{filters:m,batch_norm_scale:f,batch_norm_offset:g,batch_norm_mean:y,batch_norm_variance:b},pointwise_conv:a("MobilenetV1",c,h)}}function s(){return{conv_0:a("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:r(1),conv_2:r(2),conv_3:r(3),conv_4:r(4),conv_5:r(5),conv_6:r(6),conv_7:r(7),conv_8:r(8),conv_9:r(9),conv_10:r(10),conv_11:r(11),conv_12:r(12),conv_13:r(13)}}function i(c,u){let p=n(`${c}/weights`,4,`${u}/filters`),d=n(`${c}/biases`,1,`${u}/bias`);return{filters:p,bias:d}}function o(c){let u=i(`Prediction/BoxPredictor_${c}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${c}/box_encoding_predictor`),p=i(`Prediction/BoxPredictor_${c}/ClassPredictor`,`prediction_layer/box_predictor_${c}/class_predictor`);return{box_encoding_predictor:u,class_predictor:p}}function l(){return{conv_0:a("Prediction",0,"prediction_layer/conv_0"),conv_1:a("Prediction",1,"prediction_layer/conv_1"),conv_2:a("Prediction",2,"prediction_layer/conv_2"),conv_3:a("Prediction",3,"prediction_layer/conv_3"),conv_4:a("Prediction",4,"prediction_layer/conv_4"),conv_5:a("Prediction",5,"prediction_layer/conv_5"),conv_6:a("Prediction",6,"prediction_layer/conv_6"),conv_7:a("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:o(0),box_predictor_1:o(1),box_predictor_2:o(2),box_predictor_3:o(3),box_predictor_4:o(4),box_predictor_5:o(5)}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:l}}function kC(e){let t=[],{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=ase(e,t),r=e["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!Er(r))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${r}`);let s={mobilenetv1:n(),prediction_layer:a(),output_layer:{extra_dim:r}};return bn(e,t),{params:s,paramMappings:t}}function va(e,t,n){return D(()=>{let a=Ft(e,t.filters,n,"same");return a=Z(a,t.batch_norm_offset),Xt(a,0,6)})}var rse=.0010000000474974513;function sse(e,t,n){return D(()=>{let a=yr(e,t.filters,n,"same");return a=gr(a,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,rse),Xt(a,0,6)})}function ise(e){return[2,4,6,12].some(t=>t===e)?[2,2]:[1,1]}function IC(e,t){return D(()=>{let n,a=va(e,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((s,i)=>{let o=i+1,l=ise(o);a=sse(a,s.depthwise_conv,l),a=va(a,s.pointwise_conv,[1,1]),o===11&&(n=a)}),n===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:a,conv11:n}})}function ose(e,t,n){let a=e.arraySync(),r=Math.min(a[t][0],a[t][2]),s=Math.min(a[t][1],a[t][3]),i=Math.max(a[t][0],a[t][2]),o=Math.max(a[t][1],a[t][3]),l=Math.min(a[n][0],a[n][2]),c=Math.min(a[n][1],a[n][3]),u=Math.max(a[n][0],a[n][2]),p=Math.max(a[n][1],a[n][3]),d=(i-r)*(o-s),h=(u-l)*(p-c);if(d<=0||h<=0)return 0;let m=Math.max(r,l),f=Math.max(s,c),g=Math.min(i,u),y=Math.min(o,p),b=Math.max(g-m,0)*Math.max(y-f,0);return b/(d+h-b)}function NC(e,t,n,a,r){let s=e.shape[0],i=Math.min(n,s),o=t.map((u,p)=>({score:u,boxIndex:p})).filter(u=>u.score>r).sort((u,p)=>p.score-u.score),l=u=>u<=a?1:0,c=[];return o.forEach(u=>{if(c.length>=i)return;let p=u.score;for(let d=c.length-1;d>=0;--d){let h=ose(e,u.boxIndex,c[d]);if(h!==0&&(u.score*=l(h),u.score<=r))break}p===u.score&&c.push(u.boxIndex)}),c}function lse(e){let t=ht(Ue(e,[1,0])),n=[ge(t[2],t[0]),ge(t[3],t[1])],a=[Z(t[0],we(n[0],he(2))),Z(t[1],we(n[1],he(2)))];return{sizes:n,centers:a}}function use(e,t){let{sizes:n,centers:a}=lse(e),r=ht(Ue(t,[1,0])),s=we(L(dn(we(r[2],he(5))),n[0]),he(2)),i=Z(L(we(r[0],he(10)),n[0]),a[0]),o=we(L(dn(we(r[3],he(5))),n[1]),he(2)),l=Z(L(we(r[1],he(10)),n[1]),a[1]);return Ue(Dt([ge(i,s),ge(l,o),Z(i,s),Z(l,o)]),[1,0])}function TC(e,t,n){return D(()=>{let a=e.shape[0],r=use(q(qa(n.extra_dim,[a,1,1]),[-1,4]),q(e,[-1,4]));r=q(r,[a,r.shape[0]/a,4]);let s=da(We(t,[0,0,1],[-1,-1,-1])),i=We(s,[0,0,0],[-1,-1,1]);i=q(i,[a,i.shape[1]]);let o=ht(r),l=ht(i);return{boxes:o,scores:l}})}function ao(e,t){return D(()=>{let n=e.shape[0],a=q(to(e,t.box_encoding_predictor),[n,-1,1,4]),r=q(to(e,t.class_predictor),[n,-1,3]);return{boxPredictionEncoding:a,classPrediction:r}})}function SC(e,t,n){return D(()=>{let a=va(e,n.conv_0,[1,1]),r=va(a,n.conv_1,[2,2]),s=va(r,n.conv_2,[1,1]),i=va(s,n.conv_3,[2,2]),o=va(i,n.conv_4,[1,1]),l=va(o,n.conv_5,[2,2]),c=va(l,n.conv_6,[1,1]),u=va(c,n.conv_7,[2,2]),p=ao(t,n.box_predictor_0),d=ao(e,n.box_predictor_1),h=ao(r,n.box_predictor_2),m=ao(i,n.box_predictor_3),f=ao(l,n.box_predictor_4),g=ao(u,n.box_predictor_5),y=Qe([p.boxPredictionEncoding,d.boxPredictionEncoding,h.boxPredictionEncoding,m.boxPredictionEncoding,f.boxPredictionEncoding,g.boxPredictionEncoding],1),b=Qe([p.classPrediction,d.classPrediction,h.classPrediction,m.classPrediction,f.classPrediction,g.classPrediction],1);return{boxPredictions:y,classPredictions:b}})}var wa=class{constructor({minConfidence:t,maxResults:n}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=n||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var ro=class extends sn{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("SsdMobilenetv1 - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(512,!1),"float32"),r=ge(L(a,he(.007843137718737125)),he(1)),s=IC(r,n.mobilenetv1),{boxPredictions:i,classPredictions:o}=SC(s.out,s.conv11,n.prediction_layer);return TC(i,o,n.output_layer)})}async forward(t){return this.forwardInput(await yt(t))}async locateFaces(t,n={}){let{maxResults:a,minConfidence:r}=new wa(n),s=await yt(t),{boxes:i,scores:o}=this.forwardInput(s),l=i[0],c=o[0];for(let v=1;v{let[x,N]=[Math.max(0,y[v][0]),Math.min(1,y[v][2])].map($=>$*g),[T,C]=[Math.max(0,y[v][1]),Math.min(1,y[v][3])].map($=>$*f);return new vt(u[v],new xu(T,x,C-T,N-x),{height:s.getInputHeight(0),width:s.getInputWidth(0)})});return l.dispose(),c.dispose(),b}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return kC(t)}extractParams(t){return wC(t)}};function CC(e){let t=new ro;return t.extractWeights(e),t}function cse(e){return CC(e)}var _C=class extends ro{};var EC=.4,AC=[new De(.738768,.874946),new De(2.42204,2.65704),new De(4.30971,7.04493),new De(10.246,4.59428),new De(12.6868,11.8741)],FC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],$C=[117.001,114.697,97.404],DC="tiny_yolov2_model",MC="tiny_yolov2_separable_conv_model";var wf=e=>typeof e=="number";function Nw(e){if(!e)throw new Error(`invalid config: ${e}`);if(typeof e.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${e.withSeparableConvs}`);if(!wf(e.iouThreshold)||e.iouThreshold<0||e.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${e.iouThreshold}`);if(!Array.isArray(e.classes)||!e.classes.length||!e.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(e.classes)}`);if(!Array.isArray(e.anchors)||!e.anchors.length||!e.anchors.map(t=>t||{}).every(t=>wf(t.x)&&wf(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(e.anchors)}`);if(e.meanRgb&&(!Array.isArray(e.meanRgb)||e.meanRgb.length!==3||!e.meanRgb.every(wf)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(e.meanRgb)}`)}function Au(e){return D(()=>{let t=L(e,he(.10000000149011612));return Z(Ye(ge(e,t)),t)})}function Dr(e,t){return D(()=>{let n=ea(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Ft(n,t.conv.filters,[1,1],"valid"),n=ge(n,t.bn.sub),n=L(n,t.bn.truediv),n=Z(n,t.conv.bias),Au(n)})}function Mr(e,t){return D(()=>{let n=ea(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Ai(n,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),n=Z(n,t.bias),Au(n)})}function pse(e,t){let n=Nu(e,t);function a(i,o){let l=tt(e(i)),c=tt(e(i));return t.push({paramPath:`${o}/sub`},{paramPath:`${o}/truediv`}),{sub:l,truediv:c}}function r(i,o,l){let c=n(i,o,3,`${l}/conv`),u=a(o,`${l}/bn`);return{conv:c,bn:u}}let s=Tu(e,t);return{extractConvParams:n,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}}function RC(e,t,n,a){let{extractWeights:r,getRemainingWeights:s}=xn(e),i=[],{extractConvParams:o,extractConvWithBatchNormParams:l,extractSeparableConvParams:c}=pse(r,i),u;if(t.withSeparableConvs){let[p,d,h,m,f,g,y,b,v]=a,x=t.isFirstLayerConv2d?o(p,d,3,"conv0"):c(p,d,"conv0"),N=c(d,h,"conv1"),T=c(h,m,"conv2"),C=c(m,f,"conv3"),$=c(f,g,"conv4"),F=c(g,y,"conv5"),O=b?c(y,b,"conv6"):void 0,W=v?c(b,v,"conv7"):void 0,V=o(v||b||y,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}else{let[p,d,h,m,f,g,y,b,v]=a,x=l(p,d,"conv0"),N=l(d,h,"conv1"),T=l(h,m,"conv2"),C=l(m,f,"conv3"),$=l(f,g,"conv4"),F=l(g,y,"conv5"),O=l(y,b,"conv6"),W=l(b,v,"conv7"),V=o(v,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{params:u,paramMappings:i}}function dse(e,t){let n=Gn(e,t);function a(o){let l=n(`${o}/sub`,1),c=n(`${o}/truediv`,1);return{sub:l,truediv:c}}function r(o){let l=n(`${o}/filters`,4),c=n(`${o}/bias`,1);return{filters:l,bias:c}}function s(o){let l=r(`${o}/conv`),c=a(`${o}/bn`);return{conv:l,bn:c}}let i=Su(n);return{extractConvParams:r,extractConvWithBatchNormParams:s,extractSeparableConvParams:i}}function PC(e,t){let n=[],{extractConvParams:a,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}=dse(e,n),i;if(t.withSeparableConvs){let o=t.filterSizes&&t.filterSizes.length||9;i={conv0:t.isFirstLayerConv2d?a("conv0"):s("conv0"),conv1:s("conv1"),conv2:s("conv2"),conv3:s("conv3"),conv4:s("conv4"),conv5:s("conv5"),conv6:o>7?s("conv6"):void 0,conv7:o>8?s("conv7"):void 0,conv8:a("conv8")}}else i={conv0:r("conv0"),conv1:r("conv1"),conv2:r("conv2"),conv3:r("conv3"),conv4:r("conv4"),conv5:r("conv5"),conv6:r("conv6"),conv7:r("conv7"),conv8:a("conv8")};return bn(e,n),{params:i,paramMappings:n}}var ur=class{constructor({inputSize:t,scoreThreshold:n}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=n||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var Tw=class extends sn{constructor(t){super("TinyYolov2");Nw(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,n){let a=Dr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Dr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=Dr(a,n.conv6),a=Dr(a,n.conv7),to(a,n.conv8,"valid",!1)}runMobilenet(t,n){let a=this.config.isFirstLayerConv2d?Au(to(t,n.conv0,"valid",!1)):Mr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Mr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=n.conv6?Mr(a,n.conv6):a,a=n.conv7?Mr(a,n.conv7):a,to(a,n.conv8,"valid",!1)}forwardInput(t,n){let{params:a}=this;if(!a)throw new Error("TinyYolov2 - load model before inference");return D(()=>{let r=pe(t.toBatchTensor(n,!1),"float32");return r=this.config.meanRgb?Ba(r,this.config.meanRgb):r,r=r.div(he(256)),this.config.withSeparableConvs?this.runMobilenet(r,a):this.runTinyYolov2(r,a)})}async forward(t,n){return this.forwardInput(await yt(t),n)}async detect(t,n={}){let{inputSize:a,scoreThreshold:r}=new ur(n),s=await yt(t),i=await this.forwardInput(s,a),o=D(()=>ht(i)[0].expandDims()),l={width:s.getInputWidth(0),height:s.getInputHeight(0)},c=await this.extractBoxes(o,s.getReshapedInputDimensions(0),r);i.dispose(),o.dispose();let u=c.map(g=>g.box),p=c.map(g=>g.score),d=c.map(g=>g.classScore),h=c.map(g=>this.config.classes[g.label]);return Qv(u.map(g=>g.rescale(a)),p,this.config.iouThreshold,!0).map(g=>new ms(p[g],d[g],h[g],u[g],l))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return PC(t,this.config)}extractParams(t){let n=this.config.filterSizes||Tw.DEFAULT_FILTER_SIZES,a=n?n.length:void 0;if(a!==7&&a!==8&&a!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${a} filterSizes in config`);return RC(t,this.config,this.boxEncodingSize,n)}async extractBoxes(t,n,a){let{width:r,height:s}=n,i=Math.max(r,s),o=i/r,l=i/s,c=t.shape[1],u=this.config.anchors.length,[p,d,h]=D(()=>{let y=t.reshape([c,c,u,this.boxEncodingSize]),b=y.slice([0,0,0,0],[c,c,u,4]),v=y.slice([0,0,0,4],[c,c,u,1]),x=this.withClassScores?Ca(y.slice([0,0,0,5],[c,c,u,this.config.classes.length]),3):he(0);return[b,v,x]}),m=[],f=await d.array(),g=await p.array();for(let y=0;ya){let N=(b+Fp(g[y][b][v][0]))/c*o,T=(y+Fp(g[y][b][v][1]))/c*l,C=Math.exp(g[y][b][v][2])*this.config.anchors[v].x/c*o,$=Math.exp(g[y][b][v][3])*this.config.anchors[v].y/c*l,F=N-C/2,O=T-$/2,W={row:y,col:b,anchor:v},{classScore:V,label:H}=this.withClassScores?await this.extractPredictedClass(h,W):{classScore:1,label:0};m.push({box:new bu(F,O,F+C,O+$),score:x,classScore:x*V,label:H,...W})}}return p.dispose(),d.dispose(),h.dispose(),m}async extractPredictedClass(t,n){let{row:a,col:r,anchor:s}=n,i=await t.array();return Array(this.config.classes.length).fill(0).map((o,l)=>i[a][r][s][l]).map((o,l)=>({classScore:o,label:l})).reduce((o,l)=>o.classScore>l.classScore?o:l)}},Fu=Tw;Fu.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var $u=class extends Fu{constructor(t=!0){let n={withSeparableConvs:t,iouThreshold:EC,classes:["face"],...t?{anchors:FC,meanRgb:$C}:{anchors:AC,withClassScores:!0}};super(n)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new vt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?MC:DC}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function hse(e,t=!0){let n=new $u(t);return n.extractWeights(e),n}var kf=class extends ur{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var ka=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};async function so(e,t,n,a,r=({alignedRect:s})=>s){let s=e.map(l=>no(l)?r(l):l.detection),i=a||(t instanceof z?await Iu(t,s):await ku(t,s)),o=await n(i);return i.forEach(l=>l instanceof z&&l.dispose()),o}async function Du(e,t,n,a,r){return so([e],t,async s=>n(s[0]),a,r)}var OC=.4,LC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],zC=[117.001,114.697,97.404];var Mu=class extends Fu{constructor(){let t={withSeparableConvs:!0,iouThreshold:OC,classes:["face"],anchors:LC,meanRgb:zC,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new vt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var nt={ssdMobilenetv1:new ro,tinyFaceDetector:new Mu,tinyYolov2:new $u,faceLandmark68Net:new _u,faceLandmark68TinyNet:new gf,faceRecognitionNet:new Eu,faceExpressionNet:new hf,ageGenderNet:new ff},BC=(e,t)=>nt.ssdMobilenetv1.locateFaces(e,t),mse=(e,t)=>nt.tinyFaceDetector.locateFaces(e,t),fse=(e,t)=>nt.tinyYolov2.locateFaces(e,t),WC=e=>nt.faceLandmark68Net.detectLandmarks(e),gse=e=>nt.faceLandmark68TinyNet.detectLandmarks(e),yse=e=>nt.faceRecognitionNet.computeFaceDescriptor(e),bse=e=>nt.faceExpressionNet.predictExpressions(e),xse=e=>nt.ageGenderNet.predictAgeAndGender(e),VC=e=>nt.ssdMobilenetv1.load(e),vse=e=>nt.tinyFaceDetector.load(e),wse=e=>nt.tinyYolov2.load(e),kse=e=>nt.faceLandmark68Net.load(e),Ise=e=>nt.faceLandmark68TinyNet.load(e),Nse=e=>nt.faceRecognitionNet.load(e),Tse=e=>nt.faceExpressionNet.load(e),Sse=e=>nt.ageGenderNet.load(e),Cse=VC,_se=BC,Ese=WC;var Sw=class extends ka{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Ou=class extends Sw{async run(){let t=await this.parentTask,n=await so(t,this.input,async a=>Promise.all(a.map(r=>nt.faceExpressionNet.predictExpressions(r))),this.extractedFaces);return t.map((a,r)=>mf(a,n[r]))}withAgeAndGender(){return new Ru(this,this.input)}},Lu=class extends Sw{async run(){let t=await this.parentTask;if(!t)return;let n=await Du(t,this.input,a=>nt.faceExpressionNet.predictExpressions(a),this.extractedFaces);return mf(t,n)}withAgeAndGender(){return new Pu(this,this.input)}},lo=class extends Ou{withAgeAndGender(){return new io(this,this.input)}withFaceDescriptors(){return new ys(this,this.input)}},uo=class extends Lu{withAgeAndGender(){return new oo(this,this.input)}withFaceDescriptor(){return new bs(this,this.input)}};var Cw=class extends ka{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Ru=class extends Cw{async run(){let t=await this.parentTask,n=await so(t,this.input,async a=>Promise.all(a.map(r=>nt.ageGenderNet.predictAgeAndGender(r))),this.extractedFaces);return t.map((a,r)=>{let{age:s,gender:i,genderProbability:o}=n[r];return xf(vf(a,i,o),s)})}withFaceExpressions(){return new Ou(this,this.input)}},Pu=class extends Cw{async run(){let t=await this.parentTask;if(!t)return;let{age:n,gender:a,genderProbability:r}=await Du(t,this.input,s=>nt.ageGenderNet.predictAgeAndGender(s),this.extractedFaces);return xf(vf(t,a,r),n)}withFaceExpressions(){return new Lu(this,this.input)}},io=class extends Ru{withFaceExpressions(){return new lo(this,this.input)}withFaceDescriptors(){return new ys(this,this.input)}},oo=class extends Pu{withFaceExpressions(){return new uo(this,this.input)}withFaceDescriptor(){return new bs(this,this.input)}};var If=class extends ka{constructor(t,n){super();this.parentTask=t;this.input=n}},ys=class extends If{async run(){let t=await this.parentTask;return(await so(t,this.input,a=>Promise.all(a.map(r=>nt.faceRecognitionNet.computeFaceDescriptor(r))),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}))).map((a,r)=>bf(t[r],a))}withFaceExpressions(){return new lo(this,this.input)}withAgeAndGender(){return new io(this,this.input)}},bs=class extends If{async run(){let t=await this.parentTask;if(!t)return;let n=await Du(t,this.input,a=>nt.faceRecognitionNet.computeFaceDescriptor(a),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}));return bf(t,n)}withFaceExpressions(){return new uo(this,this.input)}withAgeAndGender(){return new oo(this,this.input)}};var Nf=class extends ka{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.useTinyLandmarkNet=a}get landmarkNet(){return this.useTinyLandmarkNet?nt.faceLandmark68TinyNet:nt.faceLandmark68Net}},Tf=class extends Nf{async run(){let t=await this.parentTask,n=t.map(s=>s.detection),a=this.input instanceof z?await Iu(this.input,n):await ku(this.input,n),r=await Promise.all(a.map(s=>this.landmarkNet.detectLandmarks(s)));return a.forEach(s=>s instanceof z&&s.dispose()),t.map((s,i)=>Cu(s,r[i]))}withFaceExpressions(){return new lo(this,this.input)}withAgeAndGender(){return new io(this,this.input)}withFaceDescriptors(){return new ys(this,this.input)}},Sf=class extends Nf{async run(){let t=await this.parentTask;if(!t)return;let{detection:n}=t,a=this.input instanceof z?await Iu(this.input,[n]):await ku(this.input,[n]),r=await this.landmarkNet.detectLandmarks(a[0]);return a.forEach(s=>s instanceof z&&s.dispose()),Cu(t,r)}withFaceExpressions(){return new uo(this,this.input)}withAgeAndGender(){return new oo(this,this.input)}withFaceDescriptor(){return new bs(this,this.input)}};var Cf=class extends ka{constructor(t,n=new wa){super();this.input=t;this.options=n}},Up=class extends Cf{async run(){let{input:t,options:n}=this,a=n instanceof kf?r=>nt.tinyFaceDetector.locateFaces(r,n):n instanceof wa?r=>nt.ssdMobilenetv1.locateFaces(r,n):n instanceof ur?r=>nt.tinyYolov2.locateFaces(r,n):null;if(!a)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return a(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let n=await this.run();t(n.map(a=>Ji({},a)))})}withFaceLandmarks(t=!1){return new Tf(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new Ou(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Ru(this.runAndExtendWithFaceDetections(),this.input)}},_f=class extends Cf{async run(){let t=await new Up(this.input,this.options),n=t[0];return t.forEach(a=>{a.score>n.score&&(n=a)}),n}runAndExtendWithFaceDetection(){return new Promise(async t=>{let n=await this.run();t(n?Ji({},n):void 0)})}withFaceLandmarks(t=!1){return new Sf(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new Lu(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Pu(this.runAndExtendWithFaceDetection(),this.input)}};function Ase(e,t=new wa){return new _f(e,t)}function Ef(e,t=new wa){return new Up(e,t)}async function UC(e,t){return Ef(e,new wa(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function Fse(e,t={}){return Ef(e,new ur(t)).withFaceLandmarks().withFaceDescriptors()}var $se=UC;function _w(e,t){if(e.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let n=Array.from(e),a=Array.from(t);return Math.sqrt(n.map((r,s)=>r-a[s]).reduce((r,s)=>r+s**2,0))}var Af=class{constructor(t,n=.6){this._distanceThreshold=n;let a=Array.isArray(t)?t:[t];if(!a.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let r=1,s=()=>`person ${r++}`;this._labeledDescriptors=a.map(i=>{if(i instanceof Ar)return i;if(i instanceof Float32Array)return new Ar(s(),[i]);if(i.descriptor&&i.descriptor instanceof Float32Array)return new Ar(s(),[i.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,n){return n.map(a=>_w(a,t)).reduce((a,r)=>a+r,0)/(n.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:n,label:a})=>new $p(a,this.computeMeanDistance(t,n))).reduce((n,a)=>n.distancet.toJSON())}}static fromJSON(t){let n=t.labeledDescriptors.map(a=>Ar.fromJSON(a));return new Af(n,t.distanceThreshold)}};function Dse(e){let t=new Mu;return t.extractWeights(e),t}function GC(e,t){let{width:n,height:a}=new yn(t.width,t.height);if(n<=0||a<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:n,height:a})}`);if(Array.isArray(e))return e.map(r=>GC(r,{width:n,height:a}));if(no(e)){let r=e.detection.forSize(n,a),s=e.unshiftedLandmarks.forSize(r.box.width,r.box.height);return Cu(Ji(e,r),s)}return or(e)?Ji(e,e.detection.forSize(n,a)):e instanceof ra||e instanceof vt?e.forSize(n,a):e}var Mse=typeof process!="undefined",Rse=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Pse={faceapi:lC,node:Mse,browser:Rse};export{ff as AgeGenderNet,bu as BoundingBox,ct as Box,ka as ComposableTask,ys as ComputeAllFaceDescriptorsTask,If as ComputeFaceDescriptorsTaskBase,bs as ComputeSingleFaceDescriptorTask,Tf as DetectAllFaceLandmarksTask,Up as DetectAllFacesTask,Nf as DetectFaceLandmarksTaskBase,Cf as DetectFacesTaskBase,Sf as DetectSingleFaceLandmarksTask,_f as DetectSingleFaceTask,yn as Dimensions,mw as FACE_EXPRESSION_LABELS,vt as FaceDetection,_C as FaceDetectionNet,hf as FaceExpressionNet,gs as FaceExpressions,_u as FaceLandmark68Net,gf as FaceLandmark68TinyNet,gC as FaceLandmarkNet,ra as FaceLandmarks,eC as FaceLandmarks5,vu as FaceLandmarks68,$p as FaceMatch,Af as FaceMatcher,Eu as FaceRecognitionNet,$r as Gender,Dp as LabeledBox,Ar as LabeledFaceDescriptors,Fr as NetInput,sn as NeuralNetwork,ms as ObjectDetection,De as Point,tC as PredictedBox,xu as Rect,ro as SsdMobilenetv1,wa as SsdMobilenetv1Options,Mu as TinyFaceDetector,kf as TinyFaceDetectorOptions,$u as TinyYolov2,ur as TinyYolov2Options,$se as allFaces,UC as allFacesSsdMobilenetv1,Fse as allFacesTinyYolov2,lw as awaitMediaLoaded,uw as bufferToImage,yse as computeFaceDescriptor,wu as createCanvas,Pp as createCanvasFromMedia,cse as createFaceDetectionNet,Qre as createFaceRecognitionNet,CC as createSsdMobilenetv1,Dse as createTinyFaceDetector,hse as createTinyYolov2,Ef as detectAllFaces,WC as detectFaceLandmarks,gse as detectFaceLandmarksTiny,Ese as detectLandmarks,Ase as detectSingleFace,bw as draw,it as env,_w as euclideanDistance,xf as extendWithAge,bf as extendWithFaceDescriptor,Ji as extendWithFaceDetection,mf as extendWithFaceExpressions,Cu as extendWithFaceLandmarks,vf as extendWithGender,Iu as extractFaceTensors,ku as extractFaces,Ure as fetchImage,dw as fetchJson,Gre as fetchNetWeights,eo as fetchOrThrow,Cn as getContext2dOrThrow,Qi as getMediaDimensions,cw as imageTensorToCanvas,pw as imageToSquare,Mre as inverseSigmoid,Jv as iou,af as isMediaElement,Rp as isMediaLoaded,ese as isWithAge,or as isWithFaceDetection,fw as isWithFaceExpressions,no as isWithFaceLandmarks,tse as isWithGender,Sse as loadAgeGenderModel,Cse as loadFaceDetectionModel,Tse as loadFaceExpressionModel,kse as loadFaceLandmarkModel,Ise as loadFaceLandmarkTinyModel,Nse as loadFaceRecognitionModel,VC as loadSsdMobilenetv1Model,vse as loadTinyFaceDetectorModel,wse as loadTinyYolov2Model,hw as loadWeightMap,_se as locateFaces,Hre as matchDimensions,Zv as minBbox,nt as nets,Qv as nonMaxSuppression,Ba as normalize,ew as padToSquare,xse as predictAgeAndGender,bse as recognizeFaceExpressions,GC as resizeResults,Zi as resolveInput,Dre as shuffleArray,Fp as sigmoid,BC as ssdMobilenetv1,Bg as tf,mse as tinyFaceDetector,fse as tinyYolov2,yt as toNetInput,qv as utils,Nw as validateConfig,Pse as version}; /** * @license * Copyright 2017 Google LLC. All Rights Reserved. diff --git a/dist/face-api.js b/dist/face-api.js index 2fdf0f7..29c61b1 100644 --- a/dist/face-api.js +++ b/dist/face-api.js @@ -4045,7 +4045,7 @@ return a / b;`,GZ=` } setOutput(${l}); } - `}};function cte(e){let{inputs:t,backend:n,attrs:a}=e,{x:r,segmentIds:s}=t,{numSegments:i}=a,o=r.shape.length,l=[],c=0,u=E.getAxesPermutation([c],o),p=r;u!=null&&(p=Cn({inputs:{x:r},backend:n,attrs:{perm:u}}),l.push(p),c=E.getInnerMostAxes(1,o)[0]);let d=E.segment_util.computeOutShape(p.shape,c,i),h=k.sizeFromShape([p.shape[c]]),m=ve({inputs:{x:p},backend:n,attrs:{shape:[-1,h]}});l.push(m);let f=bh(r.dtype),g=(x,N,T,C,$)=>{let F=x.shape[0],O=x.shape[1],W=E.segment_util.segOpComputeOptimalWindowSize(O,$),V={windowSize:W,inSize:O,batchSize:F,numSegments:$},H=new ute(V,N),K=n.compileAndRun(H,[x,T],C);if(l.push(K),K.shape[1]===$)return K;let j=h2({backend:n,attrs:{start:0,stop:$,step:1,dtype:"float32"}}),Y=g2({inputs:{x:j},backend:n,attrs:{reps:[O/W]}});return l.push(j),l.push(Y),g(K,N,Y,C,$)},y=g(m,"unsortedSegmentSum",s,f,i),b=ve({inputs:{x:y},backend:n,attrs:{shape:d}}),v=b;if(u!=null){l.push(b);let x=E.getUndoAxesPermutation(u);v=Cn({inputs:{x:v},backend:n,attrs:{perm:x}})}return l.forEach(x=>n.disposeIntermediateTensorInfo(x)),v}var pte={kernelName:Fc,backendName:"webgl",kernelFunc:cte},dte=[rZ,oZ,jX,KX,JX,eY,nY,sY,oY,uY,hY,fY,bY,wY,_Y,NY,FY,RY,DY,zY,WY,UY,qY,e7,n7,l7,c7,m7,y7,CX,w7,F7,D7,T7,O7,z7,R7,V7,H7,K7,Y7,Z7,tJ,oJ,uJ,aJ,dJ,fJ,xJ,IJ,CJ,AJ,FJ,$J,MJ,PJ,LJ,BJ,VJ,jJ,YJ,ZJ,e9,a9,o9,p9,f9,SX,y9,v7,v9,I9,S9,EX,A9,M9,P9,U9,B9,q9,Y9,eZ,uZ,yZ,fZ,wZ,IZ,TZ,hZ,CZ,EZ,DZ,OZ,WZ,XZ,MX,JZ,eQ,aQ,iQ,r7,uQ,pQ,hQ,gQ,vQ,FX,kQ,IQ,s7,HZ,SQ,MQ,AQ,PX,LQ,WQ,GQ,qQ,JQ,QQ,nee,see,oee,cee,hee,gee,xee,kee,Tee,ZY,qZ,_ee,Aee,$ee,Mee,Oee,Bee,Vee,Gee,qee,jZ,UX,Yee,Qee,nte,rte,GX,ite,lte,pte,cQ];for(let e of dte)Dc(e);var hte="2.8.5",mte={"tfjs-core":s1,"tfjs-backend-cpu":GG,"tfjs-backend-webgl":TX,"tfjs-data":jN,"tfjs-layers":$m,"tfjs-converter":BN,tfjs:hte},Vn;(function(e){e[e.float32=0]="float32",e[e.int32=1]="int32",e[e.bool=2]="bool",e[e.string=3]="string",e[e.complex64=4]="complex64"})(Vn||(Vn={}));var Mp;(function(e){e[e.linear=0]="linear",e[e.relu=1]="relu",e[e.relu6=2]="relu6",e[e.prelu=3]="prelu",e[e.leakyrelu=4]="leakyrelu"})(Mp||(Mp={}));var y2;function fte(e){y2=e.wasm.cwrap(Ni,null,["number","array","number","number","array","number","number","number","number","number","number","number","number"])}function gte(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s,bias:i,preluActivationWeights:o}=t;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("_FusedMatMul for non non-float32 tensors not yet supported.");let{transposeA:l,transposeB:c,activation:u,leakyreluAlpha:p}=a,d=n.dataIdMap.get(r.dataId).id,h=n.dataIdMap.get(s.dataId).id,m=0;if(i!=null){let $=n.dataIdMap.get(i.dataId);if($.shape.length!==1)throw new Error(`_FusedMatMul only supports rank-1 bias but got rank ${$.shape.length}.`);m=$.id}let f=o==null?0:n.dataIdMap.get(o.dataId).id,g=Mp[u];if(g==null)throw new Error(`${u} activation not yet supported for FusedConv2D in the wasm backend.`);let y=l?r.shape[2]:r.shape[1],b=c?s.shape[1]:s.shape[2],v=r.shape[0],x=n.makeOutput([v,y,b],r.dtype),N=n.dataIdMap.get(x.dataId).id,T=new Uint8Array(new Int32Array(r.shape).buffer),C=new Uint8Array(new Int32Array(s.shape).buffer);return y2(d,T,r.shape.length,h,C,s.shape.length,l,c,g,m,f,p||0,N),x}var yte={kernelName:Ni,backendName:"wasm",setupFunc:fte,kernelFunc:gte};function Un(e){let t;function n(r){t=r.wasm.cwrap(e,null,["number","number"])}function a(r){let{backend:s,inputs:{x:i}}=r,o=s.dataIdMap.get(i.dataId).id,l=s.makeOutput(i.shape,i.dtype),c=s.dataIdMap.get(l.dataId).id;return k.sizeFromShape(l.shape)===0||t(o,c),l}return{kernelName:e,backendName:"wasm",setupFunc:n,kernelFunc:a}}var bte=Un(Lo);function yn(e,t,n){let a;function r(i){a=i.wasm.cwrap(e,null,["number","array","number","number","array","number","number","number"])}function s(i){let{backend:o,inputs:l}=i,{a:c,b:u}=l,p=o.dataIdMap.get(c.dataId).id,d=o.dataIdMap.get(u.dataId).id,h=n!=null?n:c.dtype,m=E.assertAndGetBroadcastShape(c.shape,u.shape),f=o.makeOutput(m,h);if(k.sizeFromShape(m)===0)return f;let g=new Uint8Array(new Int32Array(c.shape).buffer),y=new Uint8Array(new Int32Array(u.shape).buffer),b=o.dataIdMap.get(f.dataId).id,v=()=>a(p,g,c.shape.length,d,y,u.shape.length,Vn[c.dtype],b);if(t&&c.dtype==="float32")return v(),f;let x=E.getBroadcastDims(c.shape,m),N=E.getBroadcastDims(u.shape,m),T=x.every(($,F)=>$===F),C=N.every(($,F)=>$===F);if(T&&C)return v(),f;throw new Error(`Broadcasting along outer dims is not yet supported for ${c.dtype} ${e}.`)}return{kernelName:e,backendName:"wasm",setupFunc:r,kernelFunc:s}}var xte=!0,vte=yn(Hr,xte),b2;function wte(e){b2=e.wasm.cwrap(Ms,null,["array","number","number","number"])}function kte(e){let{inputs:t,backend:n}=e,a=n.makeOutput(t[0].shape,t[0].dtype);if(k.sizeFromShape(a.shape)===0)return a;let r=t.map(o=>n.dataIdMap.get(o.dataId).id),s=new Uint8Array(new Int32Array(r).buffer),i=n.dataIdMap.get(a.dataId).id;return b2(s,r.length,Vn[a.dtype],i),a}var Ite={kernelName:Ms,backendName:"wasm",setupFunc:wte,kernelFunc:kte};function hf(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype),r=n.typedArrayFromHeap(t);return n.typedArrayFromHeap(a).set(r),a}var Nte={kernelName:il,backendName:"wasm",kernelFunc:hf},x2;function Tte(e){x2=e.wasm.cwrap(Ii,null,["number","array","number","number","number","array","number"])}function mf(e){let{inputs:t,backend:n,attrs:a}=e,[r,s]=Cte(t.x.shape,a.perm),i=!0;for(let m=0;m=r&&(s===-1||a[s]>a[i])&&(s=i);a[s]=r}return[n,a]}var _te={kernelName:Ii,backendName:"wasm",kernelFunc:mf,setupFunc:Tte};function Cu(e,t,n){let a=e.shape,r=e.shape.length,s=k.parseAxisParam(t,a),i=s,o=E.getAxesPermutation(i,r),l=null,c=!1;if(o!=null){let u=new Array(r);for(let d=0;d`new shape: ${i}, old shape: ${a.shape}. New shape and old shape must have the same number of elements.`),{dataId:a.dataId,shape:i,dtype:a.dtype}}var Rte={kernelName:Nl,backendName:"wasm",kernelFunc:za},k2;function Pte(e){k2=e.wasm.cwrap(Os,null,["number","array","number","number","array","number","number","number","number"])}function Ote(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s}=t,{transposeA:i,transposeB:o}=a;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("BatchMatMul for non non-float32 tensors not yet supported.");let l=r.shape.length,c=s.shape.length,u=i?r.shape[l-2]:r.shape[l-1],p=o?s.shape[c-1]:s.shape[c-2],d=i?r.shape[l-1]:r.shape[l-2],h=o?s.shape[c-2]:s.shape[c-1],m=r.shape.slice(0,-2),f=s.shape.slice(0,-2),g=k.sizeFromShape(m),y=k.sizeFromShape(f),b=g===y||g===1||y===1;k.assert(l>=2&&c>=2&&b,()=>`Error in matMul: the input batch dimensions must either be the same or at least one input batch dimension must be 1. Got input batch dimensions of (${m}) and (${f}).`);let v=(g>y?r.shape.slice(0,-2):s.shape.slice(0,-2)).concat([d,h]);k.assert(u===p,()=>`Error in matMul: inner shapes (${u}) and (${p}) of Tensors with shapes ${r.shape} and ${s.shape} and transposeA=${i} and transposeB=${o} must match.`);let x=i?[g,u,d]:[g,d,u],N=o?[y,h,p]:[y,p,h],T=za({inputs:{x:r},backend:n,attrs:{shape:x}}),C=za({inputs:{x:s},backend:n,attrs:{shape:N}}),$=n.dataIdMap.get(T.dataId).id,F=n.dataIdMap.get(C.dataId).id,O=i?T.shape[2]:T.shape[1],W=o?C.shape[1]:C.shape[2],V=Math.max(g,y),H=n.makeOutput([V,O,W],T.dtype),K=n.dataIdMap.get(H.dataId).id,j=new Uint8Array(new Int32Array(T.shape).buffer),Y=new Uint8Array(new Int32Array(C.shape).buffer);return k2($,j,T.shape.length,F,Y,C.shape.length,i,o,K),H.shape=v,H}var Lte={kernelName:Os,backendName:"wasm",setupFunc:Pte,kernelFunc:Ote};function ff(e){let{inputs:{x:t},attrs:{dtype:n},backend:a}=e,r=a.makeOutput(t.shape,n),s=a.typedArrayFromHeap(t);return a.typedArrayFromHeap(r).set(s),r}var zte={kernelName:Ls,backendName:"wasm",kernelFunc:ff},I2;function Bte(e){I2=e.wasm.cwrap(jr,null,["number","number","number","number"])}function Wte(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{clipValueMin:s,clipValueMax:i}=a,o=n.dataIdMap.get(r.dataId).id,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(l.dataId).id;return I2(o,s,i,c),l}var Vte={kernelName:jr,backendName:"wasm",setupFunc:Bte,kernelFunc:Wte};function N2(e){let{inputs:t,backend:n}=e,a=k.parseAxisParam(e.attrs.axis,t[0].shape)[0],r=E.computeOutShape(t.map(h=>h.shape),a),s=t.filter(h=>k.sizeFromShape(h.shape)>0);if(s.length===1)return hf({inputs:{x:s[0]},backend:n});let i=n.makeOutput(r,t[0].dtype);if(k.sizeFromShape(r)===0)return i;let o=s.map(h=>h.shape);if(E.assertParamsConsistent(o,a),s[0].dtype==="string"){let h=s.map(v=>{let x=k.sizeFromShape(v.shape.slice(a));return za({inputs:{x:v},backend:n,attrs:{shape:[-1,x]}})}),m=h.map(v=>({vals:n.readSync(v.dataId),shape:v.shape}));r=E.computeOutShape(h.map(v=>v.shape),1);let f=h[0].shape[0]===1,g=_v(m,r,t[0].dtype,f),y=E.computeOutShape(s.map(v=>v.shape),a);i.shape=y;let b=n.dataIdMap.get(i.dataId);return b.stringBytes=E.fromStringArrayToUint8(g),i}let l=k.sizeFromShape(s[0].shape.slice(0,a)),c=0,u=s.map(h=>{let m=k.sizeFromShape(h.shape.slice(a));return c+=m,m}),p=s.map(h=>n.typedArrayFromHeap(h)),d=n.typedArrayFromHeap(i);for(let h=0;h`cumsum does not support ${r.dtype} tensors in the WASM backend`);let c=E.getAxesPermutation([s],l),u=r;c!==null&&(u=mf({inputs:{x:r},attrs:{perm:c},backend:n}));let p=E.getInnerMostAxes(1,l)[0];E.assertAxesAreInnerMostDims("cumsum",[p],l);let d=n.makeOutput(u.shape,u.dtype),h=u.shape[p],m=n.dataIdMap.get(u.dataId).id,f=n.dataIdMap.get(d.dataId).id;_2(m,i?1:0,o?1:0,h,f,Vn[r.dtype]);let g=d;if(c!==null){let y=E.getUndoAxesPermutation(c);g=mf({inputs:{x:d},attrs:{perm:y},backend:n}),n.disposeData(u.dataId),n.disposeData(d.dataId)}return g}var nne={kernelName:Vs,backendName:"wasm",setupFunc:ene,kernelFunc:tne},E2;function ane(e){E2=e.wasm.cwrap(Yo,null,["number","number","number","array","number","array","array","number","number"])}function rne(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{blockSize:s,dataFormat:i}=a;k.assert(s>1,()=>`blockSize should be > 1 for depthToSpace, but was: ${s}`);let o=r.shape[0],l=i==="NHWC"?r.shape[1]:r.shape[2],c=i==="NHWC"?r.shape[2]:r.shape[3],u=i==="NHWC"?r.shape[3]:r.shape[1],p=l*s,d=c*s,h=u/(s*s),m=i==="NHWC"?[o,p,d,h]:[o,h,p,d],f=t.makeOutput(m,"float32"),g=t.dataIdMap.get(r.dataId).id,y=new Uint8Array(new Int32Array(k.computeStrides(r.shape)).buffer),b=new Uint8Array(new Int32Array(m).buffer),v=new Uint8Array(new Int32Array(k.computeStrides(m)).buffer),x=t.dataIdMap.get(f.dataId).id;return E2(g,s,i==="NHWC"?1:0,y,r.shape.length-1,b,v,m.length,x),f}var sne={kernelName:Yo,backendName:"wasm",setupFunc:ane,kernelFunc:rne},A2;function ine(e){A2=e.wasm.cwrap(Us,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function one(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s}=t,i=a.dataIdMap.get(r.dataId).id,o=a.dataIdMap.get(s.dataId).id,{strides:l,dilations:c,pad:u,dimRoundingMode:p}=n,d=c==null?[1,1]:c,h=E.computeConv2DInfo(r.shape,s.shape,l,d,u,p,!0),m=h.filterHeight,f=h.filterWidth,g=h.padInfo.top,y=h.padInfo.right,b=h.padInfo.bottom,v=h.padInfo.left,x=h.dilationHeight,N=h.dilationWidth,T=h.strideHeight,C=h.strideWidth,$=h.inChannels,F=h.outChannels,O=h.padInfo.type==="SAME"?1:0;if(h.dataFormat!=="channelsLast")throw new Error(`wasm backend DepthwiseConv2dNative does not support dataFormat:'${h.dataFormat}'. Please use 'channelsLast'.`);let W=a.makeOutput(h.outShape,"float32"),V=a.dataIdMap.get(W.dataId).id;return A2(i,r.shape[0],r.shape[1],r.shape[2],o,m,f,g,y,b,v,O,x,N,T,C,$,F,V),W}var lne={kernelName:Us,backendName:"wasm",setupFunc:ine,kernelFunc:one},une=!1,cne=yn(Qo,une,"bool"),pne=Un(Hs);function sw(e){let{inputs:t,attrs:n,backend:a}=e,{input:r}=t,{dim:s}=n,i=r.shape.length,o=r.shape.slice(),l=s;return s<0&&(k.assert(-(i+1)<=s,()=>`Axis must be in the interval [${-(i+1)}, ${i}]`),l=i+s+1),o.splice(l,0,1),za({inputs:{x:r},backend:a,attrs:{shape:o}})}var dne={kernelName:el,backendName:"wasm",kernelFunc:sw};function hne(e){let{attrs:{shape:t,value:n,dtype:a},backend:r}=e,s=r.makeOutput(t,a);return r.typedArrayFromHeap(s).fill(n),s}var mne={kernelName:wc,backendName:"wasm",kernelFunc:hne},F2;function fne(e){F2=e.wasm.cwrap(nl,null,["number","number","number","number","number","number"])}function gne(e){let{inputs:t,backend:n}=e,{image:a}=t,r=n.makeOutput(a.shape,a.dtype),s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,[o,l,c,u]=a.shape;return F2(s,o,l,c,u,i),r}var yne={kernelName:nl,backendName:"wasm",kernelFunc:gne,setupFunc:fne},bne=Un(js),xne=!1,vne=yn(qs,xne),$2;function wne(e){$2=e.wasm.cwrap(Ks,null,["number","number","number","number","number","number","number"])}function kne(e){let{backend:t,inputs:n,attrs:a}=e,{varianceEpsilon:r}=a,{x:s,mean:i,variance:o,offset:l,scale:c}=n,u=t.dataIdMap.get(s.dataId).id,p=t.dataIdMap.get(i.dataId).id,d=t.dataIdMap.get(o.dataId).id,h=l!=null?t.dataIdMap.get(l.dataId).id:0,m=c!=null?t.dataIdMap.get(c.dataId).id:0,f=t.makeOutput(s.shape,s.dtype);if(k.sizeFromShape(s.shape)===0)return f;let g=t.dataIdMap.get(f.dataId).id;return $2(u,p,d,h,m,r,g),f}var Ine={kernelName:Ks,backendName:"wasm",setupFunc:wne,kernelFunc:kne},D2;function Nne(e){D2=e.wasm.cwrap(Ti,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Tne(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d),g=Mp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return D2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Sne={kernelName:Ti,backendName:"wasm",setupFunc:Nne,kernelFunc:Tne},M2;function Cne(e){M2=e.wasm.cwrap(Si,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function _ne(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d,!0),g=Mp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedDepthwiseConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedDepthwiseConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedDepthwiseConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedDepthwiseConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return M2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Ene={kernelName:Si,backendName:"wasm",setupFunc:Cne,kernelFunc:_ne},R2;function Ane(e){R2=e.wasm.cwrap(rl,null,["number","number","number","number","number","number","array","number"])}function Fne(e){let{backend:t,inputs:n}=e,{params:a,indices:r}=n,[s,i,o,l]=Ay.prepareAndValidate(a,r),c=t.makeOutput(s,a.dtype);if(i===0)return c;let u=r.shape,p=u[u.length-1],d=t.dataIdMap.get(a.dataId).id,h=t.dataIdMap.get(r.dataId).id,m=new Uint8Array(new Int32Array(l).buffer),f=t.dataIdMap.get(c.dataId).id;return R2(d,Vn[a.dtype],h,i,p,o,m,f),c}var $ne={kernelName:rl,backendName:"wasm",setupFunc:Ane,kernelFunc:Fne},P2;function Dne(e){P2=e.wasm.cwrap("Gather",null,["number","number","array","number","number","number","array","number"])}function Mne(e){let{backend:t,inputs:n,attrs:a}=e,{x:r,indices:s}=n,{axis:i,batchDims:o}=a,l=k.parseAxisParam(i,r.shape)[0],c=E.segment_util.collectGatherOpShapeInfo(r,s,l,o),u=za({inputs:{x:r},attrs:{shape:[c.batchSize,c.outerSize,c.dimSize,c.sliceSize]},backend:t}),p=k.sizeFromShape(s.shape),d=za({inputs:{x:s},attrs:{shape:[c.batchSize,p/c.batchSize]},backend:t}),h=[c.batchSize,c.outerSize,p/c.batchSize,c.sliceSize],m=t.makeOutput(h,r.dtype);if(k.sizeFromShape(r.shape)===0)return m;let f=u.shape.length-1,g=t.dataIdMap.get(u.dataId).id,y=t.dataIdMap.get(d.dataId).id,b=t.dataIdMap.get(m.dataId).id,v=new Uint8Array(new Int32Array(k.computeStrides(u.shape)).buffer),x=new Uint8Array(new Int32Array(k.computeStrides(h)).buffer);return P2(g,Vn[r.dtype],v,f,y,c.batchSize,x,b),m.shape=c.outputShape,m}var Rne={kernelName:al,backendName:"wasm",setupFunc:Dne,kernelFunc:Mne},Pne=!1,One=yn(sl,Pne,"bool"),Lne=!1,zne=yn(Xs,Lne,"bool"),O2;function Bne(e){O2=e.wasm.cwrap(Ys,null,["number","number","number"])}function Wne(e){let{inputs:{x:t},attrs:{alpha:n},backend:a}=e,r=a.dataIdMap.get(t.dataId).id,s=a.makeOutput(t.shape,t.dtype);if(k.sizeFromShape(t.shape)!==0){let i=a.dataIdMap.get(s.dataId).id;O2(r,n,i)}return s}var Vne={kernelName:Ys,backendName:"wasm",setupFunc:Bne,kernelFunc:Wne},Une=!1,Gne=yn(cl,Une,"bool"),Hne=!1,jne=yn(pl,Hne,"bool"),qne=Un(Js),Kne=!1,Xne=yn(hl,Kne,"bool"),L2;function Yne(e){L2=e.wasm.cwrap(Zs,null,["number, number, number"])}function Jne(e){let{backend:t,inputs:n,attrs:a}=e,{reductionIndices:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=i,{transposed:c,axes:u,originalAxes:p,inputWasTransposed:d}=Cu(i,r,t);if(d){let b=t.dataIdMap.get(c.dataId).id;l=c,o=b}let h=l.shape.length;E.assertAxesAreInnerMostDims("max",u,h);let[m,f]=E.computeOutAndReduceShapes(l.shape,u),g=k.sizeFromShape(f),y=t.makeOutput(m,i.dtype);if(k.sizeFromShape(l.shape)!==0){let b=t.dataIdMap.get(y.dataId).id;L2(o,g,b)}if(d&&t.disposeData(c.dataId),s){let b=E.expandShapeToKeepDim(y.shape,p);y.shape=b}return y}var Zne={kernelName:Zs,backendName:"wasm",setupFunc:Yne,kernelFunc:Jne},Qne=!1,eae=yn(Qs,Qne),z2;function tae(e){z2=e.wasm.cwrap(ei,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function nae(e){let{inputs:t,attrs:n,backend:a}=e,r=t.x,s=a.dataIdMap.get(r.dataId).id,{filterSize:i,strides:o,pad:l,dimRoundingMode:c}=n,u=E.computePool2DInfo(r.shape,i,o,1,l,c),p=u.filterHeight,d=u.filterWidth,h=u.padInfo.top,m=u.padInfo.right,f=u.padInfo.bottom,g=u.padInfo.left,y=u.dilationHeight,b=u.dilationWidth,v=u.strideHeight,x=u.strideWidth,N=u.inChannels,T=u.outChannels;if(u.dataFormat!=="channelsLast")throw new Error(`wasm backend does not support dataFormat:'${u.dataFormat}'. Please use 'channelsLast'.`);let C=a.makeOutput(u.outShape,"float32"),$=a.dataIdMap.get(C.dataId).id;return z2(s,r.shape[0],r.shape[1],r.shape[2],p,d,h,m,f,g,y,b,v,x,N,T,$),C}var aae={kernelName:ei,backendName:"wasm",setupFunc:tae,kernelFunc:nae},B2;function rae(e){B2=e.wasm.cwrap(ti,null,["number, number, number"])}function sae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t),m=p;if(h){let x=t.dataIdMap.get(u.dataId).id;x!==o&&(c=u,l=x,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("mean",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=c;c.dtype!=="float32"&&(b=ff({backend:t,inputs:{x:c},attrs:{dtype:"float32"}}),l=t.dataIdMap.get(b.dataId).id);let v=t.makeOutput(f,"float32");if(k.sizeFromShape(c.shape)!==0){let x=t.dataIdMap.get(v.dataId).id;B2(l,y,x)}if(h&&t.disposeData(u.dataId),s){let x=E.expandShapeToKeepDim(v.shape,d);v.shape=x}return c.dtype!=="float32"&&t.disposeData(b.dataId),v}var iae={kernelName:ti,backendName:"wasm",setupFunc:rae,kernelFunc:sae},W2;function oae(e){W2=e.wasm.cwrap(ni,null,["number, number, number"])}function lae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t);if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v)}let m=c.shape.length;E.assertAxesAreInnerMostDims("min",p,m);let[f,g]=E.computeOutAndReduceShapes(c.shape,p),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;W2(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var uae={kernelName:ni,backendName:"wasm",setupFunc:oae,kernelFunc:lae},cae=!1,pae=yn(ai,cae),dae=!0,hae=yn(ri,dae),mae=Un(fl);function iw(e,t){let n=new Int32Array(e.wasm.HEAPU8.buffer,t,4),a=n[0],r=n[1],s=n[2],i=n[3];return e.wasm._free(t),{pSelectedIndices:a,selectedSize:r,pSelectedScores:s,pValidOutputs:i}}var V2;function fae(e){V2=e.wasm.cwrap(yl,"number",["number","number","number","number","number"])}function gae(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i}=a,{boxes:o,scores:l}=n,c=t.dataIdMap.get(o.dataId).id,u=t.dataIdMap.get(l.dataId).id,p=V2(c,u,s,r,i),{pSelectedIndices:d,selectedSize:h,pSelectedScores:m,pValidOutputs:f}=iw(t,p);return t.wasm._free(m),t.wasm._free(f),t.makeOutput([h],"int32",d)}var yae={kernelName:yl,backendName:"wasm",setupFunc:fae,kernelFunc:gae},U2;function bae(e){U2=e.wasm.cwrap(bl,"number",["number","number","number","number","number","bool"])}function xae(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,padToMaxOutputSize:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=U2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=iw(t,d);t.wasm._free(f);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([],"int32",g);return[y,b]}var vae={kernelName:bl,backendName:"wasm",setupFunc:bae,kernelFunc:xae},G2;function wae(e){G2=e.wasm.cwrap(xl,"number",["number","number","number","number","number","number"])}function kae(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,softNmsSigma:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=G2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=iw(t,d);t.wasm._free(g);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([m],"float32",f);return[y,b]}var Iae={kernelName:xl,backendName:"wasm",setupFunc:wae,kernelFunc:kae},Nae=!1,Tae=yn(gl,Nae,"bool"),H2;function Sae(e){H2=e.wasm.cwrap(si,null,["number","number","number","number","number"])}function Cae(e){let{inputs:t,backend:n,attrs:a}=e,{indices:r}=t,{depth:s,onValue:i,offValue:o}=a,l=n.makeOutput([...r.shape,s],"int32"),c=n.dataIdMap.get(l.dataId).id,u=n.dataIdMap.get(r.dataId).id;return H2(u,s,i,o,c),l}var _ae={kernelName:si,backendName:"wasm",setupFunc:Sae,kernelFunc:Cae};function Eae(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(1),a}var Aae={kernelName:vl,backendName:"wasm",kernelFunc:Eae};function Fae(e){let{inputs:t,backend:n,attrs:a}=e,{axis:r}=a;if(t.length===1)return sw({inputs:{input:t[0]},backend:n,attrs:{dim:r}});let s=t[0].shape,i=t[0].dtype;t.forEach(l=>{k.assertShapesMatch(s,l.shape,"All tensors passed to stack must have matching shapes"),k.assert(i===l.dtype,()=>"All tensors passed to stack must have matching dtypes")});let o=t.map(l=>sw({inputs:{input:l},backend:n,attrs:{dim:r}}));return N2({inputs:o,backend:n,attrs:{axis:r}})}var $ae={kernelName:wl,backendName:"wasm",kernelFunc:Fae},j2;function Dae(e){j2=e.wasm.cwrap(ii,null,["number","array","number","number","array","array","number","number"])}function Mae(e){let{inputs:{x:t},backend:n,attrs:{paddings:a,constantValue:r}}=e,s=a.map((m,f)=>m[0]+t.shape[f]+m[1]),i=n.dataIdMap.get(t.dataId).id,o=n.makeOutput(s,t.dtype),l=n.dataIdMap.get(o.dataId).id,c=new Uint8Array(new Int32Array(t.shape).buffer),u=a.map(m=>m[0]),p=a.map(m=>m[1]),d=new Uint8Array(new Int32Array(u).buffer),h=new Uint8Array(new Int32Array(p).buffer);return j2(i,c,t.shape.length,Vn[t.dtype],d,h,r,l),o}var Rae={kernelName:ii,backendName:"wasm",kernelFunc:Mae,setupFunc:Dae},Pae=!1,Oae=yn(oi,Pae),q2;function Lae(e){q2=e.wasm.cwrap(li,null,["number","number","number"])}function zae(e){let{inputs:t,backend:n}=e,{x:a,alpha:r}=t,s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,o=n.makeOutput(a.shape,"float32"),l=n.dataIdMap.get(o.dataId).id;return q2(s,i,l),o}var Bae={kernelName:li,backendName:"wasm",setupFunc:Lae,kernelFunc:zae},K2;function Wae(e){K2=e.wasm.cwrap(kl,null,["number","number","number","number"])}function Vae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("prod",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;K2(l,y,Vn[b.dtype],v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var Uae={kernelName:kl,backendName:"wasm",setupFunc:Wae,kernelFunc:Vae},Gae=e=>{let{backend:t,attrs:n}=e,{start:a,stop:r,step:s,dtype:i}=n,o=Fv(a,r,s,i),l=t.makeOutput([o.length],i);return t.typedArrayFromHeap(l).set(o),l},Hae={kernelName:Cc,backendName:"wasm",kernelFunc:Gae},jae=!0,qae=yn(Gs,jae),Kae=Un(ui),Xae=Un(pi),X2;function Yae(e){X2=e.wasm.cwrap(ci,null,["number","number","number","number","number","number","number","number","number","number"])}function Jae(e){let{backend:t,inputs:n,attrs:a}=e,{images:r}=n,{alignCorners:s,halfPixelCenters:i,size:o}=a,[l,c]=o,[u,p,d,h]=r.shape,m=[u,l,c,h],f=t.dataIdMap.get(r.dataId),g;f.dtype!=="float32"&&(g=ff({backend:t,inputs:{x:r},attrs:{dtype:"float32"}}),f=t.dataIdMap.get(g.dataId));let y=f.id,b=t.makeOutput(m,"float32");if(k.sizeFromShape(r.shape)===0)return b;let v=t.dataIdMap.get(b.dataId).id;return X2(y,u,p,d,h,l,c,s?1:0,i?1:0,v),g!=null&&t.disposeData(g.dataId),b}var Zae={kernelName:ci,backendName:"wasm",setupFunc:Yae,kernelFunc:Jae},Y2;function Qae(e){Y2=e.wasm.cwrap(di,null,["number","array","number","array","number","number"])}function ere(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{dims:s}=a,i=k.parseAxisParam(s,r.shape);if(r.shape.length===0)return hf({inputs:{x:r},backend:n});let o=n.makeOutput(r.shape,r.dtype),l=n.dataIdMap.get(r.dataId).id,c=n.dataIdMap.get(o.dataId).id,u=new Uint8Array(new Int32Array(i).buffer),p=new Uint8Array(new Int32Array(r.shape).buffer);return Y2(l,u,i.length,p,r.shape.length,c),za({inputs:{x:o},attrs:{shape:r.shape},backend:n})}var tre={kernelName:di,backendName:"wasm",kernelFunc:ere,setupFunc:Qae},J2;function nre(e){J2=e.wasm.cwrap(Ll,null,["number","number","number","number","number","number","number","number","array","number","number"])}function are(e){let{inputs:t,backend:n,attrs:a}=e,{image:r}=t,{radians:s,fillValue:i,center:o}=a,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(r.dataId).id,u=n.dataIdMap.get(l.dataId).id,[p,d,h,m]=r.shape,[f,g]=E.getImageCenter(o,d,h),y=i===0,b=255,v=typeof i=="number"?[i,i,i,y?0:b]:[...i,b],x=new Uint8Array(new Int32Array(v).buffer);return J2(c,p,d,h,m,s,f,g,x,v.length,u),l}var rre={kernelName:Ll,backendName:"wasm",kernelFunc:are,setupFunc:nre},sre=Un(hi),ire=Un(mi),Z2;function ore(e){Z2=e.wasm.cwrap(Tl,null,["number","number","number","number","number","number","array","number","number"])}function lre(e){let{backend:t,inputs:n,attrs:a}=e,{indices:r,updates:s}=n,{shape:i}=a,o=t.makeOutput(i,s.dtype);if(k.sizeFromShape(i)===0)return o;let{sliceRank:l,numUpdates:c,sliceSize:u,strides:p,outputSize:d}=Fy.calculateShapes(s,r,i),h=t.dataIdMap.get(r.dataId).id,m=t.dataIdMap.get(s.dataId).id,f=new Uint8Array(new Int32Array(p).buffer),g=t.dataIdMap.get(o.dataId).id;return Z2(h,m,Vn[s.dtype],l,c,u,f,d,g),o}var ure={kernelName:Tl,backendName:"wasm",setupFunc:ore,kernelFunc:lre},Q2;function cre(e){Q2=e.wasm.cwrap("SelectV2",null,["number","number","number","number","number"])}function pre(e){let{inputs:t,backend:n}=e,{condition:a,t:r,e:s}=t,i=n.dataIdMap.get(a.dataId).id,o=n.dataIdMap.get(r.dataId).id,l=n.dataIdMap.get(s.dataId).id,c=n.makeOutput(r.shape,r.dtype),u=n.dataIdMap.get(c.dataId).id,p=a.shape.length,d=r.shape.length,h=p===0||p>1||d===1?1:k.sizeFromShape(r.shape.slice(1));return Q2(i,o,l,h,u),c}var dre={kernelName:Sl,backendName:"wasm",kernelFunc:pre,setupFunc:cre},eC;function hre(e){eC=e.wasm.cwrap(gi,null,["number","number"])}function mre(e){let{backend:t,inputs:{x:n}}=e,a=t.dataIdMap.get(n.dataId).id,r=t.makeOutput(n.shape,n.dtype),s=t.dataIdMap.get(r.dataId).id;return k.sizeFromShape(r.shape)===0||eC(a,s),r}var fre={kernelName:"Sigmoid",backendName:"wasm",setupFunc:hre,kernelFunc:mre},gre=Un(fi);function gf(e){let{inputs:{x:t},attrs:{begin:n,size:a},backend:r}=e,[s,i]=dn.parseSliceParams(t,n,a),o=dn.isSliceContinous(t.shape,s,i),l=r.readSync(t.dataId),c=r.makeOutput(i,t.dtype),u=k.computeStrides(t.shape),p=r.dataIdMap.get(c.dataId);if(o){let m=dn.computeFlatOffset(s,u);return t.dtype==="string"?p.stringBytes=l.slice(m,m+k.sizeFromShape(i)):r.typedArrayFromHeap(c).set(l.subarray(m,m+k.sizeFromShape(i))),c}if(t.dtype==="string"){let m=Km(l,s,i,t.shape,t.dtype);return p.stringBytes=m,c}let d=r.typedArrayFromHeap(c),h=t.shape.length;if(h===2)yre(l,u[0],d,s,i);else if(h===3)bre(l,u[0],u[1],d,s,i);else if(h===4)xre(l,u[0],u[1],u[2],d,s,i);else{let m=Km(l,s,i,t.shape,t.dtype);d.set(m)}return c}function yre(e,t,n,a,r){let s=0,i=a[0],o=a[1],l=i+r[0];for(let c=i;c{let d=[...u];d[o]=p;let h=gf({inputs:{x:r},attrs:{begin:c,size:d},backend:a});return c[o]+=p,h})}var Tre={kernelName:$l,backendName:"wasm",kernelFunc:Nre},Sre=Un(yi),Cre=Un(Ac),_re=!0,Ere=yn(vi,_re),nC;function Are(e){nC=e.wasm.cwrap(Kr,null,["number","number","number"])}function Fre(e){let{backend:t,inputs:n,attrs:a}=e,{alpha:r}=a,{x:s}=n,i=t.dataIdMap.get(s.dataId).id,o=t.makeOutput(s.shape,s.dtype),l=t.dataIdMap.get(o.dataId).id;return nC(i,r,l),o}var $re={kernelName:Kr,backendName:"wasm",setupFunc:Are,kernelFunc:Fre},aC;function Dre(e){aC=e.wasm.cwrap(Dl,null,["number","array","number","array","array","array","array","array","number","number"])}function Mre(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{begin:s,end:i,strides:o}=a;o==null&&(o=new Array(s.length));let{beginMask:l,endMask:c,ellipsisMask:u,newAxisMask:p,shrinkAxisMask:d}=a,h=E.slice_util.maskToAxes(u);if(h.length>1)throw new Error("Multiple ellipses in slice is not allowed.");if(u!==0&&p!==0)throw new Error("Using both ellipsisMask and newAxisMask is not yet supported.");if(u!==0&&d!==0)throw new Error("Using both ellipsisMask and shrinkAxisMask is not yet supported.");let m=r.shape.length-s.length,f=E.slice_util.maskToAxes(p),g=r.shape.slice();f.forEach(F=>{s[F]=0,i[F]=1,g.splice(F,0,1)});let y=za({inputs:{x:r},attrs:{shape:g},backend:t}),{begin:b,end:v,strides:x}=E.slice_util.getNormalizedAxes(y.shape,h,m,s,i,o,l,c,u);s=b,i=v,o=x;let N=E.slice_util.maskToAxes(d);N.forEach(F=>{i[F]=s[F]+1,o[F]=1});let T=E.slice_util.computeOutShape(s,i,o),C=T.filter((F,O)=>N.indexOf(O)===-1);if(o.every(F=>F===1)){let F=gf({inputs:{x:r},attrs:{begin:s,size:T},backend:t});return za({inputs:{x:F},attrs:{shape:C},backend:t})}let $=t.makeOutput(C,"float32");if(!C.some(F=>F===0)){let F=t.dataIdMap.get(y.dataId).id,O=new Uint8Array(new Int32Array(k.computeStrides(y.shape)).buffer),W=new Uint8Array(new Int32Array(s).buffer),V=new Uint8Array(new Int32Array(i).buffer),H=new Uint8Array(new Int32Array(o).buffer),K=new Uint8Array(new Int32Array(C).buffer),j=new Uint8Array(new Int32Array(k.computeStrides(C)).buffer),Y=t.dataIdMap.get($.dataId).id;aC(F,O,y.shape.length,W,V,H,K,j,C.length,Y)}return za({inputs:{x:$},attrs:{shape:C},backend:t})}var Rre={kernelName:Dl,backendName:"wasm",setupFunc:Dre,kernelFunc:Mre},Pre=!0,Ore=yn(wi,Pre),rC;function Lre(e){rC=e.wasm.cwrap(bi,null,["number, number, number"])}function zre(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("sum",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;rC(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var Bre={kernelName:bi,backendName:"wasm",setupFunc:Lre,kernelFunc:zre},Wre=Un(ki),sC;function Vre(e){sC=e.wasm.cwrap(qr,null,["number","array","number","array","number","number"])}function Ure(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,s=n.dataIdMap.get(r.dataId).id,{reps:i}=a,o=new Array(r.shape.length);for(let d=0;d{let{x:a}=e,{k:r,sorted:s}=n,i=t.dataIdMap.get(a.dataId).id,o=new Uint8Array(new Int32Array(a.shape).buffer),l=a.shape.slice();l[l.length-1]=r;let c=t.makeOutput(l,a.dtype),u=t.dataIdMap.get(c.dataId).id,p=t.makeOutput(l,"int32"),d=t.dataIdMap.get(p.dataId).id;return iC(i,o,a.shape.length,Vn[a.dtype],r,s,u,d),[c,p]},qre={kernelName:Rl,backendName:"wasm",setupFunc:Hre,kernelFunc:jre};function Kre(e){let{inputs:t,backend:n,attrs:a}=e,{value:r}=t,{axis:s}=a;s<0&&(s+=r.shape.length);let i=r.shape[s],o=r.shape.length,l=new Array(o-1),c=0;for(let h=0;h({dataId:h,dtype:m,shape:l}))}var Xre={kernelName:Pl,backendName:"wasm",kernelFunc:Kre};function Yre(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(0),a}var Jre={kernelName:Ol,backendName:"wasm",kernelFunc:Yre},Zre=[bte,vte,Ite,Fte,Mte,Lte,zte,Vte,Ute,jte,Xte,Yte,Qte,nne,sne,lne,cne,pne,dne,mne,yne,bne,vne,yte,Ine,Sne,Ene,$ne,Rne,One,zne,Nte,Vne,Gne,jne,qne,Xne,Zne,eae,aae,iae,uae,pae,hae,mae,yae,vae,Iae,Tae,_ae,Aae,$ae,Rae,Oae,Bae,Uae,Hae,qae,Kae,Xae,Rte,Zae,tre,rre,ire,sre,ure,dre,fre,gre,vre,Ire,Tre,Sre,Cre,Ere,$re,Rre,Ore,Bre,Wre,Gre,qre,_te,Xre,Jre];for(let e of Zre)Dc(e);var ow=te();ow.registerFlag("WASM_HAS_SIMD_SUPPORT",async()=>WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,10,9,1,7,0,65,0,253,15,26,11])));ow.registerFlag("WASM_HAS_MULTITHREAD_SUPPORT",async()=>{if(ow.get("IS_NODE"))return!1;try{return new MessageChannel().port1.postMessage(new SharedArrayBuffer(1)),WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,5,4,1,3,1,1,10,11,1,9,0,65,0,254,16,2,0,26,11]))}catch(e){return!1}});var oC=Ro(lA()),Qre='var threadInfoStruct=0;var selfThreadId=0;var parentThreadId=0;var Module={};function threadPrintErr(){var text=Array.prototype.slice.call(arguments).join(" ");console.error(text)}function threadAlert(){var text=Array.prototype.slice.call(arguments).join(" ");postMessage({cmd:"alert",text:text,threadId:selfThreadId})}var err=threadPrintErr;this.alert=threadAlert;Module["instantiateWasm"]=function(info,receiveInstance){var instance=new WebAssembly.Instance(Module["wasmModule"],info);Module["wasmModule"]=null;receiveInstance(instance);return instance.exports};this.onmessage=function(e){try{if(e.data.cmd==="load"){Module["DYNAMIC_BASE"]=e.data.DYNAMIC_BASE;Module["DYNAMICTOP_PTR"]=e.data.DYNAMICTOP_PTR;Module["wasmModule"]=e.data.wasmModule;Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;Module["ENVIRONMENT_IS_PTHREAD"]=true;if(typeof e.data.urlOrBlob==="string"){importScripts(e.data.urlOrBlob)}else{var objectUrl=URL.createObjectURL(e.data.urlOrBlob);importScripts(objectUrl);URL.revokeObjectURL(objectUrl)}Module=WasmBackendModuleThreadedSimd(Module);postMessage({"cmd":"loaded"})}else if(e.data.cmd==="objectTransfer"){Module["PThread"].receiveObjectTransfer(e.data)}else if(e.data.cmd==="run"){Module["__performance_now_clock_drift"]=performance.now()-e.data.time;threadInfoStruct=e.data.threadInfoStruct;Module["__register_pthread_ptr"](threadInfoStruct,0,0);selfThreadId=e.data.selfThreadId;parentThreadId=e.data.parentThreadId;var max=e.data.stackBase;var top=e.data.stackBase+e.data.stackSize;Module["establishStackSpace"](top,max);Module["_emscripten_tls_init"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].setThreadStatus(Module["_pthread_self"](),1);try{var result=Module["dynCall_ii"](e.data.start_routine,e.data.arg);if(!Module["getNoExitRuntime"]())Module["PThread"].threadExit(result)}catch(ex){if(ex==="Canceled!"){Module["PThread"].threadCancel()}else if(ex!="unwind"){Atomics.store(Module["HEAPU32"],threadInfoStruct+4>>2,ex instanceof Module["ExitStatus"]?ex.status:-2);Atomics.store(Module["HEAPU32"],threadInfoStruct+0>>2,1);Module["_emscripten_futex_wake"](threadInfoStruct+0,2147483647);if(!(ex instanceof Module["ExitStatus"]))throw ex}}}else if(e.data.cmd==="cancel"){if(threadInfoStruct){Module["PThread"].threadCancel()}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="processThreadQueue"){if(threadInfoStruct){Module["_emscripten_current_thread_process_queued_calls"]()}}else{err("worker.js received unknown command "+e.data.cmd);err(e.data)}}catch(ex){err("worker.js onmessage() captured an uncaught exception: "+ex);if(ex.stack)err(ex.stack);throw ex}};if(typeof process==="object"&&typeof process.versions==="object"&&typeof process.versions.node==="string"){self={location:{href:__filename}};var onmessage=this.onmessage;var nodeWorkerThreads=require("worker_threads");Worker=nodeWorkerThreads.Worker;var parentPort=nodeWorkerThreads.parentPort;parentPort.on("message",function(data){onmessage({data:data})});var nodeFS=require("fs");var nodeRead=function(filename){return nodeFS.readFileSync(filename,"utf8")};function globalEval(x){global.require=require;global.Module=Module;eval.call(null,x)}importScripts=function(f){globalEval(nodeRead(f))};postMessage=function(msg){parentPort.postMessage(msg)};if(typeof performance==="undefined"){performance={now:function(){return Date.now()}}}}',ese=Ro(uA()),lC=class extends dc{constructor(e){super();this.wasm=e,this.dataIdNextNumber=1,this.wasm.tfjs.init(),this.dataIdMap=new Dd(this,ts())}write(e,t,n){let a={};return this.move(a,e,t,n),a}numDataIds(){return this.dataIdMap.numDataIds()}async time(e){let t=k.now();return e(),{kernelMs:k.now()-t}}move(e,t,n,a){let r=this.dataIdNextNumber++;if(a==="string"){let l=t;this.dataIdMap.set(e,{id:r,stringBytes:l,shape:n,dtype:a,memoryOffset:null});return}let s=k.sizeFromShape(n),i=s*k.bytesPerElement(a),o=this.wasm._malloc(i);this.dataIdMap.set(e,{id:r,memoryOffset:o,shape:n,dtype:a}),this.wasm.tfjs.registerTensor(r,s,o),t!=null&&this.wasm.HEAPU8.set(new Uint8Array(t.buffer,t.byteOffset,i),o)}async read(e){return this.readSync(e)}readSync(e){let{memoryOffset:t,dtype:n,shape:a,stringBytes:r}=this.dataIdMap.get(e);if(n==="string")return r;let s=this.wasm.HEAPU8.slice(t,t+k.sizeFromShape(a)*k.bytesPerElement(n));return tse(s.buffer,n)}disposeData(e){let t=this.dataIdMap.get(e);this.wasm._free(t.memoryOffset),this.wasm.tfjs.disposeData(t.id),this.dataIdMap.delete(e)}floatPrecision(){return 32}getMemoryOffset(e){return this.dataIdMap.get(e).memoryOffset}dispose(){this.wasm.tfjs.dispose(),this.wasm=null}memory(){return{unreliable:!1}}makeOutput(e,t,n){let a;if(n==null)a=this.write(null,e,t);else{a={};let r=this.dataIdNextNumber++;this.dataIdMap.set(a,{id:r,memoryOffset:n,shape:e,dtype:t});let s=k.sizeFromShape(e);this.wasm.tfjs.registerTensor(r,s,n)}return{dataId:a,shape:e,dtype:t}}typedArrayFromHeap({shape:e,dtype:t,dataId:n}){let a=this.wasm.HEAPU8.buffer,{memoryOffset:r}=this.dataIdMap.get(n),s=k.sizeFromShape(e);switch(t){case"float32":return new Float32Array(a,r,s);case"int32":return new Int32Array(a,r,s);case"bool":return new Uint8Array(a,r,s);default:throw new Error(`Unknown dtype ${t}`)}}};function nse(e){return(t,n)=>(k.fetch(e,{credentials:"same-origin"}).then(a=>{a.ok||t.env.a(`failed to load wasm binary file at '${e}'`),a.arrayBuffer().then(r=>{WebAssembly.instantiate(r,t).then(s=>{n(s.instance)})})}),{})}function uC(e,t,n){if(yf!=null)return yf;let a="tfjs-backend-wasm.wasm";return e&&t?a="tfjs-backend-wasm-threaded-simd.wasm":e&&(a="tfjs-backend-wasm-simd.wasm"),Rp!=null&&Rp[a]!=null?Rp[a]:n+a}async function ase(){let[e,t]=await Promise.all([te().getAsync("WASM_HAS_SIMD_SUPPORT"),te().getAsync("WASM_HAS_MULTITHREAD_SUPPORT")]);return new Promise((n,a)=>{let r={};r.locateFile=(l,c)=>{if(l.endsWith(".worker.js")){let u=Qre,p=new Blob([u],{type:"application/javascript"});return URL.createObjectURL(p)}return l.endsWith(".wasm")?uC(e,t,Pp!=null?Pp:c):c+l},lw&&(r.instantiateWasm=nse(uC(e,t,Pp!=null?Pp:"")));let s;t&&e&&yf==null?(s=oC.default(r),s.mainScriptUrlOrBlob=new Blob(["var WasmBackendModuleThreadedSimd = "+oC.default.toString()],{type:"text/javascript"})):s=ese.default(r);let i=null;s.tfjs={init:s.cwrap("init",null,[]),registerTensor:s.cwrap("register_tensor",null,["number","number","number"]),disposeData:s.cwrap("dispose_data",i,["number"]),dispose:s.cwrap("dispose",i,[])};let o=!1;s.onRuntimeInitialized=()=>{o=!0,Op=!1,n({wasm:s})},s.onAbort=()=>{o||Op||(Op=!0,a({message:"Make sure the server can serve the `.wasm` file relative to the bundled js file. For more details see https://github.com/tensorflow/tfjs/blob/master/tfjs-backend-wasm/README.md#using-bundlers"}))}})}function tse(e,t){switch(t){case"float32":return new Float32Array(e);case"int32":return new Int32Array(e);case"bool":return new Uint8Array(e);default:throw new Error(`Unknown dtype ${t}`)}}var rse=["tfjs-backend-wasm.wasm","tfjs-backend-wasm-simd.wasm","tfjs-backend-wasm-threaded-simd.wasm"],yf=null,Pp=null,Rp={},Op=!1,lw=!1;function sse(e,t=!1){if(Rt("setWasmPath has been deprecated in favor of setWasmPaths and will be removed in a future release."),Op)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPath()` before you call `tf.setBackend()` or `tf.ready()`");yf=e,lw=t}function ise(e,t=!1){if(Op)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPaths()` before you call `tf.setBackend()` or `tf.ready()`");if(typeof e=="string")Pp=e;else{Rp=e;let n=rse.filter(a=>Rp[a]==null);if(n.length>0)throw new Error(`There were no entries found for the following binaries: ${n.join(",")}. Please either call setWasmPaths with a map providing a path for each binary, or with a string indicating the directory where all the binaries can be found.`)}lw=t}var ose="2.8.5",lse=2;Th("wasm",async()=>{let{wasm:e}=await ase();return new lC(e)},lse);var Uf={};cc(Uf,{AnchorPosition:()=>cr,DrawBox:()=>Sf,DrawBoxOptions:()=>vw,DrawFaceLandmarks:()=>kw,DrawFaceLandmarksOptions:()=>ww,DrawTextField:()=>vs,DrawTextFieldOptions:()=>Lp,drawContour:()=>Fr,drawDetections:()=>yse,drawFaceExpressions:()=>bse,drawFaceLandmarks:()=>xse});function Fr(e,t,n=!1){if(e.beginPath(),t.slice(1).forEach(({x:a,y:r},s)=>{let i=t[s];e.moveTo(i.x,i.y),e.lineTo(a,r)}),n){let a=t[t.length-1],r=t[0];if(!a||!r)return;e.moveTo(a.x,a.y),e.lineTo(r.x,r.y)}e.stroke()}var bf={};cc(bf,{computeReshapedDimensions:()=>pw,getCenterPoint:()=>no,isDimensions:()=>vf,isEven:()=>xf,isFloat:()=>cw,isTensor:()=>eo,isTensor1D:()=>use,isTensor2D:()=>uw,isTensor3D:()=>$r,isTensor4D:()=>ra,isValidNumber:()=>Ba,isValidProbablitiy:()=>_u,range:()=>lr,round:()=>to});var un=class{constructor(t,n){if(!Ba(t)||!Ba(n))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:n})}`);this._width=t,this._height=n}get width(){return this._width}get height(){return this._height}reverse(){return new un(1/this.width,1/this.height)}};function eo(e,t){return e instanceof z&&e.shape.length===t}function use(e){return eo(e,1)}function uw(e){return eo(e,2)}function $r(e){return eo(e,3)}function ra(e){return eo(e,4)}function cw(e){return e%1!=0}function xf(e){return e%2==0}function to(e,t=2){let n=10**t;return Math.floor(e*n)/n}function vf(e){return e&&e.width&&e.height}function pw({width:e,height:t},n){let a=n/Math.max(t,e);return new un(Math.round(e*a),Math.round(t*a))}function no(e){return e.reduce((t,n)=>t.add(n),new De(0,0)).div(new De(e.length,e.length))}function lr(e,t,n){return Array(e).fill(0).map((a,r)=>t+r*n)}function Ba(e){return!!e&&e!==Infinity&&e!==-Infinity&&!Number.isNaN(e)||e===0}function _u(e){return Ba(e)&&e>=0&&e<=1}var De=class{constructor(t,n){this._x=t,this._y=n}get x(){return this._x}get y(){return this._y}add(t){return new De(this.x+t.x,this.y+t.y)}sub(t){return new De(this.x-t.x,this.y-t.y)}mul(t){return new De(this.x*t.x,this.y*t.y)}div(t){return new De(this.x/t.x,this.y/t.y)}abs(){return new De(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new De(Math.floor(this.x),Math.floor(this.y))}};var lt=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(Ba)}static assertIsValidBox(t,n,a=!1){if(!lt.isRect(t))throw new Error(`${n} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!a&&(t.width<0||t.height<0))throw new Error(`${n} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,n=!0){let a=t||{},r=[a.left,a.top,a.right,a.bottom].every(Ba),s=[a.x,a.y,a.width,a.height].every(Ba);if(!s&&!r)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(a)}`);let[i,o,l,c]=s?[a.x,a.y,a.width,a.height]:[a.left,a.top,a.right-a.left,a.bottom-a.top];lt.assertIsValidBox({x:i,y:o,width:l,height:c},"Box.constructor",n),this._x=i,this._y=o,this._width=l,this._height=c}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new De(this.left,this.top)}get topRight(){return new De(this.right,this.top)}get bottomLeft(){return new De(this.left,this.bottom)}get bottomRight(){return new De(this.right,this.bottom)}round(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.round(s));return new lt({x:t,y:n,width:a,height:r})}floor(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.floor(s));return new lt({x:t,y:n,width:a,height:r})}toSquare(){let{x:t,y:n,width:a,height:r}=this,s=Math.abs(a-r);return an&&(o=-p+n+a,p=n),d>t&&(l=-d+t+r,d=t),c<1&&(l=2-c,c=1),u<1&&(l=2-u,u=1),{dy:i,edy:l,dx:s,edx:o,y:u,ey:d,x:c,ex:p,w:a,h:r}}calibrate(t){return new lt({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var ao=class extends lt{constructor(t,n,a,r,s=!1){super({left:t,top:n,right:a,bottom:r},s)}};var Dr=class{constructor(t,n,a,r,s){this._imageDims=new un(s.width,s.height),this._score=t,this._classScore=n,this._className=a,this._box=new lt(r).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new lt(this._box).rescale(this.imageDims.reverse())}forSize(t,n){return new Dr(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:n})}};var bt=class extends Dr{constructor(t,n,a){super(t,t,"",n,a)}forSize(t,n){let{score:a,relativeBox:r,imageDims:s}=super.forSize(t,n);return new bt(a,r,s)}};function wf(e,t,n=!0){let a=Math.max(0,Math.min(e.right,t.right)-Math.max(e.left,t.left)),r=Math.max(0,Math.min(e.bottom,t.bottom)-Math.max(e.top,t.top)),s=a*r;return n?s/(e.area+t.area-s):s/Math.min(e.area,t.area)}function kf(e){let t=e.map(o=>o.x),n=e.map(o=>o.y),a=t.reduce((o,l)=>lloo({score:i,boxIndex:o})).sort((i,o)=>i.score-o.score).map(i=>i.boxIndex),s=[];for(;r.length>0;){let i=r.pop();s.push(i);let o=r,l=[];for(let c=0;cl[u]<=n)}return s}function ka(e,t){return D(()=>{let[n,a,r]=t,s=In([...e.shape.slice(0,3),1],n,"float32"),i=In([...e.shape.slice(0,3),1],a,"float32"),o=In([...e.shape.slice(0,3),1],r,"float32"),l=Qe([s,i,o],3);return ge(e,l)})}function Nf(e,t=!1){return D(()=>{let[n,a]=e.shape.slice(1);if(n===a)return e;let r=Math.abs(n-a),s=Math.round(r*(t?.5:1)),i=n>a?2:1,o=d=>{let h=e.shape.slice();return h[i]=d,In(h,0,"float32")},l=o(s),c=r-l.shape[i],p=[t&&c?o(c):null,e,l].filter(d=>!!d).map(d=>pe(d,"float32"));return Qe(p,i)})}function cC(e){let t=e.slice();for(let n=t.length-1;n>0;n--){let a=Math.floor(Math.random()*(n+1)),r=t[n];t[n]=t[a],t[a]=r}return t}function Eu(e){return 1/(1+Math.exp(-e))}function pC(e){return Math.log(e/(1-e))}var ro=class extends lt{constructor(t,n,a,r,s=!1){super({x:t,y:n,width:a,height:r},s)}};var cse=.5,pse=.43,dse=.45,Gn=class{constructor(t,n,a=new De(0,0)){let{width:r,height:s}=n;this._imgDims=new un(r,s),this._shift=a,this._positions=t.map(i=>i.mul(new De(r,s)).add(a))}get shift(){return new De(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new De(this.imageWidth,this.imageHeight)))}forSize(t,n){return new this.constructor(this.relativePositions,{width:t,height:n})}shiftBy(t,n){return new this.constructor(this.relativePositions,this._imgDims,new De(t,n))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,n={}){if(t){let s=t instanceof bt?t.box.floor():new lt(t);return this.shiftBy(s.x,s.y).align(null,n)}let{useDlibAlignment:a,minBoxPadding:r}={useDlibAlignment:!1,minBoxPadding:.2,...n};return a?this.alignDlib():this.alignMinBbox(r)}alignDlib(){let t=this.getRefPointsForAlignment(),[n,a,r]=t,s=p=>r.sub(p).magnitude(),i=(s(n)+s(a))/2,o=Math.floor(i/dse),l=no(t),c=Math.floor(Math.max(0,l.x-cse*o)),u=Math.floor(Math.max(0,l.y-pse*o));return new ro(c,u,Math.min(o,this.imageWidth+c),Math.min(o,this.imageHeight+u))}alignMinBbox(t){let n=kf(this.positions);return n.pad(n.width*t,n.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var dw=class extends Gn{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],no([t[3],t[4]])]}};var so=class extends Gn{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(no)}};var Au=class{constructor(t,n){this._label=t,this._distance=n}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${to(this.distance)})`:""}`}};var Fu=class extends lt{static assertIsValidLabeledBox(t,n){if(lt.assertIsValidBox(t,n),!Ba(t.label))throw new Error(`${n} - expected property label (${t.label}) to be a number`)}constructor(t,n){super(t);this._label=n}get label(){return this._label}};var ur=class{constructor(t,n){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(n)||n.some(a=>!(a instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=n}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let n=t.descriptors.map(a=>new Float32Array(a));return new ur(t.label,n)}};var hw=class extends Fu{static assertIsValidPredictedBox(t,n){if(Fu.assertIsValidLabeledBox(t,n),!_u(t.score)||!_u(t.classScore))throw new Error(`${n} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,n,a,r){super(t,n);this._score=a,this._classScore=r}get score(){return this._score}get classScore(){return this._classScore}};function Wa(e){return e.detection instanceof bt}function bs(e,t){return{...e,...{detection:t}}}function mw(){let e=window.fetch;if(!e)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:e,readFile:t}}function Tf(e){let t="";if(!e)try{e=require("fs")}catch(a){t=a.toString()}return{readFile:e?a=>new Promise((r,s)=>{e.readFile(a,(i,o)=>i?s(i):r(o))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function fw(){let e=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,n=()=>{if(e)return new e;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},a=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},r=global.fetch,s=Tf();return{Canvas:e||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:n,createImageElement:a,fetch:r,...s}}function gw(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var yw=UE(hC()),en;function fse(){if(!en)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return en}function bw(e){en=e}function xw(){return gw()?bw(mw()):yw.isNodejs()?bw(fw()):null}function gse(e){if(en||xw(),!en)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=en.Canvas,Image:n=en.Image}=e;en.Canvas=t,en.Image=n,en.createCanvasElement=e.createCanvasElement||(()=>new t),en.createImageElement=e.createImageElement||(()=>new n),en.ImageData=e.ImageData||en.ImageData,en.Video=e.Video||en.Video,en.fetch=e.fetch||en.fetch,en.readFile=e.readFile||en.readFile}var st={getEnv:fse,setEnv:bw,initialize:xw,createBrowserEnv:mw,createFileSystem:Tf,createNodejsEnv:fw,monkeyPatch:gse,isBrowser:gw,isNodejs:yw.isNodejs};xw();function xs(e){return!st.isNodejs()&&typeof e=="string"?document.getElementById(e):e}function bn(e){let{Canvas:t,CanvasRenderingContext2D:n}=st.getEnv();if(e instanceof n)return e;let a=xs(e);if(!(a instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let r=a.getContext("2d");if(!r)throw new Error("resolveContext2d - canvas 2d context is null");return r}var cr;(function(e){e.TOP_LEFT="TOP_LEFT",e.TOP_RIGHT="TOP_RIGHT",e.BOTTOM_LEFT="BOTTOM_LEFT",e.BOTTOM_RIGHT="BOTTOM_RIGHT"})(cr||(cr={}));var Lp=class{constructor(t={}){let{anchorPosition:n,backgroundColor:a,fontColor:r,fontSize:s,fontStyle:i,padding:o}=t;this.anchorPosition=n||cr.TOP_LEFT,this.backgroundColor=a||"rgba(0, 0, 0, 0.5)",this.fontColor=r||"rgba(255, 255, 255, 1)",this.fontSize=s||14,this.fontStyle=i||"Georgia",this.padding=o||4}},vs=class{constructor(t,n,a={}){this.text=typeof t=="string"?[t]:t instanceof vs?t.text:t,this.anchor=n,this.options=new Lp(a)}measureWidth(t){let{padding:n}=this.options;return this.text.map(a=>t.measureText(a).width).reduce((a,r)=>a{let m=l+p.x,f=l+p.y+(h+1)*i;a.fillText(d,m,f)})}};var vw=class{constructor(t={}){let{boxColor:n,lineWidth:a,label:r,drawLabelOptions:s}=t;this.boxColor=n||"rgba(0, 0, 255, 1)",this.lineWidth=a||2,this.label=r;let i={anchorPosition:cr.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Lp({...i,...s})}},Sf=class{constructor(t,n={}){this.box=new lt(t),this.options=new vw(n)}draw(t){let n=bn(t),{boxColor:a,lineWidth:r}=this.options,{x:s,y:i,width:o,height:l}=this.box;n.strokeStyle=a,n.lineWidth=r,n.strokeRect(s,i,o,l);let{label:c}=this.options;c&&new vs([c],{x:s-r/2,y:i},this.options.drawLabelOptions).draw(t)}};function yse(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof bt?a.score:Wa(a)?a.detection.score:void 0,s=a instanceof bt?a.box:Wa(a)?a.detection.box:new lt(a),i=r?`${to(r)}`:void 0;new Sf(s,{label:i}).draw(e)})}function $u(e){let{Image:t,Video:n}=st.getEnv();return e instanceof t&&e.complete||e instanceof n&&e.readyState>=3}function Cf(e){return new Promise((t,n)=>{if(e instanceof st.getEnv().Canvas||$u(e))return t(null);function a(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),n(s))}function r(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),t(s))}e.addEventListener("load",r),e.addEventListener("error",a)})}function _f(e){return new Promise((t,n)=>{e instanceof Blob||n(new Error("bufferToImage - expected buf to be of type: Blob"));let a=new FileReader;a.onload=()=>{typeof a.result!="string"&&n(new Error("bufferToImage - expected reader.result to be a string, in onload"));let r=st.getEnv().createImageElement();r.onload=()=>t(r),r.onerror=n,r.src=a.result},a.onerror=n,a.readAsDataURL(e)})}function ws(e){let{Image:t,Video:n}=st.getEnv();return e instanceof t?new un(e.naturalWidth,e.naturalHeight):e instanceof n?new un(e.videoWidth,e.videoHeight):new un(e.width,e.height)}function io({width:e,height:t}){let{createCanvasElement:n}=st.getEnv(),a=n();return a.width=e,a.height=t,a}function Du(e,t){let{ImageData:n}=st.getEnv();if(!(e instanceof n)&&!$u(e))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:a,height:r}=t||ws(e),s=io({width:a,height:r});return e instanceof n?bn(s).putImageData(e,0,0):bn(s).drawImage(e,0,0,a,r),s}async function Ef(e,t){let n=t||st.getEnv().createCanvasElement(),[a,r,s]=e.shape.slice(ra(e)?1:0),i=D(()=>e.as3D(a,r,s).toInt());return await Ai.toPixels(i,n),i.dispose(),n}function zp(e){let{Image:t,Canvas:n,Video:a}=st.getEnv();return e instanceof t||e instanceof n||e instanceof a}function Af(e,t,n=!1){let{Image:a,Canvas:r}=st.getEnv();if(!(e instanceof a||e instanceof r))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let s=ws(e),i=t/Math.max(s.height,s.width),o=i*s.width,l=i*s.height,c=io({width:t,height:t}),u=e instanceof r?e:Du(e),p=Math.abs(o-l)/2,d=n&&o{if($r(a)){this._imageTensors[r]=a,this._inputDimensions[r]=a.shape;return}if(ra(a)){let i=a.shape[0];if(i!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${i} passed, but not supported in input array`);this._imageTensors[r]=a,this._inputDimensions[r]=a.shape.slice(1);return}let s=a instanceof st.getEnv().Canvas?a:Du(a);this._canvases[r]=s,this._inputDimensions[r]=[s.height,s.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return lr(this.batchSize,0,1).map((t,n)=>this.getReshapedInputDimensions(n))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let n=this.getInputWidth(t),a=this.getInputHeight(t);return pw({width:n,height:a},this.inputSize)}toBatchTensor(t,n=!0){return this._inputSize=t,D(()=>{let a=lr(this.batchSize,0,1).map(s=>{let i=this.getInput(s);if(i instanceof z){let o=ra(i)?i:i.expandDims();return o=Nf(o,n),(o.shape[1]!==t||o.shape[2]!==t)&&(o=Qa.resizeBilinear(o,[t,t])),o.as3D(t,t,3)}if(i instanceof st.getEnv().Canvas)return Ai.fromPixels(Af(i,t,n));throw new Error(`toBatchTensor - at batchIdx ${s}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${i}`)});return Dt(a.map(s=>pe(s,"float32"))).as4D(this.batchSize,t,t,3)})}};async function yt(e){if(e instanceof pr)return e;let t=Array.isArray(e)?e:[e];if(!t.length)throw new Error("toNetInput - empty array passed as input");let n=r=>Array.isArray(e)?` at input index ${r}:`:"",a=t.map(xs);return a.forEach((r,s)=>{if(!zp(r)&&!$r(r)&&!ra(r))throw typeof t[s]=="string"?new Error(`toNetInput -${n(s)} string passed, but could not resolve HTMLElement for element id ${t[s]}`):new Error(`toNetInput -${n(s)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(ra(r)){let i=r.shape[0];if(i!==1)throw new Error(`toNetInput -${n(s)} tf.Tensor4D with batchSize ${i} passed, but not supported in input array`)}}),await Promise.all(a.map(r=>zp(r)&&Cf(r))),new pr(a,Array.isArray(e))}async function oo(e,t){let{Canvas:n}=st.getEnv(),a=e;if(!(e instanceof n)){let i=await yt(e);if(i.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let o=i.getInput(0);a=o instanceof n?o:await Ef(o)}let r=bn(a);return t.map(i=>i instanceof bt?i.forSize(a.width,a.height).box.floor():i).map(i=>i.clipAtImageBorders(a.width,a.height)).map(({x:i,y:o,width:l,height:c})=>{let u=io({width:l,height:c});return bn(u).putImageData(r.getImageData(i,o,l,c),0,0),u})}async function lo(e,t){if(!$r(e)&&!ra(e))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(ra(e)&&e.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return D(()=>{let[n,a,r]=e.shape.slice(ra(e)?1:0);return t.map(o=>o instanceof bt?o.forSize(a,n).box:o).map(o=>o.clipAtImageBorders(a,n)).map(({x:o,y:l,width:c,height:u})=>Ql(e.as3D(n,a,r),[l,o,0],[u,c,r]))})}async function ks(e,t){let{fetch:n}=st.getEnv(),a=await n(e,t);if(!(a.status<400))throw new Error(`failed to fetch: (${a.status}) ${a.statusText}, from url: ${a.url}`);return a}async function mC(e){let t=await ks(e),n=await t.blob();if(!n.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${n.type}, for url: ${t.url}`);return _f(n)}async function Ff(e){return(await ks(e)).json()}async function fC(e){return new Float32Array(await(await ks(e)).arrayBuffer())}function $f(e,t){let n=`${t}-weights_manifest.json`;if(!e)return{modelBaseUri:"",manifestUri:n};if(e==="/")return{modelBaseUri:"/",manifestUri:`/${n}`};let a=e.startsWith("http://")?"http://":e.startsWith("https://")?"https://":"";e=e.replace(a,"");let r=e.split("/").filter(o=>o),s=e.endsWith(".json")?r[r.length-1]:n,i=a+(e.endsWith(".json")?r.slice(0,r.length-1):r).join("/");return i=e.startsWith("/")?`/${i}`:i,{modelBaseUri:i,manifestUri:i==="/"?`/${s}`:`${i}/${s}`}}async function Df(e,t){let{manifestUri:n,modelBaseUri:a}=$f(e,t),r=await Ff(n);return qt.loadWeights(r,a)}function gC(e,t,n=!1){let{width:a,height:r}=n?ws(t):t;return e.width=a,e.height=r,{width:a,height:r}}var tn=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:n,objProp:a}=this.traversePropertyPath(t);return n[a]}reassignParamFromPath(t,n){let{obj:a,objProp:r}=this.traversePropertyPath(t);a[r].dispose(),a[r]=n}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof Xr)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof Xr))}variable(){this.getFrozenParams().forEach(({path:t,tensor:n})=>{this.reassignParamFromPath(t,n.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:n})=>{let a=Xn(n.dataSync());n.dispose(),this.reassignParamFromPath(t,a)})}dispose(t=!0){this.getParamList().forEach(n=>{if(t&&n.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${n.path}`);n.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,n)=>t.concat(n)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let n=await Df(t,this.getDefaultModelName());this.loadFromWeightMap(n)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:n}=st.getEnv(),{manifestUri:a,modelBaseUri:r}=$f(t,this.getDefaultModelName()),s=c=>Promise.all(c.map(u=>n(u).then(p=>p.buffer))),i=qt.weightsLoaderFactory(s),o=JSON.parse((await n(a)).toString()),l=await i(o,r);this.loadFromWeightMap(l)}loadFromWeightMap(t){let{paramMappings:n,params:a}=this.extractParamsFromWeightMap(t);this._paramMappings=n,this._params=a}extractWeights(t){let{paramMappings:n,params:a}=this.extractParams(t);this._paramMappings=n,this._params=a}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let n=t.split("/").reduce((s,i)=>{if(!s.nextObj.hasOwnProperty(i))throw new Error(`traversePropertyPath - object does not have property ${i}, for path ${t}`);return{obj:s.nextObj,objProp:i,nextObj:s.nextObj[i]}},{nextObj:this.params}),{obj:a,objProp:r}=n;if(!a||!r||!(a[r]instanceof z))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:a,objProp:r}}};function _n(e,t,n){return D(()=>{let a=Pi(e,t.depthwise_filter,t.pointwise_filter,n,"same");return a=Z(a,t.bias),a})}function Mf(e,t,n=!1){return D(()=>{let a=Ye(n?Z(Ft(e,t.conv0.filters,[2,2],"same"),t.conv0.bias):_n(e,t.conv0,[2,2])),r=_n(a,t.conv1,[1,1]),s=Ye(Z(a,r)),i=_n(s,t.conv2,[1,1]);return Ye(Z(a,Z(r,i)))})}function Bp(e,t,n=!1,a=!0){return D(()=>{let r=Ye(n?Z(Ft(e,t.conv0.filters,a?[2,2]:[1,1],"same"),t.conv0.bias):_n(e,t.conv0,a?[2,2]:[1,1])),s=_n(r,t.conv1,[1,1]),i=Ye(Z(r,s)),o=_n(i,t.conv2,[1,1]),l=Ye(Z(r,Z(s,o))),c=_n(l,t.conv3,[1,1]);return Ye(Z(r,Z(s,Z(o,c))))})}function uo(e,t,n="same",a=!1){return D(()=>{let r=Z(Ft(e,t.filters,[1,1],n),t.bias);return a?Ye(r):r})}function xn(e,t){Object.keys(e).forEach(n=>{t.some(a=>a.originalPath===n)||e[n].dispose()})}function Mu(e,t){return(n,a,r,s)=>{let i=Aa(e(n*a*r*r),[r,r,n,a]),o=nt(e(a));return t.push({paramPath:`${s}/filters`},{paramPath:`${s}/bias`}),{filters:i,bias:o}}}function Rf(e,t){return(n,a,r)=>{let s=Ea(e(n*a),[n,a]),i=nt(e(a));return t.push({paramPath:`${r}/weights`},{paramPath:`${r}/bias`}),{weights:s,bias:i}}}var Pf=class{constructor(t,n,a){this.depthwise_filter=t;this.pointwise_filter=n;this.bias=a}};function Ru(e,t){return(n,a,r)=>{let s=Aa(e(3*3*n),[3,3,n,1]),i=Aa(e(n*a),[1,1,n,a]),o=nt(e(a));return t.push({paramPath:`${r}/depthwise_filter`},{paramPath:`${r}/pointwise_filter`},{paramPath:`${r}/bias`}),new Pf(s,i,o)}}function Pu(e){return t=>{let n=e(`${t}/depthwise_filter`,4),a=e(`${t}/pointwise_filter`,4),r=e(`${t}/bias`,1);return new Pf(n,a,r)}}function Hn(e,t){return(n,a,r)=>{let s=e[n];if(!eo(s,a))throw new Error(`expected weightMap[${n}] to be a Tensor${a}D, instead have ${s}`);return t.push({originalPath:n,paramPath:r||n}),s}}function vn(e){let t=e;function n(r){let s=t.slice(0,r);return t=t.slice(r),s}function a(){return t}return{extractWeights:n,getRemainingWeights:a}}function Of(e,t){let n=Mu(e,t),a=Ru(e,t);function r(i,o,l,c=!1){let u=c?n(i,o,3,`${l}/conv0`):a(i,o,`${l}/conv0`),p=a(o,o,`${l}/conv1`),d=a(o,o,`${l}/conv2`);return{conv0:u,conv1:p,conv2:d}}function s(i,o,l,c=!1){let{conv0:u,conv1:p,conv2:d}=r(i,o,l,c),h=a(o,o,`${l}/conv3`);return{conv0:u,conv1:p,conv2:d,conv3:h}}return{extractDenseBlock3Params:r,extractDenseBlock4Params:s}}function yC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),{extractDenseBlock4Params:r}=Of(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2"),l=r(128,256,"dense3");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o,dense3:l}}}function Lf(e){return t=>{let n=e(`${t}/filters`,4),a=e(`${t}/bias`,1);return{filters:n,bias:a}}}function zf(e,t){let n=Hn(e,t),a=Lf(n),r=Pu(n);function s(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`);return{conv0:c,conv1:u,conv2:p}}function i(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`),d=r(`${o}/conv3`);return{conv0:c,conv1:u,conv2:p,conv3:d}}return{extractDenseBlock3Params:s,extractDenseBlock4Params:i}}function bC(e){let t=[],{extractDenseBlock4Params:n}=zf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2"),dense3:n("dense3")};return xn(e,t),{params:a,paramMappings:t}}var Wp=class extends tn{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(255)),i=Bp(s,n.dense0,!0);return i=Bp(i,n.dense1),i=Bp(i,n.dense2),i=Bp(i,n.dense3),i=Jn(i,[7,7],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return bC(t)}extractParams(t){return yC(t)}};function Vp(e,t){return D(()=>Z(ze(e,t.weights),t.bias))}function xC(e,t,n){let a=[],{extractWeights:r,getRemainingWeights:s}=vn(e),o=Rf(r,a)(t,n,"fc");if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{paramMappings:a,params:{fc:o}}}function vC(e){let t=[],n=Hn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:a("fc")};return xn(e,t),{params:r,paramMappings:t}}function Bf(e){let t={},n={};return Object.keys(e).forEach(a=>{let r=a.startsWith("fc")?n:t;r[a]=e[a]}),{featureExtractorMap:t,classifierMap:n}}var Up=class extends tn{constructor(t,n){super(t);this._faceFeatureExtractor=n}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof pr?this.faceFeatureExtractor.forwardInput(t):t;return Vp(a.as2D(a.shape[0],-1),n.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return xC(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=Bf(t);return this.faceFeatureExtractor.loadFromWeightMap(n),vC(a)}extractParams(t){let n=this.getClassifierChannelsIn(),a=this.getClassifierChannelsOut(),r=a*n+a,s=t.slice(0,t.length-r),i=t.slice(t.length-r);return this.faceFeatureExtractor.extractWeights(s),this.extractClassifierParams(i)}};var Wf=["neutral","happy","sad","angry","fearful","disgusted","surprised"],Mr=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Wf.forEach((n,a)=>{this[n]=t[a]})}asSortedArray(){return Wf.map(t=>({expression:t,probability:this[t]})).sort((t,n)=>n.probability-t.probability)}};var Gp=class extends Up{constructor(t=new Wp){super("FaceExpressionNet",t)}forwardInput(t){return D(()=>_a(this.runNet(t)))}async forward(t){return this.forwardInput(await yt(t))}async predictExpressions(t){let n=await yt(t),a=await this.forwardInput(n),r=await Promise.all(ht(a).map(async i=>{let o=await i.data();return i.dispose(),o}));a.dispose();let s=r.map(i=>new Mr(i));return n.isBatchInput?s:s[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function Vf(e){return e.expressions instanceof Mr}function Hp(e,t){return{...e,...{expressions:t}}}function bse(e,t,n=.1,a){(Array.isArray(t)?t:[t]).forEach(s=>{let i=s instanceof Mr?s:Vf(s)?s.expressions:void 0;if(!i)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let l=i.asSortedArray().filter(p=>p.probability>n),c=Wa(s)?s.detection.box.bottomLeft:a||new De(0,0);new vs(l.map(p=>`${p.expression} (${to(p.probability)})`),c).draw(e)})}function Is(e){return Wa(e)&&e.landmarks instanceof Gn&&e.unshiftedLandmarks instanceof Gn&&e.alignedRect instanceof bt}function co(e,t){let{box:n}=e.detection,a=t.shiftBy(n.x,n.y),r=a.align(),{imageDims:s}=e.detection,i=new bt(e.detection.score,r.rescale(s.reverse()),s);return{...e,...{landmarks:a,unshiftedLandmarks:t,alignedRect:i}}}var ww=class{constructor(t={}){let{drawLines:n=!0,drawPoints:a=!0,lineWidth:r,lineColor:s,pointSize:i,pointColor:o}=t;this.drawLines=n,this.drawPoints=a,this.lineWidth=r||1,this.pointSize=i||2,this.lineColor=s||"rgba(0, 255, 255, 1)",this.pointColor=o||"rgba(255, 0, 255, 1)"}},kw=class{constructor(t,n={}){this.faceLandmarks=t,this.options=new ww(n)}draw(t){let n=bn(t),{drawLines:a,drawPoints:r,lineWidth:s,lineColor:i,pointSize:o,pointColor:l}=this.options;if(a&&this.faceLandmarks instanceof so&&(n.strokeStyle=i,n.lineWidth=s,Fr(n,this.faceLandmarks.getJawOutline()),Fr(n,this.faceLandmarks.getLeftEyeBrow()),Fr(n,this.faceLandmarks.getRightEyeBrow()),Fr(n,this.faceLandmarks.getNose()),Fr(n,this.faceLandmarks.getLeftEye(),!0),Fr(n,this.faceLandmarks.getRightEye(),!0),Fr(n,this.faceLandmarks.getMouth(),!0)),r){n.strokeStyle=l,n.fillStyle=l;let c=u=>{n.beginPath(),n.arc(u.x,u.y,o,0,2*Math.PI),n.fill()};this.faceLandmarks.positions.forEach(c)}}};function xse(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof Gn?a:Is(a)?a.landmarks:void 0;if(!r)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new kw(r).draw(e)})}var wC="0.11.5";function vse(e,t){let n=Mu(e,t),a=Ru(e,t);function r(i,o,l){let c=a(i,o,`${l}/separable_conv0`),u=a(o,o,`${l}/separable_conv1`),p=n(i,o,1,`${l}/expansion_conv`);return{separable_conv0:c,separable_conv1:u,expansion_conv:p}}function s(i,o){let l=a(i,i,`${o}/separable_conv0`),c=a(i,i,`${o}/separable_conv1`),u=a(i,i,`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:n,extractSeparableConvParams:a,extractReductionBlockParams:r,extractMainBlockParams:s}}function kC(e,t){let n=[],{extractWeights:a,getRemainingWeights:r}=vn(e),{extractConvParams:s,extractSeparableConvParams:i,extractReductionBlockParams:o,extractMainBlockParams:l}=vse(a,n),c=s(3,32,3,"entry_flow/conv_in"),u=o(32,64,"entry_flow/reduction_block_0"),p=o(64,128,"entry_flow/reduction_block_1"),d={conv_in:c,reduction_block_0:u,reduction_block_1:p},h={};lr(t,0,1).forEach(y=>{h[`main_block_${y}`]=l(128,`middle_flow/main_block_${y}`)});let m=o(128,256,"exit_flow/reduction_block"),f=i(256,512,"exit_flow/separable_conv"),g={reduction_block:m,separable_conv:f};if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:n,params:{entry_flow:d,middle_flow:h,exit_flow:g}}}function wse(e,t){let n=Hn(e,t),a=Lf(n),r=Pu(n);function s(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=a(`${o}/expansion_conv`);return{separable_conv0:l,separable_conv1:c,expansion_conv:u}}function i(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=r(`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}}function IC(e,t){let n=[],{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}=wse(e,n),o=a("entry_flow/conv_in"),l=s("entry_flow/reduction_block_0"),c=s("entry_flow/reduction_block_1"),u={conv_in:o,reduction_block_0:l,reduction_block_1:c},p={};lr(t,0,1).forEach(f=>{p[`main_block_${f}`]=i(`middle_flow/main_block_${f}`)});let d=s("exit_flow/reduction_block"),h=r("exit_flow/separable_conv"),m={reduction_block:d,separable_conv:h};return xn(e,n),{params:{entry_flow:u,middle_flow:p,exit_flow:m},paramMappings:n}}function NC(e,t,n){return Z(Ft(e,t.filters,n,"same"),t.bias)}function Iw(e,t,n=!0){let a=n?Ye(e):e;return a=_n(a,t.separable_conv0,[1,1]),a=_n(Ye(a),t.separable_conv1,[1,1]),a=$t(a,[3,3],[2,2],"same"),a=Z(a,NC(e,t.expansion_conv,[2,2])),a}function kse(e,t){let n=_n(Ye(e),t.separable_conv0,[1,1]);return n=_n(Ye(n),t.separable_conv1,[1,1]),n=_n(Ye(n),t.separable_conv2,[1,1]),n=Z(n,e),n}var Nw=class extends tn{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyXception - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(256)),i=Ye(NC(s,n.entry_flow.conv_in,[2,2]));return i=Iw(i,n.entry_flow.reduction_block_0,!1),i=Iw(i,n.entry_flow.reduction_block_1),lr(this._numMainBlocks,0,1).forEach(o=>{i=kse(i,n.middle_flow[`main_block_${o}`])}),i=Iw(i,n.exit_flow.reduction_block),i=Ye(_n(i,n.exit_flow.separable_conv,[1,1])),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return IC(t,this._numMainBlocks)}extractParams(t){return kC(t,this._numMainBlocks)}};function TC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),r=Rf(n,t),s=r(512,1,"fc/age"),i=r(512,2,"fc/gender");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{fc:{age:s,gender:i}}}}function SC(e){let t=[],n=Hn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:{age:a("fc/age"),gender:a("fc/gender")}};return xn(e,t),{params:r,paramMappings:t}}var dr;(function(e){e.FEMALE="female",e.MALE="male"})(dr||(dr={}));var jp=class extends tn{constructor(t=new Nw(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof pr?this.faceFeatureExtractor.forwardInput(t):t,r=Jn(a,[7,7],[2,2],"valid").as2D(a.shape[0],-1),s=Vp(r,n.fc.age).as1D(),i=Vp(r,n.fc.gender);return{age:s,gender:i}})}forwardInput(t){return D(()=>{let{age:n,gender:a}=this.runNet(t);return{age:n,gender:_a(a)}})}async forward(t){return this.forwardInput(await yt(t))}async predictAgeAndGender(t){let n=await yt(t),a=await this.forwardInput(n),r=ht(a.age),s=ht(a.gender),i=r.map((l,c)=>({ageTensor:l,genderTensor:s[c]})),o=await Promise.all(i.map(async({ageTensor:l,genderTensor:c})=>{let u=(await l.data())[0],p=(await c.data())[0],d=p>.5,h=d?dr.MALE:dr.FEMALE,m=d?p:1-p;return l.dispose(),c.dispose(),{age:u,gender:h,genderProbability:m}}));return a.age.dispose(),a.gender.dispose(),n.isBatchInput?o:o[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return TC(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=Bf(t);return this.faceFeatureExtractor.loadFromWeightMap(n),SC(a)}extractParams(t){let n=512*1+1+(512*2+2),a=t.slice(0,t.length-n),r=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(r)}};var qp=class extends Up{postProcess(t,n,a){let r=a.map(({width:i,height:o})=>{let l=n/Math.max(o,i);return{width:i*l,height:o*l}}),s=r.length;return D(()=>{let i=(p,d)=>Dt([In([68],p,"float32"),In([68],d,"float32")],1).as2D(1,136).as1D(),o=(p,d)=>{let{width:h,height:m}=r[p];return d(h,m)?Math.abs(h-m)/2:0},l=p=>o(p,(d,h)=>do(p,(d,h)=>hi(l(d),c(d))))).div(Dt(Array.from(Array(s),(p,d)=>i(r[d].width,r[d].height))))})}forwardInput(t){return D(()=>{let n=this.runNet(t);return this.postProcess(n,t.inputSize,t.inputDimensions.map(([a,r])=>({height:a,width:r})))})}async forward(t){return this.forwardInput(await yt(t))}async detectLandmarks(t){let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(async(s,i)=>{let o=Array.from(await s.data()),l=o.filter((u,p)=>xf(p)),c=o.filter((u,p)=>!xf(p));return new so(Array(68).fill(0).map((u,p)=>new De(l[p],c[p])),{height:n.getInputHeight(i),width:n.getInputWidth(i)})}));return a.forEach(s=>s.dispose()),n.isBatchInput?r:r[0]}getClassifierChannelsOut(){return 136}};var po=class extends qp{constructor(t=new Wp){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};function CC(e){let t=[],{extractDenseBlock3Params:n}=zf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2")};return xn(e,t),{params:a,paramMappings:t}}function _C(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),{extractDenseBlock3Params:r}=Of(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o}}}var Tw=class extends tn{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyFaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(255)),i=Mf(s,n.dense0,!0);return i=Mf(i,n.dense1),i=Mf(i,n.dense2),i=Jn(i,[14,14],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return CC(t)}extractParams(t){return _C(t)}};var Kp=class extends qp{constructor(t=new Tw){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Sw=class extends po{};function EC(e,t){return Z(L(e,t.weights),t.biases)}function Cw(e,t,n,a,r="same"){let{filters:s,bias:i}=t.conv,o=Ft(e,s,n,r);return o=Z(o,i),o=EC(o,t.scale),a?Ye(o):o}function AC(e,t){return Cw(e,t,[1,1],!0)}function _w(e,t){return Cw(e,t,[1,1],!1)}function Gf(e,t){return Cw(e,t,[2,2],!0,"valid")}function Ise(e,t){function n(o,l,c){let u=e(o),p=u.length/(l*c*c);if(cw(p))throw new Error(`depth has to be an integer: ${p}, weights.length: ${u.length}, numFilters: ${l}, filterSize: ${c}`);return D(()=>Ue(Aa(u,[l,p,c,c]),[2,3,1,0]))}function a(o,l,c,u){let p=n(o,l,c),d=nt(e(l));return t.push({paramPath:`${u}/filters`},{paramPath:`${u}/bias`}),{filters:p,bias:d}}function r(o,l){let c=nt(e(o)),u=nt(e(o));return t.push({paramPath:`${l}/weights`},{paramPath:`${l}/biases`}),{weights:c,biases:u}}function s(o,l,c,u){let p=a(o,l,c,`${u}/conv`),d=r(l,`${u}/scale`);return{conv:p,scale:d}}function i(o,l,c,u,p=!1){let d=s((p?.5:1)*o,l,c,`${u}/conv1`),h=s(o,l,c,`${u}/conv2`);return{conv1:d,conv2:h}}return{extractConvLayerParams:s,extractResidualLayerParams:i}}function FC(e){let{extractWeights:t,getRemainingWeights:n}=vn(e),a=[],{extractConvLayerParams:r,extractResidualLayerParams:s}=Ise(t,a),i=r(4704,32,7,"conv32_down"),o=s(9216,32,3,"conv32_1"),l=s(9216,32,3,"conv32_2"),c=s(9216,32,3,"conv32_3"),u=s(36864,64,3,"conv64_down",!0),p=s(36864,64,3,"conv64_1"),d=s(36864,64,3,"conv64_2"),h=s(36864,64,3,"conv64_3"),m=s(147456,128,3,"conv128_down",!0),f=s(147456,128,3,"conv128_1"),g=s(147456,128,3,"conv128_2"),y=s(589824,256,3,"conv256_down",!0),b=s(589824,256,3,"conv256_1"),v=s(589824,256,3,"conv256_2"),x=s(589824,256,3,"conv256_down_out"),N=D(()=>Ue(Ea(t(256*128),[128,256]),[1,0]));if(a.push({paramPath:"fc"}),n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{params:{conv32_down:i,conv32_1:o,conv32_2:l,conv32_3:c,conv64_down:u,conv64_1:p,conv64_2:d,conv64_3:h,conv128_down:m,conv128_1:f,conv128_2:g,conv256_down:y,conv256_1:b,conv256_2:v,conv256_down_out:x,fc:N},paramMappings:a}}function Nse(e,t){let n=Hn(e,t);function a(i){let o=n(`${i}/scale/weights`,1),l=n(`${i}/scale/biases`,1);return{weights:o,biases:l}}function r(i){let o=n(`${i}/conv/filters`,4),l=n(`${i}/conv/bias`,1),c=a(i);return{conv:{filters:o,bias:l},scale:c}}function s(i){return{conv1:r(`${i}/conv1`),conv2:r(`${i}/conv2`)}}return{extractConvLayerParams:r,extractResidualLayerParams:s}}function $C(e){let t=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=Nse(e,t),r=n("conv32_down"),s=a("conv32_1"),i=a("conv32_2"),o=a("conv32_3"),l=a("conv64_down"),c=a("conv64_1"),u=a("conv64_2"),p=a("conv64_3"),d=a("conv128_down"),h=a("conv128_1"),m=a("conv128_2"),f=a("conv256_down"),g=a("conv256_1"),y=a("conv256_2"),b=a("conv256_down_out"),{fc:v}=e;if(t.push({originalPath:"fc",paramPath:"fc"}),!uw(v))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${v}`);let x={conv32_down:r,conv32_1:s,conv32_2:i,conv32_3:o,conv64_down:l,conv64_1:c,conv64_2:u,conv64_3:p,conv128_down:d,conv128_1:h,conv128_2:m,conv256_down:f,conv256_1:g,conv256_2:y,conv256_down_out:b,fc:v};return xn(e,t),{params:x,paramMappings:t}}function Va(e,t){let n=AC(e,t.conv1);return n=_w(n,t.conv2),n=Z(n,e),n=Ye(n),n}function Xp(e,t){let n=Gf(e,t.conv1);n=_w(n,t.conv2);let a=Jn(e,2,2,"valid"),r=xt(a.shape),s=a.shape[3]!==n.shape[3];if(a.shape[1]!==n.shape[1]||a.shape[2]!==n.shape[2]){let o=[...n.shape];o[1]=1;let l=xt(o);n=Qe([n,l],1);let c=[...n.shape];c[2]=1;let u=xt(c);n=Qe([n,u],2)}return a=s?Qe([a,r],3):a,n=Z(a,n),n=Ye(n),n}var ho=class extends tn{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceRecognitionNet - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(150,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(256)),i=Gf(s,n.conv32_down);i=$t(i,3,2,"valid"),i=Va(i,n.conv32_1),i=Va(i,n.conv32_2),i=Va(i,n.conv32_3),i=Xp(i,n.conv64_down),i=Va(i,n.conv64_1),i=Va(i,n.conv64_2),i=Va(i,n.conv64_3),i=Xp(i,n.conv128_down),i=Va(i,n.conv128_1),i=Va(i,n.conv128_2),i=Xp(i,n.conv256_down),i=Va(i,n.conv256_1),i=Va(i,n.conv256_2),i=Xp(i,n.conv256_down_out);let o=i.mean([1,2]);return ze(o,n.fc)})}async forward(t){return this.forwardInput(await yt(t))}async computeFaceDescriptor(t){var s;if((s=t==null?void 0:t.shape)==null?void 0:s.some(i=>i<=0))return new Float32Array(128);let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(i=>i.data()));return a.forEach(i=>i.dispose()),n.isBatchInput?r:r[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return $C(t)}extractParams(t){return FC(t)}};function DC(e){let t=new ho;return t.extractWeights(e),t}function Yp(e,t){return{...e,...{descriptor:t}}}function MC(e){return typeof e.age=="number"}function Jp(e,t){return{...e,...{age:t}}}function RC(e){return(e.gender===dr.MALE||e.gender===dr.FEMALE)&&_u(e.genderProbability)}function Zp(e,t,n){return{...e,...{gender:t,genderProbability:n}}}function Tse(e,t){function n(l,c){let u=Aa(e(3*3*l),[3,3,l,1]),p=nt(e(l)),d=nt(e(l)),h=nt(e(l)),m=nt(e(l));return t.push({paramPath:`${c}/filters`},{paramPath:`${c}/batch_norm_scale`},{paramPath:`${c}/batch_norm_offset`},{paramPath:`${c}/batch_norm_mean`},{paramPath:`${c}/batch_norm_variance`}),{filters:u,batch_norm_scale:p,batch_norm_offset:d,batch_norm_mean:h,batch_norm_variance:m}}function a(l,c,u,p,d){let h=Aa(e(l*c*u*u),[u,u,l,c]),m=nt(e(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/${d?"batch_norm_offset":"bias"}`}),{filters:h,bias:m}}function r(l,c,u,p){let{filters:d,bias:h}=a(l,c,u,p,!0);return{filters:d,batch_norm_offset:h}}function s(l,c,u){let p=n(l,`${u}/depthwise_conv`),d=r(l,c,1,`${u}/pointwise_conv`);return{depthwise_conv:p,pointwise_conv:d}}function i(){let l=r(3,32,3,"mobilenetv1/conv_0"),c=s(32,64,"mobilenetv1/conv_1"),u=s(64,128,"mobilenetv1/conv_2"),p=s(128,128,"mobilenetv1/conv_3"),d=s(128,256,"mobilenetv1/conv_4"),h=s(256,256,"mobilenetv1/conv_5"),m=s(256,512,"mobilenetv1/conv_6"),f=s(512,512,"mobilenetv1/conv_7"),g=s(512,512,"mobilenetv1/conv_8"),y=s(512,512,"mobilenetv1/conv_9"),b=s(512,512,"mobilenetv1/conv_10"),v=s(512,512,"mobilenetv1/conv_11"),x=s(512,1024,"mobilenetv1/conv_12"),N=s(1024,1024,"mobilenetv1/conv_13");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,conv_8:g,conv_9:y,conv_10:b,conv_11:v,conv_12:x,conv_13:N}}function o(){let l=r(1024,256,1,"prediction_layer/conv_0"),c=r(256,512,3,"prediction_layer/conv_1"),u=r(512,128,1,"prediction_layer/conv_2"),p=r(128,256,3,"prediction_layer/conv_3"),d=r(256,128,1,"prediction_layer/conv_4"),h=r(128,256,3,"prediction_layer/conv_5"),m=r(256,64,1,"prediction_layer/conv_6"),f=r(64,128,3,"prediction_layer/conv_7"),g=a(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=a(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),b=a(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),v=a(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),x=a(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),N=a(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),T=a(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),C=a(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),$=a(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),F=a(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),O=a(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),W=a(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,box_predictor_0:{box_encoding_predictor:g,class_predictor:y},box_predictor_1:{box_encoding_predictor:b,class_predictor:v},box_predictor_2:{box_encoding_predictor:x,class_predictor:N},box_predictor_3:{box_encoding_predictor:T,class_predictor:C},box_predictor_4:{box_encoding_predictor:$,class_predictor:F},box_predictor_5:{box_encoding_predictor:O,class_predictor:W}}}return{extractMobilenetV1Params:i,extractPredictionLayerParams:o}}function PC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),{extractMobilenetV1Params:r,extractPredictionLayerParams:s}=Tse(n,t),i=r(),o=s(),c={extra_dim:kh(n(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:{mobilenetv1:i,prediction_layer:o,output_layer:c},paramMappings:t}}function Sse(e,t){let n=Hn(e,t);function a(c,u,p){let d=n(`${c}/Conv2d_${u}_pointwise/weights`,4,`${p}/filters`),h=n(`${c}/Conv2d_${u}_pointwise/convolution_bn_offset`,1,`${p}/batch_norm_offset`);return{filters:d,batch_norm_offset:h}}function r(c){let u=`mobilenetv1/conv_${c}`,p=`MobilenetV1/Conv2d_${c}_depthwise`,d=`${u}/depthwise_conv`,h=`${u}/pointwise_conv`,m=n(`${p}/depthwise_weights`,4,`${d}/filters`),f=n(`${p}/BatchNorm/gamma`,1,`${d}/batch_norm_scale`),g=n(`${p}/BatchNorm/beta`,1,`${d}/batch_norm_offset`),y=n(`${p}/BatchNorm/moving_mean`,1,`${d}/batch_norm_mean`),b=n(`${p}/BatchNorm/moving_variance`,1,`${d}/batch_norm_variance`);return{depthwise_conv:{filters:m,batch_norm_scale:f,batch_norm_offset:g,batch_norm_mean:y,batch_norm_variance:b},pointwise_conv:a("MobilenetV1",c,h)}}function s(){return{conv_0:a("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:r(1),conv_2:r(2),conv_3:r(3),conv_4:r(4),conv_5:r(5),conv_6:r(6),conv_7:r(7),conv_8:r(8),conv_9:r(9),conv_10:r(10),conv_11:r(11),conv_12:r(12),conv_13:r(13)}}function i(c,u){let p=n(`${c}/weights`,4,`${u}/filters`),d=n(`${c}/biases`,1,`${u}/bias`);return{filters:p,bias:d}}function o(c){let u=i(`Prediction/BoxPredictor_${c}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${c}/box_encoding_predictor`),p=i(`Prediction/BoxPredictor_${c}/ClassPredictor`,`prediction_layer/box_predictor_${c}/class_predictor`);return{box_encoding_predictor:u,class_predictor:p}}function l(){return{conv_0:a("Prediction",0,"prediction_layer/conv_0"),conv_1:a("Prediction",1,"prediction_layer/conv_1"),conv_2:a("Prediction",2,"prediction_layer/conv_2"),conv_3:a("Prediction",3,"prediction_layer/conv_3"),conv_4:a("Prediction",4,"prediction_layer/conv_4"),conv_5:a("Prediction",5,"prediction_layer/conv_5"),conv_6:a("Prediction",6,"prediction_layer/conv_6"),conv_7:a("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:o(0),box_predictor_1:o(1),box_predictor_2:o(2),box_predictor_3:o(3),box_predictor_4:o(4),box_predictor_5:o(5)}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:l}}function OC(e){let t=[],{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=Sse(e,t),r=e["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!$r(r))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${r}`);let s={mobilenetv1:n(),prediction_layer:a(),output_layer:{extra_dim:r}};return xn(e,t),{params:s,paramMappings:t}}function Ia(e,t,n){return D(()=>{let a=Ft(e,t.filters,n,"same");return a=Z(a,t.batch_norm_offset),Xt(a,0,6)})}var Cse=.0010000000474974513;function _se(e,t,n){return D(()=>{let a=vr(e,t.filters,n,"same");return a=xr(a,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Cse),Xt(a,0,6)})}function Ese(e){return[2,4,6,12].some(t=>t===e)?[2,2]:[1,1]}function LC(e,t){return D(()=>{let n,a=Ia(e,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((s,i)=>{let o=i+1,l=Ese(o);a=_se(a,s.depthwise_conv,l),a=Ia(a,s.pointwise_conv,[1,1]),o===11&&(n=a)}),n===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:a,conv11:n}})}function Ase(e,t,n){let a=e.arraySync(),r=Math.min(a[t][0],a[t][2]),s=Math.min(a[t][1],a[t][3]),i=Math.max(a[t][0],a[t][2]),o=Math.max(a[t][1],a[t][3]),l=Math.min(a[n][0],a[n][2]),c=Math.min(a[n][1],a[n][3]),u=Math.max(a[n][0],a[n][2]),p=Math.max(a[n][1],a[n][3]),d=(i-r)*(o-s),h=(u-l)*(p-c);if(d<=0||h<=0)return 0;let m=Math.max(r,l),f=Math.max(s,c),g=Math.min(i,u),y=Math.min(o,p),b=Math.max(g-m,0)*Math.max(y-f,0);return b/(d+h-b)}function zC(e,t,n,a,r){let s=e.shape[0],i=Math.min(n,s),o=t.map((u,p)=>({score:u,boxIndex:p})).filter(u=>u.score>r).sort((u,p)=>p.score-u.score),l=u=>u<=a?1:0,c=[];return o.forEach(u=>{if(c.length>=i)return;let p=u.score;for(let d=c.length-1;d>=0;--d){let h=Ase(e,u.boxIndex,c[d]);if(h!==0&&(u.score*=l(h),u.score<=r))break}p===u.score&&c.push(u.boxIndex)}),c}function Fse(e){let t=ht(Ue(e,[1,0])),n=[ge(t[2],t[0]),ge(t[3],t[1])],a=[Z(t[0],we(n[0],he(2))),Z(t[1],we(n[1],he(2)))];return{sizes:n,centers:a}}function $se(e,t){let{sizes:n,centers:a}=Fse(e),r=ht(Ue(t,[1,0])),s=we(L(hn(we(r[2],he(5))),n[0]),he(2)),i=Z(L(we(r[0],he(10)),n[0]),a[0]),o=we(L(hn(we(r[3],he(5))),n[1]),he(2)),l=Z(L(we(r[1],he(10)),n[1]),a[1]);return Ue(Dt([ge(i,s),ge(l,o),Z(i,s),Z(l,o)]),[1,0])}function BC(e,t,n){return D(()=>{let a=e.shape[0],r=$se(q(Xa(n.extra_dim,[a,1,1]),[-1,4]),q(e,[-1,4]));r=q(r,[a,r.shape[0]/a,4]);let s=ma(We(t,[0,0,1],[-1,-1,-1])),i=We(s,[0,0,0],[-1,-1,1]);i=q(i,[a,i.shape[1]]);let o=ht(r),l=ht(i);return{boxes:o,scores:l}})}function mo(e,t){return D(()=>{let n=e.shape[0],a=q(uo(e,t.box_encoding_predictor),[n,-1,1,4]),r=q(uo(e,t.class_predictor),[n,-1,3]);return{boxPredictionEncoding:a,classPrediction:r}})}function WC(e,t,n){return D(()=>{let a=Ia(e,n.conv_0,[1,1]),r=Ia(a,n.conv_1,[2,2]),s=Ia(r,n.conv_2,[1,1]),i=Ia(s,n.conv_3,[2,2]),o=Ia(i,n.conv_4,[1,1]),l=Ia(o,n.conv_5,[2,2]),c=Ia(l,n.conv_6,[1,1]),u=Ia(c,n.conv_7,[2,2]),p=mo(t,n.box_predictor_0),d=mo(e,n.box_predictor_1),h=mo(r,n.box_predictor_2),m=mo(i,n.box_predictor_3),f=mo(l,n.box_predictor_4),g=mo(u,n.box_predictor_5),y=Qe([p.boxPredictionEncoding,d.boxPredictionEncoding,h.boxPredictionEncoding,m.boxPredictionEncoding,f.boxPredictionEncoding,g.boxPredictionEncoding],1),b=Qe([p.classPrediction,d.classPrediction,h.classPrediction,m.classPrediction,f.classPrediction,g.classPrediction],1);return{boxPredictions:y,classPredictions:b}})}var sa=class{constructor({minConfidence:t,maxResults:n}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=n||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Ns=class extends tn{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("SsdMobilenetv1 - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(512,!1),"float32"),r=ge(L(a,he(.007843137718737125)),he(1)),s=LC(r,n.mobilenetv1),{boxPredictions:i,classPredictions:o}=WC(s.out,s.conv11,n.prediction_layer);return BC(i,o,n.output_layer)})}async forward(t){return this.forwardInput(await yt(t))}async locateFaces(t,n={}){let{maxResults:a,minConfidence:r}=new sa(n),s=await yt(t),{boxes:i,scores:o}=this.forwardInput(s),l=i[0],c=o[0];for(let v=1;v{let[x,N]=[Math.max(0,y[v][0]),Math.min(1,y[v][2])].map($=>$*g),[T,C]=[Math.max(0,y[v][1]),Math.min(1,y[v][3])].map($=>$*f);return new bt(u[v],new ro(T,x,C-T,N-x),{height:s.getInputHeight(0),width:s.getInputWidth(0)})});return l.dispose(),c.dispose(),b}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return OC(t)}extractParams(t){return PC(t)}};function Ew(e){let t=new Ns;return t.extractWeights(e),t}function VC(e){return Ew(e)}var Aw=class extends Ns{};var UC=.4,GC=[new De(.738768,.874946),new De(2.42204,2.65704),new De(4.30971,7.04493),new De(10.246,4.59428),new De(12.6868,11.8741)],HC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],jC=[117.001,114.697,97.404],qC="tiny_yolov2_model",KC="tiny_yolov2_separable_conv_model";var Hf=e=>typeof e=="number";function jf(e){if(!e)throw new Error(`invalid config: ${e}`);if(typeof e.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${e.withSeparableConvs}`);if(!Hf(e.iouThreshold)||e.iouThreshold<0||e.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${e.iouThreshold}`);if(!Array.isArray(e.classes)||!e.classes.length||!e.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(e.classes)}`);if(!Array.isArray(e.anchors)||!e.anchors.length||!e.anchors.map(t=>t||{}).every(t=>Hf(t.x)&&Hf(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(e.anchors)}`);if(e.meanRgb&&(!Array.isArray(e.meanRgb)||e.meanRgb.length!==3||!e.meanRgb.every(Hf)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(e.meanRgb)}`)}function Ou(e){return D(()=>{let t=L(e,he(.10000000149011612));return Z(Ye(ge(e,t)),t)})}function Rr(e,t){return D(()=>{let n=ta(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Ft(n,t.conv.filters,[1,1],"valid"),n=ge(n,t.bn.sub),n=L(n,t.bn.truediv),n=Z(n,t.conv.bias),Ou(n)})}function Pr(e,t){return D(()=>{let n=ta(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Pi(n,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),n=Z(n,t.bias),Ou(n)})}function Dse(e,t){let n=Mu(e,t);function a(i,o){let l=nt(e(i)),c=nt(e(i));return t.push({paramPath:`${o}/sub`},{paramPath:`${o}/truediv`}),{sub:l,truediv:c}}function r(i,o,l){let c=n(i,o,3,`${l}/conv`),u=a(o,`${l}/bn`);return{conv:c,bn:u}}let s=Ru(e,t);return{extractConvParams:n,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}}function XC(e,t,n,a){let{extractWeights:r,getRemainingWeights:s}=vn(e),i=[],{extractConvParams:o,extractConvWithBatchNormParams:l,extractSeparableConvParams:c}=Dse(r,i),u;if(t.withSeparableConvs){let[p,d,h,m,f,g,y,b,v]=a,x=t.isFirstLayerConv2d?o(p,d,3,"conv0"):c(p,d,"conv0"),N=c(d,h,"conv1"),T=c(h,m,"conv2"),C=c(m,f,"conv3"),$=c(f,g,"conv4"),F=c(g,y,"conv5"),O=b?c(y,b,"conv6"):void 0,W=v?c(b,v,"conv7"):void 0,V=o(v||b||y,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}else{let[p,d,h,m,f,g,y,b,v]=a,x=l(p,d,"conv0"),N=l(d,h,"conv1"),T=l(h,m,"conv2"),C=l(m,f,"conv3"),$=l(f,g,"conv4"),F=l(g,y,"conv5"),O=l(y,b,"conv6"),W=l(b,v,"conv7"),V=o(v,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{params:u,paramMappings:i}}function Mse(e,t){let n=Hn(e,t);function a(o){let l=n(`${o}/sub`,1),c=n(`${o}/truediv`,1);return{sub:l,truediv:c}}function r(o){let l=n(`${o}/filters`,4),c=n(`${o}/bias`,1);return{filters:l,bias:c}}function s(o){let l=r(`${o}/conv`),c=a(`${o}/bn`);return{conv:l,bn:c}}let i=Pu(n);return{extractConvParams:r,extractConvWithBatchNormParams:s,extractSeparableConvParams:i}}function YC(e,t){let n=[],{extractConvParams:a,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}=Mse(e,n),i;if(t.withSeparableConvs){let o=t.filterSizes&&t.filterSizes.length||9;i={conv0:t.isFirstLayerConv2d?a("conv0"):s("conv0"),conv1:s("conv1"),conv2:s("conv2"),conv3:s("conv3"),conv4:s("conv4"),conv5:s("conv5"),conv6:o>7?s("conv6"):void 0,conv7:o>8?s("conv7"):void 0,conv8:a("conv8")}}else i={conv0:r("conv0"),conv1:r("conv1"),conv2:r("conv2"),conv3:r("conv3"),conv4:r("conv4"),conv5:r("conv5"),conv6:r("conv6"),conv7:r("conv7"),conv8:a("conv8")};return xn(e,n),{params:i,paramMappings:n}}var Ua=class{constructor({inputSize:t,scoreThreshold:n}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=n||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var Fw=class extends tn{constructor(t){super("TinyYolov2");jf(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,n){let a=Rr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=Rr(a,n.conv6),a=Rr(a,n.conv7),uo(a,n.conv8,"valid",!1)}runMobilenet(t,n){let a=this.config.isFirstLayerConv2d?Ou(uo(t,n.conv0,"valid",!1)):Pr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=n.conv6?Pr(a,n.conv6):a,a=n.conv7?Pr(a,n.conv7):a,uo(a,n.conv8,"valid",!1)}forwardInput(t,n){let{params:a}=this;if(!a)throw new Error("TinyYolov2 - load model before inference");return D(()=>{let r=pe(t.toBatchTensor(n,!1),"float32");return r=this.config.meanRgb?ka(r,this.config.meanRgb):r,r=r.div(he(256)),this.config.withSeparableConvs?this.runMobilenet(r,a):this.runTinyYolov2(r,a)})}async forward(t,n){return this.forwardInput(await yt(t),n)}async detect(t,n={}){let{inputSize:a,scoreThreshold:r}=new Ua(n),s=await yt(t),i=await this.forwardInput(s,a),o=D(()=>ht(i)[0].expandDims()),l={width:s.getInputWidth(0),height:s.getInputHeight(0)},c=await this.extractBoxes(o,s.getReshapedInputDimensions(0),r);i.dispose(),o.dispose();let u=c.map(g=>g.box),p=c.map(g=>g.score),d=c.map(g=>g.classScore),h=c.map(g=>this.config.classes[g.label]);return If(u.map(g=>g.rescale(a)),p,this.config.iouThreshold,!0).map(g=>new Dr(p[g],d[g],h[g],u[g],l))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return YC(t,this.config)}extractParams(t){let n=this.config.filterSizes||Fw.DEFAULT_FILTER_SIZES,a=n?n.length:void 0;if(a!==7&&a!==8&&a!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${a} filterSizes in config`);return XC(t,this.config,this.boxEncodingSize,n)}async extractBoxes(t,n,a){let{width:r,height:s}=n,i=Math.max(r,s),o=i/r,l=i/s,c=t.shape[1],u=this.config.anchors.length,[p,d,h]=D(()=>{let y=t.reshape([c,c,u,this.boxEncodingSize]),b=y.slice([0,0,0,0],[c,c,u,4]),v=y.slice([0,0,0,4],[c,c,u,1]),x=this.withClassScores?_a(y.slice([0,0,0,5],[c,c,u,this.config.classes.length]),3):he(0);return[b,v,x]}),m=[],f=await d.array(),g=await p.array();for(let y=0;ya){let N=(b+Eu(g[y][b][v][0]))/c*o,T=(y+Eu(g[y][b][v][1]))/c*l,C=Math.exp(g[y][b][v][2])*this.config.anchors[v].x/c*o,$=Math.exp(g[y][b][v][3])*this.config.anchors[v].y/c*l,F=N-C/2,O=T-$/2,W={row:y,col:b,anchor:v},{classScore:V,label:H}=this.withClassScores?await this.extractPredictedClass(h,W):{classScore:1,label:0};m.push({box:new ao(F,O,F+C,O+$),score:x,classScore:x*V,label:H,...W})}}return p.dispose(),d.dispose(),h.dispose(),m}async extractPredictedClass(t,n){let{row:a,col:r,anchor:s}=n,i=await t.array();return Array(this.config.classes.length).fill(0).map((o,l)=>i[a][r][s][l]).map((o,l)=>({classScore:o,label:l})).reduce((o,l)=>o.classScore>l.classScore?o:l)}},Lu=Fw;Lu.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var fo=class extends Lu{constructor(t=!0){let n={withSeparableConvs:t,iouThreshold:UC,classes:["face"],...t?{anchors:HC,meanRgb:jC}:{anchors:GC,withClassScores:!0}};super(n)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new bt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?KC:qC}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function JC(e,t=!0){let n=new fo(t);return n.extractWeights(e),n}var Qp=class extends Ua{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var ia=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};async function go(e,t,n,a,r=({alignedRect:s})=>s){let s=e.map(l=>Is(l)?r(l):l.detection),i=a||(t instanceof z?await lo(t,s):await oo(t,s)),o=await n(i);return i.forEach(l=>l instanceof z&&l.dispose()),o}async function zu(e,t,n,a,r){return go([e],t,async s=>n(s[0]),a,r)}var ZC=.4,QC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],e_=[117.001,114.697,97.404];var yo=class extends Lu{constructor(){let t={withSeparableConvs:!0,iouThreshold:ZC,classes:["face"],anchors:QC,meanRgb:e_,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new bt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var et={ssdMobilenetv1:new Ns,tinyFaceDetector:new yo,tinyYolov2:new fo,faceLandmark68Net:new po,faceLandmark68TinyNet:new Kp,faceRecognitionNet:new ho,faceExpressionNet:new Gp,ageGenderNet:new jp},$w=(e,t)=>et.ssdMobilenetv1.locateFaces(e,t),t_=(e,t)=>et.tinyFaceDetector.locateFaces(e,t),n_=(e,t)=>et.tinyYolov2.locateFaces(e,t),Dw=e=>et.faceLandmark68Net.detectLandmarks(e),a_=e=>et.faceLandmark68TinyNet.detectLandmarks(e),r_=e=>et.faceRecognitionNet.computeFaceDescriptor(e),s_=e=>et.faceExpressionNet.predictExpressions(e),i_=e=>et.ageGenderNet.predictAgeAndGender(e),Mw=e=>et.ssdMobilenetv1.load(e),o_=e=>et.tinyFaceDetector.load(e),l_=e=>et.tinyYolov2.load(e),u_=e=>et.faceLandmark68Net.load(e),c_=e=>et.faceLandmark68TinyNet.load(e),p_=e=>et.faceRecognitionNet.load(e),d_=e=>et.faceExpressionNet.load(e),h_=e=>et.ageGenderNet.load(e),m_=Mw,f_=$w,g_=Dw;var Rw=class extends ia{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Vu=class extends Rw{async run(){let t=await this.parentTask,n=await go(t,this.input,async a=>Promise.all(a.map(r=>et.faceExpressionNet.predictExpressions(r))),this.extractedFaces);return t.map((a,r)=>Hp(a,n[r]))}withAgeAndGender(){return new Bu(this,this.input)}},Uu=class extends Rw{async run(){let t=await this.parentTask;if(!t)return;let n=await zu(t,this.input,a=>et.faceExpressionNet.predictExpressions(a),this.extractedFaces);return Hp(t,n)}withAgeAndGender(){return new Wu(this,this.input)}},vo=class extends Vu{withAgeAndGender(){return new bo(this,this.input)}withFaceDescriptors(){return new Or(this,this.input)}},wo=class extends Uu{withAgeAndGender(){return new xo(this,this.input)}withFaceDescriptor(){return new Lr(this,this.input)}};var Pw=class extends ia{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Bu=class extends Pw{async run(){let t=await this.parentTask,n=await go(t,this.input,async a=>Promise.all(a.map(r=>et.ageGenderNet.predictAgeAndGender(r))),this.extractedFaces);return t.map((a,r)=>{let{age:s,gender:i,genderProbability:o}=n[r];return Jp(Zp(a,i,o),s)})}withFaceExpressions(){return new Vu(this,this.input)}},Wu=class extends Pw{async run(){let t=await this.parentTask;if(!t)return;let{age:n,gender:a,genderProbability:r}=await zu(t,this.input,s=>et.ageGenderNet.predictAgeAndGender(s),this.extractedFaces);return Jp(Zp(t,a,r),n)}withFaceExpressions(){return new Uu(this,this.input)}},bo=class extends Bu{withFaceExpressions(){return new vo(this,this.input)}withFaceDescriptors(){return new Or(this,this.input)}},xo=class extends Wu{withFaceExpressions(){return new wo(this,this.input)}withFaceDescriptor(){return new Lr(this,this.input)}};var ed=class extends ia{constructor(t,n){super();this.parentTask=t;this.input=n}},Or=class extends ed{async run(){let t=await this.parentTask;return(await go(t,this.input,a=>Promise.all(a.map(r=>et.faceRecognitionNet.computeFaceDescriptor(r))),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}))).map((a,r)=>Yp(t[r],a))}withFaceExpressions(){return new vo(this,this.input)}withAgeAndGender(){return new bo(this,this.input)}},Lr=class extends ed{async run(){let t=await this.parentTask;if(!t)return;let n=await zu(t,this.input,a=>et.faceRecognitionNet.computeFaceDescriptor(a),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}));return Yp(t,n)}withFaceExpressions(){return new wo(this,this.input)}withAgeAndGender(){return new xo(this,this.input)}};var td=class extends ia{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.useTinyLandmarkNet=a}get landmarkNet(){return this.useTinyLandmarkNet?et.faceLandmark68TinyNet:et.faceLandmark68Net}},nd=class extends td{async run(){let t=await this.parentTask,n=t.map(s=>s.detection),a=this.input instanceof z?await lo(this.input,n):await oo(this.input,n),r=await Promise.all(a.map(s=>this.landmarkNet.detectLandmarks(s)));return a.forEach(s=>s instanceof z&&s.dispose()),t.map((s,i)=>co(s,r[i]))}withFaceExpressions(){return new vo(this,this.input)}withAgeAndGender(){return new bo(this,this.input)}withFaceDescriptors(){return new Or(this,this.input)}},ad=class extends td{async run(){let t=await this.parentTask;if(!t)return;let{detection:n}=t,a=this.input instanceof z?await lo(this.input,[n]):await oo(this.input,[n]),r=await this.landmarkNet.detectLandmarks(a[0]);return a.forEach(s=>s instanceof z&&s.dispose()),co(t,r)}withFaceExpressions(){return new wo(this,this.input)}withAgeAndGender(){return new xo(this,this.input)}withFaceDescriptor(){return new Lr(this,this.input)}};var rd=class extends ia{constructor(t,n=new sa){super();this.input=t;this.options=n}},Gu=class extends rd{async run(){let{input:t,options:n}=this,a=n instanceof Qp?r=>et.tinyFaceDetector.locateFaces(r,n):n instanceof sa?r=>et.ssdMobilenetv1.locateFaces(r,n):n instanceof Ua?r=>et.tinyYolov2.locateFaces(r,n):null;if(!a)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return a(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let n=await this.run();t(n.map(a=>bs({},a)))})}withFaceLandmarks(t=!1){return new nd(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new Vu(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Bu(this.runAndExtendWithFaceDetections(),this.input)}},sd=class extends rd{async run(){let t=await new Gu(this.input,this.options),n=t[0];return t.forEach(a=>{a.score>n.score&&(n=a)}),n}runAndExtendWithFaceDetection(){return new Promise(async t=>{let n=await this.run();t(n?bs({},n):void 0)})}withFaceLandmarks(t=!1){return new ad(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new Uu(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Wu(this.runAndExtendWithFaceDetection(),this.input)}};function y_(e,t=new sa){return new sd(e,t)}function id(e,t=new sa){return new Gu(e,t)}async function Ow(e,t){return id(e,new sa(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function b_(e,t={}){return id(e,new Ua(t)).withFaceLandmarks().withFaceDescriptors()}var x_=Ow;function qf(e,t){if(e.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let n=Array.from(e),a=Array.from(t);return Math.sqrt(n.map((r,s)=>r-a[s]).reduce((r,s)=>r+s**2,0))}var od=class{constructor(t,n=.6){this._distanceThreshold=n;let a=Array.isArray(t)?t:[t];if(!a.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let r=1,s=()=>`person ${r++}`;this._labeledDescriptors=a.map(i=>{if(i instanceof ur)return i;if(i instanceof Float32Array)return new ur(s(),[i]);if(i.descriptor&&i.descriptor instanceof Float32Array)return new ur(s(),[i.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,n){return n.map(a=>qf(a,t)).reduce((a,r)=>a+r,0)/(n.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:n,label:a})=>new Au(a,this.computeMeanDistance(t,n))).reduce((n,a)=>n.distancet.toJSON())}}static fromJSON(t){let n=t.labeledDescriptors.map(a=>ur.fromJSON(a));return new od(n,t.distanceThreshold)}};function v_(e){let t=new yo;return t.extractWeights(e),t}function Lw(e,t){let{width:n,height:a}=new un(t.width,t.height);if(n<=0||a<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:n,height:a})}`);if(Array.isArray(e))return e.map(r=>Lw(r,{width:n,height:a}));if(Is(e)){let r=e.detection.forSize(n,a),s=e.unshiftedLandmarks.forSize(r.box.width,r.box.height);return co(bs(e,r),s)}return Wa(e)?bs(e,e.detection.forSize(n,a)):e instanceof Gn||e instanceof bt?e.forSize(n,a):e}var Pse=typeof process!="undefined",Ose=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",w_={faceapi:wC,node:Pse,browser:Ose};return Rse;})(); + `}};function cte(e){let{inputs:t,backend:n,attrs:a}=e,{x:r,segmentIds:s}=t,{numSegments:i}=a,o=r.shape.length,l=[],c=0,u=E.getAxesPermutation([c],o),p=r;u!=null&&(p=Cn({inputs:{x:r},backend:n,attrs:{perm:u}}),l.push(p),c=E.getInnerMostAxes(1,o)[0]);let d=E.segment_util.computeOutShape(p.shape,c,i),h=k.sizeFromShape([p.shape[c]]),m=ve({inputs:{x:p},backend:n,attrs:{shape:[-1,h]}});l.push(m);let f=bh(r.dtype),g=(x,N,T,C,$)=>{let F=x.shape[0],O=x.shape[1],W=E.segment_util.segOpComputeOptimalWindowSize(O,$),V={windowSize:W,inSize:O,batchSize:F,numSegments:$},H=new ute(V,N),K=n.compileAndRun(H,[x,T],C);if(l.push(K),K.shape[1]===$)return K;let j=h2({backend:n,attrs:{start:0,stop:$,step:1,dtype:"float32"}}),Y=g2({inputs:{x:j},backend:n,attrs:{reps:[O/W]}});return l.push(j),l.push(Y),g(K,N,Y,C,$)},y=g(m,"unsortedSegmentSum",s,f,i),b=ve({inputs:{x:y},backend:n,attrs:{shape:d}}),v=b;if(u!=null){l.push(b);let x=E.getUndoAxesPermutation(u);v=Cn({inputs:{x:v},backend:n,attrs:{perm:x}})}return l.forEach(x=>n.disposeIntermediateTensorInfo(x)),v}var pte={kernelName:Fc,backendName:"webgl",kernelFunc:cte},dte=[rZ,oZ,jX,KX,JX,eY,nY,sY,oY,uY,hY,fY,bY,wY,_Y,NY,FY,RY,DY,zY,WY,UY,qY,e7,n7,l7,c7,m7,y7,CX,w7,F7,D7,T7,O7,z7,R7,V7,H7,K7,Y7,Z7,tJ,oJ,uJ,aJ,dJ,fJ,xJ,IJ,CJ,AJ,FJ,$J,MJ,PJ,LJ,BJ,VJ,jJ,YJ,ZJ,e9,a9,o9,p9,f9,SX,y9,v7,v9,I9,S9,EX,A9,M9,P9,U9,B9,q9,Y9,eZ,uZ,yZ,fZ,wZ,IZ,TZ,hZ,CZ,EZ,DZ,OZ,WZ,XZ,MX,JZ,eQ,aQ,iQ,r7,uQ,pQ,hQ,gQ,vQ,FX,kQ,IQ,s7,HZ,SQ,MQ,AQ,PX,LQ,WQ,GQ,qQ,JQ,QQ,nee,see,oee,cee,hee,gee,xee,kee,Tee,ZY,qZ,_ee,Aee,$ee,Mee,Oee,Bee,Vee,Gee,qee,jZ,UX,Yee,Qee,nte,rte,GX,ite,lte,pte,cQ];for(let e of dte)Dc(e);var hte="2.8.5",mte={"tfjs-core":s1,"tfjs-backend-cpu":GG,"tfjs-backend-webgl":TX,"tfjs-data":jN,"tfjs-layers":$m,"tfjs-converter":BN,tfjs:hte},Vn;(function(e){e[e.float32=0]="float32",e[e.int32=1]="int32",e[e.bool=2]="bool",e[e.string=3]="string",e[e.complex64=4]="complex64"})(Vn||(Vn={}));var Mp;(function(e){e[e.linear=0]="linear",e[e.relu=1]="relu",e[e.relu6=2]="relu6",e[e.prelu=3]="prelu",e[e.leakyrelu=4]="leakyrelu"})(Mp||(Mp={}));var y2;function fte(e){y2=e.wasm.cwrap(Ni,null,["number","array","number","number","array","number","number","number","number","number","number","number","number"])}function gte(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s,bias:i,preluActivationWeights:o}=t;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("_FusedMatMul for non non-float32 tensors not yet supported.");let{transposeA:l,transposeB:c,activation:u,leakyreluAlpha:p}=a,d=n.dataIdMap.get(r.dataId).id,h=n.dataIdMap.get(s.dataId).id,m=0;if(i!=null){let $=n.dataIdMap.get(i.dataId);if($.shape.length!==1)throw new Error(`_FusedMatMul only supports rank-1 bias but got rank ${$.shape.length}.`);m=$.id}let f=o==null?0:n.dataIdMap.get(o.dataId).id,g=Mp[u];if(g==null)throw new Error(`${u} activation not yet supported for FusedConv2D in the wasm backend.`);let y=l?r.shape[2]:r.shape[1],b=c?s.shape[1]:s.shape[2],v=r.shape[0],x=n.makeOutput([v,y,b],r.dtype),N=n.dataIdMap.get(x.dataId).id,T=new Uint8Array(new Int32Array(r.shape).buffer),C=new Uint8Array(new Int32Array(s.shape).buffer);return y2(d,T,r.shape.length,h,C,s.shape.length,l,c,g,m,f,p||0,N),x}var yte={kernelName:Ni,backendName:"wasm",setupFunc:fte,kernelFunc:gte};function Un(e){let t;function n(r){t=r.wasm.cwrap(e,null,["number","number"])}function a(r){let{backend:s,inputs:{x:i}}=r,o=s.dataIdMap.get(i.dataId).id,l=s.makeOutput(i.shape,i.dtype),c=s.dataIdMap.get(l.dataId).id;return k.sizeFromShape(l.shape)===0||t(o,c),l}return{kernelName:e,backendName:"wasm",setupFunc:n,kernelFunc:a}}var bte=Un(Lo);function yn(e,t,n){let a;function r(i){a=i.wasm.cwrap(e,null,["number","array","number","number","array","number","number","number"])}function s(i){let{backend:o,inputs:l}=i,{a:c,b:u}=l,p=o.dataIdMap.get(c.dataId).id,d=o.dataIdMap.get(u.dataId).id,h=n!=null?n:c.dtype,m=E.assertAndGetBroadcastShape(c.shape,u.shape),f=o.makeOutput(m,h);if(k.sizeFromShape(m)===0)return f;let g=new Uint8Array(new Int32Array(c.shape).buffer),y=new Uint8Array(new Int32Array(u.shape).buffer),b=o.dataIdMap.get(f.dataId).id,v=()=>a(p,g,c.shape.length,d,y,u.shape.length,Vn[c.dtype],b);if(t&&c.dtype==="float32")return v(),f;let x=E.getBroadcastDims(c.shape,m),N=E.getBroadcastDims(u.shape,m),T=x.every(($,F)=>$===F),C=N.every(($,F)=>$===F);if(T&&C)return v(),f;throw new Error(`Broadcasting along outer dims is not yet supported for ${c.dtype} ${e}.`)}return{kernelName:e,backendName:"wasm",setupFunc:r,kernelFunc:s}}var xte=!0,vte=yn(Hr,xte),b2;function wte(e){b2=e.wasm.cwrap(Ms,null,["array","number","number","number"])}function kte(e){let{inputs:t,backend:n}=e,a=n.makeOutput(t[0].shape,t[0].dtype);if(k.sizeFromShape(a.shape)===0)return a;let r=t.map(o=>n.dataIdMap.get(o.dataId).id),s=new Uint8Array(new Int32Array(r).buffer),i=n.dataIdMap.get(a.dataId).id;return b2(s,r.length,Vn[a.dtype],i),a}var Ite={kernelName:Ms,backendName:"wasm",setupFunc:wte,kernelFunc:kte};function hf(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype),r=n.typedArrayFromHeap(t);return n.typedArrayFromHeap(a).set(r),a}var Nte={kernelName:il,backendName:"wasm",kernelFunc:hf},x2;function Tte(e){x2=e.wasm.cwrap(Ii,null,["number","array","number","number","number","array","number"])}function mf(e){let{inputs:t,backend:n,attrs:a}=e,[r,s]=Cte(t.x.shape,a.perm),i=!0;for(let m=0;m=r&&(s===-1||a[s]>a[i])&&(s=i);a[s]=r}return[n,a]}var _te={kernelName:Ii,backendName:"wasm",kernelFunc:mf,setupFunc:Tte};function Cu(e,t,n){let a=e.shape,r=e.shape.length,s=k.parseAxisParam(t,a),i=s,o=E.getAxesPermutation(i,r),l=null,c=!1;if(o!=null){let u=new Array(r);for(let d=0;d`new shape: ${i}, old shape: ${a.shape}. New shape and old shape must have the same number of elements.`),{dataId:a.dataId,shape:i,dtype:a.dtype}}var Rte={kernelName:Nl,backendName:"wasm",kernelFunc:za},k2;function Pte(e){k2=e.wasm.cwrap(Os,null,["number","array","number","number","array","number","number","number","number"])}function Ote(e){let{inputs:t,backend:n,attrs:a}=e,{a:r,b:s}=t,{transposeA:i,transposeB:o}=a;if(r.dtype!=="float32"||s.dtype!=="float32")throw new Error("BatchMatMul for non non-float32 tensors not yet supported.");let l=r.shape.length,c=s.shape.length,u=i?r.shape[l-2]:r.shape[l-1],p=o?s.shape[c-1]:s.shape[c-2],d=i?r.shape[l-1]:r.shape[l-2],h=o?s.shape[c-2]:s.shape[c-1],m=r.shape.slice(0,-2),f=s.shape.slice(0,-2),g=k.sizeFromShape(m),y=k.sizeFromShape(f),b=g===y||g===1||y===1;k.assert(l>=2&&c>=2&&b,()=>`Error in matMul: the input batch dimensions must either be the same or at least one input batch dimension must be 1. Got input batch dimensions of (${m}) and (${f}).`);let v=(g>y?r.shape.slice(0,-2):s.shape.slice(0,-2)).concat([d,h]);k.assert(u===p,()=>`Error in matMul: inner shapes (${u}) and (${p}) of Tensors with shapes ${r.shape} and ${s.shape} and transposeA=${i} and transposeB=${o} must match.`);let x=i?[g,u,d]:[g,d,u],N=o?[y,h,p]:[y,p,h],T=za({inputs:{x:r},backend:n,attrs:{shape:x}}),C=za({inputs:{x:s},backend:n,attrs:{shape:N}}),$=n.dataIdMap.get(T.dataId).id,F=n.dataIdMap.get(C.dataId).id,O=i?T.shape[2]:T.shape[1],W=o?C.shape[1]:C.shape[2],V=Math.max(g,y),H=n.makeOutput([V,O,W],T.dtype),K=n.dataIdMap.get(H.dataId).id,j=new Uint8Array(new Int32Array(T.shape).buffer),Y=new Uint8Array(new Int32Array(C.shape).buffer);return k2($,j,T.shape.length,F,Y,C.shape.length,i,o,K),H.shape=v,H}var Lte={kernelName:Os,backendName:"wasm",setupFunc:Pte,kernelFunc:Ote};function ff(e){let{inputs:{x:t},attrs:{dtype:n},backend:a}=e,r=a.makeOutput(t.shape,n),s=a.typedArrayFromHeap(t);return a.typedArrayFromHeap(r).set(s),r}var zte={kernelName:Ls,backendName:"wasm",kernelFunc:ff},I2;function Bte(e){I2=e.wasm.cwrap(jr,null,["number","number","number","number"])}function Wte(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{clipValueMin:s,clipValueMax:i}=a,o=n.dataIdMap.get(r.dataId).id,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(l.dataId).id;return I2(o,s,i,c),l}var Vte={kernelName:jr,backendName:"wasm",setupFunc:Bte,kernelFunc:Wte};function N2(e){let{inputs:t,backend:n}=e,a=k.parseAxisParam(e.attrs.axis,t[0].shape)[0],r=E.computeOutShape(t.map(h=>h.shape),a),s=t.filter(h=>k.sizeFromShape(h.shape)>0);if(s.length===1)return hf({inputs:{x:s[0]},backend:n});let i=n.makeOutput(r,t[0].dtype);if(k.sizeFromShape(r)===0)return i;let o=s.map(h=>h.shape);if(E.assertParamsConsistent(o,a),s[0].dtype==="string"){let h=s.map(v=>{let x=k.sizeFromShape(v.shape.slice(a));return za({inputs:{x:v},backend:n,attrs:{shape:[-1,x]}})}),m=h.map(v=>({vals:n.readSync(v.dataId),shape:v.shape}));r=E.computeOutShape(h.map(v=>v.shape),1);let f=h[0].shape[0]===1,g=_v(m,r,t[0].dtype,f),y=E.computeOutShape(s.map(v=>v.shape),a);i.shape=y;let b=n.dataIdMap.get(i.dataId);return b.stringBytes=E.fromStringArrayToUint8(g),i}let l=k.sizeFromShape(s[0].shape.slice(0,a)),c=0,u=s.map(h=>{let m=k.sizeFromShape(h.shape.slice(a));return c+=m,m}),p=s.map(h=>n.typedArrayFromHeap(h)),d=n.typedArrayFromHeap(i);for(let h=0;h`cumsum does not support ${r.dtype} tensors in the WASM backend`);let c=E.getAxesPermutation([s],l),u=r;c!==null&&(u=mf({inputs:{x:r},attrs:{perm:c},backend:n}));let p=E.getInnerMostAxes(1,l)[0];E.assertAxesAreInnerMostDims("cumsum",[p],l);let d=n.makeOutput(u.shape,u.dtype),h=u.shape[p],m=n.dataIdMap.get(u.dataId).id,f=n.dataIdMap.get(d.dataId).id;_2(m,i?1:0,o?1:0,h,f,Vn[r.dtype]);let g=d;if(c!==null){let y=E.getUndoAxesPermutation(c);g=mf({inputs:{x:d},attrs:{perm:y},backend:n}),n.disposeData(u.dataId),n.disposeData(d.dataId)}return g}var nne={kernelName:Vs,backendName:"wasm",setupFunc:ene,kernelFunc:tne},E2;function ane(e){E2=e.wasm.cwrap(Yo,null,["number","number","number","array","number","array","array","number","number"])}function rne(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{blockSize:s,dataFormat:i}=a;k.assert(s>1,()=>`blockSize should be > 1 for depthToSpace, but was: ${s}`);let o=r.shape[0],l=i==="NHWC"?r.shape[1]:r.shape[2],c=i==="NHWC"?r.shape[2]:r.shape[3],u=i==="NHWC"?r.shape[3]:r.shape[1],p=l*s,d=c*s,h=u/(s*s),m=i==="NHWC"?[o,p,d,h]:[o,h,p,d],f=t.makeOutput(m,"float32"),g=t.dataIdMap.get(r.dataId).id,y=new Uint8Array(new Int32Array(k.computeStrides(r.shape)).buffer),b=new Uint8Array(new Int32Array(m).buffer),v=new Uint8Array(new Int32Array(k.computeStrides(m)).buffer),x=t.dataIdMap.get(f.dataId).id;return E2(g,s,i==="NHWC"?1:0,y,r.shape.length-1,b,v,m.length,x),f}var sne={kernelName:Yo,backendName:"wasm",setupFunc:ane,kernelFunc:rne},A2;function ine(e){A2=e.wasm.cwrap(Us,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function one(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s}=t,i=a.dataIdMap.get(r.dataId).id,o=a.dataIdMap.get(s.dataId).id,{strides:l,dilations:c,pad:u,dimRoundingMode:p}=n,d=c==null?[1,1]:c,h=E.computeConv2DInfo(r.shape,s.shape,l,d,u,p,!0),m=h.filterHeight,f=h.filterWidth,g=h.padInfo.top,y=h.padInfo.right,b=h.padInfo.bottom,v=h.padInfo.left,x=h.dilationHeight,N=h.dilationWidth,T=h.strideHeight,C=h.strideWidth,$=h.inChannels,F=h.outChannels,O=h.padInfo.type==="SAME"?1:0;if(h.dataFormat!=="channelsLast")throw new Error(`wasm backend DepthwiseConv2dNative does not support dataFormat:'${h.dataFormat}'. Please use 'channelsLast'.`);let W=a.makeOutput(h.outShape,"float32"),V=a.dataIdMap.get(W.dataId).id;return A2(i,r.shape[0],r.shape[1],r.shape[2],o,m,f,g,y,b,v,O,x,N,T,C,$,F,V),W}var lne={kernelName:Us,backendName:"wasm",setupFunc:ine,kernelFunc:one},une=!1,cne=yn(Qo,une,"bool"),pne=Un(Hs);function sw(e){let{inputs:t,attrs:n,backend:a}=e,{input:r}=t,{dim:s}=n,i=r.shape.length,o=r.shape.slice(),l=s;return s<0&&(k.assert(-(i+1)<=s,()=>`Axis must be in the interval [${-(i+1)}, ${i}]`),l=i+s+1),o.splice(l,0,1),za({inputs:{x:r},backend:a,attrs:{shape:o}})}var dne={kernelName:el,backendName:"wasm",kernelFunc:sw};function hne(e){let{attrs:{shape:t,value:n,dtype:a},backend:r}=e,s=r.makeOutput(t,a);return r.typedArrayFromHeap(s).fill(n),s}var mne={kernelName:wc,backendName:"wasm",kernelFunc:hne},F2;function fne(e){F2=e.wasm.cwrap(nl,null,["number","number","number","number","number","number"])}function gne(e){let{inputs:t,backend:n}=e,{image:a}=t,r=n.makeOutput(a.shape,a.dtype),s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,[o,l,c,u]=a.shape;return F2(s,o,l,c,u,i),r}var yne={kernelName:nl,backendName:"wasm",kernelFunc:gne,setupFunc:fne},bne=Un(js),xne=!1,vne=yn(qs,xne),$2;function wne(e){$2=e.wasm.cwrap(Ks,null,["number","number","number","number","number","number","number"])}function kne(e){let{backend:t,inputs:n,attrs:a}=e,{varianceEpsilon:r}=a,{x:s,mean:i,variance:o,offset:l,scale:c}=n,u=t.dataIdMap.get(s.dataId).id,p=t.dataIdMap.get(i.dataId).id,d=t.dataIdMap.get(o.dataId).id,h=l!=null?t.dataIdMap.get(l.dataId).id:0,m=c!=null?t.dataIdMap.get(c.dataId).id:0,f=t.makeOutput(s.shape,s.dtype);if(k.sizeFromShape(s.shape)===0)return f;let g=t.dataIdMap.get(f.dataId).id;return $2(u,p,d,h,m,r,g),f}var Ine={kernelName:Ks,backendName:"wasm",setupFunc:wne,kernelFunc:kne},D2;function Nne(e){D2=e.wasm.cwrap(Ti,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function Tne(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d),g=Mp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return D2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Sne={kernelName:Ti,backendName:"wasm",setupFunc:Nne,kernelFunc:Tne},M2;function Cne(e){M2=e.wasm.cwrap(Si,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function _ne(e){let{inputs:t,attrs:n,backend:a}=e,{x:r,filter:s,bias:i,preluActivationWeights:o}=t,{strides:l,pad:c,dilations:u,dataFormat:p,dimRoundingMode:d,activation:h,leakyreluAlpha:m}=n,f=E.computeConv2DInfo(r.shape,s.shape,l,u,c,d,!0),g=Mp[h];if(g==null)throw new Error(`${h} activation not yet supported for FusedDepthwiseConv2D in the wasm backend.`);let y=a.dataIdMap.get(r.dataId).id,b=a.dataIdMap.get(s.dataId).id,v=f.outChannels,x=0;if(i!=null){let se=a.dataIdMap.get(i.dataId);if(se.shape.length!==1)throw new Error(`FusedDepthwiseConv2D only supports rank-1 bias but got rank ${se.shape.length}.`);if(se.shape[0]!==v)throw new Error(`FusedDepthwiseConv2D bias shape (${se.shape}) does not match the number of output channels (${v})`);x=se.id}let N=f.filterHeight,T=f.filterWidth,C=f.padInfo.top,$=f.padInfo.right,F=f.padInfo.bottom,O=f.padInfo.left,W=f.dilationHeight,V=f.dilationWidth,H=f.strideHeight,K=f.strideWidth,j=f.inChannels,Y=f.padInfo.type==="SAME"?1:0,J=f.batchSize,ne=f.inHeight,Q=f.inWidth;if(p!=="NHWC")throw new Error(`wasm backend FusedDepthwiseConv2D does not support dataFormat:'${p}'. Please use 'NHWC'.`);let ie=a.makeOutput(f.outShape,"float32"),ee=a.dataIdMap.get(ie.dataId).id,le=o==null?0:a.dataIdMap.get(o.dataId).id;return M2(y,J,ne,Q,b,N,T,x,C,$,F,O,Y,W,V,H,K,j,v,g,le,m||0,ee),ie}var Ene={kernelName:Si,backendName:"wasm",setupFunc:Cne,kernelFunc:_ne},R2;function Ane(e){R2=e.wasm.cwrap(rl,null,["number","number","number","number","number","number","array","number"])}function Fne(e){let{backend:t,inputs:n}=e,{params:a,indices:r}=n,[s,i,o,l]=Ay.prepareAndValidate(a,r),c=t.makeOutput(s,a.dtype);if(i===0)return c;let u=r.shape,p=u[u.length-1],d=t.dataIdMap.get(a.dataId).id,h=t.dataIdMap.get(r.dataId).id,m=new Uint8Array(new Int32Array(l).buffer),f=t.dataIdMap.get(c.dataId).id;return R2(d,Vn[a.dtype],h,i,p,o,m,f),c}var $ne={kernelName:rl,backendName:"wasm",setupFunc:Ane,kernelFunc:Fne},P2;function Dne(e){P2=e.wasm.cwrap("Gather",null,["number","number","array","number","number","number","array","number"])}function Mne(e){let{backend:t,inputs:n,attrs:a}=e,{x:r,indices:s}=n,{axis:i,batchDims:o}=a,l=k.parseAxisParam(i,r.shape)[0],c=E.segment_util.collectGatherOpShapeInfo(r,s,l,o),u=za({inputs:{x:r},attrs:{shape:[c.batchSize,c.outerSize,c.dimSize,c.sliceSize]},backend:t}),p=k.sizeFromShape(s.shape),d=za({inputs:{x:s},attrs:{shape:[c.batchSize,p/c.batchSize]},backend:t}),h=[c.batchSize,c.outerSize,p/c.batchSize,c.sliceSize],m=t.makeOutput(h,r.dtype);if(k.sizeFromShape(r.shape)===0)return m;let f=u.shape.length-1,g=t.dataIdMap.get(u.dataId).id,y=t.dataIdMap.get(d.dataId).id,b=t.dataIdMap.get(m.dataId).id,v=new Uint8Array(new Int32Array(k.computeStrides(u.shape)).buffer),x=new Uint8Array(new Int32Array(k.computeStrides(h)).buffer);return P2(g,Vn[r.dtype],v,f,y,c.batchSize,x,b),m.shape=c.outputShape,m}var Rne={kernelName:al,backendName:"wasm",setupFunc:Dne,kernelFunc:Mne},Pne=!1,One=yn(sl,Pne,"bool"),Lne=!1,zne=yn(Xs,Lne,"bool"),O2;function Bne(e){O2=e.wasm.cwrap(Ys,null,["number","number","number"])}function Wne(e){let{inputs:{x:t},attrs:{alpha:n},backend:a}=e,r=a.dataIdMap.get(t.dataId).id,s=a.makeOutput(t.shape,t.dtype);if(k.sizeFromShape(t.shape)!==0){let i=a.dataIdMap.get(s.dataId).id;O2(r,n,i)}return s}var Vne={kernelName:Ys,backendName:"wasm",setupFunc:Bne,kernelFunc:Wne},Une=!1,Gne=yn(cl,Une,"bool"),Hne=!1,jne=yn(pl,Hne,"bool"),qne=Un(Js),Kne=!1,Xne=yn(hl,Kne,"bool"),L2;function Yne(e){L2=e.wasm.cwrap(Zs,null,["number, number, number"])}function Jne(e){let{backend:t,inputs:n,attrs:a}=e,{reductionIndices:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=i,{transposed:c,axes:u,originalAxes:p,inputWasTransposed:d}=Cu(i,r,t);if(d){let b=t.dataIdMap.get(c.dataId).id;l=c,o=b}let h=l.shape.length;E.assertAxesAreInnerMostDims("max",u,h);let[m,f]=E.computeOutAndReduceShapes(l.shape,u),g=k.sizeFromShape(f),y=t.makeOutput(m,i.dtype);if(k.sizeFromShape(l.shape)!==0){let b=t.dataIdMap.get(y.dataId).id;L2(o,g,b)}if(d&&t.disposeData(c.dataId),s){let b=E.expandShapeToKeepDim(y.shape,p);y.shape=b}return y}var Zne={kernelName:Zs,backendName:"wasm",setupFunc:Yne,kernelFunc:Jne},Qne=!1,eae=yn(Qs,Qne),z2;function tae(e){z2=e.wasm.cwrap(ei,null,["number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number","number"])}function nae(e){let{inputs:t,attrs:n,backend:a}=e,r=t.x,s=a.dataIdMap.get(r.dataId).id,{filterSize:i,strides:o,pad:l,dimRoundingMode:c}=n,u=E.computePool2DInfo(r.shape,i,o,1,l,c),p=u.filterHeight,d=u.filterWidth,h=u.padInfo.top,m=u.padInfo.right,f=u.padInfo.bottom,g=u.padInfo.left,y=u.dilationHeight,b=u.dilationWidth,v=u.strideHeight,x=u.strideWidth,N=u.inChannels,T=u.outChannels;if(u.dataFormat!=="channelsLast")throw new Error(`wasm backend does not support dataFormat:'${u.dataFormat}'. Please use 'channelsLast'.`);let C=a.makeOutput(u.outShape,"float32"),$=a.dataIdMap.get(C.dataId).id;return z2(s,r.shape[0],r.shape[1],r.shape[2],p,d,h,m,f,g,y,b,v,x,N,T,$),C}var aae={kernelName:ei,backendName:"wasm",setupFunc:tae,kernelFunc:nae},B2;function rae(e){B2=e.wasm.cwrap(ti,null,["number, number, number"])}function sae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t),m=p;if(h){let x=t.dataIdMap.get(u.dataId).id;x!==o&&(c=u,l=x,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("mean",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=c;c.dtype!=="float32"&&(b=ff({backend:t,inputs:{x:c},attrs:{dtype:"float32"}}),l=t.dataIdMap.get(b.dataId).id);let v=t.makeOutput(f,"float32");if(k.sizeFromShape(c.shape)!==0){let x=t.dataIdMap.get(v.dataId).id;B2(l,y,x)}if(h&&t.disposeData(u.dataId),s){let x=E.expandShapeToKeepDim(v.shape,d);v.shape=x}return c.dtype!=="float32"&&t.disposeData(b.dataId),v}var iae={kernelName:ti,backendName:"wasm",setupFunc:rae,kernelFunc:sae},W2;function oae(e){W2=e.wasm.cwrap(ni,null,["number, number, number"])}function lae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t);if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v)}let m=c.shape.length;E.assertAxesAreInnerMostDims("min",p,m);let[f,g]=E.computeOutAndReduceShapes(c.shape,p),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;W2(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var uae={kernelName:ni,backendName:"wasm",setupFunc:oae,kernelFunc:lae},cae=!1,pae=yn(ai,cae),dae=!0,hae=yn(ri,dae),mae=Un(fl);function iw(e,t){let n=new Int32Array(e.wasm.HEAPU8.buffer,t,4),a=n[0],r=n[1],s=n[2],i=n[3];return e.wasm._free(t),{pSelectedIndices:a,selectedSize:r,pSelectedScores:s,pValidOutputs:i}}var V2;function fae(e){V2=e.wasm.cwrap(yl,"number",["number","number","number","number","number"])}function gae(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i}=a,{boxes:o,scores:l}=n,c=t.dataIdMap.get(o.dataId).id,u=t.dataIdMap.get(l.dataId).id,p=V2(c,u,s,r,i),{pSelectedIndices:d,selectedSize:h,pSelectedScores:m,pValidOutputs:f}=iw(t,p);return t.wasm._free(m),t.wasm._free(f),t.makeOutput([h],"int32",d)}var yae={kernelName:yl,backendName:"wasm",setupFunc:fae,kernelFunc:gae},U2;function bae(e){U2=e.wasm.cwrap(bl,"number",["number","number","number","number","number","bool"])}function xae(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,padToMaxOutputSize:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=U2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=iw(t,d);t.wasm._free(f);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([],"int32",g);return[y,b]}var vae={kernelName:bl,backendName:"wasm",setupFunc:bae,kernelFunc:xae},G2;function wae(e){G2=e.wasm.cwrap(xl,"number",["number","number","number","number","number","number"])}function kae(e){let{backend:t,inputs:n,attrs:a}=e,{iouThreshold:r,maxOutputSize:s,scoreThreshold:i,softNmsSigma:o}=a,{boxes:l,scores:c}=n,u=t.dataIdMap.get(l.dataId).id,p=t.dataIdMap.get(c.dataId).id,d=G2(u,p,s,r,i,o),{pSelectedIndices:h,selectedSize:m,pSelectedScores:f,pValidOutputs:g}=iw(t,d);t.wasm._free(g);let y=t.makeOutput([m],"int32",h),b=t.makeOutput([m],"float32",f);return[y,b]}var Iae={kernelName:xl,backendName:"wasm",setupFunc:wae,kernelFunc:kae},Nae=!1,Tae=yn(gl,Nae,"bool"),H2;function Sae(e){H2=e.wasm.cwrap(si,null,["number","number","number","number","number"])}function Cae(e){let{inputs:t,backend:n,attrs:a}=e,{indices:r}=t,{depth:s,onValue:i,offValue:o}=a,l=n.makeOutput([...r.shape,s],"int32"),c=n.dataIdMap.get(l.dataId).id,u=n.dataIdMap.get(r.dataId).id;return H2(u,s,i,o,c),l}var _ae={kernelName:si,backendName:"wasm",setupFunc:Sae,kernelFunc:Cae};function Eae(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(1),a}var Aae={kernelName:vl,backendName:"wasm",kernelFunc:Eae};function Fae(e){let{inputs:t,backend:n,attrs:a}=e,{axis:r}=a;if(t.length===1)return sw({inputs:{input:t[0]},backend:n,attrs:{dim:r}});let s=t[0].shape,i=t[0].dtype;t.forEach(l=>{k.assertShapesMatch(s,l.shape,"All tensors passed to stack must have matching shapes"),k.assert(i===l.dtype,()=>"All tensors passed to stack must have matching dtypes")});let o=t.map(l=>sw({inputs:{input:l},backend:n,attrs:{dim:r}}));return N2({inputs:o,backend:n,attrs:{axis:r}})}var $ae={kernelName:wl,backendName:"wasm",kernelFunc:Fae},j2;function Dae(e){j2=e.wasm.cwrap(ii,null,["number","array","number","number","array","array","number","number"])}function Mae(e){let{inputs:{x:t},backend:n,attrs:{paddings:a,constantValue:r}}=e,s=a.map((m,f)=>m[0]+t.shape[f]+m[1]),i=n.dataIdMap.get(t.dataId).id,o=n.makeOutput(s,t.dtype),l=n.dataIdMap.get(o.dataId).id,c=new Uint8Array(new Int32Array(t.shape).buffer),u=a.map(m=>m[0]),p=a.map(m=>m[1]),d=new Uint8Array(new Int32Array(u).buffer),h=new Uint8Array(new Int32Array(p).buffer);return j2(i,c,t.shape.length,Vn[t.dtype],d,h,r,l),o}var Rae={kernelName:ii,backendName:"wasm",kernelFunc:Mae,setupFunc:Dae},Pae=!1,Oae=yn(oi,Pae),q2;function Lae(e){q2=e.wasm.cwrap(li,null,["number","number","number"])}function zae(e){let{inputs:t,backend:n}=e,{x:a,alpha:r}=t,s=n.dataIdMap.get(a.dataId).id,i=n.dataIdMap.get(r.dataId).id,o=n.makeOutput(a.shape,"float32"),l=n.dataIdMap.get(o.dataId).id;return q2(s,i,l),o}var Bae={kernelName:li,backendName:"wasm",setupFunc:Lae,kernelFunc:zae},K2;function Wae(e){K2=e.wasm.cwrap(kl,null,["number","number","number","number"])}function Vae(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("prod",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;K2(l,y,Vn[b.dtype],v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var Uae={kernelName:kl,backendName:"wasm",setupFunc:Wae,kernelFunc:Vae},Gae=e=>{let{backend:t,attrs:n}=e,{start:a,stop:r,step:s,dtype:i}=n,o=Fv(a,r,s,i),l=t.makeOutput([o.length],i);return t.typedArrayFromHeap(l).set(o),l},Hae={kernelName:Cc,backendName:"wasm",kernelFunc:Gae},jae=!0,qae=yn(Gs,jae),Kae=Un(ui),Xae=Un(pi),X2;function Yae(e){X2=e.wasm.cwrap(ci,null,["number","number","number","number","number","number","number","number","number","number"])}function Jae(e){let{backend:t,inputs:n,attrs:a}=e,{images:r}=n,{alignCorners:s,halfPixelCenters:i,size:o}=a,[l,c]=o,[u,p,d,h]=r.shape,m=[u,l,c,h],f=t.dataIdMap.get(r.dataId),g;f.dtype!=="float32"&&(g=ff({backend:t,inputs:{x:r},attrs:{dtype:"float32"}}),f=t.dataIdMap.get(g.dataId));let y=f.id,b=t.makeOutput(m,"float32");if(k.sizeFromShape(r.shape)===0)return b;let v=t.dataIdMap.get(b.dataId).id;return X2(y,u,p,d,h,l,c,s?1:0,i?1:0,v),g!=null&&t.disposeData(g.dataId),b}var Zae={kernelName:ci,backendName:"wasm",setupFunc:Yae,kernelFunc:Jae},Y2;function Qae(e){Y2=e.wasm.cwrap(di,null,["number","array","number","array","number","number"])}function ere(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,{dims:s}=a,i=k.parseAxisParam(s,r.shape);if(r.shape.length===0)return hf({inputs:{x:r},backend:n});let o=n.makeOutput(r.shape,r.dtype),l=n.dataIdMap.get(r.dataId).id,c=n.dataIdMap.get(o.dataId).id,u=new Uint8Array(new Int32Array(i).buffer),p=new Uint8Array(new Int32Array(r.shape).buffer);return Y2(l,u,i.length,p,r.shape.length,c),za({inputs:{x:o},attrs:{shape:r.shape},backend:n})}var tre={kernelName:di,backendName:"wasm",kernelFunc:ere,setupFunc:Qae},J2;function nre(e){J2=e.wasm.cwrap(Ll,null,["number","number","number","number","number","number","number","number","array","number","number"])}function are(e){let{inputs:t,backend:n,attrs:a}=e,{image:r}=t,{radians:s,fillValue:i,center:o}=a,l=n.makeOutput(r.shape,r.dtype),c=n.dataIdMap.get(r.dataId).id,u=n.dataIdMap.get(l.dataId).id,[p,d,h,m]=r.shape,[f,g]=E.getImageCenter(o,d,h),y=i===0,b=255,v=typeof i=="number"?[i,i,i,y?0:b]:[...i,b],x=new Uint8Array(new Int32Array(v).buffer);return J2(c,p,d,h,m,s,f,g,x,v.length,u),l}var rre={kernelName:Ll,backendName:"wasm",kernelFunc:are,setupFunc:nre},sre=Un(hi),ire=Un(mi),Z2;function ore(e){Z2=e.wasm.cwrap(Tl,null,["number","number","number","number","number","number","array","number","number"])}function lre(e){let{backend:t,inputs:n,attrs:a}=e,{indices:r,updates:s}=n,{shape:i}=a,o=t.makeOutput(i,s.dtype);if(k.sizeFromShape(i)===0)return o;let{sliceRank:l,numUpdates:c,sliceSize:u,strides:p,outputSize:d}=Fy.calculateShapes(s,r,i),h=t.dataIdMap.get(r.dataId).id,m=t.dataIdMap.get(s.dataId).id,f=new Uint8Array(new Int32Array(p).buffer),g=t.dataIdMap.get(o.dataId).id;return Z2(h,m,Vn[s.dtype],l,c,u,f,d,g),o}var ure={kernelName:Tl,backendName:"wasm",setupFunc:ore,kernelFunc:lre},Q2;function cre(e){Q2=e.wasm.cwrap("SelectV2",null,["number","number","number","number","number"])}function pre(e){let{inputs:t,backend:n}=e,{condition:a,t:r,e:s}=t,i=n.dataIdMap.get(a.dataId).id,o=n.dataIdMap.get(r.dataId).id,l=n.dataIdMap.get(s.dataId).id,c=n.makeOutput(r.shape,r.dtype),u=n.dataIdMap.get(c.dataId).id,p=a.shape.length,d=r.shape.length,h=p===0||p>1||d===1?1:k.sizeFromShape(r.shape.slice(1));return Q2(i,o,l,h,u),c}var dre={kernelName:Sl,backendName:"wasm",kernelFunc:pre,setupFunc:cre},eC;function hre(e){eC=e.wasm.cwrap(gi,null,["number","number"])}function mre(e){let{backend:t,inputs:{x:n}}=e,a=t.dataIdMap.get(n.dataId).id,r=t.makeOutput(n.shape,n.dtype),s=t.dataIdMap.get(r.dataId).id;return k.sizeFromShape(r.shape)===0||eC(a,s),r}var fre={kernelName:"Sigmoid",backendName:"wasm",setupFunc:hre,kernelFunc:mre},gre=Un(fi);function gf(e){let{inputs:{x:t},attrs:{begin:n,size:a},backend:r}=e,[s,i]=dn.parseSliceParams(t,n,a),o=dn.isSliceContinous(t.shape,s,i),l=r.readSync(t.dataId),c=r.makeOutput(i,t.dtype),u=k.computeStrides(t.shape),p=r.dataIdMap.get(c.dataId);if(o){let m=dn.computeFlatOffset(s,u);return t.dtype==="string"?p.stringBytes=l.slice(m,m+k.sizeFromShape(i)):r.typedArrayFromHeap(c).set(l.subarray(m,m+k.sizeFromShape(i))),c}if(t.dtype==="string"){let m=Km(l,s,i,t.shape,t.dtype);return p.stringBytes=m,c}let d=r.typedArrayFromHeap(c),h=t.shape.length;if(h===2)yre(l,u[0],d,s,i);else if(h===3)bre(l,u[0],u[1],d,s,i);else if(h===4)xre(l,u[0],u[1],u[2],d,s,i);else{let m=Km(l,s,i,t.shape,t.dtype);d.set(m)}return c}function yre(e,t,n,a,r){let s=0,i=a[0],o=a[1],l=i+r[0];for(let c=i;c{let d=[...u];d[o]=p;let h=gf({inputs:{x:r},attrs:{begin:c,size:d},backend:a});return c[o]+=p,h})}var Tre={kernelName:$l,backendName:"wasm",kernelFunc:Nre},Sre=Un(yi),Cre=Un(Ac),_re=!0,Ere=yn(vi,_re),nC;function Are(e){nC=e.wasm.cwrap(Kr,null,["number","number","number"])}function Fre(e){let{backend:t,inputs:n,attrs:a}=e,{alpha:r}=a,{x:s}=n,i=t.dataIdMap.get(s.dataId).id,o=t.makeOutput(s.shape,s.dtype),l=t.dataIdMap.get(o.dataId).id;return nC(i,r,l),o}var $re={kernelName:Kr,backendName:"wasm",setupFunc:Are,kernelFunc:Fre},aC;function Dre(e){aC=e.wasm.cwrap(Dl,null,["number","array","number","array","array","array","array","array","number","number"])}function Mre(e){let{backend:t,inputs:n,attrs:a}=e,{x:r}=n,{begin:s,end:i,strides:o}=a;o==null&&(o=new Array(s.length));let{beginMask:l,endMask:c,ellipsisMask:u,newAxisMask:p,shrinkAxisMask:d}=a,h=E.slice_util.maskToAxes(u);if(h.length>1)throw new Error("Multiple ellipses in slice is not allowed.");if(u!==0&&p!==0)throw new Error("Using both ellipsisMask and newAxisMask is not yet supported.");if(u!==0&&d!==0)throw new Error("Using both ellipsisMask and shrinkAxisMask is not yet supported.");let m=r.shape.length-s.length,f=E.slice_util.maskToAxes(p),g=r.shape.slice();f.forEach(F=>{s[F]=0,i[F]=1,g.splice(F,0,1)});let y=za({inputs:{x:r},attrs:{shape:g},backend:t}),{begin:b,end:v,strides:x}=E.slice_util.getNormalizedAxes(y.shape,h,m,s,i,o,l,c,u);s=b,i=v,o=x;let N=E.slice_util.maskToAxes(d);N.forEach(F=>{i[F]=s[F]+1,o[F]=1});let T=E.slice_util.computeOutShape(s,i,o),C=T.filter((F,O)=>N.indexOf(O)===-1);if(o.every(F=>F===1)){let F=gf({inputs:{x:r},attrs:{begin:s,size:T},backend:t});return za({inputs:{x:F},attrs:{shape:C},backend:t})}let $=t.makeOutput(C,"float32");if(!C.some(F=>F===0)){let F=t.dataIdMap.get(y.dataId).id,O=new Uint8Array(new Int32Array(k.computeStrides(y.shape)).buffer),W=new Uint8Array(new Int32Array(s).buffer),V=new Uint8Array(new Int32Array(i).buffer),H=new Uint8Array(new Int32Array(o).buffer),K=new Uint8Array(new Int32Array(C).buffer),j=new Uint8Array(new Int32Array(k.computeStrides(C)).buffer),Y=t.dataIdMap.get($.dataId).id;aC(F,O,y.shape.length,W,V,H,K,j,C.length,Y)}return za({inputs:{x:$},attrs:{shape:C},backend:t})}var Rre={kernelName:Dl,backendName:"wasm",setupFunc:Dre,kernelFunc:Mre},Pre=!0,Ore=yn(wi,Pre),rC;function Lre(e){rC=e.wasm.cwrap(bi,null,["number, number, number"])}function zre(e){let{backend:t,inputs:n,attrs:a}=e,{axis:r,keepDims:s}=a,{x:i}=n,o=t.dataIdMap.get(i.dataId).id,l=o,c=i,{transposed:u,axes:p,originalAxes:d,inputWasTransposed:h}=Cu(i,r,t),m=p;if(h){let v=t.dataIdMap.get(u.dataId).id;v!==o&&(c=u,l=v,m=E.getInnerMostAxes(m.length,c.shape.length))}E.assertAxesAreInnerMostDims("sum",m,c.shape.length);let[f,g]=E.computeOutAndReduceShapes(c.shape,m),y=k.sizeFromShape(g),b=t.makeOutput(f,c.dtype);if(k.sizeFromShape(c.shape)!==0){let v=t.dataIdMap.get(b.dataId).id;rC(l,y,v)}if(h&&t.disposeData(u.dataId),s){let v=E.expandShapeToKeepDim(b.shape,d);b.shape=v}return b}var Bre={kernelName:bi,backendName:"wasm",setupFunc:Lre,kernelFunc:zre},Wre=Un(ki),sC;function Vre(e){sC=e.wasm.cwrap(qr,null,["number","array","number","array","number","number"])}function Ure(e){let{inputs:t,backend:n,attrs:a}=e,{x:r}=t,s=n.dataIdMap.get(r.dataId).id,{reps:i}=a,o=new Array(r.shape.length);for(let d=0;d{let{x:a}=e,{k:r,sorted:s}=n,i=t.dataIdMap.get(a.dataId).id,o=new Uint8Array(new Int32Array(a.shape).buffer),l=a.shape.slice();l[l.length-1]=r;let c=t.makeOutput(l,a.dtype),u=t.dataIdMap.get(c.dataId).id,p=t.makeOutput(l,"int32"),d=t.dataIdMap.get(p.dataId).id;return iC(i,o,a.shape.length,Vn[a.dtype],r,s,u,d),[c,p]},qre={kernelName:Rl,backendName:"wasm",setupFunc:Hre,kernelFunc:jre};function Kre(e){let{inputs:t,backend:n,attrs:a}=e,{value:r}=t,{axis:s}=a;s<0&&(s+=r.shape.length);let i=r.shape[s],o=r.shape.length,l=new Array(o-1),c=0;for(let h=0;h({dataId:h,dtype:m,shape:l}))}var Xre={kernelName:Pl,backendName:"wasm",kernelFunc:Kre};function Yre(e){let{inputs:{x:t},backend:n}=e,a=n.makeOutput(t.shape,t.dtype);return n.typedArrayFromHeap(a).fill(0),a}var Jre={kernelName:Ol,backendName:"wasm",kernelFunc:Yre},Zre=[bte,vte,Ite,Fte,Mte,Lte,zte,Vte,Ute,jte,Xte,Yte,Qte,nne,sne,lne,cne,pne,dne,mne,yne,bne,vne,yte,Ine,Sne,Ene,$ne,Rne,One,zne,Nte,Vne,Gne,jne,qne,Xne,Zne,eae,aae,iae,uae,pae,hae,mae,yae,vae,Iae,Tae,_ae,Aae,$ae,Rae,Oae,Bae,Uae,Hae,qae,Kae,Xae,Rte,Zae,tre,rre,ire,sre,ure,dre,fre,gre,vre,Ire,Tre,Sre,Cre,Ere,$re,Rre,Ore,Bre,Wre,Gre,qre,_te,Xre,Jre];for(let e of Zre)Dc(e);var ow=te();ow.registerFlag("WASM_HAS_SIMD_SUPPORT",async()=>WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,10,9,1,7,0,65,0,253,15,26,11])));ow.registerFlag("WASM_HAS_MULTITHREAD_SUPPORT",async()=>{if(ow.get("IS_NODE"))return!1;try{return new MessageChannel().port1.postMessage(new SharedArrayBuffer(1)),WebAssembly.validate(new Uint8Array([0,97,115,109,1,0,0,0,1,4,1,96,0,0,3,2,1,0,5,4,1,3,1,1,10,11,1,9,0,65,0,254,16,2,0,26,11]))}catch(e){return!1}});var oC=Ro(lA()),Qre='var threadInfoStruct=0;var selfThreadId=0;var parentThreadId=0;var Module={};function threadPrintErr(){var text=Array.prototype.slice.call(arguments).join(" ");console.error(text)}function threadAlert(){var text=Array.prototype.slice.call(arguments).join(" ");postMessage({cmd:"alert",text:text,threadId:selfThreadId})}var err=threadPrintErr;this.alert=threadAlert;Module["instantiateWasm"]=function(info,receiveInstance){var instance=new WebAssembly.Instance(Module["wasmModule"],info);Module["wasmModule"]=null;receiveInstance(instance);return instance.exports};this.onmessage=function(e){try{if(e.data.cmd==="load"){Module["DYNAMIC_BASE"]=e.data.DYNAMIC_BASE;Module["DYNAMICTOP_PTR"]=e.data.DYNAMICTOP_PTR;Module["wasmModule"]=e.data.wasmModule;Module["wasmMemory"]=e.data.wasmMemory;Module["buffer"]=Module["wasmMemory"].buffer;Module["ENVIRONMENT_IS_PTHREAD"]=true;if(typeof e.data.urlOrBlob==="string"){importScripts(e.data.urlOrBlob)}else{var objectUrl=URL.createObjectURL(e.data.urlOrBlob);importScripts(objectUrl);URL.revokeObjectURL(objectUrl)}Module=WasmBackendModuleThreadedSimd(Module);postMessage({"cmd":"loaded"})}else if(e.data.cmd==="objectTransfer"){Module["PThread"].receiveObjectTransfer(e.data)}else if(e.data.cmd==="run"){Module["__performance_now_clock_drift"]=performance.now()-e.data.time;threadInfoStruct=e.data.threadInfoStruct;Module["__register_pthread_ptr"](threadInfoStruct,0,0);selfThreadId=e.data.selfThreadId;parentThreadId=e.data.parentThreadId;var max=e.data.stackBase;var top=e.data.stackBase+e.data.stackSize;Module["establishStackSpace"](top,max);Module["_emscripten_tls_init"]();Module["PThread"].receiveObjectTransfer(e.data);Module["PThread"].setThreadStatus(Module["_pthread_self"](),1);try{var result=Module["dynCall_ii"](e.data.start_routine,e.data.arg);if(!Module["getNoExitRuntime"]())Module["PThread"].threadExit(result)}catch(ex){if(ex==="Canceled!"){Module["PThread"].threadCancel()}else if(ex!="unwind"){Atomics.store(Module["HEAPU32"],threadInfoStruct+4>>2,ex instanceof Module["ExitStatus"]?ex.status:-2);Atomics.store(Module["HEAPU32"],threadInfoStruct+0>>2,1);Module["_emscripten_futex_wake"](threadInfoStruct+0,2147483647);if(!(ex instanceof Module["ExitStatus"]))throw ex}}}else if(e.data.cmd==="cancel"){if(threadInfoStruct){Module["PThread"].threadCancel()}}else if(e.data.target==="setimmediate"){}else if(e.data.cmd==="processThreadQueue"){if(threadInfoStruct){Module["_emscripten_current_thread_process_queued_calls"]()}}else{err("worker.js received unknown command "+e.data.cmd);err(e.data)}}catch(ex){err("worker.js onmessage() captured an uncaught exception: "+ex);if(ex.stack)err(ex.stack);throw ex}};if(typeof process==="object"&&typeof process.versions==="object"&&typeof process.versions.node==="string"){self={location:{href:__filename}};var onmessage=this.onmessage;var nodeWorkerThreads=require("worker_threads");Worker=nodeWorkerThreads.Worker;var parentPort=nodeWorkerThreads.parentPort;parentPort.on("message",function(data){onmessage({data:data})});var nodeFS=require("fs");var nodeRead=function(filename){return nodeFS.readFileSync(filename,"utf8")};function globalEval(x){global.require=require;global.Module=Module;eval.call(null,x)}importScripts=function(f){globalEval(nodeRead(f))};postMessage=function(msg){parentPort.postMessage(msg)};if(typeof performance==="undefined"){performance={now:function(){return Date.now()}}}}',ese=Ro(uA()),lC=class extends dc{constructor(e){super();this.wasm=e,this.dataIdNextNumber=1,this.wasm.tfjs.init(),this.dataIdMap=new Dd(this,ts())}write(e,t,n){let a={};return this.move(a,e,t,n),a}numDataIds(){return this.dataIdMap.numDataIds()}async time(e){let t=k.now();return e(),{kernelMs:k.now()-t}}move(e,t,n,a){let r=this.dataIdNextNumber++;if(a==="string"){let l=t;this.dataIdMap.set(e,{id:r,stringBytes:l,shape:n,dtype:a,memoryOffset:null});return}let s=k.sizeFromShape(n),i=s*k.bytesPerElement(a),o=this.wasm._malloc(i);this.dataIdMap.set(e,{id:r,memoryOffset:o,shape:n,dtype:a}),this.wasm.tfjs.registerTensor(r,s,o),t!=null&&this.wasm.HEAPU8.set(new Uint8Array(t.buffer,t.byteOffset,i),o)}async read(e){return this.readSync(e)}readSync(e){let{memoryOffset:t,dtype:n,shape:a,stringBytes:r}=this.dataIdMap.get(e);if(n==="string")return r;let s=this.wasm.HEAPU8.slice(t,t+k.sizeFromShape(a)*k.bytesPerElement(n));return tse(s.buffer,n)}disposeData(e){let t=this.dataIdMap.get(e);this.wasm._free(t.memoryOffset),this.wasm.tfjs.disposeData(t.id),this.dataIdMap.delete(e)}floatPrecision(){return 32}getMemoryOffset(e){return this.dataIdMap.get(e).memoryOffset}dispose(){this.wasm.tfjs.dispose(),this.wasm=null}memory(){return{unreliable:!1}}makeOutput(e,t,n){let a;if(n==null)a=this.write(null,e,t);else{a={};let r=this.dataIdNextNumber++;this.dataIdMap.set(a,{id:r,memoryOffset:n,shape:e,dtype:t});let s=k.sizeFromShape(e);this.wasm.tfjs.registerTensor(r,s,n)}return{dataId:a,shape:e,dtype:t}}typedArrayFromHeap({shape:e,dtype:t,dataId:n}){let a=this.wasm.HEAPU8.buffer,{memoryOffset:r}=this.dataIdMap.get(n),s=k.sizeFromShape(e);switch(t){case"float32":return new Float32Array(a,r,s);case"int32":return new Int32Array(a,r,s);case"bool":return new Uint8Array(a,r,s);default:throw new Error(`Unknown dtype ${t}`)}}};function nse(e){return(t,n)=>(k.fetch(e,{credentials:"same-origin"}).then(a=>{a.ok||t.env.a(`failed to load wasm binary file at '${e}'`),a.arrayBuffer().then(r=>{WebAssembly.instantiate(r,t).then(s=>{n(s.instance)})})}),{})}function uC(e,t,n){if(yf!=null)return yf;let a="tfjs-backend-wasm.wasm";return e&&t?a="tfjs-backend-wasm-threaded-simd.wasm":e&&(a="tfjs-backend-wasm-simd.wasm"),Rp!=null&&Rp[a]!=null?Rp[a]:n+a}async function ase(){let[e,t]=await Promise.all([te().getAsync("WASM_HAS_SIMD_SUPPORT"),te().getAsync("WASM_HAS_MULTITHREAD_SUPPORT")]);return new Promise((n,a)=>{let r={};r.locateFile=(l,c)=>{if(l.endsWith(".worker.js")){let u=Qre,p=new Blob([u],{type:"application/javascript"});return URL.createObjectURL(p)}return l.endsWith(".wasm")?uC(e,t,Pp!=null?Pp:c):c+l},lw&&(r.instantiateWasm=nse(uC(e,t,Pp!=null?Pp:"")));let s;t&&e&&yf==null?(s=oC.default(r),s.mainScriptUrlOrBlob=new Blob(["var WasmBackendModuleThreadedSimd = "+oC.default.toString()],{type:"text/javascript"})):s=ese.default(r);let i=null;s.tfjs={init:s.cwrap("init",null,[]),registerTensor:s.cwrap("register_tensor",null,["number","number","number"]),disposeData:s.cwrap("dispose_data",i,["number"]),dispose:s.cwrap("dispose",i,[])};let o=!1;s.onRuntimeInitialized=()=>{o=!0,Op=!1,n({wasm:s})},s.onAbort=()=>{o||Op||(Op=!0,a({message:"Make sure the server can serve the `.wasm` file relative to the bundled js file. For more details see https://github.com/tensorflow/tfjs/blob/master/tfjs-backend-wasm/README.md#using-bundlers"}))}})}function tse(e,t){switch(t){case"float32":return new Float32Array(e);case"int32":return new Int32Array(e);case"bool":return new Uint8Array(e);default:throw new Error(`Unknown dtype ${t}`)}}var rse=["tfjs-backend-wasm.wasm","tfjs-backend-wasm-simd.wasm","tfjs-backend-wasm-threaded-simd.wasm"],yf=null,Pp=null,Rp={},Op=!1,lw=!1;function sse(e,t=!1){if(Rt("setWasmPath has been deprecated in favor of setWasmPaths and will be removed in a future release."),Op)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPath()` before you call `tf.setBackend()` or `tf.ready()`");yf=e,lw=t}function ise(e,t=!1){if(Op)throw new Error("The WASM backend was already initialized. Make sure you call `setWasmPaths()` before you call `tf.setBackend()` or `tf.ready()`");if(typeof e=="string")Pp=e;else{Rp=e;let n=rse.filter(a=>Rp[a]==null);if(n.length>0)throw new Error(`There were no entries found for the following binaries: ${n.join(",")}. Please either call setWasmPaths with a map providing a path for each binary, or with a string indicating the directory where all the binaries can be found.`)}lw=t}var ose="2.8.5",lse=2;Th("wasm",async()=>{let{wasm:e}=await ase();return new lC(e)},lse);var Uf={};cc(Uf,{AnchorPosition:()=>cr,DrawBox:()=>Sf,DrawBoxOptions:()=>vw,DrawFaceLandmarks:()=>kw,DrawFaceLandmarksOptions:()=>ww,DrawTextField:()=>vs,DrawTextFieldOptions:()=>Lp,drawContour:()=>Fr,drawDetections:()=>yse,drawFaceExpressions:()=>bse,drawFaceLandmarks:()=>xse});function Fr(e,t,n=!1){if(e.beginPath(),t.slice(1).forEach(({x:a,y:r},s)=>{let i=t[s];e.moveTo(i.x,i.y),e.lineTo(a,r)}),n){let a=t[t.length-1],r=t[0];if(!a||!r)return;e.moveTo(a.x,a.y),e.lineTo(r.x,r.y)}e.stroke()}var bf={};cc(bf,{computeReshapedDimensions:()=>pw,getCenterPoint:()=>no,isDimensions:()=>vf,isEven:()=>xf,isFloat:()=>cw,isTensor:()=>eo,isTensor1D:()=>use,isTensor2D:()=>uw,isTensor3D:()=>$r,isTensor4D:()=>ra,isValidNumber:()=>Ba,isValidProbablitiy:()=>_u,range:()=>lr,round:()=>to});var un=class{constructor(t,n){if(!Ba(t)||!Ba(n))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:n})}`);this._width=t,this._height=n}get width(){return this._width}get height(){return this._height}reverse(){return new un(1/this.width,1/this.height)}};function eo(e,t){return e instanceof z&&e.shape.length===t}function use(e){return eo(e,1)}function uw(e){return eo(e,2)}function $r(e){return eo(e,3)}function ra(e){return eo(e,4)}function cw(e){return e%1!=0}function xf(e){return e%2==0}function to(e,t=2){let n=10**t;return Math.floor(e*n)/n}function vf(e){return e&&e.width&&e.height}function pw({width:e,height:t},n){let a=n/Math.max(t,e);return new un(Math.round(e*a),Math.round(t*a))}function no(e){return e.reduce((t,n)=>t.add(n),new De(0,0)).div(new De(e.length,e.length))}function lr(e,t,n){return Array(e).fill(0).map((a,r)=>t+r*n)}function Ba(e){return!!e&&e!==Infinity&&e!==-Infinity&&!Number.isNaN(e)||e===0}function _u(e){return Ba(e)&&e>=0&&e<=1}var De=class{constructor(t,n){this._x=t,this._y=n}get x(){return this._x}get y(){return this._y}add(t){return new De(this.x+t.x,this.y+t.y)}sub(t){return new De(this.x-t.x,this.y-t.y)}mul(t){return new De(this.x*t.x,this.y*t.y)}div(t){return new De(this.x/t.x,this.y/t.y)}abs(){return new De(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new De(Math.floor(this.x),Math.floor(this.y))}};var lt=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(Ba)}static assertIsValidBox(t,n,a=!1){if(!lt.isRect(t))throw new Error(`${n} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!a&&(t.width<0||t.height<0))throw new Error(`${n} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,n=!0){let a=t||{},r=[a.left,a.top,a.right,a.bottom].every(Ba),s=[a.x,a.y,a.width,a.height].every(Ba);if(!s&&!r)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(a)}`);let[i,o,l,c]=s?[a.x,a.y,a.width,a.height]:[a.left,a.top,a.right-a.left,a.bottom-a.top];lt.assertIsValidBox({x:i,y:o,width:l,height:c},"Box.constructor",n),this._x=i,this._y=o,this._width=l,this._height=c}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new De(this.left,this.top)}get topRight(){return new De(this.right,this.top)}get bottomLeft(){return new De(this.left,this.bottom)}get bottomRight(){return new De(this.right,this.bottom)}round(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.round(s));return new lt({x:t,y:n,width:a,height:r})}floor(){let[t,n,a,r]=[this.x,this.y,this.width,this.height].map(s=>Math.floor(s));return new lt({x:t,y:n,width:a,height:r})}toSquare(){let{x:t,y:n,width:a,height:r}=this,s=Math.abs(a-r);return an&&(o=-p+n+a,p=n),d>t&&(l=-d+t+r,d=t),c<1&&(l=2-c,c=1),u<1&&(l=2-u,u=1),{dy:i,edy:l,dx:s,edx:o,y:u,ey:d,x:c,ex:p,w:a,h:r}}calibrate(t){return new lt({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var ao=class extends lt{constructor(t,n,a,r,s=!1){super({left:t,top:n,right:a,bottom:r},s)}};var Dr=class{constructor(t,n,a,r,s){this._imageDims=new un(s.width,s.height),this._score=t,this._classScore=n,this._className=a,this._box=new lt(r).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new lt(this._box).rescale(this.imageDims.reverse())}forSize(t,n){return new Dr(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:n})}};var bt=class extends Dr{constructor(t,n,a){super(t,t,"",n,a)}forSize(t,n){let{score:a,relativeBox:r,imageDims:s}=super.forSize(t,n);return new bt(a,r,s)}};function wf(e,t,n=!0){let a=Math.max(0,Math.min(e.right,t.right)-Math.max(e.left,t.left)),r=Math.max(0,Math.min(e.bottom,t.bottom)-Math.max(e.top,t.top)),s=a*r;return n?s/(e.area+t.area-s):s/Math.min(e.area,t.area)}function kf(e){let t=e.map(o=>o.x),n=e.map(o=>o.y),a=t.reduce((o,l)=>lloo({score:i,boxIndex:o})).sort((i,o)=>i.score-o.score).map(i=>i.boxIndex),s=[];for(;r.length>0;){let i=r.pop();s.push(i);let o=r,l=[];for(let c=0;cl[u]<=n)}return s}function ka(e,t){return D(()=>{let[n,a,r]=t,s=In([...e.shape.slice(0,3),1],n,"float32"),i=In([...e.shape.slice(0,3),1],a,"float32"),o=In([...e.shape.slice(0,3),1],r,"float32"),l=Qe([s,i,o],3);return ge(e,l)})}function Nf(e,t=!1){return D(()=>{let[n,a]=e.shape.slice(1);if(n===a)return e;let r=Math.abs(n-a),s=Math.round(r*(t?.5:1)),i=n>a?2:1,o=d=>{let h=e.shape.slice();return h[i]=d,In(h,0,"float32")},l=o(s),c=r-l.shape[i],p=[t&&c?o(c):null,e,l].filter(d=>!!d).map(d=>pe(d,"float32"));return Qe(p,i)})}function cC(e){let t=e.slice();for(let n=t.length-1;n>0;n--){let a=Math.floor(Math.random()*(n+1)),r=t[n];t[n]=t[a],t[a]=r}return t}function Eu(e){return 1/(1+Math.exp(-e))}function pC(e){return Math.log(e/(1-e))}var ro=class extends lt{constructor(t,n,a,r,s=!1){super({x:t,y:n,width:a,height:r},s)}};var cse=.5,pse=.43,dse=.45,Gn=class{constructor(t,n,a=new De(0,0)){let{width:r,height:s}=n;this._imgDims=new un(r,s),this._shift=a,this._positions=t.map(i=>i.mul(new De(r,s)).add(a))}get shift(){return new De(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new De(this.imageWidth,this.imageHeight)))}forSize(t,n){return new this.constructor(this.relativePositions,{width:t,height:n})}shiftBy(t,n){return new this.constructor(this.relativePositions,this._imgDims,new De(t,n))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,n={}){if(t){let s=t instanceof bt?t.box.floor():new lt(t);return this.shiftBy(s.x,s.y).align(null,n)}let{useDlibAlignment:a,minBoxPadding:r}={useDlibAlignment:!1,minBoxPadding:.2,...n};return a?this.alignDlib():this.alignMinBbox(r)}alignDlib(){let t=this.getRefPointsForAlignment(),[n,a,r]=t,s=p=>r.sub(p).magnitude(),i=(s(n)+s(a))/2,o=Math.floor(i/dse),l=no(t),c=Math.floor(Math.max(0,l.x-cse*o)),u=Math.floor(Math.max(0,l.y-pse*o));return new ro(c,u,Math.min(o,this.imageWidth+c),Math.min(o,this.imageHeight+u))}alignMinBbox(t){let n=kf(this.positions);return n.pad(n.width*t,n.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var dw=class extends Gn{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],no([t[3],t[4]])]}};var so=class extends Gn{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(no)}};var Au=class{constructor(t,n){this._label=t,this._distance=n}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${to(this.distance)})`:""}`}};var Fu=class extends lt{static assertIsValidLabeledBox(t,n){if(lt.assertIsValidBox(t,n),!Ba(t.label))throw new Error(`${n} - expected property label (${t.label}) to be a number`)}constructor(t,n){super(t);this._label=n}get label(){return this._label}};var ur=class{constructor(t,n){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(n)||n.some(a=>!(a instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=n}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let n=t.descriptors.map(a=>new Float32Array(a));return new ur(t.label,n)}};var hw=class extends Fu{static assertIsValidPredictedBox(t,n){if(Fu.assertIsValidLabeledBox(t,n),!_u(t.score)||!_u(t.classScore))throw new Error(`${n} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,n,a,r){super(t,n);this._score=a,this._classScore=r}get score(){return this._score}get classScore(){return this._classScore}};function Wa(e){return e.detection instanceof bt}function bs(e,t){return{...e,...{detection:t}}}function mw(){let e=window.fetch;if(!e)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:e,readFile:t}}function Tf(e){let t="";if(!e)try{e=require("fs")}catch(a){t=a.toString()}return{readFile:e?a=>new Promise((r,s)=>{e.readFile(a,(i,o)=>i?s(i):r(o))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function fw(){let e=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,n=()=>{if(e)return new e;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},a=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},r=global.fetch,s=Tf();return{Canvas:e||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:n,createImageElement:a,fetch:r,...s}}function gw(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var yw=UE(hC()),en;function fse(){if(!en)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return en}function bw(e){en=e}function xw(){return gw()?bw(mw()):yw.isNodejs()?bw(fw()):null}function gse(e){if(en||xw(),!en)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=en.Canvas,Image:n=en.Image}=e;en.Canvas=t,en.Image=n,en.createCanvasElement=e.createCanvasElement||(()=>new t),en.createImageElement=e.createImageElement||(()=>new n),en.ImageData=e.ImageData||en.ImageData,en.Video=e.Video||en.Video,en.fetch=e.fetch||en.fetch,en.readFile=e.readFile||en.readFile}var st={getEnv:fse,setEnv:bw,initialize:xw,createBrowserEnv:mw,createFileSystem:Tf,createNodejsEnv:fw,monkeyPatch:gse,isBrowser:gw,isNodejs:yw.isNodejs};xw();function xs(e){return!st.isNodejs()&&typeof e=="string"?document.getElementById(e):e}function bn(e){let{Canvas:t,CanvasRenderingContext2D:n}=st.getEnv();if(e instanceof n)return e;let a=xs(e);if(!(a instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let r=a.getContext("2d");if(!r)throw new Error("resolveContext2d - canvas 2d context is null");return r}var cr;(function(e){e.TOP_LEFT="TOP_LEFT",e.TOP_RIGHT="TOP_RIGHT",e.BOTTOM_LEFT="BOTTOM_LEFT",e.BOTTOM_RIGHT="BOTTOM_RIGHT"})(cr||(cr={}));var Lp=class{constructor(t={}){let{anchorPosition:n,backgroundColor:a,fontColor:r,fontSize:s,fontStyle:i,padding:o}=t;this.anchorPosition=n||cr.TOP_LEFT,this.backgroundColor=a||"rgba(0, 0, 0, 0.5)",this.fontColor=r||"rgba(255, 255, 255, 1)",this.fontSize=s||14,this.fontStyle=i||"Georgia",this.padding=o||4}},vs=class{constructor(t,n,a={}){this.text=typeof t=="string"?[t]:t instanceof vs?t.text:t,this.anchor=n,this.options=new Lp(a)}measureWidth(t){let{padding:n}=this.options;return this.text.map(a=>t.measureText(a).width).reduce((a,r)=>a{let m=l+p.x,f=l+p.y+(h+1)*i;a.fillText(d,m,f)})}};var vw=class{constructor(t={}){let{boxColor:n,lineWidth:a,label:r,drawLabelOptions:s}=t;this.boxColor=n||"rgba(0, 0, 255, 1)",this.lineWidth=a||2,this.label=r;let i={anchorPosition:cr.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Lp({...i,...s})}},Sf=class{constructor(t,n={}){this.box=new lt(t),this.options=new vw(n)}draw(t){let n=bn(t),{boxColor:a,lineWidth:r}=this.options,{x:s,y:i,width:o,height:l}=this.box;n.strokeStyle=a,n.lineWidth=r,n.strokeRect(s,i,o,l);let{label:c}=this.options;c&&new vs([c],{x:s-r/2,y:i},this.options.drawLabelOptions).draw(t)}};function yse(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof bt?a.score:Wa(a)?a.detection.score:void 0,s=a instanceof bt?a.box:Wa(a)?a.detection.box:new lt(a),i=r?`${to(r)}`:void 0;new Sf(s,{label:i}).draw(e)})}function $u(e){let{Image:t,Video:n}=st.getEnv();return e instanceof t&&e.complete||e instanceof n&&e.readyState>=3}function Cf(e){return new Promise((t,n)=>{if(e instanceof st.getEnv().Canvas||$u(e))return t(null);function a(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),n(s))}function r(s){!s.currentTarget||(s.currentTarget.removeEventListener("load",r),s.currentTarget.removeEventListener("error",a),t(s))}e.addEventListener("load",r),e.addEventListener("error",a)})}function _f(e){return new Promise((t,n)=>{e instanceof Blob||n(new Error("bufferToImage - expected buf to be of type: Blob"));let a=new FileReader;a.onload=()=>{typeof a.result!="string"&&n(new Error("bufferToImage - expected reader.result to be a string, in onload"));let r=st.getEnv().createImageElement();r.onload=()=>t(r),r.onerror=n,r.src=a.result},a.onerror=n,a.readAsDataURL(e)})}function ws(e){let{Image:t,Video:n}=st.getEnv();return e instanceof t?new un(e.naturalWidth,e.naturalHeight):e instanceof n?new un(e.videoWidth,e.videoHeight):new un(e.width,e.height)}function io({width:e,height:t}){let{createCanvasElement:n}=st.getEnv(),a=n();return a.width=e,a.height=t,a}function Du(e,t){let{ImageData:n}=st.getEnv();if(!(e instanceof n)&&!$u(e))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:a,height:r}=t||ws(e),s=io({width:a,height:r});return e instanceof n?bn(s).putImageData(e,0,0):bn(s).drawImage(e,0,0,a,r),s}async function Ef(e,t){let n=t||st.getEnv().createCanvasElement(),[a,r,s]=e.shape.slice(ra(e)?1:0),i=D(()=>e.as3D(a,r,s).toInt());return await Ai.toPixels(i,n),i.dispose(),n}function zp(e){let{Image:t,Canvas:n,Video:a}=st.getEnv();return e instanceof t||e instanceof n||e instanceof a}function Af(e,t,n=!1){let{Image:a,Canvas:r}=st.getEnv();if(!(e instanceof a||e instanceof r))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let s=ws(e),i=t/Math.max(s.height,s.width),o=i*s.width,l=i*s.height,c=io({width:t,height:t}),u=e instanceof r?e:Du(e),p=Math.abs(o-l)/2,d=n&&o{if($r(a)){this._imageTensors[r]=a,this._inputDimensions[r]=a.shape;return}if(ra(a)){let i=a.shape[0];if(i!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${i} passed, but not supported in input array`);this._imageTensors[r]=a,this._inputDimensions[r]=a.shape.slice(1);return}let s=a instanceof st.getEnv().Canvas?a:Du(a);this._canvases[r]=s,this._inputDimensions[r]=[s.height,s.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return lr(this.batchSize,0,1).map((t,n)=>this.getReshapedInputDimensions(n))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let n=this.getInputWidth(t),a=this.getInputHeight(t);return pw({width:n,height:a},this.inputSize)}toBatchTensor(t,n=!0){return this._inputSize=t,D(()=>{let a=lr(this.batchSize,0,1).map(s=>{let i=this.getInput(s);if(i instanceof z){let o=ra(i)?i:i.expandDims();return o=Nf(o,n),(o.shape[1]!==t||o.shape[2]!==t)&&(o=Qa.resizeBilinear(o,[t,t])),o.as3D(t,t,3)}if(i instanceof st.getEnv().Canvas)return Ai.fromPixels(Af(i,t,n));throw new Error(`toBatchTensor - at batchIdx ${s}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${i}`)});return Dt(a.map(s=>pe(s,"float32"))).as4D(this.batchSize,t,t,3)})}};async function yt(e){if(e instanceof pr)return e;let t=Array.isArray(e)?e:[e];if(!t.length)throw new Error("toNetInput - empty array passed as input");let n=r=>Array.isArray(e)?` at input index ${r}:`:"",a=t.map(xs);return a.forEach((r,s)=>{if(!zp(r)&&!$r(r)&&!ra(r))throw typeof t[s]=="string"?new Error(`toNetInput -${n(s)} string passed, but could not resolve HTMLElement for element id ${t[s]}`):new Error(`toNetInput -${n(s)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(ra(r)){let i=r.shape[0];if(i!==1)throw new Error(`toNetInput -${n(s)} tf.Tensor4D with batchSize ${i} passed, but not supported in input array`)}}),await Promise.all(a.map(r=>zp(r)&&Cf(r))),new pr(a,Array.isArray(e))}async function oo(e,t){let{Canvas:n}=st.getEnv(),a=e;if(!(e instanceof n)){let i=await yt(e);if(i.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let o=i.getInput(0);a=o instanceof n?o:await Ef(o)}let r=bn(a);return t.map(i=>i instanceof bt?i.forSize(a.width,a.height).box.floor():i).map(i=>i.clipAtImageBorders(a.width,a.height)).map(({x:i,y:o,width:l,height:c})=>{let u=io({width:l,height:c});return bn(u).putImageData(r.getImageData(i,o,l,c),0,0),u})}async function lo(e,t){if(!$r(e)&&!ra(e))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(ra(e)&&e.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return D(()=>{let[n,a,r]=e.shape.slice(ra(e)?1:0);return t.map(o=>o instanceof bt?o.forSize(a,n).box:o).map(o=>o.clipAtImageBorders(a,n)).map(({x:o,y:l,width:c,height:u})=>Ql(e.as3D(n,a,r),[l,o,0],[u,c,r]))})}async function ks(e,t){let{fetch:n}=st.getEnv(),a=await n(e,t);if(!(a.status<400))throw new Error(`failed to fetch: (${a.status}) ${a.statusText}, from url: ${a.url}`);return a}async function mC(e){let t=await ks(e),n=await t.blob();if(!n.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${n.type}, for url: ${t.url}`);return _f(n)}async function Ff(e){return(await ks(e)).json()}async function fC(e){return new Float32Array(await(await ks(e)).arrayBuffer())}function $f(e,t){let n=`${t}-weights_manifest.json`;if(!e)return{modelBaseUri:"",manifestUri:n};if(e==="/")return{modelBaseUri:"/",manifestUri:`/${n}`};let a=e.startsWith("http://")?"http://":e.startsWith("https://")?"https://":"";e=e.replace(a,"");let r=e.split("/").filter(o=>o),s=e.endsWith(".json")?r[r.length-1]:n,i=a+(e.endsWith(".json")?r.slice(0,r.length-1):r).join("/");return i=e.startsWith("/")?`/${i}`:i,{modelBaseUri:i,manifestUri:i==="/"?`/${s}`:`${i}/${s}`}}async function Df(e,t){let{manifestUri:n,modelBaseUri:a}=$f(e,t),r=await Ff(n);return qt.loadWeights(r,a)}function gC(e,t,n=!1){let{width:a,height:r}=n?ws(t):t;return e.width=a,e.height=r,{width:a,height:r}}var tn=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:n,objProp:a}=this.traversePropertyPath(t);return n[a]}reassignParamFromPath(t,n){let{obj:a,objProp:r}=this.traversePropertyPath(t);a[r].dispose(),a[r]=n}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof Xr)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof Xr))}variable(){this.getFrozenParams().forEach(({path:t,tensor:n})=>{this.reassignParamFromPath(t,n.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:n})=>{let a=Xn(n.dataSync());n.dispose(),this.reassignParamFromPath(t,a)})}dispose(t=!0){this.getParamList().forEach(n=>{if(t&&n.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${n.path}`);n.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,n)=>t.concat(n)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let n=await Df(t,this.getDefaultModelName());this.loadFromWeightMap(n)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:n}=st.getEnv(),{manifestUri:a,modelBaseUri:r}=$f(t,this.getDefaultModelName()),s=c=>Promise.all(c.map(u=>n(u).then(p=>p.buffer))),i=qt.weightsLoaderFactory(s),o=JSON.parse((await n(a)).toString()),l=await i(o,r);this.loadFromWeightMap(l)}loadFromWeightMap(t){let{paramMappings:n,params:a}=this.extractParamsFromWeightMap(t);this._paramMappings=n,this._params=a}extractWeights(t){let{paramMappings:n,params:a}=this.extractParams(t);this._paramMappings=n,this._params=a}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let n=t.split("/").reduce((s,i)=>{if(!s.nextObj.hasOwnProperty(i))throw new Error(`traversePropertyPath - object does not have property ${i}, for path ${t}`);return{obj:s.nextObj,objProp:i,nextObj:s.nextObj[i]}},{nextObj:this.params}),{obj:a,objProp:r}=n;if(!a||!r||!(a[r]instanceof z))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:a,objProp:r}}};function _n(e,t,n){return D(()=>{let a=Pi(e,t.depthwise_filter,t.pointwise_filter,n,"same");return a=Z(a,t.bias),a})}function Mf(e,t,n=!1){return D(()=>{let a=Ye(n?Z(Ft(e,t.conv0.filters,[2,2],"same"),t.conv0.bias):_n(e,t.conv0,[2,2])),r=_n(a,t.conv1,[1,1]),s=Ye(Z(a,r)),i=_n(s,t.conv2,[1,1]);return Ye(Z(a,Z(r,i)))})}function Bp(e,t,n=!1,a=!0){return D(()=>{let r=Ye(n?Z(Ft(e,t.conv0.filters,a?[2,2]:[1,1],"same"),t.conv0.bias):_n(e,t.conv0,a?[2,2]:[1,1])),s=_n(r,t.conv1,[1,1]),i=Ye(Z(r,s)),o=_n(i,t.conv2,[1,1]),l=Ye(Z(r,Z(s,o))),c=_n(l,t.conv3,[1,1]);return Ye(Z(r,Z(s,Z(o,c))))})}function uo(e,t,n="same",a=!1){return D(()=>{let r=Z(Ft(e,t.filters,[1,1],n),t.bias);return a?Ye(r):r})}function xn(e,t){Object.keys(e).forEach(n=>{t.some(a=>a.originalPath===n)||e[n].dispose()})}function Mu(e,t){return(n,a,r,s)=>{let i=Aa(e(n*a*r*r),[r,r,n,a]),o=nt(e(a));return t.push({paramPath:`${s}/filters`},{paramPath:`${s}/bias`}),{filters:i,bias:o}}}function Rf(e,t){return(n,a,r)=>{let s=Ea(e(n*a),[n,a]),i=nt(e(a));return t.push({paramPath:`${r}/weights`},{paramPath:`${r}/bias`}),{weights:s,bias:i}}}var Pf=class{constructor(t,n,a){this.depthwise_filter=t;this.pointwise_filter=n;this.bias=a}};function Ru(e,t){return(n,a,r)=>{let s=Aa(e(3*3*n),[3,3,n,1]),i=Aa(e(n*a),[1,1,n,a]),o=nt(e(a));return t.push({paramPath:`${r}/depthwise_filter`},{paramPath:`${r}/pointwise_filter`},{paramPath:`${r}/bias`}),new Pf(s,i,o)}}function Pu(e){return t=>{let n=e(`${t}/depthwise_filter`,4),a=e(`${t}/pointwise_filter`,4),r=e(`${t}/bias`,1);return new Pf(n,a,r)}}function Hn(e,t){return(n,a,r)=>{let s=e[n];if(!eo(s,a))throw new Error(`expected weightMap[${n}] to be a Tensor${a}D, instead have ${s}`);return t.push({originalPath:n,paramPath:r||n}),s}}function vn(e){let t=e;function n(r){let s=t.slice(0,r);return t=t.slice(r),s}function a(){return t}return{extractWeights:n,getRemainingWeights:a}}function Of(e,t){let n=Mu(e,t),a=Ru(e,t);function r(i,o,l,c=!1){let u=c?n(i,o,3,`${l}/conv0`):a(i,o,`${l}/conv0`),p=a(o,o,`${l}/conv1`),d=a(o,o,`${l}/conv2`);return{conv0:u,conv1:p,conv2:d}}function s(i,o,l,c=!1){let{conv0:u,conv1:p,conv2:d}=r(i,o,l,c),h=a(o,o,`${l}/conv3`);return{conv0:u,conv1:p,conv2:d,conv3:h}}return{extractDenseBlock3Params:r,extractDenseBlock4Params:s}}function yC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),{extractDenseBlock4Params:r}=Of(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2"),l=r(128,256,"dense3");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o,dense3:l}}}function Lf(e){return t=>{let n=e(`${t}/filters`,4),a=e(`${t}/bias`,1);return{filters:n,bias:a}}}function zf(e,t){let n=Hn(e,t),a=Lf(n),r=Pu(n);function s(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`);return{conv0:c,conv1:u,conv2:p}}function i(o,l=!1){let c=l?a(`${o}/conv0`):r(`${o}/conv0`),u=r(`${o}/conv1`),p=r(`${o}/conv2`),d=r(`${o}/conv3`);return{conv0:c,conv1:u,conv2:p,conv3:d}}return{extractDenseBlock3Params:s,extractDenseBlock4Params:i}}function bC(e){let t=[],{extractDenseBlock4Params:n}=zf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2"),dense3:n("dense3")};return xn(e,t),{params:a,paramMappings:t}}var Wp=class extends tn{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(255)),i=Bp(s,n.dense0,!0);return i=Bp(i,n.dense1),i=Bp(i,n.dense2),i=Bp(i,n.dense3),i=Jn(i,[7,7],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return bC(t)}extractParams(t){return yC(t)}};function Vp(e,t){return D(()=>Z(ze(e,t.weights),t.bias))}function xC(e,t,n){let a=[],{extractWeights:r,getRemainingWeights:s}=vn(e),o=Rf(r,a)(t,n,"fc");if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{paramMappings:a,params:{fc:o}}}function vC(e){let t=[],n=Hn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:a("fc")};return xn(e,t),{params:r,paramMappings:t}}function Bf(e){let t={},n={};return Object.keys(e).forEach(a=>{let r=a.startsWith("fc")?n:t;r[a]=e[a]}),{featureExtractorMap:t,classifierMap:n}}var Up=class extends tn{constructor(t,n){super(t);this._faceFeatureExtractor=n}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof pr?this.faceFeatureExtractor.forwardInput(t):t;return Vp(a.as2D(a.shape[0],-1),n.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return xC(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=Bf(t);return this.faceFeatureExtractor.loadFromWeightMap(n),vC(a)}extractParams(t){let n=this.getClassifierChannelsIn(),a=this.getClassifierChannelsOut(),r=a*n+a,s=t.slice(0,t.length-r),i=t.slice(t.length-r);return this.faceFeatureExtractor.extractWeights(s),this.extractClassifierParams(i)}};var Wf=["neutral","happy","sad","angry","fearful","disgusted","surprised"],Mr=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Wf.forEach((n,a)=>{this[n]=t[a]})}asSortedArray(){return Wf.map(t=>({expression:t,probability:this[t]})).sort((t,n)=>n.probability-t.probability)}};var Gp=class extends Up{constructor(t=new Wp){super("FaceExpressionNet",t)}forwardInput(t){return D(()=>_a(this.runNet(t)))}async forward(t){return this.forwardInput(await yt(t))}async predictExpressions(t){let n=await yt(t),a=await this.forwardInput(n),r=await Promise.all(ht(a).map(async i=>{let o=await i.data();return i.dispose(),o}));a.dispose();let s=r.map(i=>new Mr(i));return n.isBatchInput?s:s[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function Vf(e){return e.expressions instanceof Mr}function Hp(e,t){return{...e,...{expressions:t}}}function bse(e,t,n=.1,a){(Array.isArray(t)?t:[t]).forEach(s=>{let i=s instanceof Mr?s:Vf(s)?s.expressions:void 0;if(!i)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let l=i.asSortedArray().filter(p=>p.probability>n),c=Wa(s)?s.detection.box.bottomLeft:a||new De(0,0);new vs(l.map(p=>`${p.expression} (${to(p.probability)})`),c).draw(e)})}function Is(e){return Wa(e)&&e.landmarks instanceof Gn&&e.unshiftedLandmarks instanceof Gn&&e.alignedRect instanceof bt}function co(e,t){let{box:n}=e.detection,a=t.shiftBy(n.x,n.y),r=a.align(),{imageDims:s}=e.detection,i=new bt(e.detection.score,r.rescale(s.reverse()),s);return{...e,...{landmarks:a,unshiftedLandmarks:t,alignedRect:i}}}var ww=class{constructor(t={}){let{drawLines:n=!0,drawPoints:a=!0,lineWidth:r,lineColor:s,pointSize:i,pointColor:o}=t;this.drawLines=n,this.drawPoints=a,this.lineWidth=r||1,this.pointSize=i||2,this.lineColor=s||"rgba(0, 255, 255, 1)",this.pointColor=o||"rgba(255, 0, 255, 1)"}},kw=class{constructor(t,n={}){this.faceLandmarks=t,this.options=new ww(n)}draw(t){let n=bn(t),{drawLines:a,drawPoints:r,lineWidth:s,lineColor:i,pointSize:o,pointColor:l}=this.options;if(a&&this.faceLandmarks instanceof so&&(n.strokeStyle=i,n.lineWidth=s,Fr(n,this.faceLandmarks.getJawOutline()),Fr(n,this.faceLandmarks.getLeftEyeBrow()),Fr(n,this.faceLandmarks.getRightEyeBrow()),Fr(n,this.faceLandmarks.getNose()),Fr(n,this.faceLandmarks.getLeftEye(),!0),Fr(n,this.faceLandmarks.getRightEye(),!0),Fr(n,this.faceLandmarks.getMouth(),!0)),r){n.strokeStyle=l,n.fillStyle=l;let c=u=>{n.beginPath(),n.arc(u.x,u.y,o,0,2*Math.PI),n.fill()};this.faceLandmarks.positions.forEach(c)}}};function xse(e,t){(Array.isArray(t)?t:[t]).forEach(a=>{let r=a instanceof Gn?a:Is(a)?a.landmarks:void 0;if(!r)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new kw(r).draw(e)})}var wC="0.11.6";function vse(e,t){let n=Mu(e,t),a=Ru(e,t);function r(i,o,l){let c=a(i,o,`${l}/separable_conv0`),u=a(o,o,`${l}/separable_conv1`),p=n(i,o,1,`${l}/expansion_conv`);return{separable_conv0:c,separable_conv1:u,expansion_conv:p}}function s(i,o){let l=a(i,i,`${o}/separable_conv0`),c=a(i,i,`${o}/separable_conv1`),u=a(i,i,`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:n,extractSeparableConvParams:a,extractReductionBlockParams:r,extractMainBlockParams:s}}function kC(e,t){let n=[],{extractWeights:a,getRemainingWeights:r}=vn(e),{extractConvParams:s,extractSeparableConvParams:i,extractReductionBlockParams:o,extractMainBlockParams:l}=vse(a,n),c=s(3,32,3,"entry_flow/conv_in"),u=o(32,64,"entry_flow/reduction_block_0"),p=o(64,128,"entry_flow/reduction_block_1"),d={conv_in:c,reduction_block_0:u,reduction_block_1:p},h={};lr(t,0,1).forEach(y=>{h[`main_block_${y}`]=l(128,`middle_flow/main_block_${y}`)});let m=o(128,256,"exit_flow/reduction_block"),f=i(256,512,"exit_flow/separable_conv"),g={reduction_block:m,separable_conv:f};if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:n,params:{entry_flow:d,middle_flow:h,exit_flow:g}}}function wse(e,t){let n=Hn(e,t),a=Lf(n),r=Pu(n);function s(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=a(`${o}/expansion_conv`);return{separable_conv0:l,separable_conv1:c,expansion_conv:u}}function i(o){let l=r(`${o}/separable_conv0`),c=r(`${o}/separable_conv1`),u=r(`${o}/separable_conv2`);return{separable_conv0:l,separable_conv1:c,separable_conv2:u}}return{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}}function IC(e,t){let n=[],{extractConvParams:a,extractSeparableConvParams:r,extractReductionBlockParams:s,extractMainBlockParams:i}=wse(e,n),o=a("entry_flow/conv_in"),l=s("entry_flow/reduction_block_0"),c=s("entry_flow/reduction_block_1"),u={conv_in:o,reduction_block_0:l,reduction_block_1:c},p={};lr(t,0,1).forEach(f=>{p[`main_block_${f}`]=i(`middle_flow/main_block_${f}`)});let d=s("exit_flow/reduction_block"),h=r("exit_flow/separable_conv"),m={reduction_block:d,separable_conv:h};return xn(e,n),{params:{entry_flow:u,middle_flow:p,exit_flow:m},paramMappings:n}}function NC(e,t,n){return Z(Ft(e,t.filters,n,"same"),t.bias)}function Iw(e,t,n=!0){let a=n?Ye(e):e;return a=_n(a,t.separable_conv0,[1,1]),a=_n(Ye(a),t.separable_conv1,[1,1]),a=$t(a,[3,3],[2,2],"same"),a=Z(a,NC(e,t.expansion_conv,[2,2])),a}function kse(e,t){let n=_n(Ye(e),t.separable_conv0,[1,1]);return n=_n(Ye(n),t.separable_conv1,[1,1]),n=_n(Ye(n),t.separable_conv2,[1,1]),n=Z(n,e),n}var Nw=class extends tn{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyXception - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(256)),i=Ye(NC(s,n.entry_flow.conv_in,[2,2]));return i=Iw(i,n.entry_flow.reduction_block_0,!1),i=Iw(i,n.entry_flow.reduction_block_1),lr(this._numMainBlocks,0,1).forEach(o=>{i=kse(i,n.middle_flow[`main_block_${o}`])}),i=Iw(i,n.exit_flow.reduction_block),i=Ye(_n(i,n.exit_flow.separable_conv,[1,1])),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return IC(t,this._numMainBlocks)}extractParams(t){return kC(t,this._numMainBlocks)}};function TC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),r=Rf(n,t),s=r(512,1,"fc/age"),i=r(512,2,"fc/gender");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{fc:{age:s,gender:i}}}}function SC(e){let t=[],n=Hn(e,t);function a(s){let i=n(`${s}/weights`,2),o=n(`${s}/bias`,1);return{weights:i,bias:o}}let r={fc:{age:a("fc/age"),gender:a("fc/gender")}};return xn(e,t),{params:r,paramMappings:t}}var dr;(function(e){e.FEMALE="female",e.MALE="male"})(dr||(dr={}));var jp=class extends tn{constructor(t=new Nw(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:n}=this;if(!n)throw new Error(`${this._name} - load model before inference`);return D(()=>{let a=t instanceof pr?this.faceFeatureExtractor.forwardInput(t):t,r=Jn(a,[7,7],[2,2],"valid").as2D(a.shape[0],-1),s=Vp(r,n.fc.age).as1D(),i=Vp(r,n.fc.gender);return{age:s,gender:i}})}forwardInput(t){return D(()=>{let{age:n,gender:a}=this.runNet(t);return{age:n,gender:_a(a)}})}async forward(t){return this.forwardInput(await yt(t))}async predictAgeAndGender(t){let n=await yt(t),a=await this.forwardInput(n),r=ht(a.age),s=ht(a.gender),i=r.map((l,c)=>({ageTensor:l,genderTensor:s[c]})),o=await Promise.all(i.map(async({ageTensor:l,genderTensor:c})=>{let u=(await l.data())[0],p=(await c.data())[0],d=p>.5,h=d?dr.MALE:dr.FEMALE,m=d?p:1-p;return l.dispose(),c.dispose(),{age:u,gender:h,genderProbability:m}}));return a.age.dispose(),a.gender.dispose(),n.isBatchInput?o:o[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:n,paramMappings:a}=this.extractClassifierParams(t);this._params=n,this._paramMappings=a}extractClassifierParams(t){return TC(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:n,classifierMap:a}=Bf(t);return this.faceFeatureExtractor.loadFromWeightMap(n),SC(a)}extractParams(t){let n=512*1+1+(512*2+2),a=t.slice(0,t.length-n),r=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(r)}};var qp=class extends Up{postProcess(t,n,a){let r=a.map(({width:i,height:o})=>{let l=n/Math.max(o,i);return{width:i*l,height:o*l}}),s=r.length;return D(()=>{let i=(p,d)=>Dt([In([68],p,"float32"),In([68],d,"float32")],1).as2D(1,136).as1D(),o=(p,d)=>{let{width:h,height:m}=r[p];return d(h,m)?Math.abs(h-m)/2:0},l=p=>o(p,(d,h)=>do(p,(d,h)=>hi(l(d),c(d))))).div(Dt(Array.from(Array(s),(p,d)=>i(r[d].width,r[d].height))))})}forwardInput(t){return D(()=>{let n=this.runNet(t);return this.postProcess(n,t.inputSize,t.inputDimensions.map(([a,r])=>({height:a,width:r})))})}async forward(t){return this.forwardInput(await yt(t))}async detectLandmarks(t){let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(async(s,i)=>{let o=Array.from(await s.data()),l=o.filter((u,p)=>xf(p)),c=o.filter((u,p)=>!xf(p));return new so(Array(68).fill(0).map((u,p)=>new De(l[p],c[p])),{height:n.getInputHeight(i),width:n.getInputWidth(i)})}));return a.forEach(s=>s.dispose()),n.isBatchInput?r:r[0]}getClassifierChannelsOut(){return 136}};var po=class extends qp{constructor(t=new Wp){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};function CC(e){let t=[],{extractDenseBlock3Params:n}=zf(e,t),a={dense0:n("dense0",!0),dense1:n("dense1"),dense2:n("dense2")};return xn(e,t),{params:a,paramMappings:t}}function _C(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),{extractDenseBlock3Params:r}=Of(n,t),s=r(3,32,"dense0",!0),i=r(32,64,"dense1"),o=r(64,128,"dense2");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:t,params:{dense0:s,dense1:i,dense2:o}}}var Tw=class extends tn{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("TinyFaceFeatureExtractor - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(112,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(255)),i=Mf(s,n.dense0,!0);return i=Mf(i,n.dense1),i=Mf(i,n.dense2),i=Jn(i,[14,14],[2,2],"valid"),i})}async forward(t){return this.forwardInput(await yt(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return CC(t)}extractParams(t){return _C(t)}};var Kp=class extends qp{constructor(t=new Tw){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Sw=class extends po{};function EC(e,t){return Z(L(e,t.weights),t.biases)}function Cw(e,t,n,a,r="same"){let{filters:s,bias:i}=t.conv,o=Ft(e,s,n,r);return o=Z(o,i),o=EC(o,t.scale),a?Ye(o):o}function AC(e,t){return Cw(e,t,[1,1],!0)}function _w(e,t){return Cw(e,t,[1,1],!1)}function Gf(e,t){return Cw(e,t,[2,2],!0,"valid")}function Ise(e,t){function n(o,l,c){let u=e(o),p=u.length/(l*c*c);if(cw(p))throw new Error(`depth has to be an integer: ${p}, weights.length: ${u.length}, numFilters: ${l}, filterSize: ${c}`);return D(()=>Ue(Aa(u,[l,p,c,c]),[2,3,1,0]))}function a(o,l,c,u){let p=n(o,l,c),d=nt(e(l));return t.push({paramPath:`${u}/filters`},{paramPath:`${u}/bias`}),{filters:p,bias:d}}function r(o,l){let c=nt(e(o)),u=nt(e(o));return t.push({paramPath:`${l}/weights`},{paramPath:`${l}/biases`}),{weights:c,biases:u}}function s(o,l,c,u){let p=a(o,l,c,`${u}/conv`),d=r(l,`${u}/scale`);return{conv:p,scale:d}}function i(o,l,c,u,p=!1){let d=s((p?.5:1)*o,l,c,`${u}/conv1`),h=s(o,l,c,`${u}/conv2`);return{conv1:d,conv2:h}}return{extractConvLayerParams:s,extractResidualLayerParams:i}}function FC(e){let{extractWeights:t,getRemainingWeights:n}=vn(e),a=[],{extractConvLayerParams:r,extractResidualLayerParams:s}=Ise(t,a),i=r(4704,32,7,"conv32_down"),o=s(9216,32,3,"conv32_1"),l=s(9216,32,3,"conv32_2"),c=s(9216,32,3,"conv32_3"),u=s(36864,64,3,"conv64_down",!0),p=s(36864,64,3,"conv64_1"),d=s(36864,64,3,"conv64_2"),h=s(36864,64,3,"conv64_3"),m=s(147456,128,3,"conv128_down",!0),f=s(147456,128,3,"conv128_1"),g=s(147456,128,3,"conv128_2"),y=s(589824,256,3,"conv256_down",!0),b=s(589824,256,3,"conv256_1"),v=s(589824,256,3,"conv256_2"),x=s(589824,256,3,"conv256_down_out"),N=D(()=>Ue(Ea(t(256*128),[128,256]),[1,0]));if(a.push({paramPath:"fc"}),n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{params:{conv32_down:i,conv32_1:o,conv32_2:l,conv32_3:c,conv64_down:u,conv64_1:p,conv64_2:d,conv64_3:h,conv128_down:m,conv128_1:f,conv128_2:g,conv256_down:y,conv256_1:b,conv256_2:v,conv256_down_out:x,fc:N},paramMappings:a}}function Nse(e,t){let n=Hn(e,t);function a(i){let o=n(`${i}/scale/weights`,1),l=n(`${i}/scale/biases`,1);return{weights:o,biases:l}}function r(i){let o=n(`${i}/conv/filters`,4),l=n(`${i}/conv/bias`,1),c=a(i);return{conv:{filters:o,bias:l},scale:c}}function s(i){return{conv1:r(`${i}/conv1`),conv2:r(`${i}/conv2`)}}return{extractConvLayerParams:r,extractResidualLayerParams:s}}function $C(e){let t=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=Nse(e,t),r=n("conv32_down"),s=a("conv32_1"),i=a("conv32_2"),o=a("conv32_3"),l=a("conv64_down"),c=a("conv64_1"),u=a("conv64_2"),p=a("conv64_3"),d=a("conv128_down"),h=a("conv128_1"),m=a("conv128_2"),f=a("conv256_down"),g=a("conv256_1"),y=a("conv256_2"),b=a("conv256_down_out"),{fc:v}=e;if(t.push({originalPath:"fc",paramPath:"fc"}),!uw(v))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${v}`);let x={conv32_down:r,conv32_1:s,conv32_2:i,conv32_3:o,conv64_down:l,conv64_1:c,conv64_2:u,conv64_3:p,conv128_down:d,conv128_1:h,conv128_2:m,conv256_down:f,conv256_1:g,conv256_2:y,conv256_down_out:b,fc:v};return xn(e,t),{params:x,paramMappings:t}}function Va(e,t){let n=AC(e,t.conv1);return n=_w(n,t.conv2),n=Z(n,e),n=Ye(n),n}function Xp(e,t){let n=Gf(e,t.conv1);n=_w(n,t.conv2);let a=Jn(e,2,2,"valid"),r=xt(a.shape),s=a.shape[3]!==n.shape[3];if(a.shape[1]!==n.shape[1]||a.shape[2]!==n.shape[2]){let o=[...n.shape];o[1]=1;let l=xt(o);n=Qe([n,l],1);let c=[...n.shape];c[2]=1;let u=xt(c);n=Qe([n,u],2)}return a=s?Qe([a,r],3):a,n=Z(a,n),n=Ye(n),n}var ho=class extends tn{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("FaceRecognitionNet - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(150,!0),"float32"),s=ka(a,[122.782,117.001,104.298]).div(he(256)),i=Gf(s,n.conv32_down);i=$t(i,3,2,"valid"),i=Va(i,n.conv32_1),i=Va(i,n.conv32_2),i=Va(i,n.conv32_3),i=Xp(i,n.conv64_down),i=Va(i,n.conv64_1),i=Va(i,n.conv64_2),i=Va(i,n.conv64_3),i=Xp(i,n.conv128_down),i=Va(i,n.conv128_1),i=Va(i,n.conv128_2),i=Xp(i,n.conv256_down),i=Va(i,n.conv256_1),i=Va(i,n.conv256_2),i=Xp(i,n.conv256_down_out);let o=i.mean([1,2]);return ze(o,n.fc)})}async forward(t){return this.forwardInput(await yt(t))}async computeFaceDescriptor(t){var s;if((s=t==null?void 0:t.shape)==null?void 0:s.some(i=>i<=0))return new Float32Array(128);let n=await yt(t),a=D(()=>ht(this.forwardInput(n))),r=await Promise.all(a.map(i=>i.data()));return a.forEach(i=>i.dispose()),n.isBatchInput?r:r[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return $C(t)}extractParams(t){return FC(t)}};function DC(e){let t=new ho;return t.extractWeights(e),t}function Yp(e,t){return{...e,...{descriptor:t}}}function MC(e){return typeof e.age=="number"}function Jp(e,t){return{...e,...{age:t}}}function RC(e){return(e.gender===dr.MALE||e.gender===dr.FEMALE)&&_u(e.genderProbability)}function Zp(e,t,n){return{...e,...{gender:t,genderProbability:n}}}function Tse(e,t){function n(l,c){let u=Aa(e(3*3*l),[3,3,l,1]),p=nt(e(l)),d=nt(e(l)),h=nt(e(l)),m=nt(e(l));return t.push({paramPath:`${c}/filters`},{paramPath:`${c}/batch_norm_scale`},{paramPath:`${c}/batch_norm_offset`},{paramPath:`${c}/batch_norm_mean`},{paramPath:`${c}/batch_norm_variance`}),{filters:u,batch_norm_scale:p,batch_norm_offset:d,batch_norm_mean:h,batch_norm_variance:m}}function a(l,c,u,p,d){let h=Aa(e(l*c*u*u),[u,u,l,c]),m=nt(e(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/${d?"batch_norm_offset":"bias"}`}),{filters:h,bias:m}}function r(l,c,u,p){let{filters:d,bias:h}=a(l,c,u,p,!0);return{filters:d,batch_norm_offset:h}}function s(l,c,u){let p=n(l,`${u}/depthwise_conv`),d=r(l,c,1,`${u}/pointwise_conv`);return{depthwise_conv:p,pointwise_conv:d}}function i(){let l=r(3,32,3,"mobilenetv1/conv_0"),c=s(32,64,"mobilenetv1/conv_1"),u=s(64,128,"mobilenetv1/conv_2"),p=s(128,128,"mobilenetv1/conv_3"),d=s(128,256,"mobilenetv1/conv_4"),h=s(256,256,"mobilenetv1/conv_5"),m=s(256,512,"mobilenetv1/conv_6"),f=s(512,512,"mobilenetv1/conv_7"),g=s(512,512,"mobilenetv1/conv_8"),y=s(512,512,"mobilenetv1/conv_9"),b=s(512,512,"mobilenetv1/conv_10"),v=s(512,512,"mobilenetv1/conv_11"),x=s(512,1024,"mobilenetv1/conv_12"),N=s(1024,1024,"mobilenetv1/conv_13");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,conv_8:g,conv_9:y,conv_10:b,conv_11:v,conv_12:x,conv_13:N}}function o(){let l=r(1024,256,1,"prediction_layer/conv_0"),c=r(256,512,3,"prediction_layer/conv_1"),u=r(512,128,1,"prediction_layer/conv_2"),p=r(128,256,3,"prediction_layer/conv_3"),d=r(256,128,1,"prediction_layer/conv_4"),h=r(128,256,3,"prediction_layer/conv_5"),m=r(256,64,1,"prediction_layer/conv_6"),f=r(64,128,3,"prediction_layer/conv_7"),g=a(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=a(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),b=a(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),v=a(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),x=a(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),N=a(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),T=a(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),C=a(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),$=a(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),F=a(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),O=a(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),W=a(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:l,conv_1:c,conv_2:u,conv_3:p,conv_4:d,conv_5:h,conv_6:m,conv_7:f,box_predictor_0:{box_encoding_predictor:g,class_predictor:y},box_predictor_1:{box_encoding_predictor:b,class_predictor:v},box_predictor_2:{box_encoding_predictor:x,class_predictor:N},box_predictor_3:{box_encoding_predictor:T,class_predictor:C},box_predictor_4:{box_encoding_predictor:$,class_predictor:F},box_predictor_5:{box_encoding_predictor:O,class_predictor:W}}}return{extractMobilenetV1Params:i,extractPredictionLayerParams:o}}function PC(e){let t=[],{extractWeights:n,getRemainingWeights:a}=vn(e),{extractMobilenetV1Params:r,extractPredictionLayerParams:s}=Tse(n,t),i=r(),o=s(),c={extra_dim:kh(n(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:{mobilenetv1:i,prediction_layer:o,output_layer:c},paramMappings:t}}function Sse(e,t){let n=Hn(e,t);function a(c,u,p){let d=n(`${c}/Conv2d_${u}_pointwise/weights`,4,`${p}/filters`),h=n(`${c}/Conv2d_${u}_pointwise/convolution_bn_offset`,1,`${p}/batch_norm_offset`);return{filters:d,batch_norm_offset:h}}function r(c){let u=`mobilenetv1/conv_${c}`,p=`MobilenetV1/Conv2d_${c}_depthwise`,d=`${u}/depthwise_conv`,h=`${u}/pointwise_conv`,m=n(`${p}/depthwise_weights`,4,`${d}/filters`),f=n(`${p}/BatchNorm/gamma`,1,`${d}/batch_norm_scale`),g=n(`${p}/BatchNorm/beta`,1,`${d}/batch_norm_offset`),y=n(`${p}/BatchNorm/moving_mean`,1,`${d}/batch_norm_mean`),b=n(`${p}/BatchNorm/moving_variance`,1,`${d}/batch_norm_variance`);return{depthwise_conv:{filters:m,batch_norm_scale:f,batch_norm_offset:g,batch_norm_mean:y,batch_norm_variance:b},pointwise_conv:a("MobilenetV1",c,h)}}function s(){return{conv_0:a("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:r(1),conv_2:r(2),conv_3:r(3),conv_4:r(4),conv_5:r(5),conv_6:r(6),conv_7:r(7),conv_8:r(8),conv_9:r(9),conv_10:r(10),conv_11:r(11),conv_12:r(12),conv_13:r(13)}}function i(c,u){let p=n(`${c}/weights`,4,`${u}/filters`),d=n(`${c}/biases`,1,`${u}/bias`);return{filters:p,bias:d}}function o(c){let u=i(`Prediction/BoxPredictor_${c}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${c}/box_encoding_predictor`),p=i(`Prediction/BoxPredictor_${c}/ClassPredictor`,`prediction_layer/box_predictor_${c}/class_predictor`);return{box_encoding_predictor:u,class_predictor:p}}function l(){return{conv_0:a("Prediction",0,"prediction_layer/conv_0"),conv_1:a("Prediction",1,"prediction_layer/conv_1"),conv_2:a("Prediction",2,"prediction_layer/conv_2"),conv_3:a("Prediction",3,"prediction_layer/conv_3"),conv_4:a("Prediction",4,"prediction_layer/conv_4"),conv_5:a("Prediction",5,"prediction_layer/conv_5"),conv_6:a("Prediction",6,"prediction_layer/conv_6"),conv_7:a("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:o(0),box_predictor_1:o(1),box_predictor_2:o(2),box_predictor_3:o(3),box_predictor_4:o(4),box_predictor_5:o(5)}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:l}}function OC(e){let t=[],{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=Sse(e,t),r=e["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!$r(r))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${r}`);let s={mobilenetv1:n(),prediction_layer:a(),output_layer:{extra_dim:r}};return xn(e,t),{params:s,paramMappings:t}}function Ia(e,t,n){return D(()=>{let a=Ft(e,t.filters,n,"same");return a=Z(a,t.batch_norm_offset),Xt(a,0,6)})}var Cse=.0010000000474974513;function _se(e,t,n){return D(()=>{let a=vr(e,t.filters,n,"same");return a=xr(a,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Cse),Xt(a,0,6)})}function Ese(e){return[2,4,6,12].some(t=>t===e)?[2,2]:[1,1]}function LC(e,t){return D(()=>{let n,a=Ia(e,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((s,i)=>{let o=i+1,l=Ese(o);a=_se(a,s.depthwise_conv,l),a=Ia(a,s.pointwise_conv,[1,1]),o===11&&(n=a)}),n===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:a,conv11:n}})}function Ase(e,t,n){let a=e.arraySync(),r=Math.min(a[t][0],a[t][2]),s=Math.min(a[t][1],a[t][3]),i=Math.max(a[t][0],a[t][2]),o=Math.max(a[t][1],a[t][3]),l=Math.min(a[n][0],a[n][2]),c=Math.min(a[n][1],a[n][3]),u=Math.max(a[n][0],a[n][2]),p=Math.max(a[n][1],a[n][3]),d=(i-r)*(o-s),h=(u-l)*(p-c);if(d<=0||h<=0)return 0;let m=Math.max(r,l),f=Math.max(s,c),g=Math.min(i,u),y=Math.min(o,p),b=Math.max(g-m,0)*Math.max(y-f,0);return b/(d+h-b)}function zC(e,t,n,a,r){let s=e.shape[0],i=Math.min(n,s),o=t.map((u,p)=>({score:u,boxIndex:p})).filter(u=>u.score>r).sort((u,p)=>p.score-u.score),l=u=>u<=a?1:0,c=[];return o.forEach(u=>{if(c.length>=i)return;let p=u.score;for(let d=c.length-1;d>=0;--d){let h=Ase(e,u.boxIndex,c[d]);if(h!==0&&(u.score*=l(h),u.score<=r))break}p===u.score&&c.push(u.boxIndex)}),c}function Fse(e){let t=ht(Ue(e,[1,0])),n=[ge(t[2],t[0]),ge(t[3],t[1])],a=[Z(t[0],we(n[0],he(2))),Z(t[1],we(n[1],he(2)))];return{sizes:n,centers:a}}function $se(e,t){let{sizes:n,centers:a}=Fse(e),r=ht(Ue(t,[1,0])),s=we(L(hn(we(r[2],he(5))),n[0]),he(2)),i=Z(L(we(r[0],he(10)),n[0]),a[0]),o=we(L(hn(we(r[3],he(5))),n[1]),he(2)),l=Z(L(we(r[1],he(10)),n[1]),a[1]);return Ue(Dt([ge(i,s),ge(l,o),Z(i,s),Z(l,o)]),[1,0])}function BC(e,t,n){return D(()=>{let a=e.shape[0],r=$se(q(Xa(n.extra_dim,[a,1,1]),[-1,4]),q(e,[-1,4]));r=q(r,[a,r.shape[0]/a,4]);let s=ma(We(t,[0,0,1],[-1,-1,-1])),i=We(s,[0,0,0],[-1,-1,1]);i=q(i,[a,i.shape[1]]);let o=ht(r),l=ht(i);return{boxes:o,scores:l}})}function mo(e,t){return D(()=>{let n=e.shape[0],a=q(uo(e,t.box_encoding_predictor),[n,-1,1,4]),r=q(uo(e,t.class_predictor),[n,-1,3]);return{boxPredictionEncoding:a,classPrediction:r}})}function WC(e,t,n){return D(()=>{let a=Ia(e,n.conv_0,[1,1]),r=Ia(a,n.conv_1,[2,2]),s=Ia(r,n.conv_2,[1,1]),i=Ia(s,n.conv_3,[2,2]),o=Ia(i,n.conv_4,[1,1]),l=Ia(o,n.conv_5,[2,2]),c=Ia(l,n.conv_6,[1,1]),u=Ia(c,n.conv_7,[2,2]),p=mo(t,n.box_predictor_0),d=mo(e,n.box_predictor_1),h=mo(r,n.box_predictor_2),m=mo(i,n.box_predictor_3),f=mo(l,n.box_predictor_4),g=mo(u,n.box_predictor_5),y=Qe([p.boxPredictionEncoding,d.boxPredictionEncoding,h.boxPredictionEncoding,m.boxPredictionEncoding,f.boxPredictionEncoding,g.boxPredictionEncoding],1),b=Qe([p.classPrediction,d.classPrediction,h.classPrediction,m.classPrediction,f.classPrediction,g.classPrediction],1);return{boxPredictions:y,classPredictions:b}})}var sa=class{constructor({minConfidence:t,maxResults:n}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=n||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Ns=class extends tn{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:n}=this;if(!n)throw new Error("SsdMobilenetv1 - load model before inference");return D(()=>{let a=pe(t.toBatchTensor(512,!1),"float32"),r=ge(L(a,he(.007843137718737125)),he(1)),s=LC(r,n.mobilenetv1),{boxPredictions:i,classPredictions:o}=WC(s.out,s.conv11,n.prediction_layer);return BC(i,o,n.output_layer)})}async forward(t){return this.forwardInput(await yt(t))}async locateFaces(t,n={}){let{maxResults:a,minConfidence:r}=new sa(n),s=await yt(t),{boxes:i,scores:o}=this.forwardInput(s),l=i[0],c=o[0];for(let v=1;v{let[x,N]=[Math.max(0,y[v][0]),Math.min(1,y[v][2])].map($=>$*g),[T,C]=[Math.max(0,y[v][1]),Math.min(1,y[v][3])].map($=>$*f);return new bt(u[v],new ro(T,x,C-T,N-x),{height:s.getInputHeight(0),width:s.getInputWidth(0)})});return l.dispose(),c.dispose(),b}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return OC(t)}extractParams(t){return PC(t)}};function Ew(e){let t=new Ns;return t.extractWeights(e),t}function VC(e){return Ew(e)}var Aw=class extends Ns{};var UC=.4,GC=[new De(.738768,.874946),new De(2.42204,2.65704),new De(4.30971,7.04493),new De(10.246,4.59428),new De(12.6868,11.8741)],HC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],jC=[117.001,114.697,97.404],qC="tiny_yolov2_model",KC="tiny_yolov2_separable_conv_model";var Hf=e=>typeof e=="number";function jf(e){if(!e)throw new Error(`invalid config: ${e}`);if(typeof e.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${e.withSeparableConvs}`);if(!Hf(e.iouThreshold)||e.iouThreshold<0||e.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${e.iouThreshold}`);if(!Array.isArray(e.classes)||!e.classes.length||!e.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(e.classes)}`);if(!Array.isArray(e.anchors)||!e.anchors.length||!e.anchors.map(t=>t||{}).every(t=>Hf(t.x)&&Hf(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(e.anchors)}`);if(e.meanRgb&&(!Array.isArray(e.meanRgb)||e.meanRgb.length!==3||!e.meanRgb.every(Hf)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(e.meanRgb)}`)}function Ou(e){return D(()=>{let t=L(e,he(.10000000149011612));return Z(Ye(ge(e,t)),t)})}function Rr(e,t){return D(()=>{let n=ta(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Ft(n,t.conv.filters,[1,1],"valid"),n=ge(n,t.bn.sub),n=L(n,t.bn.truediv),n=Z(n,t.conv.bias),Ou(n)})}function Pr(e,t){return D(()=>{let n=ta(e,[[0,0],[1,1],[1,1],[0,0]]);return n=Pi(n,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),n=Z(n,t.bias),Ou(n)})}function Dse(e,t){let n=Mu(e,t);function a(i,o){let l=nt(e(i)),c=nt(e(i));return t.push({paramPath:`${o}/sub`},{paramPath:`${o}/truediv`}),{sub:l,truediv:c}}function r(i,o,l){let c=n(i,o,3,`${l}/conv`),u=a(o,`${l}/bn`);return{conv:c,bn:u}}let s=Ru(e,t);return{extractConvParams:n,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}}function XC(e,t,n,a){let{extractWeights:r,getRemainingWeights:s}=vn(e),i=[],{extractConvParams:o,extractConvWithBatchNormParams:l,extractSeparableConvParams:c}=Dse(r,i),u;if(t.withSeparableConvs){let[p,d,h,m,f,g,y,b,v]=a,x=t.isFirstLayerConv2d?o(p,d,3,"conv0"):c(p,d,"conv0"),N=c(d,h,"conv1"),T=c(h,m,"conv2"),C=c(m,f,"conv3"),$=c(f,g,"conv4"),F=c(g,y,"conv5"),O=b?c(y,b,"conv6"):void 0,W=v?c(b,v,"conv7"):void 0,V=o(v||b||y,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}else{let[p,d,h,m,f,g,y,b,v]=a,x=l(p,d,"conv0"),N=l(d,h,"conv1"),T=l(h,m,"conv2"),C=l(m,f,"conv3"),$=l(f,g,"conv4"),F=l(g,y,"conv5"),O=l(y,b,"conv6"),W=l(b,v,"conv7"),V=o(v,5*n,1,"conv8");u={conv0:x,conv1:N,conv2:T,conv3:C,conv4:$,conv5:F,conv6:O,conv7:W,conv8:V}}if(s().length!==0)throw new Error(`weights remaing after extract: ${s().length}`);return{params:u,paramMappings:i}}function Mse(e,t){let n=Hn(e,t);function a(o){let l=n(`${o}/sub`,1),c=n(`${o}/truediv`,1);return{sub:l,truediv:c}}function r(o){let l=n(`${o}/filters`,4),c=n(`${o}/bias`,1);return{filters:l,bias:c}}function s(o){let l=r(`${o}/conv`),c=a(`${o}/bn`);return{conv:l,bn:c}}let i=Pu(n);return{extractConvParams:r,extractConvWithBatchNormParams:s,extractSeparableConvParams:i}}function YC(e,t){let n=[],{extractConvParams:a,extractConvWithBatchNormParams:r,extractSeparableConvParams:s}=Mse(e,n),i;if(t.withSeparableConvs){let o=t.filterSizes&&t.filterSizes.length||9;i={conv0:t.isFirstLayerConv2d?a("conv0"):s("conv0"),conv1:s("conv1"),conv2:s("conv2"),conv3:s("conv3"),conv4:s("conv4"),conv5:s("conv5"),conv6:o>7?s("conv6"):void 0,conv7:o>8?s("conv7"):void 0,conv8:a("conv8")}}else i={conv0:r("conv0"),conv1:r("conv1"),conv2:r("conv2"),conv3:r("conv3"),conv4:r("conv4"),conv5:r("conv5"),conv6:r("conv6"),conv7:r("conv7"),conv8:a("conv8")};return xn(e,n),{params:i,paramMappings:n}}var Ua=class{constructor({inputSize:t,scoreThreshold:n}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=n||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var Fw=class extends tn{constructor(t){super("TinyYolov2");jf(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,n){let a=Rr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Rr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=Rr(a,n.conv6),a=Rr(a,n.conv7),uo(a,n.conv8,"valid",!1)}runMobilenet(t,n){let a=this.config.isFirstLayerConv2d?Ou(uo(t,n.conv0,"valid",!1)):Pr(t,n.conv0);return a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv1),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv2),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv3),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv4),a=$t(a,[2,2],[2,2],"same"),a=Pr(a,n.conv5),a=$t(a,[2,2],[1,1],"same"),a=n.conv6?Pr(a,n.conv6):a,a=n.conv7?Pr(a,n.conv7):a,uo(a,n.conv8,"valid",!1)}forwardInput(t,n){let{params:a}=this;if(!a)throw new Error("TinyYolov2 - load model before inference");return D(()=>{let r=pe(t.toBatchTensor(n,!1),"float32");return r=this.config.meanRgb?ka(r,this.config.meanRgb):r,r=r.div(he(256)),this.config.withSeparableConvs?this.runMobilenet(r,a):this.runTinyYolov2(r,a)})}async forward(t,n){return this.forwardInput(await yt(t),n)}async detect(t,n={}){let{inputSize:a,scoreThreshold:r}=new Ua(n),s=await yt(t),i=await this.forwardInput(s,a),o=D(()=>ht(i)[0].expandDims()),l={width:s.getInputWidth(0),height:s.getInputHeight(0)},c=await this.extractBoxes(o,s.getReshapedInputDimensions(0),r);i.dispose(),o.dispose();let u=c.map(g=>g.box),p=c.map(g=>g.score),d=c.map(g=>g.classScore),h=c.map(g=>this.config.classes[g.label]);return If(u.map(g=>g.rescale(a)),p,this.config.iouThreshold,!0).map(g=>new Dr(p[g],d[g],h[g],u[g],l))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return YC(t,this.config)}extractParams(t){let n=this.config.filterSizes||Fw.DEFAULT_FILTER_SIZES,a=n?n.length:void 0;if(a!==7&&a!==8&&a!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${a} filterSizes in config`);return XC(t,this.config,this.boxEncodingSize,n)}async extractBoxes(t,n,a){let{width:r,height:s}=n,i=Math.max(r,s),o=i/r,l=i/s,c=t.shape[1],u=this.config.anchors.length,[p,d,h]=D(()=>{let y=t.reshape([c,c,u,this.boxEncodingSize]),b=y.slice([0,0,0,0],[c,c,u,4]),v=y.slice([0,0,0,4],[c,c,u,1]),x=this.withClassScores?_a(y.slice([0,0,0,5],[c,c,u,this.config.classes.length]),3):he(0);return[b,v,x]}),m=[],f=await d.array(),g=await p.array();for(let y=0;ya){let N=(b+Eu(g[y][b][v][0]))/c*o,T=(y+Eu(g[y][b][v][1]))/c*l,C=Math.exp(g[y][b][v][2])*this.config.anchors[v].x/c*o,$=Math.exp(g[y][b][v][3])*this.config.anchors[v].y/c*l,F=N-C/2,O=T-$/2,W={row:y,col:b,anchor:v},{classScore:V,label:H}=this.withClassScores?await this.extractPredictedClass(h,W):{classScore:1,label:0};m.push({box:new ao(F,O,F+C,O+$),score:x,classScore:x*V,label:H,...W})}}return p.dispose(),d.dispose(),h.dispose(),m}async extractPredictedClass(t,n){let{row:a,col:r,anchor:s}=n,i=await t.array();return Array(this.config.classes.length).fill(0).map((o,l)=>i[a][r][s][l]).map((o,l)=>({classScore:o,label:l})).reduce((o,l)=>o.classScore>l.classScore?o:l)}},Lu=Fw;Lu.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var fo=class extends Lu{constructor(t=!0){let n={withSeparableConvs:t,iouThreshold:UC,classes:["face"],...t?{anchors:HC,meanRgb:jC}:{anchors:GC,withClassScores:!0}};super(n)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new bt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?KC:qC}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function JC(e,t=!0){let n=new fo(t);return n.extractWeights(e),n}var Qp=class extends Ua{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var ia=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};async function go(e,t,n,a,r=({alignedRect:s})=>s){let s=e.map(l=>Is(l)?r(l):l.detection),i=a||(t instanceof z?await lo(t,s):await oo(t,s)),o=await n(i);return i.forEach(l=>l instanceof z&&l.dispose()),o}async function zu(e,t,n,a,r){return go([e],t,async s=>n(s[0]),a,r)}var ZC=.4,QC=[new De(1.603231,2.094468),new De(6.041143,7.080126),new De(2.882459,3.518061),new De(4.266906,5.178857),new De(9.041765,10.66308)],e_=[117.001,114.697,97.404];var yo=class extends Lu{constructor(){let t={withSeparableConvs:!0,iouThreshold:ZC,classes:["face"],anchors:QC,meanRgb:e_,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,n){return(await this.detect(t,n)).map(r=>new bt(r.score,r.relativeBox,{width:r.imageWidth,height:r.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var et={ssdMobilenetv1:new Ns,tinyFaceDetector:new yo,tinyYolov2:new fo,faceLandmark68Net:new po,faceLandmark68TinyNet:new Kp,faceRecognitionNet:new ho,faceExpressionNet:new Gp,ageGenderNet:new jp},$w=(e,t)=>et.ssdMobilenetv1.locateFaces(e,t),t_=(e,t)=>et.tinyFaceDetector.locateFaces(e,t),n_=(e,t)=>et.tinyYolov2.locateFaces(e,t),Dw=e=>et.faceLandmark68Net.detectLandmarks(e),a_=e=>et.faceLandmark68TinyNet.detectLandmarks(e),r_=e=>et.faceRecognitionNet.computeFaceDescriptor(e),s_=e=>et.faceExpressionNet.predictExpressions(e),i_=e=>et.ageGenderNet.predictAgeAndGender(e),Mw=e=>et.ssdMobilenetv1.load(e),o_=e=>et.tinyFaceDetector.load(e),l_=e=>et.tinyYolov2.load(e),u_=e=>et.faceLandmark68Net.load(e),c_=e=>et.faceLandmark68TinyNet.load(e),p_=e=>et.faceRecognitionNet.load(e),d_=e=>et.faceExpressionNet.load(e),h_=e=>et.ageGenderNet.load(e),m_=Mw,f_=$w,g_=Dw;var Rw=class extends ia{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Vu=class extends Rw{async run(){let t=await this.parentTask,n=await go(t,this.input,async a=>Promise.all(a.map(r=>et.faceExpressionNet.predictExpressions(r))),this.extractedFaces);return t.map((a,r)=>Hp(a,n[r]))}withAgeAndGender(){return new Bu(this,this.input)}},Uu=class extends Rw{async run(){let t=await this.parentTask;if(!t)return;let n=await zu(t,this.input,a=>et.faceExpressionNet.predictExpressions(a),this.extractedFaces);return Hp(t,n)}withAgeAndGender(){return new Wu(this,this.input)}},vo=class extends Vu{withAgeAndGender(){return new bo(this,this.input)}withFaceDescriptors(){return new Or(this,this.input)}},wo=class extends Uu{withAgeAndGender(){return new xo(this,this.input)}withFaceDescriptor(){return new Lr(this,this.input)}};var Pw=class extends ia{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.extractedFaces=a}},Bu=class extends Pw{async run(){let t=await this.parentTask,n=await go(t,this.input,async a=>Promise.all(a.map(r=>et.ageGenderNet.predictAgeAndGender(r))),this.extractedFaces);return t.map((a,r)=>{let{age:s,gender:i,genderProbability:o}=n[r];return Jp(Zp(a,i,o),s)})}withFaceExpressions(){return new Vu(this,this.input)}},Wu=class extends Pw{async run(){let t=await this.parentTask;if(!t)return;let{age:n,gender:a,genderProbability:r}=await zu(t,this.input,s=>et.ageGenderNet.predictAgeAndGender(s),this.extractedFaces);return Jp(Zp(t,a,r),n)}withFaceExpressions(){return new Uu(this,this.input)}},bo=class extends Bu{withFaceExpressions(){return new vo(this,this.input)}withFaceDescriptors(){return new Or(this,this.input)}},xo=class extends Wu{withFaceExpressions(){return new wo(this,this.input)}withFaceDescriptor(){return new Lr(this,this.input)}};var ed=class extends ia{constructor(t,n){super();this.parentTask=t;this.input=n}},Or=class extends ed{async run(){let t=await this.parentTask;return(await go(t,this.input,a=>Promise.all(a.map(r=>et.faceRecognitionNet.computeFaceDescriptor(r))),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}))).map((a,r)=>Yp(t[r],a))}withFaceExpressions(){return new vo(this,this.input)}withAgeAndGender(){return new bo(this,this.input)}},Lr=class extends ed{async run(){let t=await this.parentTask;if(!t)return;let n=await zu(t,this.input,a=>et.faceRecognitionNet.computeFaceDescriptor(a),null,a=>a.landmarks.align(null,{useDlibAlignment:!0}));return Yp(t,n)}withFaceExpressions(){return new wo(this,this.input)}withAgeAndGender(){return new xo(this,this.input)}};var td=class extends ia{constructor(t,n,a){super();this.parentTask=t;this.input=n;this.useTinyLandmarkNet=a}get landmarkNet(){return this.useTinyLandmarkNet?et.faceLandmark68TinyNet:et.faceLandmark68Net}},nd=class extends td{async run(){let t=await this.parentTask,n=t.map(s=>s.detection),a=this.input instanceof z?await lo(this.input,n):await oo(this.input,n),r=await Promise.all(a.map(s=>this.landmarkNet.detectLandmarks(s)));return a.forEach(s=>s instanceof z&&s.dispose()),t.map((s,i)=>co(s,r[i]))}withFaceExpressions(){return new vo(this,this.input)}withAgeAndGender(){return new bo(this,this.input)}withFaceDescriptors(){return new Or(this,this.input)}},ad=class extends td{async run(){let t=await this.parentTask;if(!t)return;let{detection:n}=t,a=this.input instanceof z?await lo(this.input,[n]):await oo(this.input,[n]),r=await this.landmarkNet.detectLandmarks(a[0]);return a.forEach(s=>s instanceof z&&s.dispose()),co(t,r)}withFaceExpressions(){return new wo(this,this.input)}withAgeAndGender(){return new xo(this,this.input)}withFaceDescriptor(){return new Lr(this,this.input)}};var rd=class extends ia{constructor(t,n=new sa){super();this.input=t;this.options=n}},Gu=class extends rd{async run(){let{input:t,options:n}=this,a=n instanceof Qp?r=>et.tinyFaceDetector.locateFaces(r,n):n instanceof sa?r=>et.ssdMobilenetv1.locateFaces(r,n):n instanceof Ua?r=>et.tinyYolov2.locateFaces(r,n):null;if(!a)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return a(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let n=await this.run();t(n.map(a=>bs({},a)))})}withFaceLandmarks(t=!1){return new nd(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new Vu(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Bu(this.runAndExtendWithFaceDetections(),this.input)}},sd=class extends rd{async run(){let t=await new Gu(this.input,this.options),n=t[0];return t.forEach(a=>{a.score>n.score&&(n=a)}),n}runAndExtendWithFaceDetection(){return new Promise(async t=>{let n=await this.run();t(n?bs({},n):void 0)})}withFaceLandmarks(t=!1){return new ad(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new Uu(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Wu(this.runAndExtendWithFaceDetection(),this.input)}};function y_(e,t=new sa){return new sd(e,t)}function id(e,t=new sa){return new Gu(e,t)}async function Ow(e,t){return id(e,new sa(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function b_(e,t={}){return id(e,new Ua(t)).withFaceLandmarks().withFaceDescriptors()}var x_=Ow;function qf(e,t){if(e.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let n=Array.from(e),a=Array.from(t);return Math.sqrt(n.map((r,s)=>r-a[s]).reduce((r,s)=>r+s**2,0))}var od=class{constructor(t,n=.6){this._distanceThreshold=n;let a=Array.isArray(t)?t:[t];if(!a.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let r=1,s=()=>`person ${r++}`;this._labeledDescriptors=a.map(i=>{if(i instanceof ur)return i;if(i instanceof Float32Array)return new ur(s(),[i]);if(i.descriptor&&i.descriptor instanceof Float32Array)return new ur(s(),[i.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,n){return n.map(a=>qf(a,t)).reduce((a,r)=>a+r,0)/(n.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:n,label:a})=>new Au(a,this.computeMeanDistance(t,n))).reduce((n,a)=>n.distancet.toJSON())}}static fromJSON(t){let n=t.labeledDescriptors.map(a=>ur.fromJSON(a));return new od(n,t.distanceThreshold)}};function v_(e){let t=new yo;return t.extractWeights(e),t}function Lw(e,t){let{width:n,height:a}=new un(t.width,t.height);if(n<=0||a<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:n,height:a})}`);if(Array.isArray(e))return e.map(r=>Lw(r,{width:n,height:a}));if(Is(e)){let r=e.detection.forSize(n,a),s=e.unshiftedLandmarks.forSize(r.box.width,r.box.height);return co(bs(e,r),s)}return Wa(e)?bs(e,e.detection.forSize(n,a)):e instanceof Gn||e instanceof bt?e.forSize(n,a):e}var Pse=typeof process!="undefined",Ose=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",w_={faceapi:wC,node:Pse,browser:Ose};return Rse;})(); /** * @license * Copyright 2017 Google LLC. All Rights Reserved. diff --git a/dist/face-api.node-gpu.js b/dist/face-api.node-gpu.js index dbbb26e..7901b42 100644 --- a/dist/face-api.node-gpu.js +++ b/dist/face-api.node-gpu.js @@ -5,5 +5,5 @@ author: ' */ -var ln=Object.create,Ye=Object.defineProperty,fn=Object.getPrototypeOf,hn=Object.prototype.hasOwnProperty,xn=Object.getOwnPropertyNames,bn=Object.getOwnPropertyDescriptor;var fo=o=>Ye(o,"__esModule",{value:!0});var ho=(o,t)=>()=>(t||(t={exports:{}},o(t.exports,t)),t.exports),Ge=(o,t)=>{fo(o);for(var e in t)Ye(o,e,{get:t[e],enumerable:!0})},gn=(o,t,e)=>{if(fo(o),t&&typeof t=="object"||typeof t=="function")for(let r of xn(t))!hn.call(o,r)&&r!=="default"&&Ye(o,r,{get:()=>t[r],enumerable:!(e=bn(t,r))||e.enumerable});return o},b=o=>o&&o.__esModule?o:gn(Ye(o!=null?ln(fn(o)):{},"default",{value:o,enumerable:!0}),o);var g=ho(xo=>{var vn=Object.create,Er=Object.defineProperty,yn=Object.getPrototypeOf,Fn=Object.prototype.hasOwnProperty,Tn=Object.getOwnPropertyNames,Pn=Object.getOwnPropertyDescriptor,_n=o=>Er(o,"__esModule",{value:!0}),bo=(o,t,e)=>{if(_n(o),t&&typeof t=="object"||typeof t=="function")for(let r of Tn(t))!Fn.call(o,r)&&r!=="default"&&Er(o,r,{get:()=>t[r],enumerable:!(e=Pn(t,r))||e.enumerable});return o},wn=o=>o&&o.__esModule?o:bo(Er(o!=null?vn(yn(o)):{},"default",{value:o,enumerable:!0}),o);bo(xo,wn(require("@tensorflow/tfjs-node-gpu")))});var To=ho((Ln,Fo)=>{Ge(Ln,{isNodejs:()=>kn});function kn(){return typeof global=="object"&&!0&&typeof Fo!="undefined"&&typeof process!="undefined"&&!!process.version}});Ge(exports,{AgeGenderNet:()=>pr,BoundingBox:()=>ee,Box:()=>D,ComposableTask:()=>tt,ComputeAllFaceDescriptorsTask:()=>At,ComputeFaceDescriptorsTaskBase:()=>vr,ComputeSingleFaceDescriptorTask:()=>Wt,DetectAllFaceLandmarksTask:()=>Fr,DetectAllFacesTask:()=>He,DetectFaceLandmarksTaskBase:()=>yr,DetectFacesTaskBase:()=>Pr,DetectSingleFaceLandmarksTask:()=>Tr,DetectSingleFaceTask:()=>_r,Dimensions:()=>A,FACE_EXPRESSION_LABELS:()=>Jr,FaceDetection:()=>M,FaceDetectionNet:()=>Jo,FaceExpressionNet:()=>cr,FaceExpressions:()=>It,FaceLandmark68Net:()=>fe,FaceLandmark68TinyNet:()=>dr,FaceLandmarkNet:()=>Bo,FaceLandmarks:()=>V,FaceLandmarks5:()=>vo,FaceLandmarks68:()=>oe,FaceMatch:()=>Ee,FaceMatcher:()=>Dr,FaceRecognitionNet:()=>xe,Gender:()=>vt,LabeledBox:()=>Me,LabeledFaceDescriptors:()=>xt,NetInput:()=>bt,NeuralNetwork:()=>S,ObjectDetection:()=>Dt,Point:()=>x,PredictedBox:()=>yo,Rect:()=>re,SsdMobilenetv1:()=>Ut,SsdMobilenetv1Options:()=>Z,TinyFaceDetector:()=>Fe,TinyFaceDetectorOptions:()=>gr,TinyYolov2:()=>ve,TinyYolov2Options:()=>lt,allFaces:()=>Da,allFacesSsdMobilenetv1:()=>dn,allFacesTinyYolov2:()=>wa,awaitMediaLoaded:()=>Yr,bufferToImage:()=>Gr,computeFaceDescriptor:()=>da,createCanvas:()=>ne,createCanvasFromMedia:()=>Ie,createFaceDetectionNet:()=>na,createFaceRecognitionNet:()=>Un,createSsdMobilenetv1:()=>Xo,createTinyFaceDetector:()=>Ea,createTinyYolov2:()=>ia,detectAllFaces:()=>wr,detectFaceLandmarks:()=>mn,detectFaceLandmarksTiny:()=>pa,detectLandmarks:()=>Pa,detectSingleFace:()=>_a,draw:()=>Qr,env:()=>w,euclideanDistance:()=>uo,extendWithAge:()=>hr,extendWithFaceDescriptor:()=>fr,extendWithFaceDetection:()=>$t,extendWithFaceExpressions:()=>mr,extendWithFaceLandmarks:()=>le,extendWithGender:()=>xr,extractFaceTensors:()=>se,extractFaces:()=>ae,fetchImage:()=>Bn,fetchJson:()=>Ur,fetchNetWeights:()=>Rn,fetchOrThrow:()=>Yt,getContext2dOrThrow:()=>O,getMediaDimensions:()=>Ht,imageTensorToCanvas:()=>zr,imageToSquare:()=>Vr,inverseSigmoid:()=>Mn,iou:()=>Lr,isMediaElement:()=>qe,isMediaLoaded:()=>Ne,isWithAge:()=>Xn,isWithFaceDetection:()=>pt,isWithFaceExpressions:()=>qr,isWithFaceLandmarks:()=>zt,isWithGender:()=>Jn,loadAgeGenderModel:()=>ya,loadFaceDetectionModel:()=>Fa,loadFaceExpressionModel:()=>va,loadFaceLandmarkModel:()=>xa,loadFaceLandmarkTinyModel:()=>ba,loadFaceRecognitionModel:()=>ga,loadSsdMobilenetv1Model:()=>pn,loadTinyFaceDetectorModel:()=>fa,loadTinyYolov2Model:()=>ha,loadWeightMap:()=>Xr,locateFaces:()=>Ta,matchDimensions:()=>On,minBbox:()=>kr,nets:()=>P,nonMaxSuppression:()=>Sr,normalize:()=>ot,padToSquare:()=>Ar,predictAgeAndGender:()=>la,recognizeFaceExpressions:()=>ua,resizeResults:()=>un,resolveInput:()=>jt,shuffleArray:()=>En,sigmoid:()=>De,ssdMobilenetv1:()=>cn,tf:()=>Ma,tinyFaceDetector:()=>ca,tinyYolov2:()=>ma,toNetInput:()=>E,utils:()=>Mr,validateConfig:()=>ao,version:()=>Ia});var Ma=b(g());var Qr={};Ge(Qr,{AnchorPosition:()=>dt,DrawBox:()=>Xe,DrawBoxOptions:()=>Hr,DrawFaceLandmarks:()=>Kr,DrawFaceLandmarksOptions:()=>Zr,DrawTextField:()=>Mt,DrawTextFieldOptions:()=>Ce,drawContour:()=>ft,drawDetections:()=>Wn,drawFaceExpressions:()=>$n,drawFaceLandmarks:()=>jn});function ft(o,t,e=!1){if(o.beginPath(),t.slice(1).forEach(({x:r,y:n},a)=>{let s=t[a];o.moveTo(s.x,s.y),o.lineTo(r,n)}),e){let r=t[t.length-1],n=t[0];if(!r||!n)return;o.moveTo(r.x,r.y),o.lineTo(n.x,n.y)}o.stroke()}var Mr={};Ge(Mr,{computeReshapedDimensions:()=>Ir,getCenterPoint:()=>Ot,isDimensions:()=>Ve,isEven:()=>ze,isFloat:()=>Nr,isTensor:()=>Bt,isTensor1D:()=>Dn,isTensor2D:()=>Cr,isTensor3D:()=>ht,isTensor4D:()=>z,isValidNumber:()=>rt,isValidProbablitiy:()=>te,range:()=>ct,round:()=>Rt});var go=b(g());var A=class{constructor(t,e){if(!rt(t)||!rt(e))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:e})}`);this._width=t,this._height=e}get width(){return this._width}get height(){return this._height}reverse(){return new A(1/this.width,1/this.height)}};function Bt(o,t){return o instanceof go.Tensor&&o.shape.length===t}function Dn(o){return Bt(o,1)}function Cr(o){return Bt(o,2)}function ht(o){return Bt(o,3)}function z(o){return Bt(o,4)}function Nr(o){return o%1!=0}function ze(o){return o%2==0}function Rt(o,t=2){let e=10**t;return Math.floor(o*e)/e}function Ve(o){return o&&o.width&&o.height}function Ir({width:o,height:t},e){let r=e/Math.max(t,o);return new A(Math.round(o*r),Math.round(t*r))}function Ot(o){return o.reduce((t,e)=>t.add(e),new x(0,0)).div(new x(o.length,o.length))}function ct(o,t,e){return Array(o).fill(0).map((r,n)=>t+n*e)}function rt(o){return!!o&&o!==Infinity&&o!==-Infinity&&!Number.isNaN(o)||o===0}function te(o){return rt(o)&&o>=0&&o<=1}var x=class{constructor(t,e){this._x=t,this._y=e}get x(){return this._x}get y(){return this._y}add(t){return new x(this.x+t.x,this.y+t.y)}sub(t){return new x(this.x-t.x,this.y-t.y)}mul(t){return new x(this.x*t.x,this.y*t.y)}div(t){return new x(this.x/t.x,this.y/t.y)}abs(){return new x(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new x(Math.floor(this.x),Math.floor(this.y))}};var D=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(rt)}static assertIsValidBox(t,e,r=!1){if(!D.isRect(t))throw new Error(`${e} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!r&&(t.width<0||t.height<0))throw new Error(`${e} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,e=!0){let r=t||{},n=[r.left,r.top,r.right,r.bottom].every(rt),a=[r.x,r.y,r.width,r.height].every(rt);if(!a&&!n)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(r)}`);let[s,i,c,m]=a?[r.x,r.y,r.width,r.height]:[r.left,r.top,r.right-r.left,r.bottom-r.top];D.assertIsValidBox({x:s,y:i,width:c,height:m},"Box.constructor",e),this._x=s,this._y=i,this._width=c,this._height=m}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new x(this.left,this.top)}get topRight(){return new x(this.right,this.top)}get bottomLeft(){return new x(this.left,this.bottom)}get bottomRight(){return new x(this.right,this.bottom)}round(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.round(a));return new D({x:t,y:e,width:r,height:n})}floor(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.floor(a));return new D({x:t,y:e,width:r,height:n})}toSquare(){let{x:t,y:e,width:r,height:n}=this,a=Math.abs(r-n);return re&&(i=-d+e+r,d=e),u>t&&(c=-u+t+n,u=t),m<1&&(c=2-m,m=1),p<1&&(c=2-p,p=1),{dy:s,edy:c,dx:a,edx:i,y:p,ey:u,x:m,ex:d,w:r,h:n}}calibrate(t){return new D({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var ee=class extends D{constructor(t,e,r,n,a=!1){super({left:t,top:e,right:r,bottom:n},a)}};var Dt=class{constructor(t,e,r,n,a){this._imageDims=new A(a.width,a.height),this._score=t,this._classScore=e,this._className=r,this._box=new D(n).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new D(this._box).rescale(this.imageDims.reverse())}forSize(t,e){return new Dt(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:e})}};var M=class extends Dt{constructor(t,e,r){super(t,t,"",e,r)}forSize(t,e){let{score:r,relativeBox:n,imageDims:a}=super.forSize(t,e);return new M(r,n,a)}};function Lr(o,t,e=!0){let r=Math.max(0,Math.min(o.right,t.right)-Math.max(o.left,t.left)),n=Math.max(0,Math.min(o.bottom,t.bottom)-Math.max(o.top,t.top)),a=r*n;return e?a/(o.area+t.area-a):a/Math.min(o.area,t.area)}function kr(o){let t=o.map(i=>i.x),e=o.map(i=>i.y),r=t.reduce((i,c)=>ccii({score:s,boxIndex:i})).sort((s,i)=>s.score-i.score).map(s=>s.boxIndex),a=[];for(;n.length>0;){let s=n.pop();a.push(s);let i=n,c=[];for(let m=0;mc[p]<=e)}return a}var mt=b(g());function ot(o,t){return mt.tidy(()=>{let[e,r,n]=t,a=mt.fill([...o.shape.slice(0,3),1],e,"float32"),s=mt.fill([...o.shape.slice(0,3),1],r,"float32"),i=mt.fill([...o.shape.slice(0,3),1],n,"float32"),c=mt.concat([a,s,i],3);return mt.sub(o,c)})}var Et=b(g());function Ar(o,t=!1){return Et.tidy(()=>{let[e,r]=o.shape.slice(1);if(e===r)return o;let n=Math.abs(e-r),a=Math.round(n*(t?.5:1)),s=e>r?2:1,i=u=>{let l=o.shape.slice();return l[s]=u,Et.fill(l,0,"float32")},c=i(a),m=n-c.shape[s],d=[t&&m?i(m):null,o,c].filter(u=>!!u).map(u=>Et.cast(u,"float32"));return Et.concat(d,s)})}function En(o){let t=o.slice();for(let e=t.length-1;e>0;e--){let r=Math.floor(Math.random()*(e+1)),n=t[e];t[e]=t[r],t[r]=n}return t}function De(o){return 1/(1+Math.exp(-o))}function Mn(o){return Math.log(o/(1-o))}var re=class extends D{constructor(t,e,r,n,a=!1){super({x:t,y:e,width:r,height:n},a)}};var Cn=.5,Nn=.43,In=.45,V=class{constructor(t,e,r=new x(0,0)){let{width:n,height:a}=e;this._imgDims=new A(n,a),this._shift=r,this._positions=t.map(s=>s.mul(new x(n,a)).add(r))}get shift(){return new x(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new x(this.imageWidth,this.imageHeight)))}forSize(t,e){return new this.constructor(this.relativePositions,{width:t,height:e})}shiftBy(t,e){return new this.constructor(this.relativePositions,this._imgDims,new x(t,e))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,e={}){if(t){let a=t instanceof M?t.box.floor():new D(t);return this.shiftBy(a.x,a.y).align(null,e)}let{useDlibAlignment:r,minBoxPadding:n}={useDlibAlignment:!1,minBoxPadding:.2,...e};return r?this.alignDlib():this.alignMinBbox(n)}alignDlib(){let t=this.getRefPointsForAlignment(),[e,r,n]=t,a=d=>n.sub(d).magnitude(),s=(a(e)+a(r))/2,i=Math.floor(s/In),c=Ot(t),m=Math.floor(Math.max(0,c.x-Cn*i)),p=Math.floor(Math.max(0,c.y-Nn*i));return new re(m,p,Math.min(i,this.imageWidth+m),Math.min(i,this.imageHeight+p))}alignMinBbox(t){let e=kr(this.positions);return e.pad(e.width*t,e.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var vo=class extends V{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Ot([t[3],t[4]])]}};var oe=class extends V{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Ot)}};var Ee=class{constructor(t,e){this._label=t,this._distance=e}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${Rt(this.distance)})`:""}`}};var Me=class extends D{static assertIsValidLabeledBox(t,e){if(D.assertIsValidBox(t,e),!rt(t.label))throw new Error(`${e} - expected property label (${t.label}) to be a number`)}constructor(t,e){super(t);this._label=e}get label(){return this._label}};var xt=class{constructor(t,e){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(e)||e.some(r=>!(r instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=e}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let e=t.descriptors.map(r=>new Float32Array(r));return new xt(t.label,e)}};var yo=class extends Me{static assertIsValidPredictedBox(t,e){if(Me.assertIsValidLabeledBox(t,e),!te(t.score)||!te(t.classScore))throw new Error(`${e} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,e,r,n){super(t,e);this._score=r,this._classScore=n}get score(){return this._score}get classScore(){return this._classScore}};function pt(o){return o.detection instanceof M}function $t(o,t){return{...o,...{detection:t}}}function Wr(){let o=window.fetch;if(!o)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:o,readFile:t}}function Ue(o){let t="";if(!o)try{o=require("fs")}catch(r){t=r.toString()}return{readFile:o?r=>new Promise((n,a)=>{o.readFile(r,(s,i)=>s?a(s):n(i))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function Br(){let o=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,e=()=>{if(o)return new o;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},r=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},n=global.fetch,a=Ue();return{Canvas:o||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:e,createImageElement:r,fetch:n,...a}}function Rr(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var Or=b(To()),k;function Sn(){if(!k)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return k}function $r(o){k=o}function jr(){return Rr()?$r(Wr()):Or.isNodejs()?$r(Br()):null}function An(o){if(k||jr(),!k)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=k.Canvas,Image:e=k.Image}=o;k.Canvas=t,k.Image=e,k.createCanvasElement=o.createCanvasElement||(()=>new t),k.createImageElement=o.createImageElement||(()=>new e),k.ImageData=o.ImageData||k.ImageData,k.Video=o.Video||k.Video,k.fetch=o.fetch||k.fetch,k.readFile=o.readFile||k.readFile}var w={getEnv:Sn,setEnv:$r,initialize:jr,createBrowserEnv:Wr,createFileSystem:Ue,createNodejsEnv:Br,monkeyPatch:An,isBrowser:Rr,isNodejs:Or.isNodejs};jr();function jt(o){return!w.isNodejs()&&typeof o=="string"?document.getElementById(o):o}function O(o){let{Canvas:t,CanvasRenderingContext2D:e}=w.getEnv();if(o instanceof e)return o;let r=jt(o);if(!(r instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let n=r.getContext("2d");if(!n)throw new Error("resolveContext2d - canvas 2d context is null");return n}var dt;(function(o){o.TOP_LEFT="TOP_LEFT",o.TOP_RIGHT="TOP_RIGHT",o.BOTTOM_LEFT="BOTTOM_LEFT",o.BOTTOM_RIGHT="BOTTOM_RIGHT"})(dt||(dt={}));var Ce=class{constructor(t={}){let{anchorPosition:e,backgroundColor:r,fontColor:n,fontSize:a,fontStyle:s,padding:i}=t;this.anchorPosition=e||dt.TOP_LEFT,this.backgroundColor=r||"rgba(0, 0, 0, 0.5)",this.fontColor=n||"rgba(255, 255, 255, 1)",this.fontSize=a||14,this.fontStyle=s||"Georgia",this.padding=i||4}},Mt=class{constructor(t,e,r={}){this.text=typeof t=="string"?[t]:t instanceof Mt?t.text:t,this.anchor=e,this.options=new Ce(r)}measureWidth(t){let{padding:e}=this.options;return this.text.map(r=>t.measureText(r).width).reduce((r,n)=>r{let v=c+d.x,_=c+d.y+(l+1)*s;r.fillText(u,v,_)})}};var Hr=class{constructor(t={}){let{boxColor:e,lineWidth:r,label:n,drawLabelOptions:a}=t;this.boxColor=e||"rgba(0, 0, 255, 1)",this.lineWidth=r||2,this.label=n;let s={anchorPosition:dt.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Ce({...s,...a})}},Xe=class{constructor(t,e={}){this.box=new D(t),this.options=new Hr(e)}draw(t){let e=O(t),{boxColor:r,lineWidth:n}=this.options,{x:a,y:s,width:i,height:c}=this.box;e.strokeStyle=r,e.lineWidth=n,e.strokeRect(a,s,i,c);let{label:m}=this.options;m&&new Mt([m],{x:a-n/2,y:s},this.options.drawLabelOptions).draw(t)}};function Wn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof M?r.score:pt(r)?r.detection.score:void 0,a=r instanceof M?r.box:pt(r)?r.detection.box:new D(r),s=n?`${Rt(n)}`:void 0;new Xe(a,{label:s}).draw(o)})}var ue=b(g());function Ne(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t&&o.complete||o instanceof e&&o.readyState>=3}function Yr(o){return new Promise((t,e)=>{if(o instanceof w.getEnv().Canvas||Ne(o))return t(null);function r(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),e(a))}function n(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),t(a))}o.addEventListener("load",n),o.addEventListener("error",r)})}function Gr(o){return new Promise((t,e)=>{o instanceof Blob||e(new Error("bufferToImage - expected buf to be of type: Blob"));let r=new FileReader;r.onload=()=>{typeof r.result!="string"&&e(new Error("bufferToImage - expected reader.result to be a string, in onload"));let n=w.getEnv().createImageElement();n.onload=()=>t(n),n.onerror=e,n.src=r.result},r.onerror=e,r.readAsDataURL(o)})}function Ht(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t?new A(o.naturalWidth,o.naturalHeight):o instanceof e?new A(o.videoWidth,o.videoHeight):new A(o.width,o.height)}function ne({width:o,height:t}){let{createCanvasElement:e}=w.getEnv(),r=e();return r.width=o,r.height=t,r}function Ie(o,t){let{ImageData:e}=w.getEnv();if(!(o instanceof e)&&!Ne(o))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:r,height:n}=t||Ht(o),a=ne({width:r,height:n});return o instanceof e?O(a).putImageData(o,0,0):O(a).drawImage(o,0,0,r,n),a}var Je=b(g());async function zr(o,t){let e=t||w.getEnv().createCanvasElement(),[r,n,a]=o.shape.slice(z(o)?1:0),s=Je.tidy(()=>o.as3D(r,n,a).toInt());return await Je.browser.toPixels(s,e),s.dispose(),e}function qe(o){let{Image:t,Canvas:e,Video:r}=w.getEnv();return o instanceof t||o instanceof e||o instanceof r}var J=b(g());function Vr(o,t,e=!1){let{Image:r,Canvas:n}=w.getEnv();if(!(o instanceof r||o instanceof n))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let a=Ht(o),s=t/Math.max(a.height,a.width),i=s*a.width,c=s*a.height,m=ne({width:t,height:t}),p=o instanceof n?o:Ie(o),d=Math.abs(i-c)/2,u=e&&i{if(ht(r)){this._imageTensors[n]=r,this._inputDimensions[n]=r.shape;return}if(z(r)){let s=r.shape[0];if(s!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${s} passed, but not supported in input array`);this._imageTensors[n]=r,this._inputDimensions[n]=r.shape.slice(1);return}let a=r instanceof w.getEnv().Canvas?r:Ie(r);this._canvases[n]=a,this._inputDimensions[n]=[a.height,a.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ct(this.batchSize,0,1).map((t,e)=>this.getReshapedInputDimensions(e))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let e=this.getInputWidth(t),r=this.getInputHeight(t);return Ir({width:e,height:r},this.inputSize)}toBatchTensor(t,e=!0){return this._inputSize=t,J.tidy(()=>{let r=ct(this.batchSize,0,1).map(a=>{let s=this.getInput(a);if(s instanceof J.Tensor){let i=z(s)?s:s.expandDims();return i=Ar(i,e),(i.shape[1]!==t||i.shape[2]!==t)&&(i=J.image.resizeBilinear(i,[t,t])),i.as3D(t,t,3)}if(s instanceof w.getEnv().Canvas)return J.browser.fromPixels(Vr(s,t,e));throw new Error(`toBatchTensor - at batchIdx ${a}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${s}`)});return J.stack(r.map(a=>J.cast(a,"float32"))).as4D(this.batchSize,t,t,3)})}};async function E(o){if(o instanceof bt)return o;let t=Array.isArray(o)?o:[o];if(!t.length)throw new Error("toNetInput - empty array passed as input");let e=n=>Array.isArray(o)?` at input index ${n}:`:"",r=t.map(jt);return r.forEach((n,a)=>{if(!qe(n)&&!ht(n)&&!z(n))throw typeof t[a]=="string"?new Error(`toNetInput -${e(a)} string passed, but could not resolve HTMLElement for element id ${t[a]}`):new Error(`toNetInput -${e(a)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(z(n)){let s=n.shape[0];if(s!==1)throw new Error(`toNetInput -${e(a)} tf.Tensor4D with batchSize ${s} passed, but not supported in input array`)}}),await Promise.all(r.map(n=>qe(n)&&Yr(n))),new bt(r,Array.isArray(o))}async function ae(o,t){let{Canvas:e}=w.getEnv(),r=o;if(!(o instanceof e)){let s=await E(o);if(s.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let i=s.getInput(0);r=i instanceof e?i:await zr(i)}let n=O(r);return t.map(s=>s instanceof M?s.forSize(r.width,r.height).box.floor():s).map(s=>s.clipAtImageBorders(r.width,r.height)).map(({x:s,y:i,width:c,height:m})=>{let p=ne({width:c,height:m});return O(p).putImageData(n.getImageData(s,i,c,m),0,0),p})}var Ze=b(g());async function se(o,t){if(!ht(o)&&!z(o))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(z(o)&&o.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return Ze.tidy(()=>{let[e,r,n]=o.shape.slice(z(o)?1:0);return t.map(i=>i instanceof M?i.forSize(r,e).box:i).map(i=>i.clipAtImageBorders(r,e)).map(({x:i,y:c,width:m,height:p})=>Ze.slice3d(o.as3D(e,r,n),[c,i,0],[p,m,n]))})}async function Yt(o,t){let{fetch:e}=w.getEnv(),r=await e(o,t);if(!(r.status<400))throw new Error(`failed to fetch: (${r.status}) ${r.statusText}, from url: ${r.url}`);return r}async function Bn(o){let t=await Yt(o),e=await t.blob();if(!e.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${e.type}, for url: ${t.url}`);return Gr(e)}async function Ur(o){return(await Yt(o)).json()}async function Rn(o){return new Float32Array(await(await Yt(o)).arrayBuffer())}var Po=b(g());function Ke(o,t){let e=`${t}-weights_manifest.json`;if(!o)return{modelBaseUri:"",manifestUri:e};if(o==="/")return{modelBaseUri:"/",manifestUri:`/${e}`};let r=o.startsWith("http://")?"http://":o.startsWith("https://")?"https://":"";o=o.replace(r,"");let n=o.split("/").filter(i=>i),a=o.endsWith(".json")?n[n.length-1]:e,s=r+(o.endsWith(".json")?n.slice(0,n.length-1):n).join("/");return s=o.startsWith("/")?`/${s}`:s,{modelBaseUri:s,manifestUri:s==="/"?`/${a}`:`${s}/${a}`}}async function Xr(o,t){let{manifestUri:e,modelBaseUri:r}=Ke(o,t),n=await Ur(e);return Po.io.loadWeights(n,r)}function On(o,t,e=!1){let{width:r,height:n}=e?Ht(t):t;return o.width=r,o.height=n,{width:r,height:n}}var Nt=b(g());var gt=b(g());var S=class{constructor(){this._params=void 0;this._paramMappings=[]}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:e,objProp:r}=this.traversePropertyPath(t);return e[r]}reassignParamFromPath(t,e){let{obj:r,objProp:n}=this.traversePropertyPath(t);r[n].dispose(),r[n]=e}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof gt.Variable)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof gt.Variable))}variable(){this.getFrozenParams().forEach(({path:t,tensor:e})=>{this.reassignParamFromPath(t,e.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:e})=>{let r=gt.tensor(e.dataSync());e.dispose(),this.reassignParamFromPath(t,r)})}dispose(t=!0){this.getParamList().forEach(e=>{if(t&&e.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${e.path}`);e.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,e)=>t.concat(e)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let e=await Xr(t,this.getDefaultModelName());this.loadFromWeightMap(e)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:e}=w.getEnv(),{manifestUri:r,modelBaseUri:n}=Ke(t,this.getDefaultModelName()),a=m=>Promise.all(m.map(p=>e(p).then(d=>d.buffer))),s=gt.io.weightsLoaderFactory(a),i=JSON.parse((await e(r)).toString()),c=await s(i,n);this.loadFromWeightMap(c)}loadFromWeightMap(t){let{paramMappings:e,params:r}=this.extractParamsFromWeightMap(t);this._paramMappings=e,this._params=r}extractWeights(t){let{paramMappings:e,params:r}=this.extractParams(t);this._paramMappings=e,this._params=r}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let e=t.split("/").reduce((a,s)=>{if(!a.nextObj.hasOwnProperty(s))throw new Error(`traversePropertyPath - object does not have property ${s}, for path ${t}`);return{obj:a.nextObj,objProp:s,nextObj:a.nextObj[s]}},{nextObj:this.params}),{obj:r,objProp:n}=e;if(!r||!n||!(r[n]instanceof gt.Tensor))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:r,objProp:n}}};var C=b(g());var ie=b(g());function $(o,t,e){return ie.tidy(()=>{let r=ie.separableConv2d(o,t.depthwise_filter,t.pointwise_filter,e,"same");return r=ie.add(r,t.bias),r})}function Qe(o,t,e=!1){return C.tidy(()=>{let r=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,[2,2],"same"),t.conv0.bias):$(o,t.conv0,[2,2])),n=$(r,t.conv1,[1,1]),a=C.relu(C.add(r,n)),s=$(a,t.conv2,[1,1]);return C.relu(C.add(r,C.add(n,s)))})}function Le(o,t,e=!1,r=!0){return C.tidy(()=>{let n=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,r?[2,2]:[1,1],"same"),t.conv0.bias):$(o,t.conv0,r?[2,2]:[1,1])),a=$(n,t.conv1,[1,1]),s=C.relu(C.add(n,a)),i=$(s,t.conv2,[1,1]),c=C.relu(C.add(n,C.add(a,i))),m=$(c,t.conv3,[1,1]);return C.relu(C.add(n,C.add(a,C.add(i,m))))})}var Ct=b(g());function Gt(o,t,e="same",r=!1){return Ct.tidy(()=>{let n=Ct.add(Ct.conv2d(o,t.filters,[1,1],e),t.bias);return r?Ct.relu(n):n})}function W(o,t){Object.keys(o).forEach(e=>{t.some(r=>r.originalPath===e)||o[e].dispose()})}var tr=b(g());function ce(o,t){return(e,r,n,a)=>{let s=tr.tensor4d(o(e*r*n*n),[n,n,e,r]),i=tr.tensor1d(o(r));return t.push({paramPath:`${a}/filters`},{paramPath:`${a}/bias`}),{filters:s,bias:i}}}var er=b(g());function rr(o,t){return(e,r,n)=>{let a=er.tensor2d(o(e*r),[e,r]),s=er.tensor1d(o(r));return t.push({paramPath:`${n}/weights`},{paramPath:`${n}/bias`}),{weights:a,bias:s}}}var ke=b(g());var or=class{constructor(t,e,r){this.depthwise_filter=t;this.pointwise_filter=e;this.bias=r}};function me(o,t){return(e,r,n)=>{let a=ke.tensor4d(o(3*3*e),[3,3,e,1]),s=ke.tensor4d(o(e*r),[1,1,e,r]),i=ke.tensor1d(o(r));return t.push({paramPath:`${n}/depthwise_filter`},{paramPath:`${n}/pointwise_filter`},{paramPath:`${n}/bias`}),new or(a,s,i)}}function pe(o){return t=>{let e=o(`${t}/depthwise_filter`,4),r=o(`${t}/pointwise_filter`,4),n=o(`${t}/bias`,1);return new or(e,r,n)}}function j(o,t){return(e,r,n)=>{let a=o[e];if(!Bt(a,r))throw new Error(`expected weightMap[${e}] to be a Tensor${r}D, instead have ${a}`);return t.push({originalPath:e,paramPath:n||e}),a}}function B(o){let t=o;function e(n){let a=t.slice(0,n);return t=t.slice(n),a}function r(){return t}return{extractWeights:e,getRemainingWeights:r}}function nr(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c,m=!1){let p=m?e(s,i,3,`${c}/conv0`):r(s,i,`${c}/conv0`),d=r(i,i,`${c}/conv1`),u=r(i,i,`${c}/conv2`);return{conv0:p,conv1:d,conv2:u}}function a(s,i,c,m=!1){let{conv0:p,conv1:d,conv2:u}=n(s,i,c,m),l=r(i,i,`${c}/conv3`);return{conv0:p,conv1:d,conv2:u,conv3:l}}return{extractDenseBlock3Params:n,extractDenseBlock4Params:a}}function _o(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock4Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2"),c=n(128,256,"dense3");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i,dense3:c}}}function ar(o){return t=>{let e=o(`${t}/filters`,4),r=o(`${t}/bias`,1);return{filters:e,bias:r}}}function sr(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`);return{conv0:m,conv1:p,conv2:d}}function s(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`),u=n(`${i}/conv3`);return{conv0:m,conv1:p,conv2:d,conv3:u}}return{extractDenseBlock3Params:a,extractDenseBlock4Params:s}}function wo(o){let t=[],{extractDenseBlock4Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2"),dense3:e("dense3")};return W(o,t),{params:r,paramMappings:t}}var Se=class extends S{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceFeatureExtractor - load model before inference");return Nt.tidy(()=>{let r=Nt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Nt.scalar(255)),s=Le(a,e.dense0,!0);return s=Le(s,e.dense1),s=Le(s,e.dense2),s=Le(s,e.dense3),s=Nt.avgPool(s,[7,7],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return wo(t)}extractParams(t){return _o(t)}};var Mo=b(g());var de=b(g());function Ae(o,t){return de.tidy(()=>de.add(de.matMul(o,t.weights),t.bias))}function Do(o,t,e){let r=[],{extractWeights:n,getRemainingWeights:a}=B(o),i=rr(n,r)(t,e,"fc");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:r,params:{fc:i}}}function Eo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:r("fc")};return W(o,t),{params:n,paramMappings:t}}function ir(o){let t={},e={};return Object.keys(o).forEach(r=>{let n=r.startsWith("fc")?e:t;n[r]=o[r]}),{featureExtractorMap:t,classifierMap:e}}var We=class extends S{constructor(t,e){super(t);this._faceFeatureExtractor=e}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return Mo.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t;return Ae(r.as2D(r.shape[0],-1),e.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return Do(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),Eo(r)}extractParams(t){let e=this.getClassifierChannelsIn(),r=this.getClassifierChannelsOut(),n=r*e+r,a=t.slice(0,t.length-n),s=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(s)}};var Jr=["neutral","happy","sad","angry","fearful","disgusted","surprised"],It=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Jr.forEach((e,r)=>{this[e]=t[r]})}asSortedArray(){return Jr.map(t=>({expression:t,probability:this[t]})).sort((t,e)=>e.probability-t.probability)}};var cr=class extends We{constructor(t=new Se){super("FaceExpressionNet",t)}forwardInput(t){return ue.tidy(()=>ue.softmax(this.runNet(t)))}async forward(t){return this.forwardInput(await E(t))}async predictExpressions(t){let e=await E(t),r=await this.forwardInput(e),n=await Promise.all(ue.unstack(r).map(async s=>{let i=await s.data();return s.dispose(),i}));r.dispose();let a=n.map(s=>new It(s));return e.isBatchInput?a:a[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function qr(o){return o.expressions instanceof It}function mr(o,t){return{...o,...{expressions:t}}}function $n(o,t,e=.1,r){(Array.isArray(t)?t:[t]).forEach(a=>{let s=a instanceof It?a:qr(a)?a.expressions:void 0;if(!s)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let c=s.asSortedArray().filter(d=>d.probability>e),m=pt(a)?a.detection.box.bottomLeft:r||new x(0,0);new Mt(c.map(d=>`${d.expression} (${Rt(d.probability)})`),m).draw(o)})}function zt(o){return pt(o)&&o.landmarks instanceof V&&o.unshiftedLandmarks instanceof V&&o.alignedRect instanceof M}function le(o,t){let{box:e}=o.detection,r=t.shiftBy(e.x,e.y),n=r.align(),{imageDims:a}=o.detection,s=new M(o.detection.score,n.rescale(a.reverse()),a);return{...o,...{landmarks:r,unshiftedLandmarks:t,alignedRect:s}}}var Zr=class{constructor(t={}){let{drawLines:e=!0,drawPoints:r=!0,lineWidth:n,lineColor:a,pointSize:s,pointColor:i}=t;this.drawLines=e,this.drawPoints=r,this.lineWidth=n||1,this.pointSize=s||2,this.lineColor=a||"rgba(0, 255, 255, 1)",this.pointColor=i||"rgba(255, 0, 255, 1)"}},Kr=class{constructor(t,e={}){this.faceLandmarks=t,this.options=new Zr(e)}draw(t){let e=O(t),{drawLines:r,drawPoints:n,lineWidth:a,lineColor:s,pointSize:i,pointColor:c}=this.options;if(r&&this.faceLandmarks instanceof oe&&(e.strokeStyle=s,e.lineWidth=a,ft(e,this.faceLandmarks.getJawOutline()),ft(e,this.faceLandmarks.getLeftEyeBrow()),ft(e,this.faceLandmarks.getRightEyeBrow()),ft(e,this.faceLandmarks.getNose()),ft(e,this.faceLandmarks.getLeftEye(),!0),ft(e,this.faceLandmarks.getRightEye(),!0),ft(e,this.faceLandmarks.getMouth(),!0)),n){e.strokeStyle=c,e.fillStyle=c;let m=p=>{e.beginPath(),e.arc(p.x,p.y,i,0,2*Math.PI),e.fill()};this.faceLandmarks.positions.forEach(m)}}};function jn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof V?r:zt(r)?r.landmarks:void 0;if(!n)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new Kr(n).draw(o)})}var Co="0.11.4";var ut=b(g());var I=b(g());function Hn(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c){let m=r(s,i,`${c}/separable_conv0`),p=r(i,i,`${c}/separable_conv1`),d=e(s,i,1,`${c}/expansion_conv`);return{separable_conv0:m,separable_conv1:p,expansion_conv:d}}function a(s,i){let c=r(s,s,`${i}/separable_conv0`),m=r(s,s,`${i}/separable_conv1`),p=r(s,s,`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:e,extractSeparableConvParams:r,extractReductionBlockParams:n,extractMainBlockParams:a}}function No(o,t){let e=[],{extractWeights:r,getRemainingWeights:n}=B(o),{extractConvParams:a,extractSeparableConvParams:s,extractReductionBlockParams:i,extractMainBlockParams:c}=Hn(r,e),m=a(3,32,3,"entry_flow/conv_in"),p=i(32,64,"entry_flow/reduction_block_0"),d=i(64,128,"entry_flow/reduction_block_1"),u={conv_in:m,reduction_block_0:p,reduction_block_1:d},l={};ct(t,0,1).forEach(y=>{l[`main_block_${y}`]=c(128,`middle_flow/main_block_${y}`)});let v=i(128,256,"exit_flow/reduction_block"),_=s(256,512,"exit_flow/separable_conv"),h={reduction_block:v,separable_conv:_};if(n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{paramMappings:e,params:{entry_flow:u,middle_flow:l,exit_flow:h}}}function Yn(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=r(`${i}/expansion_conv`);return{separable_conv0:c,separable_conv1:m,expansion_conv:p}}function s(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=n(`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}}function Io(o,t){let e=[],{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}=Yn(o,e),i=r("entry_flow/conv_in"),c=a("entry_flow/reduction_block_0"),m=a("entry_flow/reduction_block_1"),p={conv_in:i,reduction_block_0:c,reduction_block_1:m},d={};ct(t,0,1).forEach(_=>{d[`main_block_${_}`]=s(`middle_flow/main_block_${_}`)});let u=a("exit_flow/reduction_block"),l=n("exit_flow/separable_conv"),v={reduction_block:u,separable_conv:l};return W(o,e),{params:{entry_flow:p,middle_flow:d,exit_flow:v},paramMappings:e}}function Lo(o,t,e){return I.add(I.conv2d(o,t.filters,e,"same"),t.bias)}function to(o,t,e=!0){let r=e?I.relu(o):o;return r=$(r,t.separable_conv0,[1,1]),r=$(I.relu(r),t.separable_conv1,[1,1]),r=I.maxPool(r,[3,3],[2,2],"same"),r=I.add(r,Lo(o,t.expansion_conv,[2,2])),r}function Gn(o,t){let e=$(I.relu(o),t.separable_conv0,[1,1]);return e=$(I.relu(e),t.separable_conv1,[1,1]),e=$(I.relu(e),t.separable_conv2,[1,1]),e=I.add(e,o),e}var eo=class extends S{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyXception - load model before inference");return I.tidy(()=>{let r=I.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(I.scalar(256)),s=I.relu(Lo(a,e.entry_flow.conv_in,[2,2]));return s=to(s,e.entry_flow.reduction_block_0,!1),s=to(s,e.entry_flow.reduction_block_1),ct(this._numMainBlocks,0,1).forEach(i=>{s=Gn(s,e.middle_flow[`main_block_${i}`])}),s=to(s,e.exit_flow.reduction_block),s=I.relu($(s,e.exit_flow.separable_conv,[1,1])),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return Io(t,this._numMainBlocks)}extractParams(t){return No(t,this._numMainBlocks)}};function ko(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),n=rr(e,t),a=n(512,1,"fc/age"),s=n(512,2,"fc/gender");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{fc:{age:a,gender:s}}}}function So(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:{age:r("fc/age"),gender:r("fc/gender")}};return W(o,t),{params:n,paramMappings:t}}var vt;(function(o){o.FEMALE="female",o.MALE="male"})(vt||(vt={}));var pr=class extends S{constructor(t=new eo(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return ut.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t,n=ut.avgPool(r,[7,7],[2,2],"valid").as2D(r.shape[0],-1),a=Ae(n,e.fc.age).as1D(),s=Ae(n,e.fc.gender);return{age:a,gender:s}})}forwardInput(t){return ut.tidy(()=>{let{age:e,gender:r}=this.runNet(t);return{age:e,gender:ut.softmax(r)}})}async forward(t){return this.forwardInput(await E(t))}async predictAgeAndGender(t){let e=await E(t),r=await this.forwardInput(e),n=ut.unstack(r.age),a=ut.unstack(r.gender),s=n.map((c,m)=>({ageTensor:c,genderTensor:a[m]})),i=await Promise.all(s.map(async({ageTensor:c,genderTensor:m})=>{let p=(await c.data())[0],d=(await m.data())[0],u=d>.5,l=u?vt.MALE:vt.FEMALE,v=u?d:1-d;return c.dispose(),m.dispose(),{age:p,gender:l,genderProbability:v}}));return r.age.dispose(),r.gender.dispose(),e.isBatchInput?i:i[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return ko(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),So(r)}extractParams(t){let e=512*1+1+(512*2+2),r=t.slice(0,t.length-e),n=t.slice(t.length-e);return this.faceFeatureExtractor.extractWeights(r),this.extractClassifierParams(n)}};var H=b(g());var Be=class extends We{postProcess(t,e,r){let n=r.map(({width:s,height:i})=>{let c=e/Math.max(i,s);return{width:s*c,height:i*c}}),a=n.length;return H.tidy(()=>{let s=(d,u)=>H.stack([H.fill([68],d,"float32"),H.fill([68],u,"float32")],1).as2D(1,136).as1D(),i=(d,u)=>{let{width:l,height:v}=n[d];return u(l,v)?Math.abs(l-v)/2:0},c=d=>i(d,(u,l)=>ui(d,(u,l)=>ls(c(u),m(u))))).div(H.stack(Array.from(Array(a),(d,u)=>s(n[u].width,n[u].height))))})}forwardInput(t){return H.tidy(()=>{let e=this.runNet(t);return this.postProcess(e,t.inputSize,t.inputDimensions.map(([r,n])=>({height:r,width:n})))})}async forward(t){return this.forwardInput(await E(t))}async detectLandmarks(t){let e=await E(t),r=H.tidy(()=>H.unstack(this.forwardInput(e))),n=await Promise.all(r.map(async(a,s)=>{let i=Array.from(await a.data()),c=i.filter((p,d)=>ze(d)),m=i.filter((p,d)=>!ze(d));return new oe(Array(68).fill(0).map((p,d)=>new x(c[d],m[d])),{height:e.getInputHeight(s),width:e.getInputWidth(s)})}));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getClassifierChannelsOut(){return 136}};var fe=class extends Be{constructor(t=new Se){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};var Lt=b(g());function Ao(o){let t=[],{extractDenseBlock3Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2")};return W(o,t),{params:r,paramMappings:t}}function Wo(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock3Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i}}}var ro=class extends S{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyFaceFeatureExtractor - load model before inference");return Lt.tidy(()=>{let r=Lt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Lt.scalar(255)),s=Qe(a,e.dense0,!0);return s=Qe(s,e.dense1),s=Qe(s,e.dense2),s=Lt.avgPool(s,[14,14],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return Ao(t)}extractParams(t){return Wo(t)}};var dr=class extends Be{constructor(t=new ro){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Bo=class extends fe{};var U=b(g());var he=b(g());var ur=b(g());function Ro(o,t){return ur.add(ur.mul(o,t.weights),t.biases)}function oo(o,t,e,r,n="same"){let{filters:a,bias:s}=t.conv,i=he.conv2d(o,a,e,n);return i=he.add(i,s),i=Ro(i,t.scale),r?he.relu(i):i}function Oo(o,t){return oo(o,t,[1,1],!0)}function no(o,t){return oo(o,t,[1,1],!1)}function lr(o,t){return oo(o,t,[2,2],!0,"valid")}var Y=b(g());function zn(o,t){function e(i,c,m){let p=o(i),d=p.length/(c*m*m);if(Nr(d))throw new Error(`depth has to be an integer: ${d}, weights.length: ${p.length}, numFilters: ${c}, filterSize: ${m}`);return Y.tidy(()=>Y.transpose(Y.tensor4d(p,[c,d,m,m]),[2,3,1,0]))}function r(i,c,m,p){let d=e(i,c,m),u=Y.tensor1d(o(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/bias`}),{filters:d,bias:u}}function n(i,c){let m=Y.tensor1d(o(i)),p=Y.tensor1d(o(i));return t.push({paramPath:`${c}/weights`},{paramPath:`${c}/biases`}),{weights:m,biases:p}}function a(i,c,m,p){let d=r(i,c,m,`${p}/conv`),u=n(c,`${p}/scale`);return{conv:d,scale:u}}function s(i,c,m,p,d=!1){let u=a((d?.5:1)*i,c,m,`${p}/conv1`),l=a(i,c,m,`${p}/conv2`);return{conv1:u,conv2:l}}return{extractConvLayerParams:a,extractResidualLayerParams:s}}function $o(o){let{extractWeights:t,getRemainingWeights:e}=B(o),r=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=zn(t,r),s=n(4704,32,7,"conv32_down"),i=a(9216,32,3,"conv32_1"),c=a(9216,32,3,"conv32_2"),m=a(9216,32,3,"conv32_3"),p=a(36864,64,3,"conv64_down",!0),d=a(36864,64,3,"conv64_1"),u=a(36864,64,3,"conv64_2"),l=a(36864,64,3,"conv64_3"),v=a(147456,128,3,"conv128_down",!0),_=a(147456,128,3,"conv128_1"),h=a(147456,128,3,"conv128_2"),y=a(589824,256,3,"conv256_down",!0),T=a(589824,256,3,"conv256_1"),F=a(589824,256,3,"conv256_2"),L=a(589824,256,3,"conv256_down_out"),G=Y.tidy(()=>Y.transpose(Y.tensor2d(t(256*128),[128,256]),[1,0]));if(r.push({paramPath:"fc"}),e().length!==0)throw new Error(`weights remaing after extract: ${e().length}`);return{params:{conv32_down:s,conv32_1:i,conv32_2:c,conv32_3:m,conv64_down:p,conv64_1:d,conv64_2:u,conv64_3:l,conv128_down:v,conv128_1:_,conv128_2:h,conv256_down:y,conv256_1:T,conv256_2:F,conv256_down_out:L,fc:G},paramMappings:r}}function Vn(o,t){let e=j(o,t);function r(s){let i=e(`${s}/scale/weights`,1),c=e(`${s}/scale/biases`,1);return{weights:i,biases:c}}function n(s){let i=e(`${s}/conv/filters`,4),c=e(`${s}/conv/bias`,1),m=r(s);return{conv:{filters:i,bias:c},scale:m}}function a(s){return{conv1:n(`${s}/conv1`),conv2:n(`${s}/conv2`)}}return{extractConvLayerParams:n,extractResidualLayerParams:a}}function jo(o){let t=[],{extractConvLayerParams:e,extractResidualLayerParams:r}=Vn(o,t),n=e("conv32_down"),a=r("conv32_1"),s=r("conv32_2"),i=r("conv32_3"),c=r("conv64_down"),m=r("conv64_1"),p=r("conv64_2"),d=r("conv64_3"),u=r("conv128_down"),l=r("conv128_1"),v=r("conv128_2"),_=r("conv256_down"),h=r("conv256_1"),y=r("conv256_2"),T=r("conv256_down_out"),{fc:F}=o;if(t.push({originalPath:"fc",paramPath:"fc"}),!Cr(F))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${F}`);let L={conv32_down:n,conv32_1:a,conv32_2:s,conv32_3:i,conv64_down:c,conv64_1:m,conv64_2:p,conv64_3:d,conv128_down:u,conv128_1:l,conv128_2:v,conv256_down:_,conv256_1:h,conv256_2:y,conv256_down_out:T,fc:F};return W(o,t),{params:L,paramMappings:t}}var R=b(g());function nt(o,t){let e=Oo(o,t.conv1);return e=no(e,t.conv2),e=R.add(e,o),e=R.relu(e),e}function Re(o,t){let e=lr(o,t.conv1);e=no(e,t.conv2);let r=R.avgPool(o,2,2,"valid"),n=R.zeros(r.shape),a=r.shape[3]!==e.shape[3];if(r.shape[1]!==e.shape[1]||r.shape[2]!==e.shape[2]){let i=[...e.shape];i[1]=1;let c=R.zeros(i);e=R.concat([e,c],1);let m=[...e.shape];m[2]=1;let p=R.zeros(m);e=R.concat([e,p],2)}return r=a?R.concat([r,n],3):r,e=R.add(r,e),e=R.relu(e),e}var xe=class extends S{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceRecognitionNet - load model before inference");return U.tidy(()=>{let r=U.cast(t.toBatchTensor(150,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(U.scalar(256)),s=lr(a,e.conv32_down);s=U.maxPool(s,3,2,"valid"),s=nt(s,e.conv32_1),s=nt(s,e.conv32_2),s=nt(s,e.conv32_3),s=Re(s,e.conv64_down),s=nt(s,e.conv64_1),s=nt(s,e.conv64_2),s=nt(s,e.conv64_3),s=Re(s,e.conv128_down),s=nt(s,e.conv128_1),s=nt(s,e.conv128_2),s=Re(s,e.conv256_down),s=nt(s,e.conv256_1),s=nt(s,e.conv256_2),s=Re(s,e.conv256_down_out);let i=s.mean([1,2]);return U.matMul(i,e.fc)})}async forward(t){return this.forwardInput(await E(t))}async computeFaceDescriptor(t){let e=await E(t),r=U.tidy(()=>U.unstack(this.forwardInput(e))),n=await Promise.all(r.map(a=>a.data()));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return jo(t)}extractParams(t){return $o(t)}};function Un(o){let t=new xe;return t.extractWeights(o),t}function fr(o,t){return{...o,...{descriptor:t}}}function Xn(o){return typeof o.age=="number"}function hr(o,t){return{...o,...{age:t}}}function Jn(o){return(o.gender===vt.MALE||o.gender===vt.FEMALE)&&te(o.genderProbability)}function xr(o,t,e){return{...o,...{gender:t,genderProbability:e}}}var st=b(g());var at=b(g());function qn(o,t){function e(c,m){let p=at.tensor4d(o(3*3*c),[3,3,c,1]),d=at.tensor1d(o(c)),u=at.tensor1d(o(c)),l=at.tensor1d(o(c)),v=at.tensor1d(o(c));return t.push({paramPath:`${m}/filters`},{paramPath:`${m}/batch_norm_scale`},{paramPath:`${m}/batch_norm_offset`},{paramPath:`${m}/batch_norm_mean`},{paramPath:`${m}/batch_norm_variance`}),{filters:p,batch_norm_scale:d,batch_norm_offset:u,batch_norm_mean:l,batch_norm_variance:v}}function r(c,m,p,d,u){let l=at.tensor4d(o(c*m*p*p),[p,p,c,m]),v=at.tensor1d(o(m));return t.push({paramPath:`${d}/filters`},{paramPath:`${d}/${u?"batch_norm_offset":"bias"}`}),{filters:l,bias:v}}function n(c,m,p,d){let{filters:u,bias:l}=r(c,m,p,d,!0);return{filters:u,batch_norm_offset:l}}function a(c,m,p){let d=e(c,`${p}/depthwise_conv`),u=n(c,m,1,`${p}/pointwise_conv`);return{depthwise_conv:d,pointwise_conv:u}}function s(){let c=n(3,32,3,"mobilenetv1/conv_0"),m=a(32,64,"mobilenetv1/conv_1"),p=a(64,128,"mobilenetv1/conv_2"),d=a(128,128,"mobilenetv1/conv_3"),u=a(128,256,"mobilenetv1/conv_4"),l=a(256,256,"mobilenetv1/conv_5"),v=a(256,512,"mobilenetv1/conv_6"),_=a(512,512,"mobilenetv1/conv_7"),h=a(512,512,"mobilenetv1/conv_8"),y=a(512,512,"mobilenetv1/conv_9"),T=a(512,512,"mobilenetv1/conv_10"),F=a(512,512,"mobilenetv1/conv_11"),L=a(512,1024,"mobilenetv1/conv_12"),G=a(1024,1024,"mobilenetv1/conv_13");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,conv_8:h,conv_9:y,conv_10:T,conv_11:F,conv_12:L,conv_13:G}}function i(){let c=n(1024,256,1,"prediction_layer/conv_0"),m=n(256,512,3,"prediction_layer/conv_1"),p=n(512,128,1,"prediction_layer/conv_2"),d=n(128,256,3,"prediction_layer/conv_3"),u=n(256,128,1,"prediction_layer/conv_4"),l=n(128,256,3,"prediction_layer/conv_5"),v=n(256,64,1,"prediction_layer/conv_6"),_=n(64,128,3,"prediction_layer/conv_7"),h=r(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=r(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),T=r(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),F=r(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),L=r(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),G=r(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),et=r(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),it=r(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),X=r(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),Pt=r(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),_t=r(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),wt=r(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,box_predictor_0:{box_encoding_predictor:h,class_predictor:y},box_predictor_1:{box_encoding_predictor:T,class_predictor:F},box_predictor_2:{box_encoding_predictor:L,class_predictor:G},box_predictor_3:{box_encoding_predictor:et,class_predictor:it},box_predictor_4:{box_encoding_predictor:X,class_predictor:Pt},box_predictor_5:{box_encoding_predictor:_t,class_predictor:wt}}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:i}}function Ho(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=qn(e,t),s=n(),i=a(),m={extra_dim:at.tensor3d(e(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{params:{mobilenetv1:s,prediction_layer:i,output_layer:m},paramMappings:t}}function Zn(o,t){let e=j(o,t);function r(m,p,d){let u=e(`${m}/Conv2d_${p}_pointwise/weights`,4,`${d}/filters`),l=e(`${m}/Conv2d_${p}_pointwise/convolution_bn_offset`,1,`${d}/batch_norm_offset`);return{filters:u,batch_norm_offset:l}}function n(m){let p=`mobilenetv1/conv_${m}`,d=`MobilenetV1/Conv2d_${m}_depthwise`,u=`${p}/depthwise_conv`,l=`${p}/pointwise_conv`,v=e(`${d}/depthwise_weights`,4,`${u}/filters`),_=e(`${d}/BatchNorm/gamma`,1,`${u}/batch_norm_scale`),h=e(`${d}/BatchNorm/beta`,1,`${u}/batch_norm_offset`),y=e(`${d}/BatchNorm/moving_mean`,1,`${u}/batch_norm_mean`),T=e(`${d}/BatchNorm/moving_variance`,1,`${u}/batch_norm_variance`);return{depthwise_conv:{filters:v,batch_norm_scale:_,batch_norm_offset:h,batch_norm_mean:y,batch_norm_variance:T},pointwise_conv:r("MobilenetV1",m,l)}}function a(){return{conv_0:r("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:n(1),conv_2:n(2),conv_3:n(3),conv_4:n(4),conv_5:n(5),conv_6:n(6),conv_7:n(7),conv_8:n(8),conv_9:n(9),conv_10:n(10),conv_11:n(11),conv_12:n(12),conv_13:n(13)}}function s(m,p){let d=e(`${m}/weights`,4,`${p}/filters`),u=e(`${m}/biases`,1,`${p}/bias`);return{filters:d,bias:u}}function i(m){let p=s(`Prediction/BoxPredictor_${m}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${m}/box_encoding_predictor`),d=s(`Prediction/BoxPredictor_${m}/ClassPredictor`,`prediction_layer/box_predictor_${m}/class_predictor`);return{box_encoding_predictor:p,class_predictor:d}}function c(){return{conv_0:r("Prediction",0,"prediction_layer/conv_0"),conv_1:r("Prediction",1,"prediction_layer/conv_1"),conv_2:r("Prediction",2,"prediction_layer/conv_2"),conv_3:r("Prediction",3,"prediction_layer/conv_3"),conv_4:r("Prediction",4,"prediction_layer/conv_4"),conv_5:r("Prediction",5,"prediction_layer/conv_5"),conv_6:r("Prediction",6,"prediction_layer/conv_6"),conv_7:r("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:i(0),box_predictor_1:i(1),box_predictor_2:i(2),box_predictor_3:i(3),box_predictor_4:i(4),box_predictor_5:i(5)}}return{extractMobilenetV1Params:a,extractPredictionLayerParams:c}}function Yo(o){let t=[],{extractMobilenetV1Params:e,extractPredictionLayerParams:r}=Zn(o,t),n=o["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!ht(n))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${n}`);let a={mobilenetv1:e(),prediction_layer:r(),output_layer:{extra_dim:n}};return W(o,t),{params:a,paramMappings:t}}var yt=b(g());var kt=b(g());function q(o,t,e){return kt.tidy(()=>{let r=kt.conv2d(o,t.filters,e,"same");return r=kt.add(r,t.batch_norm_offset),kt.clipByValue(r,0,6)})}var Kn=.0010000000474974513;function Qn(o,t,e){return yt.tidy(()=>{let r=yt.depthwiseConv2d(o,t.filters,e,"same");return r=yt.batchNorm(r,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Kn),yt.clipByValue(r,0,6)})}function ta(o){return[2,4,6,12].some(t=>t===o)?[2,2]:[1,1]}function Go(o,t){return yt.tidy(()=>{let e,r=q(o,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((a,s)=>{let i=s+1,c=ta(i);r=Qn(r,a.depthwise_conv,c),r=q(r,a.pointwise_conv,[1,1]),i===11&&(e=r)}),e===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:r,conv11:e}})}function ea(o,t,e){let r=o.arraySync(),n=Math.min(r[t][0],r[t][2]),a=Math.min(r[t][1],r[t][3]),s=Math.max(r[t][0],r[t][2]),i=Math.max(r[t][1],r[t][3]),c=Math.min(r[e][0],r[e][2]),m=Math.min(r[e][1],r[e][3]),p=Math.max(r[e][0],r[e][2]),d=Math.max(r[e][1],r[e][3]),u=(s-n)*(i-a),l=(p-c)*(d-m);if(u<=0||l<=0)return 0;let v=Math.max(n,c),_=Math.max(a,m),h=Math.min(s,p),y=Math.min(i,d),T=Math.max(h-v,0)*Math.max(y-_,0);return T/(u+l-T)}function zo(o,t,e,r,n){let a=o.shape[0],s=Math.min(e,a),i=t.map((p,d)=>({score:p,boxIndex:d})).filter(p=>p.score>n).sort((p,d)=>d.score-p.score),c=p=>p<=r?1:0,m=[];return i.forEach(p=>{if(m.length>=s)return;let d=p.score;for(let u=m.length-1;u>=0;--u){let l=ea(o,p.boxIndex,m[u]);if(l!==0&&(p.score*=c(l),p.score<=n))break}d===p.score&&m.push(p.boxIndex)}),m}var f=b(g());function ra(o){let t=f.unstack(f.transpose(o,[1,0])),e=[f.sub(t[2],t[0]),f.sub(t[3],t[1])],r=[f.add(t[0],f.div(e[0],f.scalar(2))),f.add(t[1],f.div(e[1],f.scalar(2)))];return{sizes:e,centers:r}}function oa(o,t){let{sizes:e,centers:r}=ra(o),n=f.unstack(f.transpose(t,[1,0])),a=f.div(f.mul(f.exp(f.div(n[2],f.scalar(5))),e[0]),f.scalar(2)),s=f.add(f.mul(f.div(n[0],f.scalar(10)),e[0]),r[0]),i=f.div(f.mul(f.exp(f.div(n[3],f.scalar(5))),e[1]),f.scalar(2)),c=f.add(f.mul(f.div(n[1],f.scalar(10)),e[1]),r[1]);return f.transpose(f.stack([f.sub(s,a),f.sub(c,i),f.add(s,a),f.add(c,i)]),[1,0])}function Vo(o,t,e){return f.tidy(()=>{let r=o.shape[0],n=oa(f.reshape(f.tile(e.extra_dim,[r,1,1]),[-1,4]),f.reshape(o,[-1,4]));n=f.reshape(n,[r,n.shape[0]/r,4]);let a=f.sigmoid(f.slice(t,[0,0,1],[-1,-1,-1])),s=f.slice(a,[0,0,0],[-1,-1,1]);s=f.reshape(s,[r,s.shape[1]]);let i=f.unstack(n),c=f.unstack(s);return{boxes:i,scores:c}})}var $e=b(g());var Oe=b(g());function Vt(o,t){return Oe.tidy(()=>{let e=o.shape[0],r=Oe.reshape(Gt(o,t.box_encoding_predictor),[e,-1,1,4]),n=Oe.reshape(Gt(o,t.class_predictor),[e,-1,3]);return{boxPredictionEncoding:r,classPrediction:n}})}function Uo(o,t,e){return $e.tidy(()=>{let r=q(o,e.conv_0,[1,1]),n=q(r,e.conv_1,[2,2]),a=q(n,e.conv_2,[1,1]),s=q(a,e.conv_3,[2,2]),i=q(s,e.conv_4,[1,1]),c=q(i,e.conv_5,[2,2]),m=q(c,e.conv_6,[1,1]),p=q(m,e.conv_7,[2,2]),d=Vt(t,e.box_predictor_0),u=Vt(o,e.box_predictor_1),l=Vt(n,e.box_predictor_2),v=Vt(s,e.box_predictor_3),_=Vt(c,e.box_predictor_4),h=Vt(p,e.box_predictor_5),y=$e.concat([d.boxPredictionEncoding,u.boxPredictionEncoding,l.boxPredictionEncoding,v.boxPredictionEncoding,_.boxPredictionEncoding,h.boxPredictionEncoding],1),T=$e.concat([d.classPrediction,u.classPrediction,l.classPrediction,v.classPrediction,_.classPrediction,h.classPrediction],1);return{boxPredictions:y,classPredictions:T}})}var Z=class{constructor({minConfidence:t,maxResults:e}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=e||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Ut=class extends S{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("SsdMobilenetv1 - load model before inference");return st.tidy(()=>{let r=st.cast(t.toBatchTensor(512,!1),"float32"),n=st.sub(st.mul(r,st.scalar(.007843137718737125)),st.scalar(1)),a=Go(n,e.mobilenetv1),{boxPredictions:s,classPredictions:i}=Uo(a.out,a.conv11,e.prediction_layer);return Vo(s,i,e.output_layer)})}async forward(t){return this.forwardInput(await E(t))}async locateFaces(t,e={}){let{maxResults:r,minConfidence:n}=new Z(e),a=await E(t),{boxes:s,scores:i}=this.forwardInput(a),c=s[0],m=i[0];for(let F=1;F{let[L,G]=[Math.max(0,y[F][0]),Math.min(1,y[F][2])].map(X=>X*h),[et,it]=[Math.max(0,y[F][1]),Math.min(1,y[F][3])].map(X=>X*_);return new M(p[F],new re(et,L,it-et,G-L),{height:a.getInputHeight(0),width:a.getInputWidth(0)})});return c.dispose(),m.dispose(),T}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return Yo(t)}extractParams(t){return Ho(t)}};function Xo(o){let t=new Ut;return t.extractWeights(o),t}function na(o){return Xo(o)}var Jo=class extends Ut{};var qo=.4,Zo=[new x(.738768,.874946),new x(2.42204,2.65704),new x(4.30971,7.04493),new x(10.246,4.59428),new x(12.6868,11.8741)],Ko=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],Qo=[117.001,114.697,97.404],tn="tiny_yolov2_model",en="tiny_yolov2_separable_conv_model";var N=b(g());var br=o=>typeof o=="number";function ao(o){if(!o)throw new Error(`invalid config: ${o}`);if(typeof o.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${o.withSeparableConvs}`);if(!br(o.iouThreshold)||o.iouThreshold<0||o.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${o.iouThreshold}`);if(!Array.isArray(o.classes)||!o.classes.length||!o.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(o.classes)}`);if(!Array.isArray(o.anchors)||!o.anchors.length||!o.anchors.map(t=>t||{}).every(t=>br(t.x)&&br(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(o.anchors)}`);if(o.meanRgb&&(!Array.isArray(o.meanRgb)||o.meanRgb.length!==3||!o.meanRgb.every(br)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(o.meanRgb)}`)}var Q=b(g());var K=b(g());function be(o){return K.tidy(()=>{let t=K.mul(o,K.scalar(.10000000149011612));return K.add(K.relu(K.sub(o,t)),t)})}function Ft(o,t){return Q.tidy(()=>{let e=Q.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=Q.conv2d(e,t.conv.filters,[1,1],"valid"),e=Q.sub(e,t.bn.sub),e=Q.mul(e,t.bn.truediv),e=Q.add(e,t.conv.bias),be(e)})}var St=b(g());function Tt(o,t){return St.tidy(()=>{let e=St.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=St.separableConv2d(e,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),e=St.add(e,t.bias),be(e)})}var so=b(g());function aa(o,t){let e=ce(o,t);function r(s,i){let c=so.tensor1d(o(s)),m=so.tensor1d(o(s));return t.push({paramPath:`${i}/sub`},{paramPath:`${i}/truediv`}),{sub:c,truediv:m}}function n(s,i,c){let m=e(s,i,3,`${c}/conv`),p=r(i,`${c}/bn`);return{conv:m,bn:p}}let a=me(o,t);return{extractConvParams:e,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}}function rn(o,t,e,r){let{extractWeights:n,getRemainingWeights:a}=B(o),s=[],{extractConvParams:i,extractConvWithBatchNormParams:c,extractSeparableConvParams:m}=aa(n,s),p;if(t.withSeparableConvs){let[d,u,l,v,_,h,y,T,F]=r,L=t.isFirstLayerConv2d?i(d,u,3,"conv0"):m(d,u,"conv0"),G=m(u,l,"conv1"),et=m(l,v,"conv2"),it=m(v,_,"conv3"),X=m(_,h,"conv4"),Pt=m(h,y,"conv5"),_t=T?m(y,T,"conv6"):void 0,wt=F?m(T,F,"conv7"):void 0,Qt=i(F||T||y,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}else{let[d,u,l,v,_,h,y,T,F]=r,L=c(d,u,"conv0"),G=c(u,l,"conv1"),et=c(l,v,"conv2"),it=c(v,_,"conv3"),X=c(_,h,"conv4"),Pt=c(h,y,"conv5"),_t=c(y,T,"conv6"),wt=c(T,F,"conv7"),Qt=i(F,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:p,paramMappings:s}}function sa(o,t){let e=j(o,t);function r(i){let c=e(`${i}/sub`,1),m=e(`${i}/truediv`,1);return{sub:c,truediv:m}}function n(i){let c=e(`${i}/filters`,4),m=e(`${i}/bias`,1);return{filters:c,bias:m}}function a(i){let c=n(`${i}/conv`),m=r(`${i}/bn`);return{conv:c,bn:m}}let s=pe(e);return{extractConvParams:n,extractConvWithBatchNormParams:a,extractSeparableConvParams:s}}function on(o,t){let e=[],{extractConvParams:r,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}=sa(o,e),s;if(t.withSeparableConvs){let i=t.filterSizes&&t.filterSizes.length||9;s={conv0:t.isFirstLayerConv2d?r("conv0"):a("conv0"),conv1:a("conv1"),conv2:a("conv2"),conv3:a("conv3"),conv4:a("conv4"),conv5:a("conv5"),conv6:i>7?a("conv6"):void 0,conv7:i>8?a("conv7"):void 0,conv8:r("conv8")}}else s={conv0:n("conv0"),conv1:n("conv1"),conv2:n("conv2"),conv3:n("conv3"),conv4:n("conv4"),conv5:n("conv5"),conv6:n("conv6"),conv7:n("conv7"),conv8:r("conv8")};return W(o,e),{params:s,paramMappings:e}}var lt=class{constructor({inputSize:t,scoreThreshold:e}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=e||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var io=class extends S{constructor(t){super("TinyYolov2");ao(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,e){let r=Ft(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=Ft(r,e.conv6),r=Ft(r,e.conv7),Gt(r,e.conv8,"valid",!1)}runMobilenet(t,e){let r=this.config.isFirstLayerConv2d?be(Gt(t,e.conv0,"valid",!1)):Tt(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=e.conv6?Tt(r,e.conv6):r,r=e.conv7?Tt(r,e.conv7):r,Gt(r,e.conv8,"valid",!1)}forwardInput(t,e){let{params:r}=this;if(!r)throw new Error("TinyYolov2 - load model before inference");return N.tidy(()=>{let n=N.cast(t.toBatchTensor(e,!1),"float32");return n=this.config.meanRgb?ot(n,this.config.meanRgb):n,n=n.div(N.scalar(256)),this.config.withSeparableConvs?this.runMobilenet(n,r):this.runTinyYolov2(n,r)})}async forward(t,e){return this.forwardInput(await E(t),e)}async detect(t,e={}){let{inputSize:r,scoreThreshold:n}=new lt(e),a=await E(t),s=await this.forwardInput(a,r),i=N.tidy(()=>N.unstack(s)[0].expandDims()),c={width:a.getInputWidth(0),height:a.getInputHeight(0)},m=await this.extractBoxes(i,a.getReshapedInputDimensions(0),n);s.dispose(),i.dispose();let p=m.map(h=>h.box),d=m.map(h=>h.score),u=m.map(h=>h.classScore),l=m.map(h=>this.config.classes[h.label]);return Sr(p.map(h=>h.rescale(r)),d,this.config.iouThreshold,!0).map(h=>new Dt(d[h],u[h],l[h],p[h],c))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return on(t,this.config)}extractParams(t){let e=this.config.filterSizes||io.DEFAULT_FILTER_SIZES,r=e?e.length:void 0;if(r!==7&&r!==8&&r!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${r} filterSizes in config`);return rn(t,this.config,this.boxEncodingSize,e)}async extractBoxes(t,e,r){let{width:n,height:a}=e,s=Math.max(n,a),i=s/n,c=s/a,m=t.shape[1],p=this.config.anchors.length,[d,u,l]=N.tidy(()=>{let y=t.reshape([m,m,p,this.boxEncodingSize]),T=y.slice([0,0,0,0],[m,m,p,4]),F=y.slice([0,0,0,4],[m,m,p,1]),L=this.withClassScores?N.softmax(y.slice([0,0,0,5],[m,m,p,this.config.classes.length]),3):N.scalar(0);return[T,F,L]}),v=[],_=await u.array(),h=await d.array();for(let y=0;yr){let G=(T+De(h[y][T][F][0]))/m*i,et=(y+De(h[y][T][F][1]))/m*c,it=Math.exp(h[y][T][F][2])*this.config.anchors[F].x/m*i,X=Math.exp(h[y][T][F][3])*this.config.anchors[F].y/m*c,Pt=G-it/2,_t=et-X/2,wt={row:y,col:T,anchor:F},{classScore:Qt,label:lo}=this.withClassScores?await this.extractPredictedClass(l,wt):{classScore:1,label:0};v.push({box:new ee(Pt,_t,Pt+it,_t+X),score:L,classScore:L*Qt,label:lo,...wt})}}return d.dispose(),u.dispose(),l.dispose(),v}async extractPredictedClass(t,e){let{row:r,col:n,anchor:a}=e,s=await t.array();return Array(this.config.classes.length).fill(0).map((i,c)=>s[r][n][a][c]).map((i,c)=>({classScore:i,label:c})).reduce((i,c)=>i.classScore>c.classScore?i:c)}},ge=io;ge.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var ve=class extends ge{constructor(t=!0){let e={withSeparableConvs:t,iouThreshold:qo,classes:["face"],...t?{anchors:Ko,meanRgb:Qo}:{anchors:Zo,withClassScores:!0}};super(e)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?en:tn}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function ia(o,t=!0){let e=new ve(t);return e.extractWeights(o),e}var gr=class extends lt{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var tt=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};var je=b(g());var co=b(g());async function Xt(o,t,e,r,n=({alignedRect:a})=>a){let a=o.map(c=>zt(c)?n(c):c.detection),s=r||(t instanceof co.Tensor?await se(t,a):await ae(t,a)),i=await e(s);return s.forEach(c=>c instanceof co.Tensor&&c.dispose()),i}async function ye(o,t,e,r,n){return Xt([o],t,async a=>e(a[0]),r,n)}var nn=.4,an=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],sn=[117.001,114.697,97.404];var Fe=class extends ge{constructor(){let t={withSeparableConvs:!0,iouThreshold:nn,classes:["face"],anchors:an,meanRgb:sn,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var P={ssdMobilenetv1:new Ut,tinyFaceDetector:new Fe,tinyYolov2:new ve,faceLandmark68Net:new fe,faceLandmark68TinyNet:new dr,faceRecognitionNet:new xe,faceExpressionNet:new cr,ageGenderNet:new pr},cn=(o,t)=>P.ssdMobilenetv1.locateFaces(o,t),ca=(o,t)=>P.tinyFaceDetector.locateFaces(o,t),ma=(o,t)=>P.tinyYolov2.locateFaces(o,t),mn=o=>P.faceLandmark68Net.detectLandmarks(o),pa=o=>P.faceLandmark68TinyNet.detectLandmarks(o),da=o=>P.faceRecognitionNet.computeFaceDescriptor(o),ua=o=>P.faceExpressionNet.predictExpressions(o),la=o=>P.ageGenderNet.predictAgeAndGender(o),pn=o=>P.ssdMobilenetv1.load(o),fa=o=>P.tinyFaceDetector.load(o),ha=o=>P.tinyYolov2.load(o),xa=o=>P.faceLandmark68Net.load(o),ba=o=>P.faceLandmark68TinyNet.load(o),ga=o=>P.faceRecognitionNet.load(o),va=o=>P.faceExpressionNet.load(o),ya=o=>P.ageGenderNet.load(o),Fa=pn,Ta=cn,Pa=mn;var mo=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},_e=class extends mo{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.faceExpressionNet.predictExpressions(n))),this.extractedFaces);return t.map((r,n)=>mr(r,e[n]))}withAgeAndGender(){return new Te(this,this.input)}},we=class extends mo{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceExpressionNet.predictExpressions(r),this.extractedFaces);return mr(t,e)}withAgeAndGender(){return new Pe(this,this.input)}},Zt=class extends _e{withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Kt=class extends we{withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var po=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},Te=class extends po{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.ageGenderNet.predictAgeAndGender(n))),this.extractedFaces);return t.map((r,n)=>{let{age:a,gender:s,genderProbability:i}=e[n];return hr(xr(r,s,i),a)})}withFaceExpressions(){return new _e(this,this.input)}},Pe=class extends po{async run(){let t=await this.parentTask;if(!t)return;let{age:e,gender:r,genderProbability:n}=await ye(t,this.input,a=>P.ageGenderNet.predictAgeAndGender(a),this.extractedFaces);return hr(xr(t,r,n),e)}withFaceExpressions(){return new we(this,this.input)}},Jt=class extends Te{withFaceExpressions(){return new Zt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},qt=class extends Pe{withFaceExpressions(){return new Kt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var vr=class extends tt{constructor(t,e){super();this.parentTask=t;this.input=e}},At=class extends vr{async run(){let t=await this.parentTask;return(await Xt(t,this.input,r=>Promise.all(r.map(n=>P.faceRecognitionNet.computeFaceDescriptor(n))),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}))).map((r,n)=>fr(t[n],r))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}},Wt=class extends vr{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceRecognitionNet.computeFaceDescriptor(r),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}));return fr(t,e)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}};var yr=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.useTinyLandmarkNet=r}get landmarkNet(){return this.useTinyLandmarkNet?P.faceLandmark68TinyNet:P.faceLandmark68Net}},Fr=class extends yr{async run(){let t=await this.parentTask,e=t.map(a=>a.detection),r=this.input instanceof je.Tensor?await se(this.input,e):await ae(this.input,e),n=await Promise.all(r.map(a=>this.landmarkNet.detectLandmarks(a)));return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),t.map((a,s)=>le(a,n[s]))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Tr=class extends yr{async run(){let t=await this.parentTask;if(!t)return;let{detection:e}=t,r=this.input instanceof je.Tensor?await se(this.input,[e]):await ae(this.input,[e]),n=await this.landmarkNet.detectLandmarks(r[0]);return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),le(t,n)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var Pr=class extends tt{constructor(t,e=new Z){super();this.input=t;this.options=e}},He=class extends Pr{async run(){let{input:t,options:e}=this,r=e instanceof gr?n=>P.tinyFaceDetector.locateFaces(n,e):e instanceof Z?n=>P.ssdMobilenetv1.locateFaces(n,e):e instanceof lt?n=>P.tinyYolov2.locateFaces(n,e):null;if(!r)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return r(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let e=await this.run();t(e.map(r=>$t({},r)))})}withFaceLandmarks(t=!1){return new Fr(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new _e(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Te(this.runAndExtendWithFaceDetections(),this.input)}},_r=class extends Pr{async run(){let t=await new He(this.input,this.options),e=t[0];return t.forEach(r=>{r.score>e.score&&(e=r)}),e}runAndExtendWithFaceDetection(){return new Promise(async t=>{let e=await this.run();t(e?$t({},e):void 0)})}withFaceLandmarks(t=!1){return new Tr(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new we(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Pe(this.runAndExtendWithFaceDetection(),this.input)}};function _a(o,t=new Z){return new _r(o,t)}function wr(o,t=new Z){return new He(o,t)}async function dn(o,t){return wr(o,new Z(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function wa(o,t={}){return wr(o,new lt(t)).withFaceLandmarks().withFaceDescriptors()}var Da=dn;function uo(o,t){if(o.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let e=Array.from(o),r=Array.from(t);return Math.sqrt(e.map((n,a)=>n-r[a]).reduce((n,a)=>n+a**2,0))}var Dr=class{constructor(t,e=.6){this._distanceThreshold=e;let r=Array.isArray(t)?t:[t];if(!r.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let n=1,a=()=>`person ${n++}`;this._labeledDescriptors=r.map(s=>{if(s instanceof xt)return s;if(s instanceof Float32Array)return new xt(a(),[s]);if(s.descriptor&&s.descriptor instanceof Float32Array)return new xt(a(),[s.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,e){return e.map(r=>uo(r,t)).reduce((r,n)=>r+n,0)/(e.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:e,label:r})=>new Ee(r,this.computeMeanDistance(t,e))).reduce((e,r)=>e.distancet.toJSON())}}static fromJSON(t){let e=t.labeledDescriptors.map(r=>xt.fromJSON(r));return new Dr(e,t.distanceThreshold)}};function Ea(o){let t=new Fe;return t.extractWeights(o),t}function un(o,t){let{width:e,height:r}=new A(t.width,t.height);if(e<=0||r<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:e,height:r})}`);if(Array.isArray(o))return o.map(n=>un(n,{width:e,height:r}));if(zt(o)){let n=o.detection.forSize(e,r),a=o.unshiftedLandmarks.forSize(n.box.width,n.box.height);return le($t(o,n),a)}return pt(o)?$t(o,o.detection.forSize(e,r)):o instanceof V||o instanceof M?o.forSize(e,r):o}var Ca=typeof process!="undefined",Na=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Ia={faceapi:Co,node:Ca,browser:Na}; +var ln=Object.create,Ye=Object.defineProperty,fn=Object.getPrototypeOf,hn=Object.prototype.hasOwnProperty,xn=Object.getOwnPropertyNames,bn=Object.getOwnPropertyDescriptor;var fo=o=>Ye(o,"__esModule",{value:!0});var ho=(o,t)=>()=>(t||(t={exports:{}},o(t.exports,t)),t.exports),Ge=(o,t)=>{fo(o);for(var e in t)Ye(o,e,{get:t[e],enumerable:!0})},gn=(o,t,e)=>{if(fo(o),t&&typeof t=="object"||typeof t=="function")for(let r of xn(t))!hn.call(o,r)&&r!=="default"&&Ye(o,r,{get:()=>t[r],enumerable:!(e=bn(t,r))||e.enumerable});return o},b=o=>o&&o.__esModule?o:gn(Ye(o!=null?ln(fn(o)):{},"default",{value:o,enumerable:!0}),o);var g=ho(xo=>{var vn=Object.create,Er=Object.defineProperty,yn=Object.getPrototypeOf,Fn=Object.prototype.hasOwnProperty,Tn=Object.getOwnPropertyNames,Pn=Object.getOwnPropertyDescriptor,_n=o=>Er(o,"__esModule",{value:!0}),bo=(o,t,e)=>{if(_n(o),t&&typeof t=="object"||typeof t=="function")for(let r of Tn(t))!Fn.call(o,r)&&r!=="default"&&Er(o,r,{get:()=>t[r],enumerable:!(e=Pn(t,r))||e.enumerable});return o},wn=o=>o&&o.__esModule?o:bo(Er(o!=null?vn(yn(o)):{},"default",{value:o,enumerable:!0}),o);bo(xo,wn(require("@tensorflow/tfjs-node-gpu")))});var To=ho((Ln,Fo)=>{Ge(Ln,{isNodejs:()=>kn});function kn(){return typeof global=="object"&&!0&&typeof Fo!="undefined"&&typeof process!="undefined"&&!!process.version}});Ge(exports,{AgeGenderNet:()=>pr,BoundingBox:()=>ee,Box:()=>D,ComposableTask:()=>tt,ComputeAllFaceDescriptorsTask:()=>At,ComputeFaceDescriptorsTaskBase:()=>vr,ComputeSingleFaceDescriptorTask:()=>Wt,DetectAllFaceLandmarksTask:()=>Fr,DetectAllFacesTask:()=>He,DetectFaceLandmarksTaskBase:()=>yr,DetectFacesTaskBase:()=>Pr,DetectSingleFaceLandmarksTask:()=>Tr,DetectSingleFaceTask:()=>_r,Dimensions:()=>A,FACE_EXPRESSION_LABELS:()=>Jr,FaceDetection:()=>M,FaceDetectionNet:()=>Jo,FaceExpressionNet:()=>cr,FaceExpressions:()=>It,FaceLandmark68Net:()=>fe,FaceLandmark68TinyNet:()=>dr,FaceLandmarkNet:()=>Bo,FaceLandmarks:()=>V,FaceLandmarks5:()=>vo,FaceLandmarks68:()=>oe,FaceMatch:()=>Ee,FaceMatcher:()=>Dr,FaceRecognitionNet:()=>xe,Gender:()=>vt,LabeledBox:()=>Me,LabeledFaceDescriptors:()=>xt,NetInput:()=>bt,NeuralNetwork:()=>S,ObjectDetection:()=>Dt,Point:()=>x,PredictedBox:()=>yo,Rect:()=>re,SsdMobilenetv1:()=>Ut,SsdMobilenetv1Options:()=>Z,TinyFaceDetector:()=>Fe,TinyFaceDetectorOptions:()=>gr,TinyYolov2:()=>ve,TinyYolov2Options:()=>lt,allFaces:()=>Da,allFacesSsdMobilenetv1:()=>dn,allFacesTinyYolov2:()=>wa,awaitMediaLoaded:()=>Yr,bufferToImage:()=>Gr,computeFaceDescriptor:()=>da,createCanvas:()=>ne,createCanvasFromMedia:()=>Ie,createFaceDetectionNet:()=>na,createFaceRecognitionNet:()=>Un,createSsdMobilenetv1:()=>Xo,createTinyFaceDetector:()=>Ea,createTinyYolov2:()=>ia,detectAllFaces:()=>wr,detectFaceLandmarks:()=>mn,detectFaceLandmarksTiny:()=>pa,detectLandmarks:()=>Pa,detectSingleFace:()=>_a,draw:()=>Qr,env:()=>w,euclideanDistance:()=>uo,extendWithAge:()=>hr,extendWithFaceDescriptor:()=>fr,extendWithFaceDetection:()=>$t,extendWithFaceExpressions:()=>mr,extendWithFaceLandmarks:()=>le,extendWithGender:()=>xr,extractFaceTensors:()=>se,extractFaces:()=>ae,fetchImage:()=>Bn,fetchJson:()=>Ur,fetchNetWeights:()=>Rn,fetchOrThrow:()=>Yt,getContext2dOrThrow:()=>O,getMediaDimensions:()=>Ht,imageTensorToCanvas:()=>zr,imageToSquare:()=>Vr,inverseSigmoid:()=>Mn,iou:()=>Lr,isMediaElement:()=>qe,isMediaLoaded:()=>Ne,isWithAge:()=>Xn,isWithFaceDetection:()=>pt,isWithFaceExpressions:()=>qr,isWithFaceLandmarks:()=>zt,isWithGender:()=>Jn,loadAgeGenderModel:()=>ya,loadFaceDetectionModel:()=>Fa,loadFaceExpressionModel:()=>va,loadFaceLandmarkModel:()=>xa,loadFaceLandmarkTinyModel:()=>ba,loadFaceRecognitionModel:()=>ga,loadSsdMobilenetv1Model:()=>pn,loadTinyFaceDetectorModel:()=>fa,loadTinyYolov2Model:()=>ha,loadWeightMap:()=>Xr,locateFaces:()=>Ta,matchDimensions:()=>On,minBbox:()=>kr,nets:()=>P,nonMaxSuppression:()=>Sr,normalize:()=>ot,padToSquare:()=>Ar,predictAgeAndGender:()=>la,recognizeFaceExpressions:()=>ua,resizeResults:()=>un,resolveInput:()=>jt,shuffleArray:()=>En,sigmoid:()=>De,ssdMobilenetv1:()=>cn,tf:()=>Ma,tinyFaceDetector:()=>ca,tinyYolov2:()=>ma,toNetInput:()=>E,utils:()=>Mr,validateConfig:()=>ao,version:()=>Ia});var Ma=b(g());var Qr={};Ge(Qr,{AnchorPosition:()=>dt,DrawBox:()=>Xe,DrawBoxOptions:()=>Hr,DrawFaceLandmarks:()=>Kr,DrawFaceLandmarksOptions:()=>Zr,DrawTextField:()=>Mt,DrawTextFieldOptions:()=>Ce,drawContour:()=>ft,drawDetections:()=>Wn,drawFaceExpressions:()=>$n,drawFaceLandmarks:()=>jn});function ft(o,t,e=!1){if(o.beginPath(),t.slice(1).forEach(({x:r,y:n},a)=>{let s=t[a];o.moveTo(s.x,s.y),o.lineTo(r,n)}),e){let r=t[t.length-1],n=t[0];if(!r||!n)return;o.moveTo(r.x,r.y),o.lineTo(n.x,n.y)}o.stroke()}var Mr={};Ge(Mr,{computeReshapedDimensions:()=>Ir,getCenterPoint:()=>Ot,isDimensions:()=>Ve,isEven:()=>ze,isFloat:()=>Nr,isTensor:()=>Bt,isTensor1D:()=>Dn,isTensor2D:()=>Cr,isTensor3D:()=>ht,isTensor4D:()=>z,isValidNumber:()=>rt,isValidProbablitiy:()=>te,range:()=>ct,round:()=>Rt});var go=b(g());var A=class{constructor(t,e){if(!rt(t)||!rt(e))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:e})}`);this._width=t,this._height=e}get width(){return this._width}get height(){return this._height}reverse(){return new A(1/this.width,1/this.height)}};function Bt(o,t){return o instanceof go.Tensor&&o.shape.length===t}function Dn(o){return Bt(o,1)}function Cr(o){return Bt(o,2)}function ht(o){return Bt(o,3)}function z(o){return Bt(o,4)}function Nr(o){return o%1!=0}function ze(o){return o%2==0}function Rt(o,t=2){let e=10**t;return Math.floor(o*e)/e}function Ve(o){return o&&o.width&&o.height}function Ir({width:o,height:t},e){let r=e/Math.max(t,o);return new A(Math.round(o*r),Math.round(t*r))}function Ot(o){return o.reduce((t,e)=>t.add(e),new x(0,0)).div(new x(o.length,o.length))}function ct(o,t,e){return Array(o).fill(0).map((r,n)=>t+n*e)}function rt(o){return!!o&&o!==Infinity&&o!==-Infinity&&!Number.isNaN(o)||o===0}function te(o){return rt(o)&&o>=0&&o<=1}var x=class{constructor(t,e){this._x=t,this._y=e}get x(){return this._x}get y(){return this._y}add(t){return new x(this.x+t.x,this.y+t.y)}sub(t){return new x(this.x-t.x,this.y-t.y)}mul(t){return new x(this.x*t.x,this.y*t.y)}div(t){return new x(this.x/t.x,this.y/t.y)}abs(){return new x(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new x(Math.floor(this.x),Math.floor(this.y))}};var D=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(rt)}static assertIsValidBox(t,e,r=!1){if(!D.isRect(t))throw new Error(`${e} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!r&&(t.width<0||t.height<0))throw new Error(`${e} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,e=!0){let r=t||{},n=[r.left,r.top,r.right,r.bottom].every(rt),a=[r.x,r.y,r.width,r.height].every(rt);if(!a&&!n)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(r)}`);let[s,i,c,m]=a?[r.x,r.y,r.width,r.height]:[r.left,r.top,r.right-r.left,r.bottom-r.top];D.assertIsValidBox({x:s,y:i,width:c,height:m},"Box.constructor",e),this._x=s,this._y=i,this._width=c,this._height=m}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new x(this.left,this.top)}get topRight(){return new x(this.right,this.top)}get bottomLeft(){return new x(this.left,this.bottom)}get bottomRight(){return new x(this.right,this.bottom)}round(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.round(a));return new D({x:t,y:e,width:r,height:n})}floor(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.floor(a));return new D({x:t,y:e,width:r,height:n})}toSquare(){let{x:t,y:e,width:r,height:n}=this,a=Math.abs(r-n);return re&&(i=-d+e+r,d=e),u>t&&(c=-u+t+n,u=t),m<1&&(c=2-m,m=1),p<1&&(c=2-p,p=1),{dy:s,edy:c,dx:a,edx:i,y:p,ey:u,x:m,ex:d,w:r,h:n}}calibrate(t){return new D({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var ee=class extends D{constructor(t,e,r,n,a=!1){super({left:t,top:e,right:r,bottom:n},a)}};var Dt=class{constructor(t,e,r,n,a){this._imageDims=new A(a.width,a.height),this._score=t,this._classScore=e,this._className=r,this._box=new D(n).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new D(this._box).rescale(this.imageDims.reverse())}forSize(t,e){return new Dt(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:e})}};var M=class extends Dt{constructor(t,e,r){super(t,t,"",e,r)}forSize(t,e){let{score:r,relativeBox:n,imageDims:a}=super.forSize(t,e);return new M(r,n,a)}};function Lr(o,t,e=!0){let r=Math.max(0,Math.min(o.right,t.right)-Math.max(o.left,t.left)),n=Math.max(0,Math.min(o.bottom,t.bottom)-Math.max(o.top,t.top)),a=r*n;return e?a/(o.area+t.area-a):a/Math.min(o.area,t.area)}function kr(o){let t=o.map(i=>i.x),e=o.map(i=>i.y),r=t.reduce((i,c)=>ccii({score:s,boxIndex:i})).sort((s,i)=>s.score-i.score).map(s=>s.boxIndex),a=[];for(;n.length>0;){let s=n.pop();a.push(s);let i=n,c=[];for(let m=0;mc[p]<=e)}return a}var mt=b(g());function ot(o,t){return mt.tidy(()=>{let[e,r,n]=t,a=mt.fill([...o.shape.slice(0,3),1],e,"float32"),s=mt.fill([...o.shape.slice(0,3),1],r,"float32"),i=mt.fill([...o.shape.slice(0,3),1],n,"float32"),c=mt.concat([a,s,i],3);return mt.sub(o,c)})}var Et=b(g());function Ar(o,t=!1){return Et.tidy(()=>{let[e,r]=o.shape.slice(1);if(e===r)return o;let n=Math.abs(e-r),a=Math.round(n*(t?.5:1)),s=e>r?2:1,i=u=>{let l=o.shape.slice();return l[s]=u,Et.fill(l,0,"float32")},c=i(a),m=n-c.shape[s],d=[t&&m?i(m):null,o,c].filter(u=>!!u).map(u=>Et.cast(u,"float32"));return Et.concat(d,s)})}function En(o){let t=o.slice();for(let e=t.length-1;e>0;e--){let r=Math.floor(Math.random()*(e+1)),n=t[e];t[e]=t[r],t[r]=n}return t}function De(o){return 1/(1+Math.exp(-o))}function Mn(o){return Math.log(o/(1-o))}var re=class extends D{constructor(t,e,r,n,a=!1){super({x:t,y:e,width:r,height:n},a)}};var Cn=.5,Nn=.43,In=.45,V=class{constructor(t,e,r=new x(0,0)){let{width:n,height:a}=e;this._imgDims=new A(n,a),this._shift=r,this._positions=t.map(s=>s.mul(new x(n,a)).add(r))}get shift(){return new x(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new x(this.imageWidth,this.imageHeight)))}forSize(t,e){return new this.constructor(this.relativePositions,{width:t,height:e})}shiftBy(t,e){return new this.constructor(this.relativePositions,this._imgDims,new x(t,e))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,e={}){if(t){let a=t instanceof M?t.box.floor():new D(t);return this.shiftBy(a.x,a.y).align(null,e)}let{useDlibAlignment:r,minBoxPadding:n}={useDlibAlignment:!1,minBoxPadding:.2,...e};return r?this.alignDlib():this.alignMinBbox(n)}alignDlib(){let t=this.getRefPointsForAlignment(),[e,r,n]=t,a=d=>n.sub(d).magnitude(),s=(a(e)+a(r))/2,i=Math.floor(s/In),c=Ot(t),m=Math.floor(Math.max(0,c.x-Cn*i)),p=Math.floor(Math.max(0,c.y-Nn*i));return new re(m,p,Math.min(i,this.imageWidth+m),Math.min(i,this.imageHeight+p))}alignMinBbox(t){let e=kr(this.positions);return e.pad(e.width*t,e.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var vo=class extends V{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Ot([t[3],t[4]])]}};var oe=class extends V{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Ot)}};var Ee=class{constructor(t,e){this._label=t,this._distance=e}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${Rt(this.distance)})`:""}`}};var Me=class extends D{static assertIsValidLabeledBox(t,e){if(D.assertIsValidBox(t,e),!rt(t.label))throw new Error(`${e} - expected property label (${t.label}) to be a number`)}constructor(t,e){super(t);this._label=e}get label(){return this._label}};var xt=class{constructor(t,e){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(e)||e.some(r=>!(r instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=e}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let e=t.descriptors.map(r=>new Float32Array(r));return new xt(t.label,e)}};var yo=class extends Me{static assertIsValidPredictedBox(t,e){if(Me.assertIsValidLabeledBox(t,e),!te(t.score)||!te(t.classScore))throw new Error(`${e} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,e,r,n){super(t,e);this._score=r,this._classScore=n}get score(){return this._score}get classScore(){return this._classScore}};function pt(o){return o.detection instanceof M}function $t(o,t){return{...o,...{detection:t}}}function Wr(){let o=window.fetch;if(!o)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:o,readFile:t}}function Ue(o){let t="";if(!o)try{o=require("fs")}catch(r){t=r.toString()}return{readFile:o?r=>new Promise((n,a)=>{o.readFile(r,(s,i)=>s?a(s):n(i))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function Br(){let o=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,e=()=>{if(o)return new o;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},r=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},n=global.fetch,a=Ue();return{Canvas:o||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:e,createImageElement:r,fetch:n,...a}}function Rr(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var Or=b(To()),k;function Sn(){if(!k)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return k}function $r(o){k=o}function jr(){return Rr()?$r(Wr()):Or.isNodejs()?$r(Br()):null}function An(o){if(k||jr(),!k)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=k.Canvas,Image:e=k.Image}=o;k.Canvas=t,k.Image=e,k.createCanvasElement=o.createCanvasElement||(()=>new t),k.createImageElement=o.createImageElement||(()=>new e),k.ImageData=o.ImageData||k.ImageData,k.Video=o.Video||k.Video,k.fetch=o.fetch||k.fetch,k.readFile=o.readFile||k.readFile}var w={getEnv:Sn,setEnv:$r,initialize:jr,createBrowserEnv:Wr,createFileSystem:Ue,createNodejsEnv:Br,monkeyPatch:An,isBrowser:Rr,isNodejs:Or.isNodejs};jr();function jt(o){return!w.isNodejs()&&typeof o=="string"?document.getElementById(o):o}function O(o){let{Canvas:t,CanvasRenderingContext2D:e}=w.getEnv();if(o instanceof e)return o;let r=jt(o);if(!(r instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let n=r.getContext("2d");if(!n)throw new Error("resolveContext2d - canvas 2d context is null");return n}var dt;(function(o){o.TOP_LEFT="TOP_LEFT",o.TOP_RIGHT="TOP_RIGHT",o.BOTTOM_LEFT="BOTTOM_LEFT",o.BOTTOM_RIGHT="BOTTOM_RIGHT"})(dt||(dt={}));var Ce=class{constructor(t={}){let{anchorPosition:e,backgroundColor:r,fontColor:n,fontSize:a,fontStyle:s,padding:i}=t;this.anchorPosition=e||dt.TOP_LEFT,this.backgroundColor=r||"rgba(0, 0, 0, 0.5)",this.fontColor=n||"rgba(255, 255, 255, 1)",this.fontSize=a||14,this.fontStyle=s||"Georgia",this.padding=i||4}},Mt=class{constructor(t,e,r={}){this.text=typeof t=="string"?[t]:t instanceof Mt?t.text:t,this.anchor=e,this.options=new Ce(r)}measureWidth(t){let{padding:e}=this.options;return this.text.map(r=>t.measureText(r).width).reduce((r,n)=>r{let v=c+d.x,_=c+d.y+(l+1)*s;r.fillText(u,v,_)})}};var Hr=class{constructor(t={}){let{boxColor:e,lineWidth:r,label:n,drawLabelOptions:a}=t;this.boxColor=e||"rgba(0, 0, 255, 1)",this.lineWidth=r||2,this.label=n;let s={anchorPosition:dt.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Ce({...s,...a})}},Xe=class{constructor(t,e={}){this.box=new D(t),this.options=new Hr(e)}draw(t){let e=O(t),{boxColor:r,lineWidth:n}=this.options,{x:a,y:s,width:i,height:c}=this.box;e.strokeStyle=r,e.lineWidth=n,e.strokeRect(a,s,i,c);let{label:m}=this.options;m&&new Mt([m],{x:a-n/2,y:s},this.options.drawLabelOptions).draw(t)}};function Wn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof M?r.score:pt(r)?r.detection.score:void 0,a=r instanceof M?r.box:pt(r)?r.detection.box:new D(r),s=n?`${Rt(n)}`:void 0;new Xe(a,{label:s}).draw(o)})}var ue=b(g());function Ne(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t&&o.complete||o instanceof e&&o.readyState>=3}function Yr(o){return new Promise((t,e)=>{if(o instanceof w.getEnv().Canvas||Ne(o))return t(null);function r(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),e(a))}function n(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),t(a))}o.addEventListener("load",n),o.addEventListener("error",r)})}function Gr(o){return new Promise((t,e)=>{o instanceof Blob||e(new Error("bufferToImage - expected buf to be of type: Blob"));let r=new FileReader;r.onload=()=>{typeof r.result!="string"&&e(new Error("bufferToImage - expected reader.result to be a string, in onload"));let n=w.getEnv().createImageElement();n.onload=()=>t(n),n.onerror=e,n.src=r.result},r.onerror=e,r.readAsDataURL(o)})}function Ht(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t?new A(o.naturalWidth,o.naturalHeight):o instanceof e?new A(o.videoWidth,o.videoHeight):new A(o.width,o.height)}function ne({width:o,height:t}){let{createCanvasElement:e}=w.getEnv(),r=e();return r.width=o,r.height=t,r}function Ie(o,t){let{ImageData:e}=w.getEnv();if(!(o instanceof e)&&!Ne(o))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:r,height:n}=t||Ht(o),a=ne({width:r,height:n});return o instanceof e?O(a).putImageData(o,0,0):O(a).drawImage(o,0,0,r,n),a}var Je=b(g());async function zr(o,t){let e=t||w.getEnv().createCanvasElement(),[r,n,a]=o.shape.slice(z(o)?1:0),s=Je.tidy(()=>o.as3D(r,n,a).toInt());return await Je.browser.toPixels(s,e),s.dispose(),e}function qe(o){let{Image:t,Canvas:e,Video:r}=w.getEnv();return o instanceof t||o instanceof e||o instanceof r}var J=b(g());function Vr(o,t,e=!1){let{Image:r,Canvas:n}=w.getEnv();if(!(o instanceof r||o instanceof n))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let a=Ht(o),s=t/Math.max(a.height,a.width),i=s*a.width,c=s*a.height,m=ne({width:t,height:t}),p=o instanceof n?o:Ie(o),d=Math.abs(i-c)/2,u=e&&i{if(ht(r)){this._imageTensors[n]=r,this._inputDimensions[n]=r.shape;return}if(z(r)){let s=r.shape[0];if(s!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${s} passed, but not supported in input array`);this._imageTensors[n]=r,this._inputDimensions[n]=r.shape.slice(1);return}let a=r instanceof w.getEnv().Canvas?r:Ie(r);this._canvases[n]=a,this._inputDimensions[n]=[a.height,a.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ct(this.batchSize,0,1).map((t,e)=>this.getReshapedInputDimensions(e))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let e=this.getInputWidth(t),r=this.getInputHeight(t);return Ir({width:e,height:r},this.inputSize)}toBatchTensor(t,e=!0){return this._inputSize=t,J.tidy(()=>{let r=ct(this.batchSize,0,1).map(a=>{let s=this.getInput(a);if(s instanceof J.Tensor){let i=z(s)?s:s.expandDims();return i=Ar(i,e),(i.shape[1]!==t||i.shape[2]!==t)&&(i=J.image.resizeBilinear(i,[t,t])),i.as3D(t,t,3)}if(s instanceof w.getEnv().Canvas)return J.browser.fromPixels(Vr(s,t,e));throw new Error(`toBatchTensor - at batchIdx ${a}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${s}`)});return J.stack(r.map(a=>J.cast(a,"float32"))).as4D(this.batchSize,t,t,3)})}};async function E(o){if(o instanceof bt)return o;let t=Array.isArray(o)?o:[o];if(!t.length)throw new Error("toNetInput - empty array passed as input");let e=n=>Array.isArray(o)?` at input index ${n}:`:"",r=t.map(jt);return r.forEach((n,a)=>{if(!qe(n)&&!ht(n)&&!z(n))throw typeof t[a]=="string"?new Error(`toNetInput -${e(a)} string passed, but could not resolve HTMLElement for element id ${t[a]}`):new Error(`toNetInput -${e(a)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(z(n)){let s=n.shape[0];if(s!==1)throw new Error(`toNetInput -${e(a)} tf.Tensor4D with batchSize ${s} passed, but not supported in input array`)}}),await Promise.all(r.map(n=>qe(n)&&Yr(n))),new bt(r,Array.isArray(o))}async function ae(o,t){let{Canvas:e}=w.getEnv(),r=o;if(!(o instanceof e)){let s=await E(o);if(s.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let i=s.getInput(0);r=i instanceof e?i:await zr(i)}let n=O(r);return t.map(s=>s instanceof M?s.forSize(r.width,r.height).box.floor():s).map(s=>s.clipAtImageBorders(r.width,r.height)).map(({x:s,y:i,width:c,height:m})=>{let p=ne({width:c,height:m});return O(p).putImageData(n.getImageData(s,i,c,m),0,0),p})}var Ze=b(g());async function se(o,t){if(!ht(o)&&!z(o))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(z(o)&&o.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return Ze.tidy(()=>{let[e,r,n]=o.shape.slice(z(o)?1:0);return t.map(i=>i instanceof M?i.forSize(r,e).box:i).map(i=>i.clipAtImageBorders(r,e)).map(({x:i,y:c,width:m,height:p})=>Ze.slice3d(o.as3D(e,r,n),[c,i,0],[p,m,n]))})}async function Yt(o,t){let{fetch:e}=w.getEnv(),r=await e(o,t);if(!(r.status<400))throw new Error(`failed to fetch: (${r.status}) ${r.statusText}, from url: ${r.url}`);return r}async function Bn(o){let t=await Yt(o),e=await t.blob();if(!e.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${e.type}, for url: ${t.url}`);return Gr(e)}async function Ur(o){return(await Yt(o)).json()}async function Rn(o){return new Float32Array(await(await Yt(o)).arrayBuffer())}var Po=b(g());function Ke(o,t){let e=`${t}-weights_manifest.json`;if(!o)return{modelBaseUri:"",manifestUri:e};if(o==="/")return{modelBaseUri:"/",manifestUri:`/${e}`};let r=o.startsWith("http://")?"http://":o.startsWith("https://")?"https://":"";o=o.replace(r,"");let n=o.split("/").filter(i=>i),a=o.endsWith(".json")?n[n.length-1]:e,s=r+(o.endsWith(".json")?n.slice(0,n.length-1):n).join("/");return s=o.startsWith("/")?`/${s}`:s,{modelBaseUri:s,manifestUri:s==="/"?`/${a}`:`${s}/${a}`}}async function Xr(o,t){let{manifestUri:e,modelBaseUri:r}=Ke(o,t),n=await Ur(e);return Po.io.loadWeights(n,r)}function On(o,t,e=!1){let{width:r,height:n}=e?Ht(t):t;return o.width=r,o.height=n,{width:r,height:n}}var Nt=b(g());var gt=b(g());var S=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:e,objProp:r}=this.traversePropertyPath(t);return e[r]}reassignParamFromPath(t,e){let{obj:r,objProp:n}=this.traversePropertyPath(t);r[n].dispose(),r[n]=e}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof gt.Variable)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof gt.Variable))}variable(){this.getFrozenParams().forEach(({path:t,tensor:e})=>{this.reassignParamFromPath(t,e.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:e})=>{let r=gt.tensor(e.dataSync());e.dispose(),this.reassignParamFromPath(t,r)})}dispose(t=!0){this.getParamList().forEach(e=>{if(t&&e.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${e.path}`);e.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,e)=>t.concat(e)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let e=await Xr(t,this.getDefaultModelName());this.loadFromWeightMap(e)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:e}=w.getEnv(),{manifestUri:r,modelBaseUri:n}=Ke(t,this.getDefaultModelName()),a=m=>Promise.all(m.map(p=>e(p).then(d=>d.buffer))),s=gt.io.weightsLoaderFactory(a),i=JSON.parse((await e(r)).toString()),c=await s(i,n);this.loadFromWeightMap(c)}loadFromWeightMap(t){let{paramMappings:e,params:r}=this.extractParamsFromWeightMap(t);this._paramMappings=e,this._params=r}extractWeights(t){let{paramMappings:e,params:r}=this.extractParams(t);this._paramMappings=e,this._params=r}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let e=t.split("/").reduce((a,s)=>{if(!a.nextObj.hasOwnProperty(s))throw new Error(`traversePropertyPath - object does not have property ${s}, for path ${t}`);return{obj:a.nextObj,objProp:s,nextObj:a.nextObj[s]}},{nextObj:this.params}),{obj:r,objProp:n}=e;if(!r||!n||!(r[n]instanceof gt.Tensor))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:r,objProp:n}}};var C=b(g());var ie=b(g());function $(o,t,e){return ie.tidy(()=>{let r=ie.separableConv2d(o,t.depthwise_filter,t.pointwise_filter,e,"same");return r=ie.add(r,t.bias),r})}function Qe(o,t,e=!1){return C.tidy(()=>{let r=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,[2,2],"same"),t.conv0.bias):$(o,t.conv0,[2,2])),n=$(r,t.conv1,[1,1]),a=C.relu(C.add(r,n)),s=$(a,t.conv2,[1,1]);return C.relu(C.add(r,C.add(n,s)))})}function Le(o,t,e=!1,r=!0){return C.tidy(()=>{let n=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,r?[2,2]:[1,1],"same"),t.conv0.bias):$(o,t.conv0,r?[2,2]:[1,1])),a=$(n,t.conv1,[1,1]),s=C.relu(C.add(n,a)),i=$(s,t.conv2,[1,1]),c=C.relu(C.add(n,C.add(a,i))),m=$(c,t.conv3,[1,1]);return C.relu(C.add(n,C.add(a,C.add(i,m))))})}var Ct=b(g());function Gt(o,t,e="same",r=!1){return Ct.tidy(()=>{let n=Ct.add(Ct.conv2d(o,t.filters,[1,1],e),t.bias);return r?Ct.relu(n):n})}function W(o,t){Object.keys(o).forEach(e=>{t.some(r=>r.originalPath===e)||o[e].dispose()})}var tr=b(g());function ce(o,t){return(e,r,n,a)=>{let s=tr.tensor4d(o(e*r*n*n),[n,n,e,r]),i=tr.tensor1d(o(r));return t.push({paramPath:`${a}/filters`},{paramPath:`${a}/bias`}),{filters:s,bias:i}}}var er=b(g());function rr(o,t){return(e,r,n)=>{let a=er.tensor2d(o(e*r),[e,r]),s=er.tensor1d(o(r));return t.push({paramPath:`${n}/weights`},{paramPath:`${n}/bias`}),{weights:a,bias:s}}}var ke=b(g());var or=class{constructor(t,e,r){this.depthwise_filter=t;this.pointwise_filter=e;this.bias=r}};function me(o,t){return(e,r,n)=>{let a=ke.tensor4d(o(3*3*e),[3,3,e,1]),s=ke.tensor4d(o(e*r),[1,1,e,r]),i=ke.tensor1d(o(r));return t.push({paramPath:`${n}/depthwise_filter`},{paramPath:`${n}/pointwise_filter`},{paramPath:`${n}/bias`}),new or(a,s,i)}}function pe(o){return t=>{let e=o(`${t}/depthwise_filter`,4),r=o(`${t}/pointwise_filter`,4),n=o(`${t}/bias`,1);return new or(e,r,n)}}function j(o,t){return(e,r,n)=>{let a=o[e];if(!Bt(a,r))throw new Error(`expected weightMap[${e}] to be a Tensor${r}D, instead have ${a}`);return t.push({originalPath:e,paramPath:n||e}),a}}function B(o){let t=o;function e(n){let a=t.slice(0,n);return t=t.slice(n),a}function r(){return t}return{extractWeights:e,getRemainingWeights:r}}function nr(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c,m=!1){let p=m?e(s,i,3,`${c}/conv0`):r(s,i,`${c}/conv0`),d=r(i,i,`${c}/conv1`),u=r(i,i,`${c}/conv2`);return{conv0:p,conv1:d,conv2:u}}function a(s,i,c,m=!1){let{conv0:p,conv1:d,conv2:u}=n(s,i,c,m),l=r(i,i,`${c}/conv3`);return{conv0:p,conv1:d,conv2:u,conv3:l}}return{extractDenseBlock3Params:n,extractDenseBlock4Params:a}}function _o(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock4Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2"),c=n(128,256,"dense3");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i,dense3:c}}}function ar(o){return t=>{let e=o(`${t}/filters`,4),r=o(`${t}/bias`,1);return{filters:e,bias:r}}}function sr(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`);return{conv0:m,conv1:p,conv2:d}}function s(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`),u=n(`${i}/conv3`);return{conv0:m,conv1:p,conv2:d,conv3:u}}return{extractDenseBlock3Params:a,extractDenseBlock4Params:s}}function wo(o){let t=[],{extractDenseBlock4Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2"),dense3:e("dense3")};return W(o,t),{params:r,paramMappings:t}}var Se=class extends S{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceFeatureExtractor - load model before inference");return Nt.tidy(()=>{let r=Nt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Nt.scalar(255)),s=Le(a,e.dense0,!0);return s=Le(s,e.dense1),s=Le(s,e.dense2),s=Le(s,e.dense3),s=Nt.avgPool(s,[7,7],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return wo(t)}extractParams(t){return _o(t)}};var Mo=b(g());var de=b(g());function Ae(o,t){return de.tidy(()=>de.add(de.matMul(o,t.weights),t.bias))}function Do(o,t,e){let r=[],{extractWeights:n,getRemainingWeights:a}=B(o),i=rr(n,r)(t,e,"fc");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:r,params:{fc:i}}}function Eo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:r("fc")};return W(o,t),{params:n,paramMappings:t}}function ir(o){let t={},e={};return Object.keys(o).forEach(r=>{let n=r.startsWith("fc")?e:t;n[r]=o[r]}),{featureExtractorMap:t,classifierMap:e}}var We=class extends S{constructor(t,e){super(t);this._faceFeatureExtractor=e}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return Mo.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t;return Ae(r.as2D(r.shape[0],-1),e.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return Do(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),Eo(r)}extractParams(t){let e=this.getClassifierChannelsIn(),r=this.getClassifierChannelsOut(),n=r*e+r,a=t.slice(0,t.length-n),s=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(s)}};var Jr=["neutral","happy","sad","angry","fearful","disgusted","surprised"],It=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Jr.forEach((e,r)=>{this[e]=t[r]})}asSortedArray(){return Jr.map(t=>({expression:t,probability:this[t]})).sort((t,e)=>e.probability-t.probability)}};var cr=class extends We{constructor(t=new Se){super("FaceExpressionNet",t)}forwardInput(t){return ue.tidy(()=>ue.softmax(this.runNet(t)))}async forward(t){return this.forwardInput(await E(t))}async predictExpressions(t){let e=await E(t),r=await this.forwardInput(e),n=await Promise.all(ue.unstack(r).map(async s=>{let i=await s.data();return s.dispose(),i}));r.dispose();let a=n.map(s=>new It(s));return e.isBatchInput?a:a[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function qr(o){return o.expressions instanceof It}function mr(o,t){return{...o,...{expressions:t}}}function $n(o,t,e=.1,r){(Array.isArray(t)?t:[t]).forEach(a=>{let s=a instanceof It?a:qr(a)?a.expressions:void 0;if(!s)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let c=s.asSortedArray().filter(d=>d.probability>e),m=pt(a)?a.detection.box.bottomLeft:r||new x(0,0);new Mt(c.map(d=>`${d.expression} (${Rt(d.probability)})`),m).draw(o)})}function zt(o){return pt(o)&&o.landmarks instanceof V&&o.unshiftedLandmarks instanceof V&&o.alignedRect instanceof M}function le(o,t){let{box:e}=o.detection,r=t.shiftBy(e.x,e.y),n=r.align(),{imageDims:a}=o.detection,s=new M(o.detection.score,n.rescale(a.reverse()),a);return{...o,...{landmarks:r,unshiftedLandmarks:t,alignedRect:s}}}var Zr=class{constructor(t={}){let{drawLines:e=!0,drawPoints:r=!0,lineWidth:n,lineColor:a,pointSize:s,pointColor:i}=t;this.drawLines=e,this.drawPoints=r,this.lineWidth=n||1,this.pointSize=s||2,this.lineColor=a||"rgba(0, 255, 255, 1)",this.pointColor=i||"rgba(255, 0, 255, 1)"}},Kr=class{constructor(t,e={}){this.faceLandmarks=t,this.options=new Zr(e)}draw(t){let e=O(t),{drawLines:r,drawPoints:n,lineWidth:a,lineColor:s,pointSize:i,pointColor:c}=this.options;if(r&&this.faceLandmarks instanceof oe&&(e.strokeStyle=s,e.lineWidth=a,ft(e,this.faceLandmarks.getJawOutline()),ft(e,this.faceLandmarks.getLeftEyeBrow()),ft(e,this.faceLandmarks.getRightEyeBrow()),ft(e,this.faceLandmarks.getNose()),ft(e,this.faceLandmarks.getLeftEye(),!0),ft(e,this.faceLandmarks.getRightEye(),!0),ft(e,this.faceLandmarks.getMouth(),!0)),n){e.strokeStyle=c,e.fillStyle=c;let m=p=>{e.beginPath(),e.arc(p.x,p.y,i,0,2*Math.PI),e.fill()};this.faceLandmarks.positions.forEach(m)}}};function jn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof V?r:zt(r)?r.landmarks:void 0;if(!n)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new Kr(n).draw(o)})}var Co="0.11.6";var ut=b(g());var I=b(g());function Hn(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c){let m=r(s,i,`${c}/separable_conv0`),p=r(i,i,`${c}/separable_conv1`),d=e(s,i,1,`${c}/expansion_conv`);return{separable_conv0:m,separable_conv1:p,expansion_conv:d}}function a(s,i){let c=r(s,s,`${i}/separable_conv0`),m=r(s,s,`${i}/separable_conv1`),p=r(s,s,`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:e,extractSeparableConvParams:r,extractReductionBlockParams:n,extractMainBlockParams:a}}function No(o,t){let e=[],{extractWeights:r,getRemainingWeights:n}=B(o),{extractConvParams:a,extractSeparableConvParams:s,extractReductionBlockParams:i,extractMainBlockParams:c}=Hn(r,e),m=a(3,32,3,"entry_flow/conv_in"),p=i(32,64,"entry_flow/reduction_block_0"),d=i(64,128,"entry_flow/reduction_block_1"),u={conv_in:m,reduction_block_0:p,reduction_block_1:d},l={};ct(t,0,1).forEach(y=>{l[`main_block_${y}`]=c(128,`middle_flow/main_block_${y}`)});let v=i(128,256,"exit_flow/reduction_block"),_=s(256,512,"exit_flow/separable_conv"),h={reduction_block:v,separable_conv:_};if(n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{paramMappings:e,params:{entry_flow:u,middle_flow:l,exit_flow:h}}}function Yn(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=r(`${i}/expansion_conv`);return{separable_conv0:c,separable_conv1:m,expansion_conv:p}}function s(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=n(`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}}function Io(o,t){let e=[],{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}=Yn(o,e),i=r("entry_flow/conv_in"),c=a("entry_flow/reduction_block_0"),m=a("entry_flow/reduction_block_1"),p={conv_in:i,reduction_block_0:c,reduction_block_1:m},d={};ct(t,0,1).forEach(_=>{d[`main_block_${_}`]=s(`middle_flow/main_block_${_}`)});let u=a("exit_flow/reduction_block"),l=n("exit_flow/separable_conv"),v={reduction_block:u,separable_conv:l};return W(o,e),{params:{entry_flow:p,middle_flow:d,exit_flow:v},paramMappings:e}}function Lo(o,t,e){return I.add(I.conv2d(o,t.filters,e,"same"),t.bias)}function to(o,t,e=!0){let r=e?I.relu(o):o;return r=$(r,t.separable_conv0,[1,1]),r=$(I.relu(r),t.separable_conv1,[1,1]),r=I.maxPool(r,[3,3],[2,2],"same"),r=I.add(r,Lo(o,t.expansion_conv,[2,2])),r}function Gn(o,t){let e=$(I.relu(o),t.separable_conv0,[1,1]);return e=$(I.relu(e),t.separable_conv1,[1,1]),e=$(I.relu(e),t.separable_conv2,[1,1]),e=I.add(e,o),e}var eo=class extends S{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyXception - load model before inference");return I.tidy(()=>{let r=I.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(I.scalar(256)),s=I.relu(Lo(a,e.entry_flow.conv_in,[2,2]));return s=to(s,e.entry_flow.reduction_block_0,!1),s=to(s,e.entry_flow.reduction_block_1),ct(this._numMainBlocks,0,1).forEach(i=>{s=Gn(s,e.middle_flow[`main_block_${i}`])}),s=to(s,e.exit_flow.reduction_block),s=I.relu($(s,e.exit_flow.separable_conv,[1,1])),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return Io(t,this._numMainBlocks)}extractParams(t){return No(t,this._numMainBlocks)}};function ko(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),n=rr(e,t),a=n(512,1,"fc/age"),s=n(512,2,"fc/gender");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{fc:{age:a,gender:s}}}}function So(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:{age:r("fc/age"),gender:r("fc/gender")}};return W(o,t),{params:n,paramMappings:t}}var vt;(function(o){o.FEMALE="female",o.MALE="male"})(vt||(vt={}));var pr=class extends S{constructor(t=new eo(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return ut.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t,n=ut.avgPool(r,[7,7],[2,2],"valid").as2D(r.shape[0],-1),a=Ae(n,e.fc.age).as1D(),s=Ae(n,e.fc.gender);return{age:a,gender:s}})}forwardInput(t){return ut.tidy(()=>{let{age:e,gender:r}=this.runNet(t);return{age:e,gender:ut.softmax(r)}})}async forward(t){return this.forwardInput(await E(t))}async predictAgeAndGender(t){let e=await E(t),r=await this.forwardInput(e),n=ut.unstack(r.age),a=ut.unstack(r.gender),s=n.map((c,m)=>({ageTensor:c,genderTensor:a[m]})),i=await Promise.all(s.map(async({ageTensor:c,genderTensor:m})=>{let p=(await c.data())[0],d=(await m.data())[0],u=d>.5,l=u?vt.MALE:vt.FEMALE,v=u?d:1-d;return c.dispose(),m.dispose(),{age:p,gender:l,genderProbability:v}}));return r.age.dispose(),r.gender.dispose(),e.isBatchInput?i:i[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return ko(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),So(r)}extractParams(t){let e=512*1+1+(512*2+2),r=t.slice(0,t.length-e),n=t.slice(t.length-e);return this.faceFeatureExtractor.extractWeights(r),this.extractClassifierParams(n)}};var H=b(g());var Be=class extends We{postProcess(t,e,r){let n=r.map(({width:s,height:i})=>{let c=e/Math.max(i,s);return{width:s*c,height:i*c}}),a=n.length;return H.tidy(()=>{let s=(d,u)=>H.stack([H.fill([68],d,"float32"),H.fill([68],u,"float32")],1).as2D(1,136).as1D(),i=(d,u)=>{let{width:l,height:v}=n[d];return u(l,v)?Math.abs(l-v)/2:0},c=d=>i(d,(u,l)=>ui(d,(u,l)=>ls(c(u),m(u))))).div(H.stack(Array.from(Array(a),(d,u)=>s(n[u].width,n[u].height))))})}forwardInput(t){return H.tidy(()=>{let e=this.runNet(t);return this.postProcess(e,t.inputSize,t.inputDimensions.map(([r,n])=>({height:r,width:n})))})}async forward(t){return this.forwardInput(await E(t))}async detectLandmarks(t){let e=await E(t),r=H.tidy(()=>H.unstack(this.forwardInput(e))),n=await Promise.all(r.map(async(a,s)=>{let i=Array.from(await a.data()),c=i.filter((p,d)=>ze(d)),m=i.filter((p,d)=>!ze(d));return new oe(Array(68).fill(0).map((p,d)=>new x(c[d],m[d])),{height:e.getInputHeight(s),width:e.getInputWidth(s)})}));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getClassifierChannelsOut(){return 136}};var fe=class extends Be{constructor(t=new Se){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};var Lt=b(g());function Ao(o){let t=[],{extractDenseBlock3Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2")};return W(o,t),{params:r,paramMappings:t}}function Wo(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock3Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i}}}var ro=class extends S{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyFaceFeatureExtractor - load model before inference");return Lt.tidy(()=>{let r=Lt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Lt.scalar(255)),s=Qe(a,e.dense0,!0);return s=Qe(s,e.dense1),s=Qe(s,e.dense2),s=Lt.avgPool(s,[14,14],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return Ao(t)}extractParams(t){return Wo(t)}};var dr=class extends Be{constructor(t=new ro){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Bo=class extends fe{};var U=b(g());var he=b(g());var ur=b(g());function Ro(o,t){return ur.add(ur.mul(o,t.weights),t.biases)}function oo(o,t,e,r,n="same"){let{filters:a,bias:s}=t.conv,i=he.conv2d(o,a,e,n);return i=he.add(i,s),i=Ro(i,t.scale),r?he.relu(i):i}function Oo(o,t){return oo(o,t,[1,1],!0)}function no(o,t){return oo(o,t,[1,1],!1)}function lr(o,t){return oo(o,t,[2,2],!0,"valid")}var Y=b(g());function zn(o,t){function e(i,c,m){let p=o(i),d=p.length/(c*m*m);if(Nr(d))throw new Error(`depth has to be an integer: ${d}, weights.length: ${p.length}, numFilters: ${c}, filterSize: ${m}`);return Y.tidy(()=>Y.transpose(Y.tensor4d(p,[c,d,m,m]),[2,3,1,0]))}function r(i,c,m,p){let d=e(i,c,m),u=Y.tensor1d(o(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/bias`}),{filters:d,bias:u}}function n(i,c){let m=Y.tensor1d(o(i)),p=Y.tensor1d(o(i));return t.push({paramPath:`${c}/weights`},{paramPath:`${c}/biases`}),{weights:m,biases:p}}function a(i,c,m,p){let d=r(i,c,m,`${p}/conv`),u=n(c,`${p}/scale`);return{conv:d,scale:u}}function s(i,c,m,p,d=!1){let u=a((d?.5:1)*i,c,m,`${p}/conv1`),l=a(i,c,m,`${p}/conv2`);return{conv1:u,conv2:l}}return{extractConvLayerParams:a,extractResidualLayerParams:s}}function $o(o){let{extractWeights:t,getRemainingWeights:e}=B(o),r=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=zn(t,r),s=n(4704,32,7,"conv32_down"),i=a(9216,32,3,"conv32_1"),c=a(9216,32,3,"conv32_2"),m=a(9216,32,3,"conv32_3"),p=a(36864,64,3,"conv64_down",!0),d=a(36864,64,3,"conv64_1"),u=a(36864,64,3,"conv64_2"),l=a(36864,64,3,"conv64_3"),v=a(147456,128,3,"conv128_down",!0),_=a(147456,128,3,"conv128_1"),h=a(147456,128,3,"conv128_2"),y=a(589824,256,3,"conv256_down",!0),T=a(589824,256,3,"conv256_1"),F=a(589824,256,3,"conv256_2"),L=a(589824,256,3,"conv256_down_out"),G=Y.tidy(()=>Y.transpose(Y.tensor2d(t(256*128),[128,256]),[1,0]));if(r.push({paramPath:"fc"}),e().length!==0)throw new Error(`weights remaing after extract: ${e().length}`);return{params:{conv32_down:s,conv32_1:i,conv32_2:c,conv32_3:m,conv64_down:p,conv64_1:d,conv64_2:u,conv64_3:l,conv128_down:v,conv128_1:_,conv128_2:h,conv256_down:y,conv256_1:T,conv256_2:F,conv256_down_out:L,fc:G},paramMappings:r}}function Vn(o,t){let e=j(o,t);function r(s){let i=e(`${s}/scale/weights`,1),c=e(`${s}/scale/biases`,1);return{weights:i,biases:c}}function n(s){let i=e(`${s}/conv/filters`,4),c=e(`${s}/conv/bias`,1),m=r(s);return{conv:{filters:i,bias:c},scale:m}}function a(s){return{conv1:n(`${s}/conv1`),conv2:n(`${s}/conv2`)}}return{extractConvLayerParams:n,extractResidualLayerParams:a}}function jo(o){let t=[],{extractConvLayerParams:e,extractResidualLayerParams:r}=Vn(o,t),n=e("conv32_down"),a=r("conv32_1"),s=r("conv32_2"),i=r("conv32_3"),c=r("conv64_down"),m=r("conv64_1"),p=r("conv64_2"),d=r("conv64_3"),u=r("conv128_down"),l=r("conv128_1"),v=r("conv128_2"),_=r("conv256_down"),h=r("conv256_1"),y=r("conv256_2"),T=r("conv256_down_out"),{fc:F}=o;if(t.push({originalPath:"fc",paramPath:"fc"}),!Cr(F))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${F}`);let L={conv32_down:n,conv32_1:a,conv32_2:s,conv32_3:i,conv64_down:c,conv64_1:m,conv64_2:p,conv64_3:d,conv128_down:u,conv128_1:l,conv128_2:v,conv256_down:_,conv256_1:h,conv256_2:y,conv256_down_out:T,fc:F};return W(o,t),{params:L,paramMappings:t}}var R=b(g());function nt(o,t){let e=Oo(o,t.conv1);return e=no(e,t.conv2),e=R.add(e,o),e=R.relu(e),e}function Re(o,t){let e=lr(o,t.conv1);e=no(e,t.conv2);let r=R.avgPool(o,2,2,"valid"),n=R.zeros(r.shape),a=r.shape[3]!==e.shape[3];if(r.shape[1]!==e.shape[1]||r.shape[2]!==e.shape[2]){let i=[...e.shape];i[1]=1;let c=R.zeros(i);e=R.concat([e,c],1);let m=[...e.shape];m[2]=1;let p=R.zeros(m);e=R.concat([e,p],2)}return r=a?R.concat([r,n],3):r,e=R.add(r,e),e=R.relu(e),e}var xe=class extends S{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceRecognitionNet - load model before inference");return U.tidy(()=>{let r=U.cast(t.toBatchTensor(150,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(U.scalar(256)),s=lr(a,e.conv32_down);s=U.maxPool(s,3,2,"valid"),s=nt(s,e.conv32_1),s=nt(s,e.conv32_2),s=nt(s,e.conv32_3),s=Re(s,e.conv64_down),s=nt(s,e.conv64_1),s=nt(s,e.conv64_2),s=nt(s,e.conv64_3),s=Re(s,e.conv128_down),s=nt(s,e.conv128_1),s=nt(s,e.conv128_2),s=Re(s,e.conv256_down),s=nt(s,e.conv256_1),s=nt(s,e.conv256_2),s=Re(s,e.conv256_down_out);let i=s.mean([1,2]);return U.matMul(i,e.fc)})}async forward(t){return this.forwardInput(await E(t))}async computeFaceDescriptor(t){var a;if((a=t==null?void 0:t.shape)==null?void 0:a.some(s=>s<=0))return new Float32Array(128);let e=await E(t),r=U.tidy(()=>U.unstack(this.forwardInput(e))),n=await Promise.all(r.map(s=>s.data()));return r.forEach(s=>s.dispose()),e.isBatchInput?n:n[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return jo(t)}extractParams(t){return $o(t)}};function Un(o){let t=new xe;return t.extractWeights(o),t}function fr(o,t){return{...o,...{descriptor:t}}}function Xn(o){return typeof o.age=="number"}function hr(o,t){return{...o,...{age:t}}}function Jn(o){return(o.gender===vt.MALE||o.gender===vt.FEMALE)&&te(o.genderProbability)}function xr(o,t,e){return{...o,...{gender:t,genderProbability:e}}}var st=b(g());var at=b(g());function qn(o,t){function e(c,m){let p=at.tensor4d(o(3*3*c),[3,3,c,1]),d=at.tensor1d(o(c)),u=at.tensor1d(o(c)),l=at.tensor1d(o(c)),v=at.tensor1d(o(c));return t.push({paramPath:`${m}/filters`},{paramPath:`${m}/batch_norm_scale`},{paramPath:`${m}/batch_norm_offset`},{paramPath:`${m}/batch_norm_mean`},{paramPath:`${m}/batch_norm_variance`}),{filters:p,batch_norm_scale:d,batch_norm_offset:u,batch_norm_mean:l,batch_norm_variance:v}}function r(c,m,p,d,u){let l=at.tensor4d(o(c*m*p*p),[p,p,c,m]),v=at.tensor1d(o(m));return t.push({paramPath:`${d}/filters`},{paramPath:`${d}/${u?"batch_norm_offset":"bias"}`}),{filters:l,bias:v}}function n(c,m,p,d){let{filters:u,bias:l}=r(c,m,p,d,!0);return{filters:u,batch_norm_offset:l}}function a(c,m,p){let d=e(c,`${p}/depthwise_conv`),u=n(c,m,1,`${p}/pointwise_conv`);return{depthwise_conv:d,pointwise_conv:u}}function s(){let c=n(3,32,3,"mobilenetv1/conv_0"),m=a(32,64,"mobilenetv1/conv_1"),p=a(64,128,"mobilenetv1/conv_2"),d=a(128,128,"mobilenetv1/conv_3"),u=a(128,256,"mobilenetv1/conv_4"),l=a(256,256,"mobilenetv1/conv_5"),v=a(256,512,"mobilenetv1/conv_6"),_=a(512,512,"mobilenetv1/conv_7"),h=a(512,512,"mobilenetv1/conv_8"),y=a(512,512,"mobilenetv1/conv_9"),T=a(512,512,"mobilenetv1/conv_10"),F=a(512,512,"mobilenetv1/conv_11"),L=a(512,1024,"mobilenetv1/conv_12"),G=a(1024,1024,"mobilenetv1/conv_13");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,conv_8:h,conv_9:y,conv_10:T,conv_11:F,conv_12:L,conv_13:G}}function i(){let c=n(1024,256,1,"prediction_layer/conv_0"),m=n(256,512,3,"prediction_layer/conv_1"),p=n(512,128,1,"prediction_layer/conv_2"),d=n(128,256,3,"prediction_layer/conv_3"),u=n(256,128,1,"prediction_layer/conv_4"),l=n(128,256,3,"prediction_layer/conv_5"),v=n(256,64,1,"prediction_layer/conv_6"),_=n(64,128,3,"prediction_layer/conv_7"),h=r(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=r(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),T=r(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),F=r(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),L=r(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),G=r(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),et=r(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),it=r(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),X=r(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),Pt=r(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),_t=r(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),wt=r(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,box_predictor_0:{box_encoding_predictor:h,class_predictor:y},box_predictor_1:{box_encoding_predictor:T,class_predictor:F},box_predictor_2:{box_encoding_predictor:L,class_predictor:G},box_predictor_3:{box_encoding_predictor:et,class_predictor:it},box_predictor_4:{box_encoding_predictor:X,class_predictor:Pt},box_predictor_5:{box_encoding_predictor:_t,class_predictor:wt}}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:i}}function Ho(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=qn(e,t),s=n(),i=a(),m={extra_dim:at.tensor3d(e(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{params:{mobilenetv1:s,prediction_layer:i,output_layer:m},paramMappings:t}}function Zn(o,t){let e=j(o,t);function r(m,p,d){let u=e(`${m}/Conv2d_${p}_pointwise/weights`,4,`${d}/filters`),l=e(`${m}/Conv2d_${p}_pointwise/convolution_bn_offset`,1,`${d}/batch_norm_offset`);return{filters:u,batch_norm_offset:l}}function n(m){let p=`mobilenetv1/conv_${m}`,d=`MobilenetV1/Conv2d_${m}_depthwise`,u=`${p}/depthwise_conv`,l=`${p}/pointwise_conv`,v=e(`${d}/depthwise_weights`,4,`${u}/filters`),_=e(`${d}/BatchNorm/gamma`,1,`${u}/batch_norm_scale`),h=e(`${d}/BatchNorm/beta`,1,`${u}/batch_norm_offset`),y=e(`${d}/BatchNorm/moving_mean`,1,`${u}/batch_norm_mean`),T=e(`${d}/BatchNorm/moving_variance`,1,`${u}/batch_norm_variance`);return{depthwise_conv:{filters:v,batch_norm_scale:_,batch_norm_offset:h,batch_norm_mean:y,batch_norm_variance:T},pointwise_conv:r("MobilenetV1",m,l)}}function a(){return{conv_0:r("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:n(1),conv_2:n(2),conv_3:n(3),conv_4:n(4),conv_5:n(5),conv_6:n(6),conv_7:n(7),conv_8:n(8),conv_9:n(9),conv_10:n(10),conv_11:n(11),conv_12:n(12),conv_13:n(13)}}function s(m,p){let d=e(`${m}/weights`,4,`${p}/filters`),u=e(`${m}/biases`,1,`${p}/bias`);return{filters:d,bias:u}}function i(m){let p=s(`Prediction/BoxPredictor_${m}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${m}/box_encoding_predictor`),d=s(`Prediction/BoxPredictor_${m}/ClassPredictor`,`prediction_layer/box_predictor_${m}/class_predictor`);return{box_encoding_predictor:p,class_predictor:d}}function c(){return{conv_0:r("Prediction",0,"prediction_layer/conv_0"),conv_1:r("Prediction",1,"prediction_layer/conv_1"),conv_2:r("Prediction",2,"prediction_layer/conv_2"),conv_3:r("Prediction",3,"prediction_layer/conv_3"),conv_4:r("Prediction",4,"prediction_layer/conv_4"),conv_5:r("Prediction",5,"prediction_layer/conv_5"),conv_6:r("Prediction",6,"prediction_layer/conv_6"),conv_7:r("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:i(0),box_predictor_1:i(1),box_predictor_2:i(2),box_predictor_3:i(3),box_predictor_4:i(4),box_predictor_5:i(5)}}return{extractMobilenetV1Params:a,extractPredictionLayerParams:c}}function Yo(o){let t=[],{extractMobilenetV1Params:e,extractPredictionLayerParams:r}=Zn(o,t),n=o["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!ht(n))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${n}`);let a={mobilenetv1:e(),prediction_layer:r(),output_layer:{extra_dim:n}};return W(o,t),{params:a,paramMappings:t}}var yt=b(g());var kt=b(g());function q(o,t,e){return kt.tidy(()=>{let r=kt.conv2d(o,t.filters,e,"same");return r=kt.add(r,t.batch_norm_offset),kt.clipByValue(r,0,6)})}var Kn=.0010000000474974513;function Qn(o,t,e){return yt.tidy(()=>{let r=yt.depthwiseConv2d(o,t.filters,e,"same");return r=yt.batchNorm(r,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Kn),yt.clipByValue(r,0,6)})}function ta(o){return[2,4,6,12].some(t=>t===o)?[2,2]:[1,1]}function Go(o,t){return yt.tidy(()=>{let e,r=q(o,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((a,s)=>{let i=s+1,c=ta(i);r=Qn(r,a.depthwise_conv,c),r=q(r,a.pointwise_conv,[1,1]),i===11&&(e=r)}),e===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:r,conv11:e}})}function ea(o,t,e){let r=o.arraySync(),n=Math.min(r[t][0],r[t][2]),a=Math.min(r[t][1],r[t][3]),s=Math.max(r[t][0],r[t][2]),i=Math.max(r[t][1],r[t][3]),c=Math.min(r[e][0],r[e][2]),m=Math.min(r[e][1],r[e][3]),p=Math.max(r[e][0],r[e][2]),d=Math.max(r[e][1],r[e][3]),u=(s-n)*(i-a),l=(p-c)*(d-m);if(u<=0||l<=0)return 0;let v=Math.max(n,c),_=Math.max(a,m),h=Math.min(s,p),y=Math.min(i,d),T=Math.max(h-v,0)*Math.max(y-_,0);return T/(u+l-T)}function zo(o,t,e,r,n){let a=o.shape[0],s=Math.min(e,a),i=t.map((p,d)=>({score:p,boxIndex:d})).filter(p=>p.score>n).sort((p,d)=>d.score-p.score),c=p=>p<=r?1:0,m=[];return i.forEach(p=>{if(m.length>=s)return;let d=p.score;for(let u=m.length-1;u>=0;--u){let l=ea(o,p.boxIndex,m[u]);if(l!==0&&(p.score*=c(l),p.score<=n))break}d===p.score&&m.push(p.boxIndex)}),m}var f=b(g());function ra(o){let t=f.unstack(f.transpose(o,[1,0])),e=[f.sub(t[2],t[0]),f.sub(t[3],t[1])],r=[f.add(t[0],f.div(e[0],f.scalar(2))),f.add(t[1],f.div(e[1],f.scalar(2)))];return{sizes:e,centers:r}}function oa(o,t){let{sizes:e,centers:r}=ra(o),n=f.unstack(f.transpose(t,[1,0])),a=f.div(f.mul(f.exp(f.div(n[2],f.scalar(5))),e[0]),f.scalar(2)),s=f.add(f.mul(f.div(n[0],f.scalar(10)),e[0]),r[0]),i=f.div(f.mul(f.exp(f.div(n[3],f.scalar(5))),e[1]),f.scalar(2)),c=f.add(f.mul(f.div(n[1],f.scalar(10)),e[1]),r[1]);return f.transpose(f.stack([f.sub(s,a),f.sub(c,i),f.add(s,a),f.add(c,i)]),[1,0])}function Vo(o,t,e){return f.tidy(()=>{let r=o.shape[0],n=oa(f.reshape(f.tile(e.extra_dim,[r,1,1]),[-1,4]),f.reshape(o,[-1,4]));n=f.reshape(n,[r,n.shape[0]/r,4]);let a=f.sigmoid(f.slice(t,[0,0,1],[-1,-1,-1])),s=f.slice(a,[0,0,0],[-1,-1,1]);s=f.reshape(s,[r,s.shape[1]]);let i=f.unstack(n),c=f.unstack(s);return{boxes:i,scores:c}})}var $e=b(g());var Oe=b(g());function Vt(o,t){return Oe.tidy(()=>{let e=o.shape[0],r=Oe.reshape(Gt(o,t.box_encoding_predictor),[e,-1,1,4]),n=Oe.reshape(Gt(o,t.class_predictor),[e,-1,3]);return{boxPredictionEncoding:r,classPrediction:n}})}function Uo(o,t,e){return $e.tidy(()=>{let r=q(o,e.conv_0,[1,1]),n=q(r,e.conv_1,[2,2]),a=q(n,e.conv_2,[1,1]),s=q(a,e.conv_3,[2,2]),i=q(s,e.conv_4,[1,1]),c=q(i,e.conv_5,[2,2]),m=q(c,e.conv_6,[1,1]),p=q(m,e.conv_7,[2,2]),d=Vt(t,e.box_predictor_0),u=Vt(o,e.box_predictor_1),l=Vt(n,e.box_predictor_2),v=Vt(s,e.box_predictor_3),_=Vt(c,e.box_predictor_4),h=Vt(p,e.box_predictor_5),y=$e.concat([d.boxPredictionEncoding,u.boxPredictionEncoding,l.boxPredictionEncoding,v.boxPredictionEncoding,_.boxPredictionEncoding,h.boxPredictionEncoding],1),T=$e.concat([d.classPrediction,u.classPrediction,l.classPrediction,v.classPrediction,_.classPrediction,h.classPrediction],1);return{boxPredictions:y,classPredictions:T}})}var Z=class{constructor({minConfidence:t,maxResults:e}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=e||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Ut=class extends S{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("SsdMobilenetv1 - load model before inference");return st.tidy(()=>{let r=st.cast(t.toBatchTensor(512,!1),"float32"),n=st.sub(st.mul(r,st.scalar(.007843137718737125)),st.scalar(1)),a=Go(n,e.mobilenetv1),{boxPredictions:s,classPredictions:i}=Uo(a.out,a.conv11,e.prediction_layer);return Vo(s,i,e.output_layer)})}async forward(t){return this.forwardInput(await E(t))}async locateFaces(t,e={}){let{maxResults:r,minConfidence:n}=new Z(e),a=await E(t),{boxes:s,scores:i}=this.forwardInput(a),c=s[0],m=i[0];for(let F=1;F{let[L,G]=[Math.max(0,y[F][0]),Math.min(1,y[F][2])].map(X=>X*h),[et,it]=[Math.max(0,y[F][1]),Math.min(1,y[F][3])].map(X=>X*_);return new M(p[F],new re(et,L,it-et,G-L),{height:a.getInputHeight(0),width:a.getInputWidth(0)})});return c.dispose(),m.dispose(),T}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return Yo(t)}extractParams(t){return Ho(t)}};function Xo(o){let t=new Ut;return t.extractWeights(o),t}function na(o){return Xo(o)}var Jo=class extends Ut{};var qo=.4,Zo=[new x(.738768,.874946),new x(2.42204,2.65704),new x(4.30971,7.04493),new x(10.246,4.59428),new x(12.6868,11.8741)],Ko=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],Qo=[117.001,114.697,97.404],tn="tiny_yolov2_model",en="tiny_yolov2_separable_conv_model";var N=b(g());var br=o=>typeof o=="number";function ao(o){if(!o)throw new Error(`invalid config: ${o}`);if(typeof o.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${o.withSeparableConvs}`);if(!br(o.iouThreshold)||o.iouThreshold<0||o.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${o.iouThreshold}`);if(!Array.isArray(o.classes)||!o.classes.length||!o.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(o.classes)}`);if(!Array.isArray(o.anchors)||!o.anchors.length||!o.anchors.map(t=>t||{}).every(t=>br(t.x)&&br(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(o.anchors)}`);if(o.meanRgb&&(!Array.isArray(o.meanRgb)||o.meanRgb.length!==3||!o.meanRgb.every(br)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(o.meanRgb)}`)}var Q=b(g());var K=b(g());function be(o){return K.tidy(()=>{let t=K.mul(o,K.scalar(.10000000149011612));return K.add(K.relu(K.sub(o,t)),t)})}function Ft(o,t){return Q.tidy(()=>{let e=Q.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=Q.conv2d(e,t.conv.filters,[1,1],"valid"),e=Q.sub(e,t.bn.sub),e=Q.mul(e,t.bn.truediv),e=Q.add(e,t.conv.bias),be(e)})}var St=b(g());function Tt(o,t){return St.tidy(()=>{let e=St.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=St.separableConv2d(e,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),e=St.add(e,t.bias),be(e)})}var so=b(g());function aa(o,t){let e=ce(o,t);function r(s,i){let c=so.tensor1d(o(s)),m=so.tensor1d(o(s));return t.push({paramPath:`${i}/sub`},{paramPath:`${i}/truediv`}),{sub:c,truediv:m}}function n(s,i,c){let m=e(s,i,3,`${c}/conv`),p=r(i,`${c}/bn`);return{conv:m,bn:p}}let a=me(o,t);return{extractConvParams:e,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}}function rn(o,t,e,r){let{extractWeights:n,getRemainingWeights:a}=B(o),s=[],{extractConvParams:i,extractConvWithBatchNormParams:c,extractSeparableConvParams:m}=aa(n,s),p;if(t.withSeparableConvs){let[d,u,l,v,_,h,y,T,F]=r,L=t.isFirstLayerConv2d?i(d,u,3,"conv0"):m(d,u,"conv0"),G=m(u,l,"conv1"),et=m(l,v,"conv2"),it=m(v,_,"conv3"),X=m(_,h,"conv4"),Pt=m(h,y,"conv5"),_t=T?m(y,T,"conv6"):void 0,wt=F?m(T,F,"conv7"):void 0,Qt=i(F||T||y,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}else{let[d,u,l,v,_,h,y,T,F]=r,L=c(d,u,"conv0"),G=c(u,l,"conv1"),et=c(l,v,"conv2"),it=c(v,_,"conv3"),X=c(_,h,"conv4"),Pt=c(h,y,"conv5"),_t=c(y,T,"conv6"),wt=c(T,F,"conv7"),Qt=i(F,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:p,paramMappings:s}}function sa(o,t){let e=j(o,t);function r(i){let c=e(`${i}/sub`,1),m=e(`${i}/truediv`,1);return{sub:c,truediv:m}}function n(i){let c=e(`${i}/filters`,4),m=e(`${i}/bias`,1);return{filters:c,bias:m}}function a(i){let c=n(`${i}/conv`),m=r(`${i}/bn`);return{conv:c,bn:m}}let s=pe(e);return{extractConvParams:n,extractConvWithBatchNormParams:a,extractSeparableConvParams:s}}function on(o,t){let e=[],{extractConvParams:r,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}=sa(o,e),s;if(t.withSeparableConvs){let i=t.filterSizes&&t.filterSizes.length||9;s={conv0:t.isFirstLayerConv2d?r("conv0"):a("conv0"),conv1:a("conv1"),conv2:a("conv2"),conv3:a("conv3"),conv4:a("conv4"),conv5:a("conv5"),conv6:i>7?a("conv6"):void 0,conv7:i>8?a("conv7"):void 0,conv8:r("conv8")}}else s={conv0:n("conv0"),conv1:n("conv1"),conv2:n("conv2"),conv3:n("conv3"),conv4:n("conv4"),conv5:n("conv5"),conv6:n("conv6"),conv7:n("conv7"),conv8:r("conv8")};return W(o,e),{params:s,paramMappings:e}}var lt=class{constructor({inputSize:t,scoreThreshold:e}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=e||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var io=class extends S{constructor(t){super("TinyYolov2");ao(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,e){let r=Ft(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=Ft(r,e.conv6),r=Ft(r,e.conv7),Gt(r,e.conv8,"valid",!1)}runMobilenet(t,e){let r=this.config.isFirstLayerConv2d?be(Gt(t,e.conv0,"valid",!1)):Tt(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=e.conv6?Tt(r,e.conv6):r,r=e.conv7?Tt(r,e.conv7):r,Gt(r,e.conv8,"valid",!1)}forwardInput(t,e){let{params:r}=this;if(!r)throw new Error("TinyYolov2 - load model before inference");return N.tidy(()=>{let n=N.cast(t.toBatchTensor(e,!1),"float32");return n=this.config.meanRgb?ot(n,this.config.meanRgb):n,n=n.div(N.scalar(256)),this.config.withSeparableConvs?this.runMobilenet(n,r):this.runTinyYolov2(n,r)})}async forward(t,e){return this.forwardInput(await E(t),e)}async detect(t,e={}){let{inputSize:r,scoreThreshold:n}=new lt(e),a=await E(t),s=await this.forwardInput(a,r),i=N.tidy(()=>N.unstack(s)[0].expandDims()),c={width:a.getInputWidth(0),height:a.getInputHeight(0)},m=await this.extractBoxes(i,a.getReshapedInputDimensions(0),n);s.dispose(),i.dispose();let p=m.map(h=>h.box),d=m.map(h=>h.score),u=m.map(h=>h.classScore),l=m.map(h=>this.config.classes[h.label]);return Sr(p.map(h=>h.rescale(r)),d,this.config.iouThreshold,!0).map(h=>new Dt(d[h],u[h],l[h],p[h],c))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return on(t,this.config)}extractParams(t){let e=this.config.filterSizes||io.DEFAULT_FILTER_SIZES,r=e?e.length:void 0;if(r!==7&&r!==8&&r!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${r} filterSizes in config`);return rn(t,this.config,this.boxEncodingSize,e)}async extractBoxes(t,e,r){let{width:n,height:a}=e,s=Math.max(n,a),i=s/n,c=s/a,m=t.shape[1],p=this.config.anchors.length,[d,u,l]=N.tidy(()=>{let y=t.reshape([m,m,p,this.boxEncodingSize]),T=y.slice([0,0,0,0],[m,m,p,4]),F=y.slice([0,0,0,4],[m,m,p,1]),L=this.withClassScores?N.softmax(y.slice([0,0,0,5],[m,m,p,this.config.classes.length]),3):N.scalar(0);return[T,F,L]}),v=[],_=await u.array(),h=await d.array();for(let y=0;yr){let G=(T+De(h[y][T][F][0]))/m*i,et=(y+De(h[y][T][F][1]))/m*c,it=Math.exp(h[y][T][F][2])*this.config.anchors[F].x/m*i,X=Math.exp(h[y][T][F][3])*this.config.anchors[F].y/m*c,Pt=G-it/2,_t=et-X/2,wt={row:y,col:T,anchor:F},{classScore:Qt,label:lo}=this.withClassScores?await this.extractPredictedClass(l,wt):{classScore:1,label:0};v.push({box:new ee(Pt,_t,Pt+it,_t+X),score:L,classScore:L*Qt,label:lo,...wt})}}return d.dispose(),u.dispose(),l.dispose(),v}async extractPredictedClass(t,e){let{row:r,col:n,anchor:a}=e,s=await t.array();return Array(this.config.classes.length).fill(0).map((i,c)=>s[r][n][a][c]).map((i,c)=>({classScore:i,label:c})).reduce((i,c)=>i.classScore>c.classScore?i:c)}},ge=io;ge.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var ve=class extends ge{constructor(t=!0){let e={withSeparableConvs:t,iouThreshold:qo,classes:["face"],...t?{anchors:Ko,meanRgb:Qo}:{anchors:Zo,withClassScores:!0}};super(e)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?en:tn}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function ia(o,t=!0){let e=new ve(t);return e.extractWeights(o),e}var gr=class extends lt{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var tt=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};var je=b(g());var co=b(g());async function Xt(o,t,e,r,n=({alignedRect:a})=>a){let a=o.map(c=>zt(c)?n(c):c.detection),s=r||(t instanceof co.Tensor?await se(t,a):await ae(t,a)),i=await e(s);return s.forEach(c=>c instanceof co.Tensor&&c.dispose()),i}async function ye(o,t,e,r,n){return Xt([o],t,async a=>e(a[0]),r,n)}var nn=.4,an=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],sn=[117.001,114.697,97.404];var Fe=class extends ge{constructor(){let t={withSeparableConvs:!0,iouThreshold:nn,classes:["face"],anchors:an,meanRgb:sn,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var P={ssdMobilenetv1:new Ut,tinyFaceDetector:new Fe,tinyYolov2:new ve,faceLandmark68Net:new fe,faceLandmark68TinyNet:new dr,faceRecognitionNet:new xe,faceExpressionNet:new cr,ageGenderNet:new pr},cn=(o,t)=>P.ssdMobilenetv1.locateFaces(o,t),ca=(o,t)=>P.tinyFaceDetector.locateFaces(o,t),ma=(o,t)=>P.tinyYolov2.locateFaces(o,t),mn=o=>P.faceLandmark68Net.detectLandmarks(o),pa=o=>P.faceLandmark68TinyNet.detectLandmarks(o),da=o=>P.faceRecognitionNet.computeFaceDescriptor(o),ua=o=>P.faceExpressionNet.predictExpressions(o),la=o=>P.ageGenderNet.predictAgeAndGender(o),pn=o=>P.ssdMobilenetv1.load(o),fa=o=>P.tinyFaceDetector.load(o),ha=o=>P.tinyYolov2.load(o),xa=o=>P.faceLandmark68Net.load(o),ba=o=>P.faceLandmark68TinyNet.load(o),ga=o=>P.faceRecognitionNet.load(o),va=o=>P.faceExpressionNet.load(o),ya=o=>P.ageGenderNet.load(o),Fa=pn,Ta=cn,Pa=mn;var mo=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},_e=class extends mo{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.faceExpressionNet.predictExpressions(n))),this.extractedFaces);return t.map((r,n)=>mr(r,e[n]))}withAgeAndGender(){return new Te(this,this.input)}},we=class extends mo{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceExpressionNet.predictExpressions(r),this.extractedFaces);return mr(t,e)}withAgeAndGender(){return new Pe(this,this.input)}},Zt=class extends _e{withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Kt=class extends we{withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var po=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},Te=class extends po{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.ageGenderNet.predictAgeAndGender(n))),this.extractedFaces);return t.map((r,n)=>{let{age:a,gender:s,genderProbability:i}=e[n];return hr(xr(r,s,i),a)})}withFaceExpressions(){return new _e(this,this.input)}},Pe=class extends po{async run(){let t=await this.parentTask;if(!t)return;let{age:e,gender:r,genderProbability:n}=await ye(t,this.input,a=>P.ageGenderNet.predictAgeAndGender(a),this.extractedFaces);return hr(xr(t,r,n),e)}withFaceExpressions(){return new we(this,this.input)}},Jt=class extends Te{withFaceExpressions(){return new Zt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},qt=class extends Pe{withFaceExpressions(){return new Kt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var vr=class extends tt{constructor(t,e){super();this.parentTask=t;this.input=e}},At=class extends vr{async run(){let t=await this.parentTask;return(await Xt(t,this.input,r=>Promise.all(r.map(n=>P.faceRecognitionNet.computeFaceDescriptor(n))),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}))).map((r,n)=>fr(t[n],r))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}},Wt=class extends vr{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceRecognitionNet.computeFaceDescriptor(r),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}));return fr(t,e)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}};var yr=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.useTinyLandmarkNet=r}get landmarkNet(){return this.useTinyLandmarkNet?P.faceLandmark68TinyNet:P.faceLandmark68Net}},Fr=class extends yr{async run(){let t=await this.parentTask,e=t.map(a=>a.detection),r=this.input instanceof je.Tensor?await se(this.input,e):await ae(this.input,e),n=await Promise.all(r.map(a=>this.landmarkNet.detectLandmarks(a)));return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),t.map((a,s)=>le(a,n[s]))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Tr=class extends yr{async run(){let t=await this.parentTask;if(!t)return;let{detection:e}=t,r=this.input instanceof je.Tensor?await se(this.input,[e]):await ae(this.input,[e]),n=await this.landmarkNet.detectLandmarks(r[0]);return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),le(t,n)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var Pr=class extends tt{constructor(t,e=new Z){super();this.input=t;this.options=e}},He=class extends Pr{async run(){let{input:t,options:e}=this,r=e instanceof gr?n=>P.tinyFaceDetector.locateFaces(n,e):e instanceof Z?n=>P.ssdMobilenetv1.locateFaces(n,e):e instanceof lt?n=>P.tinyYolov2.locateFaces(n,e):null;if(!r)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return r(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let e=await this.run();t(e.map(r=>$t({},r)))})}withFaceLandmarks(t=!1){return new Fr(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new _e(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Te(this.runAndExtendWithFaceDetections(),this.input)}},_r=class extends Pr{async run(){let t=await new He(this.input,this.options),e=t[0];return t.forEach(r=>{r.score>e.score&&(e=r)}),e}runAndExtendWithFaceDetection(){return new Promise(async t=>{let e=await this.run();t(e?$t({},e):void 0)})}withFaceLandmarks(t=!1){return new Tr(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new we(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Pe(this.runAndExtendWithFaceDetection(),this.input)}};function _a(o,t=new Z){return new _r(o,t)}function wr(o,t=new Z){return new He(o,t)}async function dn(o,t){return wr(o,new Z(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function wa(o,t={}){return wr(o,new lt(t)).withFaceLandmarks().withFaceDescriptors()}var Da=dn;function uo(o,t){if(o.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let e=Array.from(o),r=Array.from(t);return Math.sqrt(e.map((n,a)=>n-r[a]).reduce((n,a)=>n+a**2,0))}var Dr=class{constructor(t,e=.6){this._distanceThreshold=e;let r=Array.isArray(t)?t:[t];if(!r.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let n=1,a=()=>`person ${n++}`;this._labeledDescriptors=r.map(s=>{if(s instanceof xt)return s;if(s instanceof Float32Array)return new xt(a(),[s]);if(s.descriptor&&s.descriptor instanceof Float32Array)return new xt(a(),[s.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,e){return e.map(r=>uo(r,t)).reduce((r,n)=>r+n,0)/(e.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:e,label:r})=>new Ee(r,this.computeMeanDistance(t,e))).reduce((e,r)=>e.distancet.toJSON())}}static fromJSON(t){let e=t.labeledDescriptors.map(r=>xt.fromJSON(r));return new Dr(e,t.distanceThreshold)}};function Ea(o){let t=new Fe;return t.extractWeights(o),t}function un(o,t){let{width:e,height:r}=new A(t.width,t.height);if(e<=0||r<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:e,height:r})}`);if(Array.isArray(o))return o.map(n=>un(n,{width:e,height:r}));if(zt(o)){let n=o.detection.forSize(e,r),a=o.unshiftedLandmarks.forSize(n.box.width,n.box.height);return le($t(o,n),a)}return pt(o)?$t(o,o.detection.forSize(e,r)):o instanceof V||o instanceof M?o.forSize(e,r):o}var Ca=typeof process!="undefined",Na=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Ia={faceapi:Co,node:Ca,browser:Na}; //# sourceMappingURL=face-api.node-gpu.js.map diff --git a/dist/face-api.node-gpu.js.map b/dist/face-api.node-gpu.js.map index b0014fc..bd09b4a 100644 --- a/dist/face-api.node-gpu.js.map +++ b/dist/face-api.node-gpu.js.map @@ -1,7 +1,7 @@ { "version": 3, "sources": ["../src/tfjs/tf-node-gpu.ts", "../src/env/isNodejs.ts", "../src/index.ts", "../src/draw/index.ts", "../src/draw/drawContour.ts", "../src/utils/index.ts", "../src/classes/Dimensions.ts", "../src/classes/Point.ts", "../src/classes/Box.ts", "../src/classes/BoundingBox.ts", "../src/classes/ObjectDetection.ts", "../src/classes/FaceDetection.ts", "../src/ops/iou.ts", "../src/ops/minBbox.ts", "../src/ops/nonMaxSuppression.ts", "../src/ops/normalize.ts", "../src/ops/padToSquare.ts", "../src/ops/shuffleArray.ts", "../src/ops/index.ts", "../src/classes/Rect.ts", "../src/classes/FaceLandmarks.ts", "../src/classes/FaceLandmarks5.ts", "../src/classes/FaceLandmarks68.ts", "../src/classes/FaceMatch.ts", "../src/classes/LabeledBox.ts", "../src/classes/LabeledFaceDescriptors.ts", "../src/classes/PredictedBox.ts", "../src/factories/WithFaceDetection.ts", "../src/env/createBrowserEnv.ts", "../src/env/createFileSystem.ts", "../src/env/createNodejsEnv.ts", "../src/env/isBrowser.ts", "../src/env/index.ts", "../src/dom/resolveInput.ts", "../src/dom/getContext2dOrThrow.ts", "../src/draw/DrawTextField.ts", "../src/draw/DrawBox.ts", "../src/draw/drawDetections.ts", "../src/faceExpressionNet/FaceExpressionNet.ts", "../src/dom/isMediaLoaded.ts", "../src/dom/awaitMediaLoaded.ts", "../src/dom/bufferToImage.ts", "../src/dom/getMediaDimensions.ts", "../src/dom/createCanvas.ts", "../src/dom/imageTensorToCanvas.ts", "../src/dom/isMediaElement.ts", "../src/dom/NetInput.ts", "../src/dom/imageToSquare.ts", "../src/dom/toNetInput.ts", "../src/dom/extractFaces.ts", "../src/dom/extractFaceTensors.ts", "../src/dom/fetchOrThrow.ts", "../src/dom/fetchImage.ts", "../src/dom/fetchJson.ts", "../src/dom/fetchNetWeights.ts", "../src/dom/loadWeightMap.ts", "../src/common/getModelUris.ts", "../src/dom/matchDimensions.ts", "../src/faceFeatureExtractor/FaceFeatureExtractor.ts", "../src/NeuralNetwork.ts", "../src/faceFeatureExtractor/denseBlock.ts", "../src/common/depthwiseSeparableConv.ts", "../src/common/convLayer.ts", "../src/common/disposeUnusedWeightTensors.ts", "../src/common/extractConvParamsFactory.ts", "../src/common/extractFCParamsFactory.ts", "../src/common/extractSeparableConvParamsFactory.ts", "../src/common/types.ts", "../src/common/extractWeightEntryFactory.ts", "../src/common/extractWeightsFactory.ts", "../src/faceFeatureExtractor/extractorsFactory.ts", "../src/faceFeatureExtractor/extractParams.ts", "../src/common/loadConvParamsFactory.ts", "../src/faceFeatureExtractor/loadParamsFactory.ts", "../src/faceFeatureExtractor/extractParamsFromWeightMap.ts", "../src/faceProcessor/FaceProcessor.ts", "../src/common/fullyConnectedLayer.ts", "../src/faceProcessor/extractParams.ts", "../src/faceProcessor/extractParamsFromWeightMap.ts", "../src/faceProcessor/util.ts", "../src/faceExpressionNet/FaceExpressions.ts", "../src/factories/WithFaceExpressions.ts", "../src/draw/drawFaceExpressions.ts", "../src/factories/WithFaceLandmarks.ts", "../src/draw/DrawFaceLandmarks.ts", "../src/ageGenderNet/AgeGenderNet.ts", "../src/xception/TinyXception.ts", "../src/xception/extractParams.ts", "../src/xception/extractParamsFromWeightMap.ts", "../src/ageGenderNet/extractParams.ts", "../src/ageGenderNet/extractParamsFromWeightMap.ts", "../src/ageGenderNet/types.ts", "../src/faceLandmarkNet/FaceLandmark68NetBase.ts", "../src/faceLandmarkNet/FaceLandmark68Net.ts", "../src/faceFeatureExtractor/TinyFaceFeatureExtractor.ts", "../src/faceFeatureExtractor/extractParamsFromWeightMapTiny.ts", "../src/faceFeatureExtractor/extractParamsTiny.ts", "../src/faceLandmarkNet/FaceLandmark68TinyNet.ts", "../src/faceLandmarkNet/index.ts", "../src/faceRecognitionNet/FaceRecognitionNet.ts", "../src/faceRecognitionNet/convLayer.ts", "../src/faceRecognitionNet/scaleLayer.ts", "../src/faceRecognitionNet/extractParams.ts", "../src/faceRecognitionNet/extractParamsFromWeightMap.ts", "../src/faceRecognitionNet/residualLayer.ts", "../src/faceRecognitionNet/index.ts", "../src/factories/WithFaceDescriptor.ts", "../src/factories/WithAge.ts", "../src/factories/WithGender.ts", "../src/ssdMobilenetv1/SsdMobilenetv1.ts", "../src/ssdMobilenetv1/extractParams.ts", "../src/ssdMobilenetv1/extractParamsFromWeightMap.ts", "../src/ssdMobilenetv1/mobileNetV1.ts", "../src/ssdMobilenetv1/pointwiseConvLayer.ts", "../src/ssdMobilenetv1/nonMaxSuppression.ts", "../src/ssdMobilenetv1/outputLayer.ts", "../src/ssdMobilenetv1/predictionLayer.ts", "../src/ssdMobilenetv1/boxPredictionLayer.ts", "../src/ssdMobilenetv1/SsdMobilenetv1Options.ts", "../src/ssdMobilenetv1/index.ts", "../src/tinyYolov2/const.ts", "../src/tinyYolov2/TinyYolov2Base.ts", "../src/tinyYolov2/config.ts", "../src/tinyYolov2/convWithBatchNorm.ts", "../src/tinyYolov2/leaky.ts", "../src/tinyYolov2/depthwiseSeparableConv.ts", "../src/tinyYolov2/extractParams.ts", "../src/tinyYolov2/extractParamsFromWeightMap.ts", "../src/tinyYolov2/TinyYolov2Options.ts", "../src/tinyYolov2/TinyYolov2.ts", "../src/tinyYolov2/index.ts", "../src/tinyFaceDetector/TinyFaceDetectorOptions.ts", "../src/globalApi/ComposableTask.ts", "../src/globalApi/DetectFaceLandmarksTasks.ts", "../src/globalApi/extractFacesAndComputeResults.ts", "../src/tinyFaceDetector/const.ts", "../src/tinyFaceDetector/TinyFaceDetector.ts", "../src/globalApi/nets.ts", "../src/globalApi/PredictFaceExpressionsTask.ts", "../src/globalApi/PredictAgeAndGenderTask.ts", "../src/globalApi/ComputeFaceDescriptorsTasks.ts", "../src/globalApi/DetectFacesTasks.ts", "../src/globalApi/detectFaces.ts", "../src/globalApi/allFaces.ts", "../src/euclideanDistance.ts", "../src/globalApi/FaceMatcher.ts", "../src/tinyFaceDetector/index.ts", "../src/resizeResults.ts"], - "sourcesContent": ["/* eslint-disable import/no-extraneous-dependencies */\n/* eslint-disable node/no-unpublished-import */\n\nexport * from '@tensorflow/tfjs-node-gpu';\n", "export function isNodejs(): boolean {\n return typeof global === 'object'\n && typeof require === 'function'\n && typeof module !== 'undefined'\n // issues with gatsby.js: module.exports is undefined\n // && !!module.exports\n && typeof process !== 'undefined' && !!process.version;\n}\n", "import * as tf from '../dist/tfjs.esm';\nimport * as draw from './draw/index';\nimport * as utils from './utils/index';\nimport * as pkg from '../package.json';\n\nexport { tf, draw, utils };\n\nexport * from './ageGenderNet/index';\nexport * from './classes/index';\nexport * from './dom/index';\nexport * from './env/index';\nexport * from './faceExpressionNet/index';\nexport * from './faceLandmarkNet/index';\nexport * from './faceRecognitionNet/index';\nexport * from './factories/index';\nexport * from './globalApi/index';\nexport * from './ops/index';\nexport * from './ssdMobilenetv1/index';\nexport * from './tinyFaceDetector/index';\nexport * from './tinyYolov2/index';\nexport * from './euclideanDistance';\nexport * from './NeuralNetwork';\nexport * from './resizeResults';\n\nconst node = (typeof process !== 'undefined');\n// eslint-disable-next-line no-undef\nconst browser = (typeof navigator !== 'undefined') && (typeof navigator.userAgent !== 'undefined');\nexport const version = { faceapi: pkg.version as string, node, browser };\n", "export * from './drawContour';\nexport * from './drawDetections';\nexport * from './drawFaceExpressions';\nexport * from './DrawBox';\nexport * from './DrawFaceLandmarks';\nexport * from './DrawTextField';\n", "import { Point } from '../classes/index';\n\nexport function drawContour(\n ctx: CanvasRenderingContext2D,\n points: Point[],\n isClosed: boolean = false,\n) {\n ctx.beginPath();\n\n points.slice(1).forEach(({ x, y }, prevIdx) => {\n const from = points[prevIdx];\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(x, y);\n });\n\n if (isClosed) {\n const from = points[points.length - 1];\n const to = points[0];\n if (!from || !to) {\n return;\n }\n\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(to.x, to.y);\n }\n\n ctx.stroke();\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Point } from '../classes/index';\nimport { Dimensions, IDimensions } from '../classes/Dimensions';\n\nexport function isTensor(tensor: any, dim: number) {\n return tensor instanceof tf.Tensor && tensor.shape.length === dim;\n}\n\nexport function isTensor1D(tensor: any): tensor is tf.Tensor1D {\n return isTensor(tensor, 1);\n}\n\nexport function isTensor2D(tensor: any): tensor is tf.Tensor2D {\n return isTensor(tensor, 2);\n}\n\nexport function isTensor3D(tensor: any): tensor is tf.Tensor3D {\n return isTensor(tensor, 3);\n}\n\nexport function isTensor4D(tensor: any): tensor is tf.Tensor4D {\n return isTensor(tensor, 4);\n}\n\nexport function isFloat(num: number) {\n return num % 1 !== 0;\n}\n\nexport function isEven(num: number) {\n return num % 2 === 0;\n}\n\nexport function round(num: number, prec: number = 2) {\n const f = 10 ** prec;\n return Math.floor(num * f) / f;\n}\n\nexport function isDimensions(obj: any): boolean {\n return obj && obj.width && obj.height;\n}\n\nexport function computeReshapedDimensions({ width, height }: IDimensions, inputSize: number) {\n const scale = inputSize / Math.max(height, width);\n return new Dimensions(Math.round(width * scale), Math.round(height * scale));\n}\n\nexport function getCenterPoint(pts: Point[]): Point {\n return pts.reduce((sum, pt) => sum.add(pt), new Point(0, 0))\n .div(new Point(pts.length, pts.length));\n}\n\nexport function range(num: number, start: number, step: number): number[] {\n return Array(num).fill(0).map((_, i) => start + (i * step));\n}\n\nexport function isValidNumber(num: any) {\n // eslint-disable-next-line no-mixed-operators\n return !!num && (num !== Infinity) && (num !== -Infinity) && !Number.isNaN(num) || num === 0;\n}\n\nexport function isValidProbablitiy(num: any) {\n return isValidNumber(num) && num >= 0 && num <= 1.0;\n}\n", "import { isValidNumber } from '../utils/index';\n\nexport interface IDimensions {\n width: number\n height: number\n}\n\nexport class Dimensions implements IDimensions {\n private _width: number\n\n private _height: number\n\n constructor(width: number, height: number) {\n if (!isValidNumber(width) || !isValidNumber(height)) {\n throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({ width, height })}`);\n }\n\n this._width = width;\n this._height = height;\n }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public reverse(): Dimensions {\n return new Dimensions(1 / this.width, 1 / this.height);\n }\n}\n", "export interface IPoint {\n x: number\n y: number\n}\n\nexport class Point implements IPoint {\n private _x: number\n\n private _y: number\n\n constructor(x: number, y: number) {\n this._x = x;\n this._y = y;\n }\n\n get x(): number { return this._x; }\n\n get y(): number { return this._y; }\n\n public add(pt: IPoint): Point {\n return new Point(this.x + pt.x, this.y + pt.y);\n }\n\n public sub(pt: IPoint): Point {\n return new Point(this.x - pt.x, this.y - pt.y);\n }\n\n public mul(pt: IPoint): Point {\n return new Point(this.x * pt.x, this.y * pt.y);\n }\n\n public div(pt: IPoint): Point {\n return new Point(this.x / pt.x, this.y / pt.y);\n }\n\n public abs(): Point {\n return new Point(Math.abs(this.x), Math.abs(this.y));\n }\n\n public magnitude(): number {\n return Math.sqrt((this.x ** 2) + (this.y ** 2));\n }\n\n public floor(): Point {\n return new Point(Math.floor(this.x), Math.floor(this.y));\n }\n}\n", "import { isDimensions, isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { IDimensions } from './Dimensions';\nimport { Point } from './Point';\nimport { IRect } from './Rect';\n\nexport class Box implements IBoundingBox, IRect {\n public static isRect(rect: any): boolean {\n return !!rect && [rect.x, rect.y, rect.width, rect.height].every(isValidNumber);\n }\n\n public static assertIsValidBox(box: any, callee: string, allowNegativeDimensions: boolean = false) {\n if (!Box.isRect(box)) {\n throw new Error(`${callee} - invalid box: ${JSON.stringify(box)}, expected object with properties x, y, width, height`);\n }\n\n if (!allowNegativeDimensions && (box.width < 0 || box.height < 0)) {\n throw new Error(`${callee} - width (${box.width}) and height (${box.height}) must be positive numbers`);\n }\n }\n\n private _x: number\n\n private _y: number\n\n private _width: number\n\n private _height: number\n\n constructor(_box: IBoundingBox | IRect, allowNegativeDimensions: boolean = true) {\n const box = (_box || {}) as any;\n\n const isBbox = [box.left, box.top, box.right, box.bottom].every(isValidNumber);\n const isRect = [box.x, box.y, box.width, box.height].every(isValidNumber);\n\n if (!isRect && !isBbox) {\n throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(box)}`);\n }\n\n const [x, y, width, height] = isRect\n ? [box.x, box.y, box.width, box.height]\n : [box.left, box.top, box.right - box.left, box.bottom - box.top];\n\n Box.assertIsValidBox({\n x, y, width, height,\n }, 'Box.constructor', allowNegativeDimensions);\n\n this._x = x;\n this._y = y;\n this._width = width;\n this._height = height;\n }\n\n public get x(): number { return this._x; }\n\n public get y(): number { return this._y; }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public get left(): number { return this.x; }\n\n public get top(): number { return this.y; }\n\n public get right(): number { return this.x + this.width; }\n\n public get bottom(): number { return this.y + this.height; }\n\n public get area(): number { return this.width * this.height; }\n\n public get topLeft(): Point { return new Point(this.left, this.top); }\n\n public get topRight(): Point { return new Point(this.right, this.top); }\n\n public get bottomLeft(): Point { return new Point(this.left, this.bottom); }\n\n public get bottomRight(): Point { return new Point(this.right, this.bottom); }\n\n public round(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.round(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public floor(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.floor(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public toSquare(): Box {\n let {\n x, y, width, height,\n } = this;\n const diff = Math.abs(width - height);\n if (width < height) {\n x -= (diff / 2);\n width += diff;\n }\n if (height < width) {\n y -= (diff / 2);\n height += diff;\n }\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public rescale(s: IDimensions | number): Box {\n const scaleX = isDimensions(s) ? (s as IDimensions).width : s as number;\n const scaleY = isDimensions(s) ? (s as IDimensions).height : s as number;\n return new Box({\n x: this.x * scaleX,\n y: this.y * scaleY,\n width: this.width * scaleX,\n height: this.height * scaleY,\n });\n }\n\n public pad(padX: number, padY: number): Box {\n const [x, y, width, height] = [\n this.x - (padX / 2),\n this.y - (padY / 2),\n this.width + padX,\n this.height + padY,\n ];\n return new Box({\n x, y, width, height,\n });\n }\n\n public clipAtImageBorders(imgWidth: number, imgHeight: number): Box {\n const {\n x, y, right, bottom,\n } = this;\n const clippedX = Math.max(x, 0);\n const clippedY = Math.max(y, 0);\n\n const newWidth = right - clippedX;\n const newHeight = bottom - clippedY;\n const clippedWidth = Math.min(newWidth, imgWidth - clippedX);\n const clippedHeight = Math.min(newHeight, imgHeight - clippedY);\n\n return (new Box({\n x: clippedX, y: clippedY, width: clippedWidth, height: clippedHeight,\n })).floor();\n }\n\n public shift(sx: number, sy: number): Box {\n const { width, height } = this;\n const x = this.x + sx;\n const y = this.y + sy;\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public padAtBorders(imageHeight: number, imageWidth: number) {\n const w = this.width + 1;\n const h = this.height + 1;\n\n const dx = 1;\n const dy = 1;\n let edx = w;\n let edy = h;\n\n let x = this.left;\n let y = this.top;\n let ex = this.right;\n let ey = this.bottom;\n\n if (ex > imageWidth) {\n edx = -ex + imageWidth + w;\n ex = imageWidth;\n }\n if (ey > imageHeight) {\n edy = -ey + imageHeight + h;\n ey = imageHeight;\n }\n if (x < 1) {\n edy = 2 - x;\n x = 1;\n }\n if (y < 1) {\n edy = 2 - y;\n y = 1;\n }\n\n return {\n dy, edy, dx, edx, y, ey, x, ex, w, h,\n };\n }\n\n public calibrate(region: Box) {\n return new Box({\n left: this.left + (region.left * this.width),\n top: this.top + (region.top * this.height),\n right: this.right + (region.right * this.width),\n bottom: this.bottom + (region.bottom * this.height),\n }).toSquare().round();\n }\n}\n", "import { Box } from './Box';\n\nexport interface IBoundingBox {\n left: number\n top: number\n right: number\n bottom: number\n}\n\nexport class BoundingBox extends Box implements IBoundingBox {\n constructor(left: number, top: number, right: number, bottom: number, allowNegativeDimensions: boolean = false) {\n super({\n left, top, right, bottom,\n }, allowNegativeDimensions);\n }\n}\n", "import { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { IRect, Rect } from './Rect';\n\nexport class ObjectDetection {\n private _score: number\n\n private _classScore: number\n\n private _className: string\n\n private _box: Rect\n\n private _imageDims: Dimensions\n\n constructor(\n score: number,\n classScore: number,\n className: string,\n relativeBox: IRect,\n imageDims: IDimensions,\n ) {\n this._imageDims = new Dimensions(imageDims.width, imageDims.height);\n this._score = score;\n this._classScore = classScore;\n this._className = className;\n this._box = new Box(relativeBox).rescale(this._imageDims);\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n\n public get className(): string { return this._className; }\n\n public get box(): Box { return this._box; }\n\n public get imageDims(): Dimensions { return this._imageDims; }\n\n public get imageWidth(): number { return this.imageDims.width; }\n\n public get imageHeight(): number { return this.imageDims.height; }\n\n public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()); }\n\n public forSize(width: number, height: number): ObjectDetection {\n return new ObjectDetection(\n this.score,\n this.classScore,\n this.className,\n this.relativeBox,\n { width, height },\n );\n }\n}\n", "import { Box } from './Box';\nimport { IDimensions } from './Dimensions';\nimport { ObjectDetection } from './ObjectDetection';\nimport { Rect } from './Rect';\n\nexport interface IFaceDetecion {\n score: number\n box: Box\n}\n\nexport class FaceDetection extends ObjectDetection implements IFaceDetecion {\n constructor(\n score: number,\n relativeBox: Rect,\n imageDims: IDimensions,\n ) {\n super(score, score, '', relativeBox, imageDims);\n }\n\n public forSize(width: number, height: number): FaceDetection {\n const { score, relativeBox, imageDims } = super.forSize(width, height);\n return new FaceDetection(score, relativeBox, imageDims);\n }\n}\n", "import { Box } from '../classes/Box';\n\nexport function iou(box1: Box, box2: Box, isIOU: boolean = true) {\n const width = Math.max(0.0, Math.min(box1.right, box2.right) - Math.max(box1.left, box2.left));\n const height = Math.max(0.0, Math.min(box1.bottom, box2.bottom) - Math.max(box1.top, box2.top));\n const interSection = width * height;\n\n return isIOU\n ? interSection / (box1.area + box2.area - interSection)\n : interSection / Math.min(box1.area, box2.area);\n}\n", "import { BoundingBox, IPoint } from '../classes/index';\n\nexport function minBbox(pts: IPoint[]): BoundingBox {\n const xs = pts.map((pt) => pt.x);\n const ys = pts.map((pt) => pt.y);\n const minX = xs.reduce((min, x) => (x < min ? x : min), Infinity);\n const minY = ys.reduce((min, y) => (y < min ? y : min), Infinity);\n const maxX = xs.reduce((max, x) => (max < x ? x : max), 0);\n const maxY = ys.reduce((max, y) => (max < y ? y : max), 0);\n\n return new BoundingBox(minX, minY, maxX, maxY);\n}\n", "import { Box } from '../classes/Box';\nimport { iou } from './iou';\n\nexport function nonMaxSuppression(\n boxes: Box[],\n scores: number[],\n iouThreshold: number,\n isIOU: boolean = true,\n): number[] {\n let indicesSortedByScore = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .sort((c1, c2) => c1.score - c2.score)\n .map((c) => c.boxIndex);\n\n const pick: number[] = [];\n\n while (indicesSortedByScore.length > 0) {\n const curr = indicesSortedByScore.pop() as number;\n pick.push(curr);\n\n const indices = indicesSortedByScore;\n\n const outputs: number[] = [];\n for (let i = 0; i < indices.length; i++) {\n const idx = indices[i];\n\n const currBox = boxes[curr];\n const idxBox = boxes[idx];\n\n outputs.push(iou(currBox, idxBox, isIOU));\n }\n\n indicesSortedByScore = indicesSortedByScore.filter(\n (_, j) => outputs[j] <= iouThreshold,\n );\n }\n\n return pick;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function normalize(x: tf.Tensor4D, meanRgb: number[]): tf.Tensor4D {\n return tf.tidy(() => {\n const [r, g, b] = meanRgb;\n const avg_r = tf.fill([...x.shape.slice(0, 3), 1], r, 'float32');\n const avg_g = tf.fill([...x.shape.slice(0, 3), 1], g, 'float32');\n const avg_b = tf.fill([...x.shape.slice(0, 3), 1], b, 'float32');\n const avg_rgb = tf.concat([avg_r, avg_g, avg_b], 3);\n\n return tf.sub(x, avg_rgb);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n/**\n * Pads the smaller dimension of an image tensor with zeros, such that width === height.\n *\n * @param imgTensor The image tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The padded tensor with width === height.\n */\nexport function padToSquare(\n imgTensor: tf.Tensor4D,\n isCenterImage: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const [height, width] = imgTensor.shape.slice(1);\n if (height === width) {\n return imgTensor;\n }\n\n const dimDiff = Math.abs(height - width);\n const paddingAmount = Math.round(dimDiff * (isCenterImage ? 0.5 : 1));\n const paddingAxis = height > width ? 2 : 1;\n\n const createPaddingTensor = (paddingAmountLocal: number): tf.Tensor => {\n const paddingTensorShape = imgTensor.shape.slice();\n paddingTensorShape[paddingAxis] = paddingAmountLocal;\n return tf.fill(paddingTensorShape, 0, 'float32');\n };\n\n const paddingTensorAppend = createPaddingTensor(paddingAmount);\n const remainingPaddingAmount = dimDiff - (paddingTensorAppend.shape[paddingAxis] as number);\n\n const paddingTensorPrepend = isCenterImage && remainingPaddingAmount\n ? createPaddingTensor(remainingPaddingAmount)\n : null;\n\n const tensorsToStack = [\n paddingTensorPrepend,\n imgTensor,\n paddingTensorAppend,\n ]\n .filter((t) => !!t)\n // .map((t: tf.Tensor) => t.toFloat()) as tf.Tensor4D[]\n .map((t: tf.Tensor) => tf.cast(t, 'float32')) as tf.Tensor4D[];\n return tf.concat(tensorsToStack, paddingAxis);\n });\n}\n", "export function shuffleArray(inputArray: any[]) {\n const array = inputArray.slice();\n for (let i = array.length - 1; i > 0; i--) {\n const j = Math.floor(Math.random() * (i + 1));\n const x = array[i];\n array[i] = array[j];\n array[j] = x;\n }\n return array;\n}\n", "export * from './iou';\nexport * from './minBbox';\nexport * from './nonMaxSuppression';\nexport * from './normalize';\nexport * from './padToSquare';\nexport * from './shuffleArray';\n\nexport function sigmoid(x: number) {\n return 1 / (1 + Math.exp(-x));\n}\n\nexport function inverseSigmoid(x: number) {\n return Math.log(x / (1 - x));\n}\n", "import { Box } from './Box';\n\nexport interface IRect {\n x: number\n y: number\n width: number\n height: number\n}\n\nexport class Rect extends Box implements IRect {\n constructor(x: number, y: number, width: number, height: number, allowNegativeDimensions: boolean = false) {\n super({\n x, y, width, height,\n }, allowNegativeDimensions);\n }\n}\n", "import { minBbox } from '../ops/index';\nimport { getCenterPoint } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { FaceDetection } from './FaceDetection';\nimport { Point } from './Point';\nimport { IRect, Rect } from './Rect';\n\n// face alignment constants\nconst relX = 0.5;\nconst relY = 0.43;\nconst relScale = 0.45;\n\nexport interface IFaceLandmarks {\n positions: Point[]\n shift: Point\n}\n\nexport class FaceLandmarks implements IFaceLandmarks {\n protected _shift: Point\n\n protected _positions: Point[]\n\n protected _imgDims: Dimensions\n\n constructor(\n relativeFaceLandmarkPositions: Point[],\n imgDims: IDimensions,\n shift: Point = new Point(0, 0),\n ) {\n const { width, height } = imgDims;\n this._imgDims = new Dimensions(width, height);\n this._shift = shift;\n this._positions = relativeFaceLandmarkPositions.map(\n (pt) => pt.mul(new Point(width, height)).add(shift),\n );\n }\n\n public get shift(): Point { return new Point(this._shift.x, this._shift.y); }\n\n public get imageWidth(): number { return this._imgDims.width; }\n\n public get imageHeight(): number { return this._imgDims.height; }\n\n public get positions(): Point[] { return this._positions; }\n\n public get relativePositions(): Point[] {\n return this._positions.map(\n (pt) => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight)),\n );\n }\n\n public forSize(width: number, height: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n { width, height },\n );\n }\n\n public shiftBy(x: number, y: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n this._imgDims,\n new Point(x, y),\n );\n }\n\n public shiftByPoint(pt: Point): T {\n return this.shiftBy(pt.x, pt.y);\n }\n\n /**\n * Aligns the face landmarks after face detection from the relative positions of the faces\n * bounding box, or it's current shift. This function should be used to align the face images\n * after face detection has been performed, before they are passed to the face recognition net.\n * This will make the computed face descriptor more accurate.\n *\n * @param detection (optional) The bounding box of the face or the face detection result. If\n * no argument was passed the position of the face landmarks are assumed to be relative to\n * it's current shift.\n * @returns The bounding box of the aligned face.\n */\n public align(\n detection?: FaceDetection | IRect | IBoundingBox | null,\n options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { },\n ): Box {\n if (detection) {\n const box = detection instanceof FaceDetection\n ? detection.box.floor()\n : new Box(detection);\n\n return this.shiftBy(box.x, box.y).align(null, options);\n }\n\n const { useDlibAlignment, minBoxPadding } = { useDlibAlignment: false, minBoxPadding: 0.2, ...options };\n\n if (useDlibAlignment) {\n return this.alignDlib();\n }\n\n return this.alignMinBbox(minBoxPadding);\n }\n\n private alignDlib(): Box {\n const centers = this.getRefPointsForAlignment();\n\n const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers;\n const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude();\n const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;\n\n const size = Math.floor(eyeToMouthDist / relScale);\n\n const refPoint = getCenterPoint(centers);\n // TODO: pad in case rectangle is out of image bounds\n const x = Math.floor(Math.max(0, refPoint.x - (relX * size)));\n const y = Math.floor(Math.max(0, refPoint.y - (relY * size)));\n\n return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y));\n }\n\n private alignMinBbox(padding: number): Box {\n const box = minBbox(this.positions);\n return box.pad(box.width * padding, box.height * padding);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n throw new Error('getRefPointsForAlignment not implemented by base class');\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks5 extends FaceLandmarks {\n protected getRefPointsForAlignment(): Point[] {\n const pts = this.positions;\n return [\n pts[0],\n pts[1],\n getCenterPoint([pts[3], pts[4]]),\n ];\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks68 extends FaceLandmarks {\n public getJawOutline(): Point[] {\n return this.positions.slice(0, 17);\n }\n\n public getLeftEyeBrow(): Point[] {\n return this.positions.slice(17, 22);\n }\n\n public getRightEyeBrow(): Point[] {\n return this.positions.slice(22, 27);\n }\n\n public getNose(): Point[] {\n return this.positions.slice(27, 36);\n }\n\n public getLeftEye(): Point[] {\n return this.positions.slice(36, 42);\n }\n\n public getRightEye(): Point[] {\n return this.positions.slice(42, 48);\n }\n\n public getMouth(): Point[] {\n return this.positions.slice(48, 68);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n return [\n this.getLeftEye(),\n this.getRightEye(),\n this.getMouth(),\n ].map(getCenterPoint);\n }\n}\n", "import { round } from '../utils/index';\n\nexport interface IFaceMatch {\n label: string\n distance: number\n}\n\nexport class FaceMatch implements IFaceMatch {\n private _label: string\n\n private _distance: number\n\n constructor(label: string, distance: number) {\n this._label = label;\n this._distance = distance;\n }\n\n public get label(): string { return this._label; }\n\n public get distance(): number { return this._distance; }\n\n public toString(withDistance: boolean = true): string {\n return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`;\n }\n}\n", "import { isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { IRect } from './Rect';\n\nexport class LabeledBox extends Box {\n public static assertIsValidLabeledBox(box: any, callee: string) {\n Box.assertIsValidBox(box, callee);\n\n if (!isValidNumber(box.label)) {\n throw new Error(`${callee} - expected property label (${box.label}) to be a number`);\n }\n }\n\n private _label: number\n\n constructor(box: IBoundingBox | IRect | any, label: number) {\n super(box);\n this._label = label;\n }\n\n public get label(): number { return this._label; }\n}\n", "export class LabeledFaceDescriptors {\n private _label: string\n\n private _descriptors: Float32Array[]\n\n constructor(label: string, descriptors: Float32Array[]) {\n if (!(typeof label === 'string')) {\n throw new Error('LabeledFaceDescriptors - constructor expected label to be a string');\n }\n\n if (!Array.isArray(descriptors) || descriptors.some((desc) => !(desc instanceof Float32Array))) {\n throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array');\n }\n\n this._label = label;\n this._descriptors = descriptors;\n }\n\n public get label(): string { return this._label; }\n\n public get descriptors(): Float32Array[] { return this._descriptors; }\n\n public toJSON(): any {\n return {\n label: this.label,\n descriptors: this.descriptors.map((d) => Array.from(d)),\n };\n }\n\n public static fromJSON(json: any): LabeledFaceDescriptors {\n const descriptors = json.descriptors.map((d: any) => new Float32Array(d));\n return new LabeledFaceDescriptors(json.label, descriptors);\n }\n}\n", "import { isValidProbablitiy } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { LabeledBox } from './LabeledBox';\nimport { IRect } from './Rect';\n\nexport class PredictedBox extends LabeledBox {\n public static assertIsValidPredictedBox(box: any, callee: string) {\n LabeledBox.assertIsValidLabeledBox(box, callee);\n\n if (\n !isValidProbablitiy(box.score)\n || !isValidProbablitiy(box.classScore)\n ) {\n throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`);\n }\n }\n\n private _score: number\n\n private _classScore: number\n\n constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {\n super(box, label);\n this._score = score;\n this._classScore = classScore;\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\n\nexport type WithFaceDetection = TSource & {\n detection: FaceDetection\n}\n\nexport function isWithFaceDetection(obj: any): obj is WithFaceDetection<{}> {\n return obj.detection instanceof FaceDetection;\n}\n\nexport function extendWithFaceDetection<\n TSource\n>(\n sourceObj: TSource,\n detection: FaceDetection,\n): WithFaceDetection {\n const extension = { detection };\n return { ...sourceObj, ...extension };\n}\n", "import { Environment } from './types';\n\nexport function createBrowserEnv(): Environment {\n const fetch = window.fetch;\n if (!fetch) throw new Error('fetch - missing fetch implementation for browser environment');\n\n const readFile = () => {\n throw new Error('readFile - filesystem not available for browser environment');\n };\n\n return {\n Canvas: HTMLCanvasElement,\n CanvasRenderingContext2D,\n Image: HTMLImageElement,\n ImageData,\n Video: HTMLVideoElement,\n createCanvasElement: () => document.createElement('canvas'),\n createImageElement: () => document.createElement('img'),\n fetch,\n readFile,\n };\n}\n", "import { FileSystem } from './types';\n\nexport function createFileSystem(fs?: any): FileSystem {\n let requireFsError = '';\n\n if (!fs) {\n try {\n // eslint-disable-next-line global-require\n fs = require('fs');\n } catch (err) {\n requireFsError = err.toString();\n }\n }\n\n const readFile = fs\n ? (filePath: string) => new Promise((resolve, reject) => {\n fs.readFile(filePath, (err: any, buffer: Buffer) => (err ? reject(err) : resolve(buffer)));\n })\n : () => {\n throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`);\n };\n\n return {\n readFile,\n };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { createFileSystem } from './createFileSystem';\nimport { Environment } from './types';\n\nexport function createNodejsEnv(): Environment {\n // eslint-disable-next-line dot-notation\n const Canvas = global['Canvas'] || global.HTMLCanvasElement;\n const Image = global.Image || global.HTMLImageElement;\n\n const createCanvasElement = () => {\n if (Canvas) return new Canvas();\n throw new Error('createCanvasElement - missing Canvas implementation for nodejs environment');\n };\n\n const createImageElement = () => {\n if (Image) return new Image();\n throw new Error('createImageElement - missing Image implementation for nodejs environment');\n };\n\n const fetch = global.fetch;\n // if (!fetch) throw new Error('fetch - missing fetch implementation for nodejs environment');\n\n const fileSystem = createFileSystem();\n\n return {\n Canvas: Canvas || class {},\n CanvasRenderingContext2D: global.CanvasRenderingContext2D || class {},\n Image: Image || class {},\n ImageData: global.ImageData || class {},\n Video: global.HTMLVideoElement || class {},\n createCanvasElement,\n createImageElement,\n fetch,\n ...fileSystem,\n };\n}\n", "export function isBrowser(): boolean {\n return typeof window === 'object'\n && typeof document !== 'undefined'\n && typeof HTMLImageElement !== 'undefined'\n && typeof HTMLCanvasElement !== 'undefined'\n && typeof HTMLVideoElement !== 'undefined'\n && typeof ImageData !== 'undefined'\n && typeof CanvasRenderingContext2D !== 'undefined';\n}\n", "import { createBrowserEnv } from './createBrowserEnv';\nimport { createFileSystem } from './createFileSystem';\nimport { createNodejsEnv } from './createNodejsEnv';\nimport { isBrowser } from './isBrowser';\nimport { isNodejs } from './isNodejs';\nimport { Environment } from './types';\n\nlet environment: Environment | null;\n\nfunction getEnv(): Environment {\n if (!environment) {\n throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()');\n }\n return environment;\n}\n\nfunction setEnv(env: Environment) {\n environment = env;\n}\n\nfunction initialize() {\n // check for isBrowser() first to prevent electron renderer process\n // to be initialized with wrong environment due to isNodejs() returning true\n if (isBrowser()) return setEnv(createBrowserEnv());\n if (isNodejs()) return setEnv(createNodejsEnv());\n return null;\n}\n\nfunction monkeyPatch(env: Partial) {\n if (!environment) {\n initialize();\n }\n\n if (!environment) {\n throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()');\n }\n\n const { Canvas = environment.Canvas, Image = environment.Image } = env;\n environment.Canvas = Canvas;\n environment.Image = Image;\n environment.createCanvasElement = env.createCanvasElement || (() => new Canvas());\n environment.createImageElement = env.createImageElement || (() => new Image());\n\n environment.ImageData = env.ImageData || environment.ImageData;\n environment.Video = env.Video || environment.Video;\n environment.fetch = env.fetch || environment.fetch;\n environment.readFile = env.readFile || environment.readFile;\n}\n\nexport const env = {\n getEnv,\n setEnv,\n initialize,\n createBrowserEnv,\n createFileSystem,\n createNodejsEnv,\n monkeyPatch,\n isBrowser,\n isNodejs,\n};\n\ninitialize();\n\nexport * from './types';\n", "import { env } from '../env/index';\n\nexport function resolveInput(arg: string | any) {\n if (!env.isNodejs() && typeof arg === 'string') {\n return document.getElementById(arg);\n }\n return arg;\n}\n", "import { env } from '../env/index';\nimport { resolveInput } from './resolveInput';\n\nexport function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {\n const { Canvas, CanvasRenderingContext2D } = env.getEnv();\n\n if (canvasArg instanceof CanvasRenderingContext2D) {\n return canvasArg;\n }\n\n const canvas = resolveInput(canvasArg);\n\n if (!(canvas instanceof Canvas)) {\n throw new Error('resolveContext2d - expected canvas to be of instance of Canvas');\n }\n\n const ctx = canvas.getContext('2d');\n if (!ctx) {\n throw new Error('resolveContext2d - canvas 2d context is null');\n }\n\n return ctx;\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IDimensions, IPoint } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { resolveInput } from '../dom/resolveInput';\n\n// eslint-disable-next-line no-shadow\nexport enum AnchorPosition {\n // eslint-disable-next-line no-unused-vars\n TOP_LEFT = 'TOP_LEFT',\n // eslint-disable-next-line no-unused-vars\n TOP_RIGHT = 'TOP_RIGHT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_LEFT = 'BOTTOM_LEFT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_RIGHT = 'BOTTOM_RIGHT'\n}\n\nexport interface IDrawTextFieldOptions {\n anchorPosition?: AnchorPosition\n backgroundColor?: string\n fontColor?: string\n fontSize?: number\n fontStyle?: string\n padding?: number\n}\n\nexport class DrawTextFieldOptions implements IDrawTextFieldOptions {\n public anchorPosition: AnchorPosition\n\n public backgroundColor: string\n\n public fontColor: string\n\n public fontSize: number\n\n public fontStyle: string\n\n public padding: number\n\n constructor(options: IDrawTextFieldOptions = {}) {\n const {\n anchorPosition, backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = options;\n this.anchorPosition = anchorPosition || AnchorPosition.TOP_LEFT;\n this.backgroundColor = backgroundColor || 'rgba(0, 0, 0, 0.5)';\n this.fontColor = fontColor || 'rgba(255, 255, 255, 1)';\n this.fontSize = fontSize || 14;\n this.fontStyle = fontStyle || 'Georgia';\n this.padding = padding || 4;\n }\n}\n\nexport class DrawTextField {\n public text: string[]\n\n public anchor : IPoint\n\n public options: DrawTextFieldOptions\n\n constructor(\n text: string | string[] | DrawTextField,\n anchor: IPoint,\n options: IDrawTextFieldOptions = {},\n ) {\n // eslint-disable-next-line no-nested-ternary\n this.text = typeof text === 'string'\n ? [text]\n : (text instanceof DrawTextField ? text.text : text);\n this.anchor = anchor;\n this.options = new DrawTextFieldOptions(options);\n }\n\n measureWidth(ctx: CanvasRenderingContext2D): number {\n const { padding } = this.options;\n return this.text.map((l) => ctx.measureText(l).width).reduce((w0, w1) => (w0 < w1 ? w1 : w0), 0) + (2 * padding);\n }\n\n measureHeight(): number {\n const { fontSize, padding } = this.options;\n return this.text.length * fontSize + (2 * padding);\n }\n\n getUpperLeft(ctx: CanvasRenderingContext2D, canvasDims?: IDimensions): IPoint {\n const { anchorPosition } = this.options;\n const isShiftLeft = anchorPosition === AnchorPosition.BOTTOM_RIGHT || anchorPosition === AnchorPosition.TOP_RIGHT;\n const isShiftTop = anchorPosition === AnchorPosition.BOTTOM_LEFT || anchorPosition === AnchorPosition.BOTTOM_RIGHT;\n\n const textFieldWidth = this.measureWidth(ctx);\n const textFieldHeight = this.measureHeight();\n const x = (isShiftLeft ? this.anchor.x - textFieldWidth : this.anchor.x);\n const y = isShiftTop ? this.anchor.y - textFieldHeight : this.anchor.y;\n\n // adjust anchor if text box exceeds canvas borders\n if (canvasDims) {\n const { width, height } = canvasDims;\n const newX = Math.max(Math.min(x, width - textFieldWidth), 0);\n const newY = Math.max(Math.min(y, height - textFieldHeight), 0);\n return { x: newX, y: newY };\n }\n return { x, y };\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const canvas = resolveInput(canvasArg);\n const ctx = getContext2dOrThrow(canvas);\n\n const {\n backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = this.options;\n\n ctx.font = `${fontSize}px ${fontStyle}`;\n const maxTextWidth = this.measureWidth(ctx);\n const textHeight = this.measureHeight();\n\n ctx.fillStyle = backgroundColor;\n const upperLeft = this.getUpperLeft(ctx, canvas);\n ctx.fillRect(upperLeft.x, upperLeft.y, maxTextWidth, textHeight);\n\n ctx.fillStyle = fontColor;\n this.text.forEach((textLine, i) => {\n const x = padding + upperLeft.x;\n const y = padding + upperLeft.y + ((i + 1) * fontSize);\n ctx.fillText(textLine, x, y);\n });\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { Box, IBoundingBox, IRect } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport {\n AnchorPosition, DrawTextField, DrawTextFieldOptions, IDrawTextFieldOptions,\n} from './DrawTextField';\n\nexport interface IDrawBoxOptions {\n boxColor?: string\n lineWidth?: number\n drawLabelOptions?: IDrawTextFieldOptions\n label?: string\n}\n\nexport class DrawBoxOptions {\n public boxColor: string\n\n public lineWidth: number\n\n public drawLabelOptions: DrawTextFieldOptions\n\n public label?: string\n\n constructor(options: IDrawBoxOptions = {}) {\n const {\n boxColor, lineWidth, label, drawLabelOptions,\n } = options;\n this.boxColor = boxColor || 'rgba(0, 0, 255, 1)';\n this.lineWidth = lineWidth || 2;\n this.label = label;\n\n const defaultDrawLabelOptions = {\n anchorPosition: AnchorPosition.BOTTOM_LEFT,\n backgroundColor: this.boxColor,\n };\n this.drawLabelOptions = new DrawTextFieldOptions({ ...defaultDrawLabelOptions, ...drawLabelOptions });\n }\n}\n\nexport class DrawBox {\n public box: Box\n\n public options: DrawBoxOptions\n\n constructor(\n box: IBoundingBox | IRect,\n options: IDrawBoxOptions = {},\n ) {\n this.box = new Box(box);\n this.options = new DrawBoxOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const { boxColor, lineWidth } = this.options;\n\n const {\n x, y, width, height,\n } = this.box;\n ctx.strokeStyle = boxColor;\n ctx.lineWidth = lineWidth;\n ctx.strokeRect(x, y, width, height);\n\n const { label } = this.options;\n if (label) {\n new DrawTextField([label], { x: x - (lineWidth / 2), y }, this.options.drawLabelOptions).draw(canvasArg);\n }\n }\n}\n", "import { Box, IBoundingBox, IRect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { round } from '../utils/index';\nimport { DrawBox } from './DrawBox';\n\nexport type TDrawDetectionsInput = IRect | IBoundingBox | FaceDetection | WithFaceDetection<{}>\n\nexport function drawDetections(\n canvasArg: string | HTMLCanvasElement,\n detections: TDrawDetectionsInput | Array,\n) {\n const detectionsArray = Array.isArray(detections) ? detections : [detections];\n\n detectionsArray.forEach((det) => {\n // eslint-disable-next-line no-nested-ternary\n const score = det instanceof FaceDetection\n ? det.score\n : (isWithFaceDetection(det) ? det.detection.score : undefined);\n\n // eslint-disable-next-line no-nested-ternary\n const box = det instanceof FaceDetection\n ? det.box\n : (isWithFaceDetection(det) ? det.detection.box : new Box(det));\n\n const label = score ? `${round(score)}` : undefined;\n new DrawBox(box, { label }).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { FaceExpressions } from './FaceExpressions';\n\nexport class FaceExpressionNet extends FaceProcessor {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceExpressionNet', faceFeatureExtractor);\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n return tf.tidy(() => tf.softmax(this.runNet(input)));\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictExpressions(input: TNetInput) {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n const probabilitesByBatch = await Promise.all(tf.unstack(out).map(async (t) => {\n const data = await t.data();\n t.dispose();\n return data;\n }));\n out.dispose();\n\n const predictionsByBatch = probabilitesByBatch\n .map((probabilites) => new FaceExpressions(probabilites as Float32Array));\n\n return netInput.isBatchInput\n ? predictionsByBatch\n : predictionsByBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_expression_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n\n protected getClassifierChannelsOut(): number {\n return 7;\n }\n}\n", "import { env } from '../env/index';\n\nexport function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {\n const { Image, Video } = env.getEnv();\n\n return (media instanceof Image && media.complete)\n || (media instanceof Video && media.readyState >= 3);\n}\n", "import { env } from '../env/index';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {\n // eslint-disable-next-line consistent-return\n return new Promise((resolve, reject) => {\n if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {\n return resolve(null);\n }\n\n function onError(e: Event) {\n if (!e.currentTarget) return;\n // eslint-disable-next-line no-use-before-define\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n reject(e);\n }\n\n function onLoad(e: Event) {\n if (!e.currentTarget) return;\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n resolve(e);\n }\n\n media.addEventListener('load', onLoad);\n media.addEventListener('error', onError);\n });\n}\n", "import { env } from '../env/index';\n\nexport function bufferToImage(buf: Blob): Promise {\n return new Promise((resolve, reject) => {\n if (!(buf instanceof Blob)) reject(new Error('bufferToImage - expected buf to be of type: Blob'));\n const reader = new FileReader();\n reader.onload = () => {\n if (typeof reader.result !== 'string') reject(new Error('bufferToImage - expected reader.result to be a string, in onload'));\n const img = env.getEnv().createImageElement();\n img.onload = () => resolve(img);\n img.onerror = reject;\n img.src = reader.result as string;\n };\n reader.onerror = reject;\n reader.readAsDataURL(buf);\n });\n}\n", "import { Dimensions, IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\n\nexport function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {\n const { Image, Video } = env.getEnv();\n\n if (input instanceof Image) {\n return new Dimensions(input.naturalWidth, input.naturalHeight);\n }\n if (input instanceof Video) {\n return new Dimensions(input.videoWidth, input.videoHeight);\n }\n return new Dimensions(input.width, input.height);\n}\n", "import { IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {\n const { createCanvasElement } = env.getEnv();\n const canvas = createCanvasElement();\n canvas.width = width;\n canvas.height = height;\n return canvas;\n}\n\nexport function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {\n const { ImageData } = env.getEnv();\n\n if (!(media instanceof ImageData) && !isMediaLoaded(media)) {\n throw new Error('createCanvasFromMedia - media has not finished loading yet');\n }\n\n const { width, height } = dims || getMediaDimensions(media);\n const canvas = createCanvas({ width, height });\n\n if (media instanceof ImageData) {\n getContext2dOrThrow(canvas).putImageData(media, 0, 0);\n } else {\n getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height);\n }\n return canvas;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { env } from '../env/index';\nimport { isTensor4D } from '../utils/index';\n\nexport async function imageTensorToCanvas(\n imgTensor: tf.Tensor,\n canvas?: HTMLCanvasElement,\n): Promise {\n const targetCanvas = canvas || env.getEnv().createCanvasElement();\n\n const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0);\n const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt());\n await tf.browser.toPixels(imgTensor3D, targetCanvas);\n\n imgTensor3D.dispose();\n\n return targetCanvas;\n}\n", "import { env } from '../env/index';\n\nexport function isMediaElement(input: any) {\n const { Image, Canvas, Video } = env.getEnv();\n\n return input instanceof Image\n || input instanceof Canvas\n || input instanceof Video;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Dimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { padToSquare } from '../ops/padToSquare';\nimport {\n computeReshapedDimensions, isTensor3D, isTensor4D, range,\n} from '../utils/index';\nimport { createCanvasFromMedia } from './createCanvas';\nimport { imageToSquare } from './imageToSquare';\nimport { TResolvedNetInput } from './types';\n\nexport class NetInput {\n private _imageTensors: Array = []\n\n private _canvases: HTMLCanvasElement[] = []\n\n private _batchSize: number\n\n private _treatAsBatchInput: boolean = false\n\n private _inputDimensions: number[][] = []\n\n private _inputSize: number\n\n constructor(\n inputs: Array,\n treatAsBatchInput: boolean = false,\n ) {\n if (!Array.isArray(inputs)) {\n throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`);\n }\n\n this._treatAsBatchInput = treatAsBatchInput;\n this._batchSize = inputs.length;\n\n inputs.forEach((input, idx) => {\n if (isTensor3D(input)) {\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = input.shape;\n return;\n }\n\n if (isTensor4D(input)) {\n const batchSize = (input as any).shape[0];\n if (batchSize !== 1) {\n throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = (input as any).shape.slice(1);\n return;\n }\n\n const canvas = (input as any) instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input);\n this._canvases[idx] = canvas;\n this._inputDimensions[idx] = [canvas.height, canvas.width, 3];\n });\n }\n\n public get imageTensors(): Array {\n return this._imageTensors;\n }\n\n public get canvases(): HTMLCanvasElement[] {\n return this._canvases;\n }\n\n public get isBatchInput(): boolean {\n return this.batchSize > 1 || this._treatAsBatchInput;\n }\n\n public get batchSize(): number {\n return this._batchSize;\n }\n\n public get inputDimensions(): number[][] {\n return this._inputDimensions;\n }\n\n public get inputSize(): number | undefined {\n return this._inputSize;\n }\n\n public get reshapedInputDimensions(): Dimensions[] {\n return range(this.batchSize, 0, 1).map(\n (_, batchIdx) => this.getReshapedInputDimensions(batchIdx),\n );\n }\n\n public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {\n return this.canvases[batchIdx] || this.imageTensors[batchIdx];\n }\n\n public getInputDimensions(batchIdx: number): number[] {\n return this._inputDimensions[batchIdx];\n }\n\n public getInputHeight(batchIdx: number): number {\n return this._inputDimensions[batchIdx][0];\n }\n\n public getInputWidth(batchIdx: number): number {\n return this._inputDimensions[batchIdx][1];\n }\n\n public getReshapedInputDimensions(batchIdx: number): Dimensions {\n if (typeof this.inputSize !== 'number') {\n throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet');\n }\n\n const width = this.getInputWidth(batchIdx);\n const height = this.getInputHeight(batchIdx);\n return computeReshapedDimensions({ width, height }, this.inputSize);\n }\n\n /**\n * Create a batch tensor from all input canvases and tensors\n * with size [batchSize, inputSize, inputSize, 3].\n *\n * @param inputSize Height and width of the tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The batch tensor.\n */\n public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {\n this._inputSize = inputSize;\n\n return tf.tidy(() => {\n const inputTensors = range(this.batchSize, 0, 1).map((batchIdx) => {\n const input = this.getInput(batchIdx);\n\n if (input instanceof tf.Tensor) {\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n let imgTensor = isTensor4D(input) ? input : input.expandDims();\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n imgTensor = padToSquare(imgTensor, isCenterInputs);\n\n if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {\n imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize]);\n }\n\n return imgTensor.as3D(inputSize, inputSize, 3);\n }\n\n if (input instanceof env.getEnv().Canvas) {\n return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs));\n }\n\n throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`);\n });\n\n // const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)\n const batchTensor = tf.stack(inputTensors.map((t) => tf.cast(t, 'float32'))).as4D(this.batchSize, inputSize, inputSize, 3);\n // const batchTensor = tf.stack(inputTensors.map(t => tf.Tensor.as4D(tf.cast(t, 'float32'))), this.batchSize, inputSize, inputSize, 3);\n\n return batchTensor;\n });\n }\n}\n", "import { env } from '../env/index';\nimport { createCanvas, createCanvasFromMedia } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {\n const { Image, Canvas } = env.getEnv();\n\n if (!(input instanceof Image || input instanceof Canvas)) {\n throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement');\n }\n\n const dims = getMediaDimensions(input);\n const scale = inputSize / Math.max(dims.height, dims.width);\n const width = scale * dims.width;\n const height = scale * dims.height;\n\n const targetCanvas = createCanvas({ width: inputSize, height: inputSize });\n const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input);\n\n const offset = Math.abs(width - height) / 2;\n const dx = centerImage && width < height ? offset : 0;\n const dy = centerImage && height < width ? offset : 0;\n getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height);\n\n return targetCanvas;\n}\n", "import { isTensor3D, isTensor4D } from '../utils/index';\nimport { awaitMediaLoaded } from './awaitMediaLoaded';\nimport { isMediaElement } from './isMediaElement';\nimport { NetInput } from './NetInput';\nimport { resolveInput } from './resolveInput';\nimport { TNetInput } from './types';\n\n/**\n * Validates the input to make sure, they are valid net inputs and awaits all media elements\n * to be finished loading.\n *\n * @param input The input, which can be a media element or an array of different media elements.\n * @returns A NetInput instance, which can be passed into one of the neural networks.\n */\nexport async function toNetInput(inputs: TNetInput): Promise {\n if (inputs instanceof NetInput) {\n return inputs;\n }\n\n const inputArgArray = Array.isArray(inputs)\n ? inputs\n : [inputs];\n\n if (!inputArgArray.length) {\n throw new Error('toNetInput - empty array passed as input');\n }\n\n const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');\n\n const inputArray = inputArgArray.map(resolveInput);\n\n inputArray.forEach((input, i) => {\n if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {\n if (typeof inputArgArray[i] === 'string') {\n throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);\n }\n\n throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);\n }\n\n if (isTensor4D(input)) {\n // if tf.Tensor4D is passed in the input array, the batch size has to be 1\n const batchSize = input.shape[0];\n if (batchSize !== 1) {\n throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n }\n });\n\n // wait for all media elements being loaded\n await Promise.all(\n inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),\n );\n\n return new NetInput(inputArray, Array.isArray(inputs));\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { Rect } from '../classes/Rect';\nimport { env } from '../env/index';\nimport { createCanvas } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { imageTensorToCanvas } from './imageTensorToCanvas';\nimport { toNetInput } from './toNetInput';\nimport { TNetInput } from './types';\n\n/**\n * Extracts the image regions containing the detected faces.\n *\n * @param input The image that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns The Canvases of the corresponding image region for each detected face.\n */\nexport async function extractFaces(\n input: TNetInput,\n detections: Array,\n): Promise {\n const { Canvas } = env.getEnv();\n\n let canvas = input as HTMLCanvasElement;\n\n if (!(input instanceof Canvas)) {\n const netInput = await toNetInput(input);\n\n if (netInput.batchSize > 1) {\n throw new Error('extractFaces - batchSize > 1 not supported');\n }\n\n const tensorOrCanvas = netInput.getInput(0);\n canvas = tensorOrCanvas instanceof Canvas\n ? tensorOrCanvas\n : await imageTensorToCanvas(tensorOrCanvas);\n }\n\n const ctx = getContext2dOrThrow(canvas);\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(canvas.width, canvas.height).box.floor()\n : det),\n )\n .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));\n\n return boxes.map(({\n x, y, width, height,\n }) => {\n const faceImg = createCanvas({ width, height });\n getContext2dOrThrow(faceImg)\n .putImageData(ctx.getImageData(x, y, width, height), 0, 0);\n return faceImg;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isTensor3D, isTensor4D } from '../utils/index';\n\n/**\n * Extracts the tensors of the image regions containing the detected faces.\n * Useful if you want to compute the face descriptors for the face images.\n * Using this method is faster then extracting a canvas for each face and\n * converting them to tensors individually.\n *\n * @param imageTensor The image tensor that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns Tensors of the corresponding image region for each detected face.\n */\nexport async function extractFaceTensors(\n imageTensor: tf.Tensor3D | tf.Tensor4D,\n detections: Array,\n): Promise {\n if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {\n throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D');\n }\n\n if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {\n throw new Error('extractFaceTensors - batchSize > 1 not supported');\n }\n\n return tf.tidy(() => {\n const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0);\n\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(imgWidth, imgHeight).box\n : det),\n )\n .map((box) => box.clipAtImageBorders(imgWidth, imgHeight));\n\n const faceTensors = boxes.map(({\n x, y, width, height,\n }) => tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels]));\n\n return faceTensors;\n });\n}\n", "import { env } from '../env/index';\n\nexport async function fetchOrThrow(\n url: string,\n // eslint-disable-next-line no-undef\n init?: RequestInit,\n): Promise {\n const { fetch } = env.getEnv();\n const res = await fetch(url, init);\n if (!(res.status < 400)) {\n throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`);\n }\n return res;\n}\n", "import { bufferToImage } from './bufferToImage';\nimport { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchImage(uri: string): Promise {\n const res = await fetchOrThrow(uri);\n const blob = await (res).blob();\n\n if (!blob.type.startsWith('image/')) {\n throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`);\n }\n return bufferToImage(blob);\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchJson(uri: string): Promise {\n return (await fetchOrThrow(uri)).json();\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchNetWeights(uri: string): Promise {\n return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer());\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { getModelUris } from '../common/getModelUris';\nimport { fetchJson } from './fetchJson';\n\nexport async function loadWeightMap(\n uri: string | undefined,\n defaultModelName: string,\n): Promise {\n const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName);\n const manifest = await fetchJson(manifestUri);\n // if (manifest['weightsManifest']) manifest = manifest['weightsManifest'];\n return tf.io.loadWeights(manifest, modelBaseUri);\n}\n", "export function getModelUris(uri: string | undefined, defaultModelName: string) {\n const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`;\n\n if (!uri) {\n return {\n modelBaseUri: '',\n manifestUri: defaultManifestFilename,\n };\n }\n\n if (uri === '/') {\n return {\n modelBaseUri: '/',\n manifestUri: `/${defaultManifestFilename}`,\n };\n }\n // eslint-disable-next-line no-nested-ternary\n const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';\n uri = uri.replace(protocol, '');\n\n const parts = uri.split('/').filter((s) => s);\n\n const manifestFile = uri.endsWith('.json')\n ? parts[parts.length - 1]\n : defaultManifestFilename;\n\n let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/');\n modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri;\n\n return {\n modelBaseUri,\n manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`,\n };\n}\n", "import { IDimensions } from '../classes/index';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {\n const { width, height } = useMediaDimensions\n ? getMediaDimensions(reference)\n : reference;\n input.width = width;\n input.height = height;\n return { width, height };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock4 } from './denseBlock';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';\n\nexport class FaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('FaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock4(normalized, params.dense0, true);\n out = denseBlock4(out, params.dense1);\n out = denseBlock4(out, params.dense2);\n out = denseBlock4(out, params.dense3);\n out = tf.avgPool(out, [7, 7], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../dist/tfjs.esm';\n\nimport { ParamMapping } from './common/index';\nimport { getModelUris } from './common/getModelUris';\nimport { loadWeightMap } from './dom/index';\nimport { env } from './env/index';\n\nexport abstract class NeuralNetwork {\n protected _params: TNetParams | undefined = undefined\n\n protected _paramMappings: ParamMapping[] = []\n\n public _name: any;\n\n public get params(): TNetParams | undefined { return this._params; }\n\n public get paramMappings(): ParamMapping[] { return this._paramMappings; }\n\n public get isLoaded(): boolean { return !!this.params; }\n\n public getParamFromPath(paramPath: string): tf.Tensor {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n return obj[objProp];\n }\n\n public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n obj[objProp].dispose();\n obj[objProp] = tensor;\n }\n\n public getParamList() {\n return this._paramMappings.map(({ paramPath }) => ({\n path: paramPath,\n tensor: this.getParamFromPath(paramPath),\n }));\n }\n\n public getTrainableParams() {\n return this.getParamList().filter((param) => param.tensor instanceof tf.Variable);\n }\n\n public getFrozenParams() {\n return this.getParamList().filter((param) => !(param.tensor instanceof tf.Variable));\n }\n\n public variable() {\n this.getFrozenParams().forEach(({ path, tensor }) => {\n this.reassignParamFromPath(path, tensor.variable());\n });\n }\n\n public freeze() {\n this.getTrainableParams().forEach(({ path, tensor: variable }) => {\n const tensor = tf.tensor(variable.dataSync());\n variable.dispose();\n this.reassignParamFromPath(path, tensor);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.getParamList().forEach((param) => {\n if (throwOnRedispose && param.tensor.isDisposed) {\n throw new Error(`param tensor has already been disposed for path ${param.path}`);\n }\n param.tensor.dispose();\n });\n this._params = undefined;\n }\n\n public serializeParams(): Float32Array {\n return new Float32Array(\n this.getParamList()\n .map(({ tensor }) => Array.from(tensor.dataSync()) as number[])\n .reduce((flat, arr) => flat.concat(arr)),\n );\n }\n\n public async load(weightsOrUrl: Float32Array | string | undefined): Promise {\n if (weightsOrUrl instanceof Float32Array) {\n this.extractWeights(weightsOrUrl);\n return;\n }\n\n await this.loadFromUri(weightsOrUrl);\n }\n\n public async loadFromUri(uri: string | undefined) {\n if (uri && typeof uri !== 'string') {\n throw new Error(`${this._name}.loadFromUri - expected model uri`);\n }\n\n const weightMap = await loadWeightMap(uri, this.getDefaultModelName());\n this.loadFromWeightMap(weightMap);\n }\n\n public async loadFromDisk(filePath: string | undefined) {\n if (filePath && typeof filePath !== 'string') {\n throw new Error(`${this._name}.loadFromDisk - expected model file path`);\n }\n\n const { readFile } = env.getEnv();\n\n const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName());\n\n const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(\n filePaths.map((fp) => readFile(fp).then((buf) => buf.buffer)),\n );\n const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk);\n const manifest = JSON.parse((await readFile(manifestUri)).toString());\n const weightMap = await loadWeights(manifest, modelBaseUri);\n\n this.loadFromWeightMap(weightMap);\n }\n\n public loadFromWeightMap(weightMap: tf.NamedTensorMap) {\n const {\n paramMappings,\n params,\n } = this.extractParamsFromWeightMap(weightMap);\n\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n public extractWeights(weights: Float32Array) {\n const {\n paramMappings,\n params,\n } = this.extractParams(weights);\n\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n private traversePropertyPath(paramPath: string) {\n if (!this.params) {\n throw new Error('traversePropertyPath - model has no loaded params');\n }\n\n const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {\n // eslint-disable-next-line no-prototype-builtins\n if (!res.nextObj.hasOwnProperty(objProp)) {\n throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`);\n }\n\n return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] };\n }, { nextObj: this.params });\n\n const { obj, objProp } = result;\n if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {\n throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`);\n }\n\n return { obj, objProp };\n }\n\n protected abstract getDefaultModelName(): string\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, SeparableConvParams } from '../common/index';\nimport { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function denseBlock3(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock3Params,\n isFirstLayer: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n });\n}\n\nexport function denseBlock4(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock4Params,\n isFirstLayer: boolean = false,\n isScaleDown: boolean = true,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from './types';\n\nexport function depthwiseSeparableConv(\n x: tf.Tensor4D,\n params: SeparableConvParams,\n stride: [number, number],\n): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same');\n out = tf.add(out, params.bias);\n return out;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\nexport function convLayer(\n x: tf.Tensor4D,\n params: ConvParams,\n padding: 'valid' | 'same' = 'same',\n withRelu: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out = tf.add(\n tf.conv2d(x, params.filters, [1, 1], padding),\n params.bias,\n ) as tf.Tensor4D;\n\n return withRelu ? tf.relu(out) : out;\n });\n}\n", "import { ParamMapping } from './types';\n\nexport function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {\n Object.keys(weightMap).forEach((path) => {\n if (!paramMappings.some((pm) => pm.originalPath === path)) {\n weightMap[path].dispose();\n }\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';\n\nexport function extractConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams => {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, FCParams, ParamMapping } from './types';\n\nexport function extractFCParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): FCParams => {\n const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);\n const fc_bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return {\n weights: fc_weights,\n bias: fc_bias,\n };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';\n\nexport function extractSeparableConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams => {\n const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1]);\n const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut]);\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/depthwise_filter` },\n { paramPath: `${mappedPrefix}/pointwise_filter` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n\nexport function loadSeparableConvParamsFactory(\n // eslint-disable-next-line no-unused-vars\n extractWeightEntry: (originalPath: string, paramRank: number) => T,\n) {\n return (prefix: string): SeparableConvParams => {\n const depthwise_filter = extractWeightEntry(`${prefix}/depthwise_filter`, 4);\n const pointwise_filter = extractWeightEntry(`${prefix}/pointwise_filter`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n// eslint-disable-next-line no-unused-vars\nexport type ExtractWeightsFunction = (numWeights: number) => Float32Array\n\nexport type ParamMapping = {\n originalPath?: string\n paramPath: string\n}\n\nexport type ConvParams = {\n filters: tf.Tensor4D\n bias: tf.Tensor1D\n}\n\nexport type FCParams = {\n weights: tf.Tensor2D\n bias: tf.Tensor1D\n}\n\nexport class SeparableConvParams {\n // eslint-disable-next-line no-useless-constructor\n constructor(\n // eslint-disable-next-line no-unused-vars\n public depthwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public pointwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public bias: tf.Tensor1D,\n // eslint-disable-next-line no-empty-function\n ) {}\n}\n", "import { isTensor } from '../utils/index';\nimport { ParamMapping } from './types';\n\nexport function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {\n return (originalPath: string, paramRank: number, mappedPath?: string) => {\n const tensor = weightMap[originalPath];\n\n if (!isTensor(tensor, paramRank)) {\n throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`);\n }\n\n paramMappings.push(\n { originalPath, paramPath: mappedPath || originalPath },\n );\n\n return tensor;\n };\n}\n", "export function extractWeightsFactory(weights: Float32Array) {\n let remainingWeights = weights;\n\n function extractWeights(numWeights: number): Float32Array {\n const ret = remainingWeights.slice(0, numWeights);\n remainingWeights = remainingWeights.slice(numWeights);\n return ret;\n }\n\n function getRemainingWeights(): Float32Array {\n return remainingWeights;\n }\n\n return {\n extractWeights,\n getRemainingWeights,\n };\n}\n", "import {\n extractConvParamsFactory,\n extractSeparableConvParamsFactory,\n ExtractWeightsFunction,\n ParamMapping,\n} from '../common/index';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)\n : extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`);\n const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`);\n const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer);\n const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock4Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock4Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock4Params(64, 128, 'dense2');\n const dense3 = extractDenseBlock4Params(128, 256, 'dense3');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: {\n dense0, dense1, dense2, dense3,\n },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\n// eslint-disable-next-line no-unused-vars\nexport function loadConvParamsFactory(extractWeightEntry: (originalPath: string, paramRank: number) => T) {\n return (prefix: string): ConvParams => {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return { filters, bias };\n };\n}\n", "import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n const conv3 = extractSeparableConvParams(`${prefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock4Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock4Params('dense0', true),\n dense1: extractDenseBlock4Params('dense1'),\n dense2: extractDenseBlock4Params('dense2'),\n dense3: extractDenseBlock4Params('dense3'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { NetInput } from '../dom/index';\nimport {\n FaceFeatureExtractorParams,\n IFaceFeatureExtractor,\n TinyFaceFeatureExtractorParams,\n} from '../faceFeatureExtractor/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { NetParams } from './types';\nimport { seperateWeightMaps } from './util';\n\nexport abstract class FaceProcessor<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends NeuralNetwork {\n protected _faceFeatureExtractor: IFaceFeatureExtractor\n\n constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor) {\n super(_name);\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): IFaceFeatureExtractor {\n return this._faceFeatureExtractor;\n }\n\n protected abstract getDefaultModelName(): string\n\n protected abstract getClassifierChannelsIn(): number\n\n protected abstract getClassifierChannelsOut(): number\n\n public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut());\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const cIn = this.getClassifierChannelsIn();\n const cOut = this.getClassifierChannelsOut();\n const classifierWeightSize = (cOut * cIn) + cOut;\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from './types';\n\nexport function fullyConnectedLayer(\n x: tf.Tensor2D,\n params: FCParams,\n): tf.Tensor2D {\n return tf.tidy(() => tf.add(\n tf.matMul(x, params.weights),\n params.bias,\n ));\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const fc = extractFCParams(channelsIn, channelsOut, 'fc');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: extractFcParams('fc'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function seperateWeightMaps(weightMap: tf.NamedTensorMap) {\n const featureExtractorMap: tf.NamedTensorMap = {};\n const classifierMap: tf.NamedTensorMap = {};\n\n Object.keys(weightMap).forEach((key) => {\n const map = key.startsWith('fc') ? classifierMap : featureExtractorMap;\n map[key] = weightMap[key];\n });\n\n return { featureExtractorMap, classifierMap };\n}\n", "export const FACE_EXPRESSION_LABELS = ['neutral', 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised'];\n\nexport class FaceExpressions {\n public neutral: number\n\n public happy: number\n\n public sad: number\n\n public angry: number\n\n public fearful: number\n\n public disgusted: number\n\n public surprised: number\n\n constructor(probabilities: number[] | Float32Array) {\n if (probabilities.length !== 7) {\n throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${probabilities.length}`);\n }\n\n FACE_EXPRESSION_LABELS.forEach((expression, idx) => {\n this[expression] = probabilities[idx];\n });\n }\n\n asSortedArray() {\n return FACE_EXPRESSION_LABELS\n .map((expression) => ({ expression, probability: this[expression] as number }))\n .sort((e0, e1) => e1.probability - e0.probability);\n }\n}\n", "import { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\n\nexport type WithFaceExpressions = TSource & {\n expressions: FaceExpressions\n}\n\nexport function isWithFaceExpressions(obj: any): obj is WithFaceExpressions<{}> {\n return obj.expressions instanceof FaceExpressions;\n}\n\nexport function extendWithFaceExpressions<\n TSource\n>(\n sourceObj: TSource,\n expressions: FaceExpressions,\n): WithFaceExpressions {\n const extension = { expressions };\n return { ...sourceObj, ...extension };\n}\n", "import { IPoint, Point } from '../classes/index';\nimport { FaceExpressions } from '../faceExpressionNet/index';\nimport { isWithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { round } from '../utils/index';\nimport { DrawTextField } from './DrawTextField';\n\nexport type DrawFaceExpressionsInput = FaceExpressions | WithFaceExpressions<{}>\n\nexport function drawFaceExpressions(\n canvasArg: string | HTMLCanvasElement,\n faceExpressions: DrawFaceExpressionsInput | Array,\n minConfidence = 0.1,\n textFieldAnchor?: IPoint,\n) {\n const faceExpressionsArray = Array.isArray(faceExpressions) ? faceExpressions : [faceExpressions];\n\n faceExpressionsArray.forEach((e) => {\n // eslint-disable-next-line no-nested-ternary\n const expr = e instanceof FaceExpressions\n ? e\n : (isWithFaceExpressions(e) ? e.expressions : undefined);\n if (!expr) {\n throw new Error('drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof');\n }\n\n const sorted = expr.asSortedArray();\n const resultsToDisplay = sorted.filter((exprLocal) => exprLocal.probability > minConfidence);\n\n const anchor = isWithFaceDetection(e)\n ? e.detection.box.bottomLeft\n : (textFieldAnchor || new Point(0, 0));\n\n const drawTextField = new DrawTextField(\n resultsToDisplay.map((exprLocal) => `${exprLocal.expression} (${round(exprLocal.probability)})`),\n anchor,\n );\n drawTextField.draw(canvasArg);\n });\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { isWithFaceDetection, WithFaceDetection } from './WithFaceDetection';\n\nexport type WithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 > = TSource & {\n landmarks: TFaceLandmarks\n unshiftedLandmarks: TFaceLandmarks\n alignedRect: FaceDetection\n }\n\nexport function isWithFaceLandmarks(obj: any): obj is WithFaceLandmarks, FaceLandmarks> {\n return isWithFaceDetection(obj)\n // eslint-disable-next-line dot-notation\n && obj['landmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['unshiftedLandmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['alignedRect'] instanceof FaceDetection;\n}\n\nexport function extendWithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 >(sourceObj: TSource, unshiftedLandmarks: TFaceLandmarks): WithFaceLandmarks {\n const { box: shift } = sourceObj.detection;\n const landmarks = unshiftedLandmarks.shiftBy(shift.x, shift.y);\n\n const rect = landmarks.align();\n const { imageDims } = sourceObj.detection;\n const alignedRect = new FaceDetection(sourceObj.detection.score, rect.rescale(imageDims.reverse()), imageDims);\n\n const extension = {\n landmarks,\n unshiftedLandmarks,\n alignedRect,\n };\n\n return { ...sourceObj, ...extension };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IPoint } from '../classes/index';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { drawContour } from './drawContour';\n\nexport interface IDrawFaceLandmarksOptions {\n drawLines?: boolean\n drawPoints?: boolean\n lineWidth?: number\n pointSize?: number\n lineColor?: string\n pointColor?: string\n}\n\nexport class DrawFaceLandmarksOptions {\n public drawLines: boolean\n\n public drawPoints: boolean\n\n public lineWidth: number\n\n public pointSize: number\n\n public lineColor: string\n\n public pointColor: string\n\n constructor(options: IDrawFaceLandmarksOptions = {}) {\n const {\n drawLines = true, drawPoints = true, lineWidth, lineColor, pointSize, pointColor,\n } = options;\n this.drawLines = drawLines;\n this.drawPoints = drawPoints;\n this.lineWidth = lineWidth || 1;\n this.pointSize = pointSize || 2;\n this.lineColor = lineColor || 'rgba(0, 255, 255, 1)';\n this.pointColor = pointColor || 'rgba(255, 0, 255, 1)';\n }\n}\n\nexport class DrawFaceLandmarks {\n public faceLandmarks: FaceLandmarks\n\n public options: DrawFaceLandmarksOptions\n\n constructor(\n faceLandmarks: FaceLandmarks,\n options: IDrawFaceLandmarksOptions = {},\n ) {\n this.faceLandmarks = faceLandmarks;\n this.options = new DrawFaceLandmarksOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const {\n drawLines, drawPoints, lineWidth, lineColor, pointSize, pointColor,\n } = this.options;\n\n if (drawLines && this.faceLandmarks instanceof FaceLandmarks68) {\n ctx.strokeStyle = lineColor;\n ctx.lineWidth = lineWidth;\n drawContour(ctx, this.faceLandmarks.getJawOutline());\n drawContour(ctx, this.faceLandmarks.getLeftEyeBrow());\n drawContour(ctx, this.faceLandmarks.getRightEyeBrow());\n drawContour(ctx, this.faceLandmarks.getNose());\n drawContour(ctx, this.faceLandmarks.getLeftEye(), true);\n drawContour(ctx, this.faceLandmarks.getRightEye(), true);\n drawContour(ctx, this.faceLandmarks.getMouth(), true);\n }\n\n if (drawPoints) {\n ctx.strokeStyle = pointColor;\n ctx.fillStyle = pointColor;\n\n const drawPoint = (pt: IPoint) => {\n ctx.beginPath();\n ctx.arc(pt.x, pt.y, pointSize, 0, 2 * Math.PI);\n ctx.fill();\n };\n this.faceLandmarks.positions.forEach(drawPoint);\n }\n }\n}\n\nexport type DrawFaceLandmarksInput = FaceLandmarks | WithFaceLandmarks>\n\nexport function drawFaceLandmarks(\n canvasArg: string | HTMLCanvasElement,\n faceLandmarks: DrawFaceLandmarksInput | Array,\n) {\n const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];\n faceLandmarksArray.forEach((f) => {\n // eslint-disable-next-line no-nested-ternary\n const landmarks = f instanceof FaceLandmarks\n ? f\n : (isWithFaceLandmarks(f) ? f.landmarks : undefined);\n if (!landmarks) {\n throw new Error('drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof');\n }\n\n new DrawFaceLandmarks(landmarks).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { seperateWeightMaps } from '../faceProcessor/util';\nimport { TinyXception } from '../xception/TinyXception';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport {\n AgeAndGenderPrediction, Gender, NetOutput, NetParams,\n} from './types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\n\nexport class AgeGenderNet extends NeuralNetwork {\n private _faceFeatureExtractor: TinyXception\n\n constructor(faceFeatureExtractor: TinyXception = new TinyXception(2)) {\n super('AgeGenderNet');\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): TinyXception {\n return this._faceFeatureExtractor;\n }\n\n public runNet(input: NetInput | tf.Tensor4D): NetOutput {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n\n const pooled = tf.avgPool(bottleneckFeatures, [7, 7], [2, 2], 'valid').as2D(bottleneckFeatures.shape[0], -1);\n const age = fullyConnectedLayer(pooled, params.fc.age).as1D();\n const gender = fullyConnectedLayer(pooled, params.fc.gender);\n return { age, gender };\n });\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): NetOutput {\n return tf.tidy(() => {\n const { age, gender } = this.runNet(input);\n return { age, gender: tf.softmax(gender) };\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictAgeAndGender(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n\n const ages = tf.unstack(out.age);\n const genders = tf.unstack(out.gender);\n const ageAndGenderTensors = ages.map((ageTensor, i) => ({\n ageTensor,\n genderTensor: genders[i],\n }));\n\n const predictionsByBatch = await Promise.all(\n ageAndGenderTensors.map(async ({ ageTensor, genderTensor }) => {\n const age = (await ageTensor.data())[0];\n const probMale = (await genderTensor.data())[0];\n const isMale = probMale > 0.5;\n const gender = isMale ? Gender.MALE : Gender.FEMALE;\n const genderProbability = isMale ? probMale : (1 - probMale);\n\n ageTensor.dispose();\n genderTensor.dispose();\n return { age, gender, genderProbability };\n }),\n );\n out.age.dispose();\n out.gender.dispose();\n\n return netInput.isBatchInput ? predictionsByBatch as AgeAndGenderPrediction[] : predictionsByBatch[0] as AgeAndGenderPrediction;\n }\n\n protected getDefaultModelName(): string {\n return 'age_gender_model';\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights);\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const classifierWeightSize = (512 * 1 + 1) + (512 * 2 + 2);\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, depthwiseSeparableConv } from '../common/index';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { range } from '../utils/index';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction conv(x: tf.Tensor4D, params: ConvParams, stride: [number, number]): tf.Tensor4D {\n return tf.add(tf.conv2d(x, params.filters, stride, 'same'), params.bias);\n}\n\nfunction reductionBlock(x: tf.Tensor4D, params: ReductionBlockParams, isActivateInput: boolean = true): tf.Tensor4D {\n let out = isActivateInput ? tf.relu(x) : x;\n out = depthwiseSeparableConv(out, params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = tf.maxPool(out, [3, 3], [2, 2], 'same');\n out = tf.add(out, conv(x, params.expansion_conv, [2, 2]));\n return out;\n}\n\nfunction mainBlock(x: tf.Tensor4D, params: MainBlockParams): tf.Tensor4D {\n let out = depthwiseSeparableConv(tf.relu(x), params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv2, [1, 1]);\n out = tf.add(out, x);\n return out;\n}\n\nexport class TinyXception extends NeuralNetwork {\n private _numMainBlocks: number\n\n constructor(numMainBlocks: number) {\n super('TinyXception');\n this._numMainBlocks = numMainBlocks;\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyXception - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = tf.relu(conv(normalized, params.entry_flow.conv_in, [2, 2]));\n out = reductionBlock(out, params.entry_flow.reduction_block_0, false);\n out = reductionBlock(out, params.entry_flow.reduction_block_1);\n\n range(this._numMainBlocks, 0, 1).forEach((idx) => {\n out = mainBlock(out, params.middle_flow[`main_block_${idx}`]);\n });\n\n out = reductionBlock(out, params.exit_flow.reduction_block);\n out = tf.relu(depthwiseSeparableConv(out, params.exit_flow.separable_conv, [1, 1]));\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_xception_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this._numMainBlocks);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights, this._numMainBlocks);\n }\n}\n", "import { extractConvParamsFactory, extractSeparableConvParamsFactory, extractWeightsFactory } from '../common/index';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractReductionBlockParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(channels: number, mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParams(weights: Float32Array, numMainBlocks: number): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const entry_flow_conv_in = extractConvParams(3, 32, 3, 'entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams(32, 64, 'entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams(64, 128, 'entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(128, `middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams(128, 256, 'exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams(256, 512, 'exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { entry_flow, middle_flow, exit_flow },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors,\n extractWeightEntryFactory,\n loadSeparableConvParamsFactory,\n ParamMapping,\n} from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractReductionBlockParams(mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(`${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(`${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n numMainBlocks: number,\n): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const entry_flow_conv_in = extractConvParams('entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams('entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams('entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(`middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams('exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams('exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params: { entry_flow, middle_flow, exit_flow }, paramMappings };\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const age = extractFCParams(512, 1, 'fc/age');\n const gender = extractFCParams(512, 2, 'fc/gender');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc: { age, gender } },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: {\n age: extractFcParams('fc/age'),\n gender: extractFcParams('fc/gender'),\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from '../common/index';\n\n// eslint-disable-next-line no-shadow\nexport enum Gender {\n // eslint-disable-next-line no-unused-vars\n FEMALE = 'female',\n // eslint-disable-next-line no-unused-vars\n MALE = 'male'\n}\n\nexport type AgeAndGenderPrediction = {\n age: number\n gender: Gender\n genderProbability: number\n}\n\nexport type NetOutput = { age: tf.Tensor1D, gender: tf.Tensor2D }\n\nexport type NetParams = {\n fc: {\n age: FCParams\n gender: FCParams\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { IDimensions, Point } from '../classes/index';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { isEven } from '../utils/index';\n\nexport abstract class FaceLandmark68NetBase<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends FaceProcessor {\n public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {\n const inputDimensions = originalDimensions.map(({ width, height }) => {\n const scale = inputSize / Math.max(height, width);\n return {\n width: width * scale,\n height: height * scale,\n };\n });\n\n const batchSize = inputDimensions.length;\n\n return tf.tidy(() => {\n const createInterleavedTensor = (fillX: number, fillY: number) => tf.stack([tf.fill([68], fillX, 'float32'), tf.fill([68], fillY, 'float32')], 1).as2D(1, 136).as1D();\n\n // eslint-disable-next-line no-unused-vars\n const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {\n const { width, height } = inputDimensions[batchIdx];\n return cond(width, height) ? Math.abs(width - height) / 2 : 0;\n };\n\n const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h);\n const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w);\n\n const landmarkTensors = output\n .mul(tf.fill([batchSize, 136], inputSize, 'float32'))\n .sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n getPaddingX(batchIdx),\n getPaddingY(batchIdx),\n ))))\n .div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n inputDimensions[batchIdx].width,\n inputDimensions[batchIdx].height,\n ))));\n\n return landmarkTensors as tf.Tensor2D;\n });\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n return tf.tidy(() => {\n const out = this.runNet(input);\n return this.postProcess(\n out,\n input.inputSize as number,\n input.inputDimensions.map(([height, width]) => ({ height, width })),\n );\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async detectLandmarks(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const landmarkTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const landmarksForBatch = await Promise.all(landmarkTensors.map(\n async (landmarkTensor, batchIdx) => {\n const landmarksArray = Array.from(await landmarkTensor.data());\n const xCoords = landmarksArray.filter((_, i) => isEven(i));\n const yCoords = landmarksArray.filter((_, i) => !isEven(i));\n\n return new FaceLandmarks68(\n Array(68).fill(0).map((_, i) => new Point(xCoords[i] as number, yCoords[i] as number)),\n {\n height: netInput.getInputHeight(batchIdx),\n width: netInput.getInputWidth(batchIdx),\n },\n );\n },\n ));\n\n landmarkTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput ? landmarksForBatch as FaceLandmarks68[] : landmarksForBatch[0] as FaceLandmarks68;\n }\n\n protected getClassifierChannelsOut(): number {\n return 136;\n }\n}\n", "import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68Net extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceLandmark68Net', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock3 } from './denseBlock';\nimport { extractParamsFromWeightMapTiny } from './extractParamsFromWeightMapTiny';\nimport { extractParamsTiny } from './extractParamsTiny';\nimport { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';\n\nexport class TinyFaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('TinyFaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyFaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock3(normalized, params.dense0, true);\n out = denseBlock3(out, params.dense1);\n out = denseBlock3(out, params.dense2);\n out = tf.avgPool(out, [14, 14], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_tiny_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMapTiny(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParamsTiny(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMapTiny(\n weightMap: tf.NamedTensorMap,\n): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock3Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock3Params('dense0', true),\n dense1: extractDenseBlock3Params('dense1'),\n dense2: extractDenseBlock3Params('dense2'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock3Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock3Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock3Params(64, 128, 'dense2');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { dense0, dense1, dense2 },\n };\n}\n", "import { TinyFaceFeatureExtractor } from '../faceFeatureExtractor/TinyFaceFeatureExtractor';\nimport { TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68TinyNet extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: TinyFaceFeatureExtractor = new TinyFaceFeatureExtractor()) {\n super('FaceLandmark68TinyNet', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_tiny_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 128;\n }\n}\n", "import { FaceLandmark68Net } from './FaceLandmark68Net';\n\nexport * from './FaceLandmark68Net';\nexport * from './FaceLandmark68TinyNet';\n\nexport class FaceLandmarkNet extends FaceLandmark68Net {}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { convDown } from './convLayer';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { residual, residualDown } from './residualLayer';\nimport { NetParams } from './types';\n\nexport class FaceRecognitionNet extends NeuralNetwork {\n constructor() {\n super('FaceRecognitionNet');\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceRecognitionNet - load model before inference');\n }\n\n return tf.tidy(() => {\n // const batchTensor = input.toBatchTensor(150, true).toFloat()\n const batchTensor = tf.cast(input.toBatchTensor(150, true), 'float32');\n\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = convDown(normalized, params.conv32_down);\n out = tf.maxPool(out, 3, 2, 'valid');\n\n out = residual(out, params.conv32_1);\n out = residual(out, params.conv32_2);\n out = residual(out, params.conv32_3);\n\n out = residualDown(out, params.conv64_down);\n out = residual(out, params.conv64_1);\n out = residual(out, params.conv64_2);\n out = residual(out, params.conv64_3);\n\n out = residualDown(out, params.conv128_down);\n out = residual(out, params.conv128_1);\n out = residual(out, params.conv128_2);\n\n out = residualDown(out, params.conv256_down);\n out = residual(out, params.conv256_1);\n out = residual(out, params.conv256_2);\n out = residualDown(out, params.conv256_down_out);\n\n const globalAvg = out.mean([1, 2]) as tf.Tensor2D;\n const fullyConnected = tf.matMul(globalAvg, params.fc);\n\n return fullyConnected;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async computeFaceDescriptor(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n\n const faceDescriptorTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map(\n (t) => t.data(),\n )) as Float32Array[];\n\n faceDescriptorTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput\n ? faceDescriptorsForBatch\n : faceDescriptorsForBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_recognition_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { scale } from './scaleLayer';\nimport { ConvLayerParams } from './types';\n\nfunction convLayer(\n x: tf.Tensor4D,\n params: ConvLayerParams,\n strides: [number, number],\n withRelu: boolean,\n padding: 'valid' | 'same' = 'same',\n): tf.Tensor4D {\n const { filters, bias } = params.conv;\n\n let out = tf.conv2d(x, filters, strides, padding);\n out = tf.add(out, bias);\n out = scale(out, params.scale);\n return withRelu ? tf.relu(out) : out;\n}\n\nexport function conv(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], true);\n}\n\nexport function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], false);\n}\n\nexport function convDown(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [2, 2], true, 'valid');\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ScaleLayerParams } from './types';\n\nexport function scale(x: tf.Tensor4D, params: ScaleLayerParams): tf.Tensor4D {\n return tf.add(tf.mul(x, params.weights), params.biases);\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping,\n} from '../common/index';\nimport { isFloat } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {\n const weights = extractWeights(numFilterValues);\n const depth = weights.length / (numFilters * filterSize * filterSize);\n\n if (isFloat(depth)) {\n throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`);\n }\n\n return tf.tidy(\n () => tf.transpose(\n tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),\n [2, 3, 1, 0],\n ),\n );\n }\n\n function extractConvParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams {\n const filters = extractFilterValues(numFilterValues, numFilters, filterSize);\n const bias = tf.tensor1d(extractWeights(numFilters));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n }\n\n function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {\n const weights = tf.tensor1d(extractWeights(numWeights));\n const biases = tf.tensor1d(extractWeights(numWeights));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/biases` },\n );\n\n return {\n weights,\n biases,\n };\n }\n\n function extractConvLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvLayerParams {\n const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`);\n const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`);\n\n return { conv, scale };\n }\n\n function extractResidualLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n isDown: boolean = false,\n ): ResidualLayerParams {\n const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`);\n const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`);\n\n return { conv1, conv2 };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down');\n const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1');\n const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2');\n const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3');\n\n const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true);\n const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1');\n const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2');\n const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3');\n\n const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true);\n const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1');\n const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2');\n\n const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true);\n const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1');\n const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2');\n const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out');\n\n const fc = tf.tidy(\n () => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0]),\n );\n paramMappings.push({ paramPath: 'fc' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common/index';\nimport { isTensor2D } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractScaleLayerParams(prefix: string): ScaleLayerParams {\n const weights = extractWeightEntry(`${prefix}/scale/weights`, 1);\n const biases = extractWeightEntry(`${prefix}/scale/biases`, 1);\n\n return { weights, biases };\n }\n\n function extractConvLayerParams(prefix: string): ConvLayerParams {\n const filters = extractWeightEntry(`${prefix}/conv/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/conv/bias`, 1);\n const scale = extractScaleLayerParams(prefix);\n\n return { conv: { filters, bias }, scale };\n }\n\n function extractResidualLayerParams(prefix: string): ResidualLayerParams {\n return {\n conv1: extractConvLayerParams(`${prefix}/conv1`),\n conv2: extractConvLayerParams(`${prefix}/conv2`),\n };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const conv32_down = extractConvLayerParams('conv32_down');\n const conv32_1 = extractResidualLayerParams('conv32_1');\n const conv32_2 = extractResidualLayerParams('conv32_2');\n const conv32_3 = extractResidualLayerParams('conv32_3');\n\n const conv64_down = extractResidualLayerParams('conv64_down');\n const conv64_1 = extractResidualLayerParams('conv64_1');\n const conv64_2 = extractResidualLayerParams('conv64_2');\n const conv64_3 = extractResidualLayerParams('conv64_3');\n\n const conv128_down = extractResidualLayerParams('conv128_down');\n const conv128_1 = extractResidualLayerParams('conv128_1');\n const conv128_2 = extractResidualLayerParams('conv128_2');\n\n const conv256_down = extractResidualLayerParams('conv256_down');\n const conv256_1 = extractResidualLayerParams('conv256_1');\n const conv256_2 = extractResidualLayerParams('conv256_2');\n const conv256_down_out = extractResidualLayerParams('conv256_down_out');\n\n const { fc } = weightMap;\n paramMappings.push({ originalPath: 'fc', paramPath: 'fc' });\n\n if (!isTensor2D(fc)) {\n throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { conv, convDown, convNoRelu } from './convLayer';\nimport { ResidualLayerParams } from './types';\n\nexport function residual(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = conv(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n out = tf.add(out, x);\n out = tf.relu(out);\n return out;\n}\n\nexport function residualDown(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = convDown(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n\n let pooled = tf.avgPool(x, 2, 2, 'valid') as tf.Tensor4D;\n const zeros = tf.zeros(pooled.shape);\n const isPad = pooled.shape[3] !== out.shape[3];\n const isAdjustShape = pooled.shape[1] !== out.shape[1] || pooled.shape[2] !== out.shape[2];\n\n if (isAdjustShape) {\n const padShapeX = [...out.shape] as [number, number, number, number];\n padShapeX[1] = 1;\n const zerosW = tf.zeros(padShapeX);\n out = tf.concat([out, zerosW], 1);\n\n const padShapeY = [...out.shape] as [number, number, number, number];\n padShapeY[2] = 1;\n const zerosH = tf.zeros(padShapeY);\n out = tf.concat([out, zerosH], 2);\n }\n\n pooled = isPad ? tf.concat([pooled, zeros], 3) : pooled;\n out = tf.add(pooled, out) as tf.Tensor4D;\n\n out = tf.relu(out);\n return out;\n}\n", "import { FaceRecognitionNet } from './FaceRecognitionNet';\n\nexport * from './FaceRecognitionNet';\n\nexport function createFaceRecognitionNet(weights: Float32Array) {\n const net = new FaceRecognitionNet();\n net.extractWeights(weights);\n return net;\n}\n", "export type WithFaceDescriptor = TSource & {\n descriptor: Float32Array\n}\n\nexport function extendWithFaceDescriptor<\n TSource\n>(\n sourceObj: TSource,\n descriptor: Float32Array,\n): WithFaceDescriptor {\n const extension = { descriptor };\n return { ...sourceObj, ...extension };\n}\n", "export type WithAge = TSource & {\n age: number\n}\n\nexport function isWithAge(obj: any): obj is WithAge<{}> {\n return typeof obj.age === 'number';\n}\n\nexport function extendWithAge<\n TSource\n>(\n sourceObj: TSource,\n age: number,\n): WithAge {\n const extension = { age };\n return { ...sourceObj, ...extension };\n}\n", "import { Gender } from '../ageGenderNet/types';\nimport { isValidProbablitiy } from '../utils/index';\n\nexport type WithGender = TSource & {\n gender: Gender\n genderProbability: number\n}\n\nexport function isWithGender(obj: any): obj is WithGender<{}> {\n return (obj.gender === Gender.MALE || obj.gender === Gender.FEMALE)\n && isValidProbablitiy(obj.genderProbability);\n}\n\nexport function extendWithGender<\n TSource\n>(\n sourceObj: TSource,\n gender: Gender,\n genderProbability: number,\n): WithGender {\n const extension = { gender, genderProbability };\n return { ...sourceObj, ...extension };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { mobileNetV1 } from './mobileNetV1';\nimport { nonMaxSuppression } from './nonMaxSuppression';\nimport { outputLayer } from './outputLayer';\nimport { predictionLayer } from './predictionLayer';\nimport { ISsdMobilenetv1Options, SsdMobilenetv1Options } from './SsdMobilenetv1Options';\nimport { NetParams } from './types';\n\nexport class SsdMobilenetv1 extends NeuralNetwork {\n constructor() {\n super('SsdMobilenetv1');\n }\n\n public forwardInput(input: NetInput) {\n const { params } = this;\n\n if (!params) {\n throw new Error('SsdMobilenetv1 - load model before inference');\n }\n\n return tf.tidy(() => {\n // const batchTensor = input.toBatchTensor(512, false).toFloat()\n const batchTensor = tf.cast(input.toBatchTensor(512, false), 'float32');\n\n const x = tf.sub(tf.mul(batchTensor, tf.scalar(0.007843137718737125)), tf.scalar(1)) as tf.Tensor4D;\n const features = mobileNetV1(x, params.mobilenetv1);\n\n const {\n boxPredictions,\n classPredictions,\n } = predictionLayer(features.out, features.conv11, params.prediction_layer);\n\n return outputLayer(boxPredictions, classPredictions, params.output_layer);\n });\n }\n\n public async forward(input: TNetInput) {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async locateFaces(\n input: TNetInput,\n options: ISsdMobilenetv1Options = {},\n ): Promise {\n const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);\n\n const netInput = await toNetInput(input);\n\n const {\n boxes: _boxes,\n scores: _scores,\n } = this.forwardInput(netInput);\n\n // TODO batches\n const boxes = _boxes[0];\n const scores = _scores[0];\n for (let i = 1; i < _boxes.length; i++) {\n _boxes[i].dispose();\n _scores[i].dispose();\n }\n\n // TODO find a better way to filter by minConfidence\n const scoresData = Array.from(await scores.data());\n\n const iouThreshold = 0.5;\n const indices = nonMaxSuppression(\n boxes,\n scoresData as number[],\n maxResults,\n iouThreshold,\n minConfidence,\n );\n\n const reshapedDims = netInput.getReshapedInputDimensions(0);\n const inputSize = netInput.inputSize as number;\n const padX = inputSize / reshapedDims.width;\n const padY = inputSize / reshapedDims.height;\n\n const boxesData = boxes.arraySync();\n const results = indices\n .map((idx) => {\n const [top, bottom] = [\n Math.max(0, boxesData[idx][0]),\n Math.min(1.0, boxesData[idx][2]),\n ].map((val) => val * padY);\n const [left, right] = [\n Math.max(0, boxesData[idx][1]),\n Math.min(1.0, boxesData[idx][3]),\n ].map((val) => val * padX);\n return new FaceDetection(\n scoresData[idx] as number,\n new Rect(\n left,\n top,\n right - left,\n bottom - top,\n ),\n {\n height: netInput.getInputHeight(0),\n width: netInput.getInputWidth(0),\n },\n );\n });\n\n boxes.dispose();\n scores.dispose();\n\n return results;\n }\n\n protected getDefaultModelName(): string {\n return 'ssd_mobilenetv1_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ExtractWeightsFunction, ParamMapping, ConvParams, extractWeightsFactory,\n} from '../common/index';\nimport {\n MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractDepthwiseConvParams(numChannels: number, mappedPrefix: string): MobileNetV1.DepthwiseConvParams {\n const filters = tf.tensor4d(extractWeights(3 * 3 * numChannels), [3, 3, numChannels, 1]);\n const batch_norm_scale = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_offset = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_mean = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_variance = tf.tensor1d(extractWeights(numChannels));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/batch_norm_scale` },\n { paramPath: `${mappedPrefix}/batch_norm_offset` },\n { paramPath: `${mappedPrefix}/batch_norm_mean` },\n { paramPath: `${mappedPrefix}/batch_norm_variance` },\n );\n\n return {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n };\n }\n\n function extractConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n isPointwiseConv?: boolean,\n ): ConvParams {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/${isPointwiseConv ? 'batch_norm_offset' : 'bias'}` },\n );\n\n return { filters, bias };\n }\n\n function extractPointwiseConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): PointwiseConvParams {\n const {\n filters,\n bias,\n } = extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix, true);\n\n return {\n filters,\n batch_norm_offset: bias,\n };\n }\n\n function extractConvPairParams(\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): MobileNetV1.ConvPairParams {\n const depthwise_conv = extractDepthwiseConvParams(channelsIn, `${mappedPrefix}/depthwise_conv`);\n const pointwise_conv = extractPointwiseConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/pointwise_conv`);\n\n return { depthwise_conv, pointwise_conv };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n const conv_0 = extractPointwiseConvParams(3, 32, 3, 'mobilenetv1/conv_0');\n\n const conv_1 = extractConvPairParams(32, 64, 'mobilenetv1/conv_1');\n const conv_2 = extractConvPairParams(64, 128, 'mobilenetv1/conv_2');\n const conv_3 = extractConvPairParams(128, 128, 'mobilenetv1/conv_3');\n const conv_4 = extractConvPairParams(128, 256, 'mobilenetv1/conv_4');\n const conv_5 = extractConvPairParams(256, 256, 'mobilenetv1/conv_5');\n const conv_6 = extractConvPairParams(256, 512, 'mobilenetv1/conv_6');\n const conv_7 = extractConvPairParams(512, 512, 'mobilenetv1/conv_7');\n const conv_8 = extractConvPairParams(512, 512, 'mobilenetv1/conv_8');\n const conv_9 = extractConvPairParams(512, 512, 'mobilenetv1/conv_9');\n const conv_10 = extractConvPairParams(512, 512, 'mobilenetv1/conv_10');\n const conv_11 = extractConvPairParams(512, 512, 'mobilenetv1/conv_11');\n const conv_12 = extractConvPairParams(512, 1024, 'mobilenetv1/conv_12');\n const conv_13 = extractConvPairParams(1024, 1024, 'mobilenetv1/conv_13');\n\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n conv_8,\n conv_9,\n conv_10,\n conv_11,\n conv_12,\n conv_13,\n };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n const conv_0 = extractPointwiseConvParams(1024, 256, 1, 'prediction_layer/conv_0');\n const conv_1 = extractPointwiseConvParams(256, 512, 3, 'prediction_layer/conv_1');\n const conv_2 = extractPointwiseConvParams(512, 128, 1, 'prediction_layer/conv_2');\n const conv_3 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_3');\n const conv_4 = extractPointwiseConvParams(256, 128, 1, 'prediction_layer/conv_4');\n const conv_5 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_5');\n const conv_6 = extractPointwiseConvParams(256, 64, 1, 'prediction_layer/conv_6');\n const conv_7 = extractPointwiseConvParams(64, 128, 3, 'prediction_layer/conv_7');\n\n const box_encoding_0_predictor = extractConvParams(512, 12, 1, 'prediction_layer/box_predictor_0/box_encoding_predictor');\n const class_predictor_0 = extractConvParams(512, 9, 1, 'prediction_layer/box_predictor_0/class_predictor');\n const box_encoding_1_predictor = extractConvParams(1024, 24, 1, 'prediction_layer/box_predictor_1/box_encoding_predictor');\n const class_predictor_1 = extractConvParams(1024, 18, 1, 'prediction_layer/box_predictor_1/class_predictor');\n const box_encoding_2_predictor = extractConvParams(512, 24, 1, 'prediction_layer/box_predictor_2/box_encoding_predictor');\n const class_predictor_2 = extractConvParams(512, 18, 1, 'prediction_layer/box_predictor_2/class_predictor');\n const box_encoding_3_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_3/box_encoding_predictor');\n const class_predictor_3 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_3/class_predictor');\n const box_encoding_4_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_4/box_encoding_predictor');\n const class_predictor_4 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_4/class_predictor');\n const box_encoding_5_predictor = extractConvParams(128, 24, 1, 'prediction_layer/box_predictor_5/box_encoding_predictor');\n const class_predictor_5 = extractConvParams(128, 18, 1, 'prediction_layer/box_predictor_5/class_predictor');\n\n const box_predictor_0 = {\n box_encoding_predictor: box_encoding_0_predictor,\n class_predictor: class_predictor_0,\n };\n const box_predictor_1 = {\n box_encoding_predictor: box_encoding_1_predictor,\n class_predictor: class_predictor_1,\n };\n const box_predictor_2 = {\n box_encoding_predictor: box_encoding_2_predictor,\n class_predictor: class_predictor_2,\n };\n const box_predictor_3 = {\n box_encoding_predictor: box_encoding_3_predictor,\n class_predictor: class_predictor_3,\n };\n const box_predictor_4 = {\n box_encoding_predictor: box_encoding_4_predictor,\n class_predictor: class_predictor_4,\n };\n const box_predictor_5 = {\n box_encoding_predictor: box_encoding_5_predictor,\n class_predictor: class_predictor_5,\n };\n\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n box_predictor_0,\n box_predictor_1,\n box_predictor_2,\n box_predictor_3,\n box_predictor_4,\n box_predictor_5,\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const mobilenetv1 = extractMobilenetV1Params();\n const prediction_layer = extractPredictionLayerParams();\n const extra_dim = tf.tensor3d(\n extractWeights(5118 * 4),\n [1, 5118, 4],\n );\n const output_layer = {\n extra_dim,\n };\n\n paramMappings.push({ paramPath: 'output_layer/extra_dim' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n params: {\n mobilenetv1,\n prediction_layer,\n output_layer,\n },\n paramMappings,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping,\n} from '../common/index';\nimport { isTensor3D } from '../utils/index';\nimport {\n BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractPointwiseConvParams(prefix: string, idx: number, mappedPrefix: string): PointwiseConvParams {\n const filters = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/weights`, 4, `${mappedPrefix}/filters`);\n const batch_norm_offset = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/convolution_bn_offset`, 1, `${mappedPrefix}/batch_norm_offset`);\n\n return { filters, batch_norm_offset };\n }\n\n function extractConvPairParams(idx: number): MobileNetV1.ConvPairParams {\n const mappedPrefix = `mobilenetv1/conv_${idx}`;\n const prefixDepthwiseConv = `MobilenetV1/Conv2d_${idx}_depthwise`;\n const mappedPrefixDepthwiseConv = `${mappedPrefix}/depthwise_conv`;\n const mappedPrefixPointwiseConv = `${mappedPrefix}/pointwise_conv`;\n\n const filters = extractWeightEntry(`${prefixDepthwiseConv}/depthwise_weights`, 4, `${mappedPrefixDepthwiseConv}/filters`);\n const batch_norm_scale = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/gamma`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_scale`);\n const batch_norm_offset = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/beta`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_offset`);\n const batch_norm_mean = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_mean`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_mean`);\n const batch_norm_variance = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_variance`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_variance`);\n\n return {\n depthwise_conv: {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n },\n pointwise_conv: extractPointwiseConvParams('MobilenetV1', idx, mappedPrefixPointwiseConv),\n };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n return {\n conv_0: extractPointwiseConvParams('MobilenetV1', 0, 'mobilenetv1/conv_0'),\n conv_1: extractConvPairParams(1),\n conv_2: extractConvPairParams(2),\n conv_3: extractConvPairParams(3),\n conv_4: extractConvPairParams(4),\n conv_5: extractConvPairParams(5),\n conv_6: extractConvPairParams(6),\n conv_7: extractConvPairParams(7),\n conv_8: extractConvPairParams(8),\n conv_9: extractConvPairParams(9),\n conv_10: extractConvPairParams(10),\n conv_11: extractConvPairParams(11),\n conv_12: extractConvPairParams(12),\n conv_13: extractConvPairParams(13),\n };\n }\n\n function extractConvParams(prefix: string, mappedPrefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/weights`, 4, `${mappedPrefix}/filters`);\n const bias = extractWeightEntry(`${prefix}/biases`, 1, `${mappedPrefix}/bias`);\n\n return { filters, bias };\n }\n\n function extractBoxPredictorParams(idx: number): BoxPredictionParams {\n const box_encoding_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/BoxEncodingPredictor`,\n `prediction_layer/box_predictor_${idx}/box_encoding_predictor`,\n );\n const class_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/ClassPredictor`,\n `prediction_layer/box_predictor_${idx}/class_predictor`,\n );\n\n return { box_encoding_predictor, class_predictor };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n return {\n conv_0: extractPointwiseConvParams('Prediction', 0, 'prediction_layer/conv_0'),\n conv_1: extractPointwiseConvParams('Prediction', 1, 'prediction_layer/conv_1'),\n conv_2: extractPointwiseConvParams('Prediction', 2, 'prediction_layer/conv_2'),\n conv_3: extractPointwiseConvParams('Prediction', 3, 'prediction_layer/conv_3'),\n conv_4: extractPointwiseConvParams('Prediction', 4, 'prediction_layer/conv_4'),\n conv_5: extractPointwiseConvParams('Prediction', 5, 'prediction_layer/conv_5'),\n conv_6: extractPointwiseConvParams('Prediction', 6, 'prediction_layer/conv_6'),\n conv_7: extractPointwiseConvParams('Prediction', 7, 'prediction_layer/conv_7'),\n box_predictor_0: extractBoxPredictorParams(0),\n box_predictor_1: extractBoxPredictorParams(1),\n box_predictor_2: extractBoxPredictorParams(2),\n box_predictor_3: extractBoxPredictorParams(3),\n box_predictor_4: extractBoxPredictorParams(4),\n box_predictor_5: extractBoxPredictorParams(5),\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const extra_dim = weightMap['Output/extra_dim'];\n paramMappings.push({ originalPath: 'Output/extra_dim', paramPath: 'output_layer/extra_dim' });\n\n if (!isTensor3D(extra_dim)) {\n throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${extra_dim}`);\n }\n\n const params = {\n mobilenetv1: extractMobilenetV1Params(),\n prediction_layer: extractPredictionLayerParams(),\n output_layer: {\n extra_dim,\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { MobileNetV1 } from './types';\n\nconst epsilon = 0.0010000000474974513;\n\nfunction depthwiseConvLayer(\n x: tf.Tensor4D,\n params: MobileNetV1.DepthwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.depthwiseConv2d(x, params.filters, strides, 'same');\n out = tf.batchNorm(\n out,\n params.batch_norm_mean,\n params.batch_norm_variance,\n params.batch_norm_offset,\n params.batch_norm_scale,\n epsilon,\n );\n return tf.clipByValue(out, 0, 6);\n });\n}\n\nfunction getStridesForLayerIdx(layerIdx: number): [number, number] {\n return [2, 4, 6, 12].some((idx) => idx === layerIdx) ? [2, 2] : [1, 1];\n}\n\nexport function mobileNetV1(x: tf.Tensor4D, params: MobileNetV1.Params) {\n return tf.tidy(() => {\n let conv11;\n let out = pointwiseConvLayer(x, params.conv_0, [2, 2]);\n\n const convPairParams = [\n params.conv_1,\n params.conv_2,\n params.conv_3,\n params.conv_4,\n params.conv_5,\n params.conv_6,\n params.conv_7,\n params.conv_8,\n params.conv_9,\n params.conv_10,\n params.conv_11,\n params.conv_12,\n params.conv_13,\n ];\n\n convPairParams.forEach((param, i) => {\n const layerIdx = i + 1;\n const depthwiseConvStrides = getStridesForLayerIdx(layerIdx);\n out = depthwiseConvLayer(out, param.depthwise_conv, depthwiseConvStrides);\n out = pointwiseConvLayer(out, param.pointwise_conv, [1, 1]);\n if (layerIdx === 11) {\n conv11 = out;\n }\n });\n\n if (conv11 === null) {\n throw new Error('mobileNetV1 - output of conv layer 11 is null');\n }\n\n return {\n out,\n conv11: conv11 as any,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { PointwiseConvParams } from './types';\n\nexport function pointwiseConvLayer(\n x: tf.Tensor4D,\n params: PointwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.conv2d(x, params.filters, strides, 'same');\n out = tf.add(out, params.batch_norm_offset);\n return tf.clipByValue(out, 0, 6);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nfunction IOU(boxes: tf.Tensor2D, i: number, j: number) {\n const boxesData = boxes.arraySync();\n const yminI = Math.min(boxesData[i][0], boxesData[i][2]);\n const xminI = Math.min(boxesData[i][1], boxesData[i][3]);\n const ymaxI = Math.max(boxesData[i][0], boxesData[i][2]);\n const xmaxI = Math.max(boxesData[i][1], boxesData[i][3]);\n const yminJ = Math.min(boxesData[j][0], boxesData[j][2]);\n const xminJ = Math.min(boxesData[j][1], boxesData[j][3]);\n const ymaxJ = Math.max(boxesData[j][0], boxesData[j][2]);\n const xmaxJ = Math.max(boxesData[j][1], boxesData[j][3]);\n const areaI = (ymaxI - yminI) * (xmaxI - xminI);\n const areaJ = (ymaxJ - yminJ) * (xmaxJ - xminJ);\n if (areaI <= 0 || areaJ <= 0) {\n return 0.0;\n }\n const intersectionYmin = Math.max(yminI, yminJ);\n const intersectionXmin = Math.max(xminI, xminJ);\n const intersectionYmax = Math.min(ymaxI, ymaxJ);\n const intersectionXmax = Math.min(xmaxI, xmaxJ);\n const intersectionArea = Math.max(intersectionYmax - intersectionYmin, 0.0)\n * Math.max(intersectionXmax - intersectionXmin, 0.0);\n return intersectionArea / (areaI + areaJ - intersectionArea);\n}\n\nexport function nonMaxSuppression(\n boxes: tf.Tensor2D,\n scores: number[],\n maxOutputSize: number,\n iouThreshold: number,\n scoreThreshold: number,\n): number[] {\n const numBoxes = boxes.shape[0];\n const outputSize = Math.min(\n maxOutputSize,\n numBoxes,\n );\n\n const candidates = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .filter((c) => c.score > scoreThreshold)\n .sort((c1, c2) => c2.score - c1.score);\n\n const suppressFunc = (x: number) => (x <= iouThreshold ? 1 : 0);\n\n const selected: number[] = [];\n\n candidates.forEach((c) => {\n if (selected.length >= outputSize) {\n return;\n }\n const originalScore = c.score;\n\n for (let j = selected.length - 1; j >= 0; --j) {\n const iou = IOU(boxes, c.boxIndex, selected[j]);\n if (iou === 0.0) continue;\n c.score *= suppressFunc(iou);\n if (c.score <= scoreThreshold) break;\n }\n if (originalScore === c.score) {\n selected.push(c.boxIndex);\n }\n });\n\n return selected;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { OutputLayerParams } from './types';\n\nfunction getCenterCoordinatesAndSizesLayer(x: tf.Tensor2D) {\n const vec = tf.unstack(tf.transpose(x, [1, 0]));\n\n const sizes = [\n tf.sub(vec[2], vec[0]),\n tf.sub(vec[3], vec[1]),\n ];\n\n const centers = [\n tf.add(vec[0], tf.div(sizes[0], tf.scalar(2))),\n tf.add(vec[1], tf.div(sizes[1], tf.scalar(2))),\n ];\n\n return {\n sizes,\n centers,\n };\n}\n\nfunction decodeBoxesLayer(x0: tf.Tensor2D, x1: tf.Tensor2D) {\n const {\n sizes,\n centers,\n } = getCenterCoordinatesAndSizesLayer(x0);\n\n const vec = tf.unstack(tf.transpose(x1, [1, 0]));\n\n const div0_out = tf.div(tf.mul(tf.exp(tf.div(vec[2], tf.scalar(5))), sizes[0]), tf.scalar(2));\n const add0_out = tf.add(tf.mul(tf.div(vec[0], tf.scalar(10)), sizes[0]), centers[0]);\n\n const div1_out = tf.div(tf.mul(tf.exp(tf.div(vec[3], tf.scalar(5))), sizes[1]), tf.scalar(2));\n const add1_out = tf.add(tf.mul(tf.div(vec[1], tf.scalar(10)), sizes[1]), centers[1]);\n\n return tf.transpose(\n tf.stack([\n tf.sub(add0_out, div0_out),\n tf.sub(add1_out, div1_out),\n tf.add(add0_out, div0_out),\n tf.add(add1_out, div1_out),\n ]),\n [1, 0],\n );\n}\n\nexport function outputLayer(\n boxPredictions: tf.Tensor4D,\n classPredictions: tf.Tensor4D,\n params: OutputLayerParams,\n) {\n return tf.tidy(() => {\n const batchSize = boxPredictions.shape[0];\n\n let boxes = decodeBoxesLayer(\n tf.reshape(tf.tile(params.extra_dim, [batchSize, 1, 1]), [-1, 4]) as tf.Tensor2D,\n tf.reshape(boxPredictions, [-1, 4]) as tf.Tensor2D,\n );\n boxes = tf.reshape(\n boxes,\n [batchSize, (boxes.shape[0] / batchSize), 4],\n );\n\n const scoresAndClasses = tf.sigmoid(tf.slice(classPredictions, [0, 0, 1], [-1, -1, -1]));\n let scores = tf.slice(scoresAndClasses, [0, 0, 0], [-1, -1, 1]) as tf.Tensor;\n\n scores = tf.reshape(\n scores,\n [batchSize, scores.shape[1] as number],\n );\n\n const boxesByBatch = tf.unstack(boxes) as tf.Tensor2D[];\n const scoresByBatch = tf.unstack(scores) as tf.Tensor1D[];\n\n return {\n boxes: boxesByBatch,\n scores: scoresByBatch,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { boxPredictionLayer } from './boxPredictionLayer';\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { PredictionLayerParams } from './types';\n\nexport function predictionLayer(\n x: tf.Tensor4D,\n conv11: tf.Tensor4D,\n params: PredictionLayerParams,\n) {\n return tf.tidy(() => {\n const conv0 = pointwiseConvLayer(x, params.conv_0, [1, 1]);\n const conv1 = pointwiseConvLayer(conv0, params.conv_1, [2, 2]);\n const conv2 = pointwiseConvLayer(conv1, params.conv_2, [1, 1]);\n const conv3 = pointwiseConvLayer(conv2, params.conv_3, [2, 2]);\n const conv4 = pointwiseConvLayer(conv3, params.conv_4, [1, 1]);\n const conv5 = pointwiseConvLayer(conv4, params.conv_5, [2, 2]);\n const conv6 = pointwiseConvLayer(conv5, params.conv_6, [1, 1]);\n const conv7 = pointwiseConvLayer(conv6, params.conv_7, [2, 2]);\n\n const boxPrediction0 = boxPredictionLayer(conv11, params.box_predictor_0);\n const boxPrediction1 = boxPredictionLayer(x, params.box_predictor_1);\n const boxPrediction2 = boxPredictionLayer(conv1, params.box_predictor_2);\n const boxPrediction3 = boxPredictionLayer(conv3, params.box_predictor_3);\n const boxPrediction4 = boxPredictionLayer(conv5, params.box_predictor_4);\n const boxPrediction5 = boxPredictionLayer(conv7, params.box_predictor_5);\n\n const boxPredictions = tf.concat([\n boxPrediction0.boxPredictionEncoding,\n boxPrediction1.boxPredictionEncoding,\n boxPrediction2.boxPredictionEncoding,\n boxPrediction3.boxPredictionEncoding,\n boxPrediction4.boxPredictionEncoding,\n boxPrediction5.boxPredictionEncoding,\n ], 1) as tf.Tensor4D;\n\n const classPredictions = tf.concat([\n boxPrediction0.classPrediction,\n boxPrediction1.classPrediction,\n boxPrediction2.classPrediction,\n boxPrediction3.classPrediction,\n boxPrediction4.classPrediction,\n boxPrediction5.classPrediction,\n ], 1) as tf.Tensor4D;\n\n return {\n boxPredictions,\n classPredictions,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { convLayer } from '../common/index';\nimport { BoxPredictionParams } from './types';\n\nexport function boxPredictionLayer(\n x: tf.Tensor4D,\n params: BoxPredictionParams,\n) {\n return tf.tidy(() => {\n const batchSize = x.shape[0];\n\n const boxPredictionEncoding = tf.reshape(\n convLayer(x, params.box_encoding_predictor),\n [batchSize, -1, 1, 4],\n );\n const classPrediction = tf.reshape(\n convLayer(x, params.class_predictor),\n [batchSize, -1, 3],\n );\n\n return {\n boxPredictionEncoding,\n classPrediction,\n };\n });\n}\n", "export interface ISsdMobilenetv1Options {\n minConfidence?: number\n maxResults?: number\n}\n\nexport class SsdMobilenetv1Options {\n protected _name: string = 'SsdMobilenetv1Options'\n\n private _minConfidence: number\n\n private _maxResults: number\n\n constructor({ minConfidence, maxResults }: ISsdMobilenetv1Options = {}) {\n this._minConfidence = minConfidence || 0.5;\n this._maxResults = maxResults || 100;\n\n if (typeof this._minConfidence !== 'number' || this._minConfidence <= 0 || this._minConfidence >= 1) {\n throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);\n }\n\n if (typeof this._maxResults !== 'number') {\n throw new Error(`${this._name} - expected maxResults to be a number`);\n }\n }\n\n get minConfidence(): number { return this._minConfidence; }\n\n get maxResults(): number { return this._maxResults; }\n}\n", "import { SsdMobilenetv1 } from './SsdMobilenetv1';\n\nexport * from './SsdMobilenetv1';\nexport * from './SsdMobilenetv1Options';\n\nexport function createSsdMobilenetv1(weights: Float32Array) {\n const net = new SsdMobilenetv1();\n net.extractWeights(weights);\n return net;\n}\n\nexport function createFaceDetectionNet(weights: Float32Array) {\n return createSsdMobilenetv1(weights);\n}\n\n// alias for backward compatibily\nexport class FaceDetectionNet extends SsdMobilenetv1 {}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(0.738768, 0.874946),\n new Point(2.42204, 2.65704),\n new Point(4.30971, 7.04493),\n new Point(10.246, 4.59428),\n new Point(12.6868, 11.8741),\n];\n\nexport const BOX_ANCHORS_SEPARABLE = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB_SEPARABLE: [number, number, number] = [117.001, 114.697, 97.404];\n\nexport const DEFAULT_MODEL_NAME = 'tiny_yolov2_model';\nexport const DEFAULT_MODEL_NAME_SEPARABLE_CONV = 'tiny_yolov2_separable_conv_model';\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { BoundingBox } from '../classes/BoundingBox';\nimport { Dimensions } from '../classes/Dimensions';\nimport { ObjectDetection } from '../classes/ObjectDetection';\nimport { convLayer } from '../common/index';\nimport { ConvParams, SeparableConvParams } from '../common/types';\nimport { toNetInput } from '../dom/index';\nimport { NetInput } from '../dom/NetInput';\nimport { TNetInput } from '../dom/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { sigmoid } from '../ops/index';\nimport { nonMaxSuppression } from '../ops/nonMaxSuppression';\nimport { normalize } from '../ops/normalize';\nimport { TinyYolov2Config, validateConfig } from './config';\nimport { convWithBatchNorm } from './convWithBatchNorm';\nimport { depthwiseSeparableConv } from './depthwiseSeparableConv';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { leaky } from './leaky';\nimport { ITinyYolov2Options, TinyYolov2Options } from './TinyYolov2Options';\nimport { DefaultTinyYolov2NetParams, MobilenetParams, TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2Base extends NeuralNetwork {\n public static DEFAULT_FILTER_SIZES = [\n 3, 16, 32, 64, 128, 256, 512, 1024, 1024,\n ]\n\n private _config: TinyYolov2Config\n\n constructor(config: TinyYolov2Config) {\n super('TinyYolov2');\n validateConfig(config);\n this._config = config;\n }\n\n public get config(): TinyYolov2Config {\n return this._config;\n }\n\n public get withClassScores(): boolean {\n return this.config.withClassScores || this.config.classes.length > 1;\n }\n\n public get boxEncodingSize(): number {\n return 5 + (this.withClassScores ? this.config.classes.length : 0);\n }\n\n public runTinyYolov2(x: tf.Tensor4D, params: DefaultTinyYolov2NetParams): tf.Tensor4D {\n let out = convWithBatchNorm(x, params.conv0);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = convWithBatchNorm(out, params.conv6);\n out = convWithBatchNorm(out, params.conv7);\n\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public runMobilenet(x: tf.Tensor4D, params: MobilenetParams): tf.Tensor4D {\n let out = this.config.isFirstLayerConv2d\n ? leaky(convLayer(x, params.conv0 as ConvParams, 'valid', false))\n : depthwiseSeparableConv(x, params.conv0 as SeparableConvParams);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = params.conv6 ? depthwiseSeparableConv(out, params.conv6) : out;\n out = params.conv7 ? depthwiseSeparableConv(out, params.conv7) : out;\n\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public forwardInput(input: NetInput, inputSize: number): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyYolov2 - load model before inference');\n }\n\n return tf.tidy(() => {\n // let batchTensor = input.toBatchTensor(inputSize, false).toFloat()\n let batchTensor = tf.cast(input.toBatchTensor(inputSize, false), 'float32');\n batchTensor = this.config.meanRgb\n ? normalize(batchTensor, this.config.meanRgb)\n : batchTensor;\n batchTensor = batchTensor.div(tf.scalar(256)) as tf.Tensor4D;\n\n return this.config.withSeparableConvs\n ? this.runMobilenet(batchTensor, params as MobilenetParams)\n : this.runTinyYolov2(batchTensor, params as DefaultTinyYolov2NetParams);\n });\n }\n\n public async forward(input: TNetInput, inputSize: number): Promise {\n return this.forwardInput(await toNetInput(input), inputSize);\n }\n\n public async detect(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise {\n const { inputSize, scoreThreshold } = new TinyYolov2Options(forwardParams);\n\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput, inputSize);\n const out0 = tf.tidy(() => tf.unstack(out)[0].expandDims()) as tf.Tensor4D;\n\n const inputDimensions = {\n width: netInput.getInputWidth(0),\n height: netInput.getInputHeight(0),\n };\n\n const results = await this.extractBoxes(out0, netInput.getReshapedInputDimensions(0), scoreThreshold);\n out.dispose();\n out0.dispose();\n\n const boxes = results.map((res) => res.box);\n const scores = results.map((res) => res.score);\n const classScores = results.map((res) => res.classScore);\n const classNames = results.map((res) => this.config.classes[res.label]);\n\n const indices = nonMaxSuppression(\n boxes.map((box) => box.rescale(inputSize)),\n scores,\n this.config.iouThreshold,\n true,\n );\n\n const detections = indices.map((idx) => new ObjectDetection(\n scores[idx],\n classScores[idx],\n classNames[idx],\n boxes[idx],\n inputDimensions,\n ));\n\n return detections;\n }\n\n protected getDefaultModelName(): string {\n return '';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this.config);\n }\n\n protected extractParams(weights: Float32Array) {\n const filterSizes = this.config.filterSizes || TinyYolov2Base.DEFAULT_FILTER_SIZES;\n\n const numFilters = filterSizes ? filterSizes.length : undefined;\n if (numFilters !== 7 && numFilters !== 8 && numFilters !== 9) {\n throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${numFilters} filterSizes in config`);\n }\n return extractParams(weights, this.config, this.boxEncodingSize, filterSizes);\n }\n\n protected async extractBoxes(\n outputTensor: tf.Tensor4D,\n inputBlobDimensions: Dimensions,\n scoreThreshold?: number,\n ) {\n const { width, height } = inputBlobDimensions;\n const inputSize = Math.max(width, height);\n const correctionFactorX = inputSize / width;\n const correctionFactorY = inputSize / height;\n\n const numCells = outputTensor.shape[1];\n const numBoxes = this.config.anchors.length;\n\n const [boxesTensor, scoresTensor, classScoresTensor] = tf.tidy(() => {\n const reshaped = outputTensor.reshape([numCells, numCells, numBoxes, this.boxEncodingSize]);\n\n const boxes = reshaped.slice([0, 0, 0, 0], [numCells, numCells, numBoxes, 4]);\n const scores = reshaped.slice([0, 0, 0, 4], [numCells, numCells, numBoxes, 1]);\n const classScores = this.withClassScores\n ? tf.softmax(reshaped.slice([0, 0, 0, 5], [numCells, numCells, numBoxes, this.config.classes.length]), 3)\n : tf.scalar(0);\n return [boxes, scores, classScores];\n });\n\n const results = [] as any;\n\n const scoresData = await scoresTensor.array();\n const boxesData = await boxesTensor.array();\n for (let row = 0; row < numCells; row++) {\n for (let col = 0; col < numCells; col++) {\n for (let anchor = 0; anchor < numBoxes; anchor++) {\n const score = sigmoid(scoresData[row][col][anchor][0]);\n if (!scoreThreshold || score > scoreThreshold) {\n const ctX = ((col + sigmoid(boxesData[row][col][anchor][0])) / numCells) * correctionFactorX;\n const ctY = ((row + sigmoid(boxesData[row][col][anchor][1])) / numCells) * correctionFactorY;\n const widthLocal = ((Math.exp(boxesData[row][col][anchor][2]) * this.config.anchors[anchor].x) / numCells) * correctionFactorX;\n const heightLocal = ((Math.exp(boxesData[row][col][anchor][3]) * this.config.anchors[anchor].y) / numCells) * correctionFactorY;\n\n const x = (ctX - (widthLocal / 2));\n const y = (ctY - (heightLocal / 2));\n\n const pos = { row, col, anchor };\n const { classScore, label } = this.withClassScores\n ? await this.extractPredictedClass(classScoresTensor as tf.Tensor4D, pos)\n : { classScore: 1, label: 0 };\n\n results.push({\n box: new BoundingBox(x, y, x + widthLocal, y + heightLocal),\n score,\n classScore: score * classScore,\n label,\n ...pos,\n });\n }\n }\n }\n }\n\n boxesTensor.dispose();\n scoresTensor.dispose();\n classScoresTensor.dispose();\n\n return results;\n }\n\n private async extractPredictedClass(classesTensor: tf.Tensor4D, pos: { row: number, col: number, anchor: number }) {\n const { row, col, anchor } = pos;\n const classesData = await classesTensor.array();\n return Array(this.config.classes.length).fill(0)\n .map((_, i) => classesData[row][col][anchor][i])\n .map((classScore, label) => ({\n classScore,\n label,\n }))\n .reduce((max, curr) => (max.classScore > curr.classScore ? max : curr));\n }\n}\n", "import { Point } from '../classes/Point';\n\nexport type TinyYolov2Config = {\n withSeparableConvs: boolean\n iouThreshold: number\n anchors: Point[]\n classes: string[]\n meanRgb?: [number, number, number]\n withClassScores?: boolean,\n filterSizes?: number[]\n isFirstLayerConv2d?: boolean\n}\n\nconst isNumber = (arg: any) => typeof arg === 'number';\n\nexport function validateConfig(config: any) {\n if (!config) {\n throw new Error(`invalid config: ${config}`);\n }\n\n if (typeof config.withSeparableConvs !== 'boolean') {\n throw new Error(`config.withSeparableConvs has to be a boolean, have: ${config.withSeparableConvs}`);\n }\n\n if (!isNumber(config.iouThreshold) || config.iouThreshold < 0 || config.iouThreshold > 1.0) {\n throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${config.iouThreshold}`);\n }\n\n if (\n !Array.isArray(config.classes)\n || !config.classes.length\n || !config.classes.every((c: any) => typeof c === 'string')\n ) {\n throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(config.classes)}`);\n }\n\n if (\n !Array.isArray(config.anchors)\n || !config.anchors.length\n || !config.anchors.map((a: any) => a || {}).every((a: any) => isNumber(a.x) && isNumber(a.y))\n ) {\n throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(config.anchors)}`);\n }\n\n if (config.meanRgb && (\n !Array.isArray(config.meanRgb)\n || config.meanRgb.length !== 3\n || !config.meanRgb.every(isNumber)\n )) {\n throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(config.meanRgb)}`);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { leaky } from './leaky';\nimport { ConvWithBatchNorm } from './types';\n\nexport function convWithBatchNorm(x: tf.Tensor4D, params: ConvWithBatchNorm): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n\n out = tf.conv2d(out, params.conv.filters, [1, 1], 'valid');\n out = tf.sub(out, params.bn.sub);\n out = tf.mul(out, params.bn.truediv);\n out = tf.add(out, params.conv.bias);\n\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function leaky(x: tf.Tensor4D): tf.Tensor4D {\n return tf.tidy(() => {\n const min = tf.mul(x, tf.scalar(0.10000000149011612));\n return tf.add(tf.relu(tf.sub(x, min)), min);\n // return tf.maximum(x, min)\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from '../common/types';\nimport { leaky } from './leaky';\n\nexport function depthwiseSeparableConv(x: tf.Tensor4D, params: SeparableConvParams): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n\n out = tf.separableConv2d(out, params.depthwise_filter, params.pointwise_filter, [1, 1], 'valid');\n out = tf.add(out, params.bias);\n\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { extractConvParamsFactory } from '../common/index';\nimport { extractSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightsFactory } from '../common/extractWeightsFactory';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n\n function extractBatchNormParams(size: number, mappedPrefix: string): BatchNorm {\n const sub = tf.tensor1d(extractWeights(size));\n const truediv = tf.tensor1d(extractWeights(size));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/sub` },\n { paramPath: `${mappedPrefix}/truediv` },\n );\n\n return { sub, truediv };\n }\n\n function extractConvWithBatchNormParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv`);\n const bn = extractBatchNormParams(channelsOut, `${mappedPrefix}/bn`);\n\n return { conv, bn };\n }\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParams(\n weights: Float32Array,\n config: TinyYolov2Config,\n boxEncodingSize: number,\n filterSizes: number[],\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n\n const conv0 = config.isFirstLayerConv2d\n ? extractConvParams(s0, s1, 3, 'conv0')\n : extractSeparableConvParams(s0, s1, 'conv0');\n const conv1 = extractSeparableConvParams(s1, s2, 'conv1');\n const conv2 = extractSeparableConvParams(s2, s3, 'conv2');\n const conv3 = extractSeparableConvParams(s3, s4, 'conv3');\n const conv4 = extractSeparableConvParams(s4, s5, 'conv4');\n const conv5 = extractSeparableConvParams(s5, s6, 'conv5');\n const conv6 = s7 ? extractSeparableConvParams(s6, s7, 'conv6') : undefined;\n const conv7 = s8 ? extractSeparableConvParams(s7, s8, 'conv7') : undefined;\n const conv8 = extractConvParams(s8 || s7 || s6, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n } else {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = extractConvWithBatchNormParams(s0, s1, 'conv0');\n const conv1 = extractConvWithBatchNormParams(s1, s2, 'conv1');\n const conv2 = extractConvWithBatchNormParams(s2, s3, 'conv2');\n const conv3 = extractConvWithBatchNormParams(s3, s4, 'conv3');\n const conv4 = extractConvWithBatchNormParams(s4, s5, 'conv4');\n const conv5 = extractConvWithBatchNormParams(s5, s6, 'conv5');\n const conv6 = extractConvWithBatchNormParams(s6, s7, 'conv6');\n const conv7 = extractConvWithBatchNormParams(s7, s8, 'conv7');\n const conv8 = extractConvParams(s8, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n }\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from '../common/index';\nimport { disposeUnusedWeightTensors } from '../common/disposeUnusedWeightTensors';\nimport { loadSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightEntryFactory } from '../common/extractWeightEntryFactory';\nimport { ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractBatchNormParams(prefix: string): BatchNorm {\n const sub = extractWeightEntry(`${prefix}/sub`, 1);\n const truediv = extractWeightEntry(`${prefix}/truediv`, 1);\n return { sub, truediv };\n }\n\n function extractConvParams(prefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { filters, bias };\n }\n\n function extractConvWithBatchNormParams(prefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(`${prefix}/conv`);\n const bn = extractBatchNormParams(`${prefix}/bn`);\n return { conv, bn };\n }\n\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n config: TinyYolov2Config,\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n // eslint-disable-next-line no-mixed-operators\n const numFilters = (config.filterSizes && config.filterSizes.length || 9);\n params = {\n conv0: config.isFirstLayerConv2d ? extractConvParams('conv0') : extractSeparableConvParams('conv0'),\n conv1: extractSeparableConvParams('conv1'),\n conv2: extractSeparableConvParams('conv2'),\n conv3: extractSeparableConvParams('conv3'),\n conv4: extractSeparableConvParams('conv4'),\n conv5: extractSeparableConvParams('conv5'),\n conv6: numFilters > 7 ? extractSeparableConvParams('conv6') : undefined,\n conv7: numFilters > 8 ? extractSeparableConvParams('conv7') : undefined,\n conv8: extractConvParams('conv8'),\n };\n } else {\n params = {\n conv0: extractConvWithBatchNormParams('conv0'),\n conv1: extractConvWithBatchNormParams('conv1'),\n conv2: extractConvWithBatchNormParams('conv2'),\n conv3: extractConvWithBatchNormParams('conv3'),\n conv4: extractConvWithBatchNormParams('conv4'),\n conv5: extractConvWithBatchNormParams('conv5'),\n conv6: extractConvWithBatchNormParams('conv6'),\n conv7: extractConvWithBatchNormParams('conv7'),\n conv8: extractConvParams('conv8'),\n };\n }\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "export interface ITinyYolov2Options {\n inputSize?: number\n scoreThreshold?: number\n}\n\nexport class TinyYolov2Options {\n protected _name: string = 'TinyYolov2Options'\n\n private _inputSize: number\n\n private _scoreThreshold: number\n\n constructor({ inputSize, scoreThreshold }: ITinyYolov2Options = {}) {\n this._inputSize = inputSize || 416;\n this._scoreThreshold = scoreThreshold || 0.5;\n\n if (typeof this._inputSize !== 'number' || this._inputSize % 32 !== 0) {\n throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);\n }\n\n if (typeof this._scoreThreshold !== 'number' || this._scoreThreshold <= 0 || this._scoreThreshold >= 1) {\n throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`);\n }\n }\n\n get inputSize(): number { return this._inputSize; }\n\n get scoreThreshold(): number { return this._scoreThreshold; }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/types';\nimport { TNetInput } from '../dom/types';\nimport {\n BOX_ANCHORS,\n BOX_ANCHORS_SEPARABLE,\n DEFAULT_MODEL_NAME,\n DEFAULT_MODEL_NAME_SEPARABLE_CONV,\n IOU_THRESHOLD,\n MEAN_RGB_SEPARABLE,\n} from './const';\nimport { TinyYolov2Base } from './TinyYolov2Base';\nimport { ITinyYolov2Options } from './TinyYolov2Options';\nimport { TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2 extends TinyYolov2Base {\n constructor(withSeparableConvs: boolean = true) {\n const config = {\n withSeparableConvs,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n ...(withSeparableConvs\n ? {\n anchors: BOX_ANCHORS_SEPARABLE,\n meanRgb: MEAN_RGB_SEPARABLE,\n }\n : {\n anchors: BOX_ANCHORS,\n withClassScores: true,\n }),\n };\n\n super(config);\n }\n\n public get withSeparableConvs(): boolean {\n return this.config.withSeparableConvs;\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return this.withSeparableConvs ? DEFAULT_MODEL_NAME_SEPARABLE_CONV : DEFAULT_MODEL_NAME;\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { TinyYolov2 } from './TinyYolov2';\n\nexport * from './TinyYolov2Options';\n\nexport * from './config';\nexport * from './types';\n\nexport { TinyYolov2 };\n\nexport function createTinyYolov2(weights: Float32Array, withSeparableConvs: boolean = true) {\n const net = new TinyYolov2(withSeparableConvs);\n net.extractWeights(weights);\n return net;\n}\n", "import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\n\nexport interface ITinyFaceDetectorOptions extends ITinyYolov2Options {}\n\nexport class TinyFaceDetectorOptions extends TinyYolov2Options {\n protected _name: string = 'TinyFaceDetectorOptions'\n}\n", "export class ComposableTask {\n public async then(\n // eslint-disable-next-line no-unused-vars\n onfulfilled: (value: T) => T | PromiseLike,\n ): Promise {\n return onfulfilled(await this.run());\n }\n\n public async run(): Promise {\n throw new Error('ComposableTask - run is not implemented');\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class DetectFaceLandmarksTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected useTinyLandmarkNet: boolean,\n ) {\n super();\n }\n\n protected get landmarkNet(): FaceLandmark68Net | FaceLandmark68TinyNet {\n return this.useTinyLandmarkNet\n ? nets.faceLandmark68TinyNet\n : nets.faceLandmark68Net;\n }\n}\n\nexport class DetectAllFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n const detections = parentResults.map((res) => res.detection);\n\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, detections)\n : await extractFaces(this.input, detections);\n\n const faceLandmarksByFace = await Promise.all(faces.map(\n (face) => this.landmarkNet.detectLandmarks(face),\n )) as FaceLandmarks68[];\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return parentResults.map((parentResult, i) => extendWithFaceLandmarks(parentResult, faceLandmarksByFace[i]));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class DetectSingleFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { detection } = parentResult;\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, [detection])\n : await extractFaces(this.input, [detection]);\n\n const landmarks = await this.landmarkNet.detectLandmarks(faces[0]) as FaceLandmarks68;\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return extendWithFaceLandmarks(parentResult, landmarks);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\n\nexport async function extractAllFacesAndComputeResults, TResult>(\n parentResults: TSource[],\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResults: (faces: Array) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment: (parentResult: WithFaceLandmarks) => FaceDetection = ({ alignedRect }) => alignedRect,\n) {\n const faceBoxes = parentResults.map((parentResult) => (isWithFaceLandmarks(parentResult)\n ? getRectForAlignment(parentResult)\n : parentResult.detection));\n const faces: Array = extractedFaces || (\n input instanceof tf.Tensor\n ? await extractFaceTensors(input, faceBoxes)\n : await extractFaces(input, faceBoxes)\n );\n\n const results = await computeResults(faces);\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return results;\n}\n\nexport async function extractSingleFaceAndComputeResult, TResult>(\n parentResult: TSource,\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResult: (face: HTMLCanvasElement | tf.Tensor3D) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment?: (parentResultLocal: WithFaceLandmarks) => FaceDetection,\n) {\n return extractAllFacesAndComputeResults(\n [parentResult],\n input,\n async (faces) => computeResult(faces[0]),\n extractedFaces,\n getRectForAlignment,\n );\n}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB: [number, number, number] = [117.001, 114.697, 97.404];\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/index';\nimport { TNetInput } from '../dom/index';\nimport { ITinyYolov2Options } from '../tinyYolov2/index';\nimport { TinyYolov2Base } from '../tinyYolov2/TinyYolov2Base';\nimport { TinyYolov2NetParams } from '../tinyYolov2/types';\nimport { BOX_ANCHORS, IOU_THRESHOLD, MEAN_RGB } from './const';\n\nexport class TinyFaceDetector extends TinyYolov2Base {\n constructor() {\n const config = {\n withSeparableConvs: true,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n anchors: BOX_ANCHORS,\n meanRgb: MEAN_RGB,\n isFirstLayerConv2d: true,\n filterSizes: [3, 16, 32, 64, 128, 256, 512],\n };\n\n super(config);\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_face_detector_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { AgeGenderNet } from '../ageGenderNet/AgeGenderNet';\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressionNet } from '../faceExpressionNet/FaceExpressionNet';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { FaceRecognitionNet } from '../faceRecognitionNet/FaceRecognitionNet';\nimport { SsdMobilenetv1 } from '../ssdMobilenetv1/SsdMobilenetv1';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetector } from '../tinyFaceDetector/TinyFaceDetector';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { ITinyYolov2Options, TinyYolov2 } from '../tinyYolov2/index';\n\nexport const nets = {\n ssdMobilenetv1: new SsdMobilenetv1(),\n tinyFaceDetector: new TinyFaceDetector(),\n tinyYolov2: new TinyYolov2(),\n faceLandmark68Net: new FaceLandmark68Net(),\n faceLandmark68TinyNet: new FaceLandmark68TinyNet(),\n faceRecognitionNet: new FaceRecognitionNet(),\n faceExpressionNet: new FaceExpressionNet(),\n ageGenderNet: new AgeGenderNet(),\n};\n\n/**\n * Attempts to detect all faces in an image using SSD Mobilenetv1 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see SsdMobilenetv1Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const ssdMobilenetv1 = (input: TNetInput, options: SsdMobilenetv1Options): Promise => nets.ssdMobilenetv1.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Face Detector.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyFaceDetectorOptions constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyFaceDetector = (input: TNetInput, options: TinyFaceDetectorOptions): Promise => nets.tinyFaceDetector.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Yolov2 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyYolov2Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyYolov2 = (input: TNetInput, options: ITinyYolov2Options): Promise => nets.tinyYolov2.locateFaces(input, options);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarks = (input: TNetInput): Promise => nets.faceLandmark68Net.detectLandmarks(input);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image\n * using a tinier version of the 68 point face landmark model, which is slightly\n * faster at inference, but also slightly less accurate.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarksTiny = (input: TNetInput): Promise => nets.faceLandmark68TinyNet.detectLandmarks(input);\n\n/**\n * Computes a 128 entry vector (face descriptor / face embeddings) from the face shown in an image,\n * which uniquely represents the features of that persons face. The computed face descriptor can\n * be used to measure the similarity between faces, by computing the euclidean distance of two\n * face descriptors.\n *\n * @param inputs The face image extracted from the aligned bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Face descriptor with 128 entries or array thereof in case of batch input.\n */\nexport const computeFaceDescriptor = (input: TNetInput): Promise => nets.faceRecognitionNet.computeFaceDescriptor(input);\n\n/**\n * Recognizes the facial expressions from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Facial expressions with corresponding probabilities or array thereof in case of batch input.\n */\nexport const recognizeFaceExpressions = (input: TNetInput): Promise => nets.faceExpressionNet.predictExpressions(input);\n\n/**\n * Predicts age and gender from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Predictions with age, gender and gender probability or array thereof in case of batch input.\n */\nexport const predictAgeAndGender = (input: TNetInput): Promise => nets.ageGenderNet.predictAgeAndGender(input);\n\nexport const loadSsdMobilenetv1Model = (url: string) => nets.ssdMobilenetv1.load(url);\nexport const loadTinyFaceDetectorModel = (url: string) => nets.tinyFaceDetector.load(url);\nexport const loadTinyYolov2Model = (url: string) => nets.tinyYolov2.load(url);\nexport const loadFaceLandmarkModel = (url: string) => nets.faceLandmark68Net.load(url);\nexport const loadFaceLandmarkTinyModel = (url: string) => nets.faceLandmark68TinyNet.load(url);\nexport const loadFaceRecognitionModel = (url: string) => nets.faceRecognitionNet.load(url);\nexport const loadFaceExpressionModel = (url: string) => nets.faceExpressionNet.load(url);\nexport const loadAgeGenderModel = (url: string) => nets.ageGenderNet.load(url);\n\n// backward compatibility\nexport const loadFaceDetectionModel = loadSsdMobilenetv1Model;\nexport const locateFaces = ssdMobilenetv1;\nexport const detectLandmarks = detectFaceLandmarks;\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderTask,\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\n\nexport class PredictFaceExpressionsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const faceExpressionsByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map(\n (parentResult, i) => extendWithFaceExpressions(parentResult, faceExpressionsByFace[i]),\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const faceExpressions = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithFaceExpressions(parentResult, faceExpressions);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictAllFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { TNetInput } from '../dom/index';\nimport { extendWithAge, WithAge } from '../factories/WithAge';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { extendWithGender, WithGender } from '../factories/WithGender';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllFaceExpressionsTask,\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class PredictAgeAndGenderTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase>[], TSource[]> {\n public async run(): Promise>[]> {\n const parentResults = await this.parentTask;\n\n const ageAndGenderByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map((parentResult, i) => {\n const { age, gender, genderProbability } = ageAndGenderByFace[i];\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n });\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase> | undefined, TSource | undefined> {\n public async run(): Promise> | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { age, gender, genderProbability } = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictAllAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDescriptor, WithFaceDescriptor } from '../factories/WithFaceDescriptor';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class ComputeFaceDescriptorsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n ) {\n super();\n }\n}\n\nexport class ComputeAllFaceDescriptorsTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const descriptors = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n (faces) => Promise.all(faces.map((face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise)),\n null,\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return descriptors.map((descriptor, i) => extendWithFaceDescriptor(parentResults[i], descriptor));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n\nexport class ComputeSingleFaceDescriptorTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n const descriptor = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise,\n null,\n // eslint-disable-next-line no-shadow\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return extendWithFaceDescriptor(parentResult, descriptor);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { TinyYolov2Options } from '../tinyYolov2/index';\nimport { ComposableTask } from './ComposableTask';\nimport { DetectAllFaceLandmarksTask, DetectSingleFaceLandmarksTask } from './DetectFaceLandmarksTasks';\nimport { nets } from './nets';\nimport { PredictAllAgeAndGenderTask, PredictSingleAgeAndGenderTask } from './PredictAgeAndGenderTask';\nimport { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from './PredictFaceExpressionsTask';\nimport { FaceDetectionOptions } from './types';\n\nexport class DetectFacesTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n ) {\n super();\n }\n}\n\nexport class DetectAllFacesTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const { input, options } = this;\n\n // eslint-disable-next-line no-nested-ternary\n const faceDetectionFunction = options instanceof TinyFaceDetectorOptions\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyFaceDetector.locateFaces(input, options)\n : (\n // eslint-disable-next-line no-nested-ternary\n options instanceof SsdMobilenetv1Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.ssdMobilenetv1.locateFaces(input, options)\n : (\n options instanceof TinyYolov2Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyYolov2.locateFaces(input, options)\n : null\n )\n );\n\n if (!faceDetectionFunction) {\n throw new Error('detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options');\n }\n\n return faceDetectionFunction(input);\n }\n\n private runAndExtendWithFaceDetections(): Promise[]> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise[]>(async (resolve) => {\n const detections = await this.run();\n resolve(detections.map((detection) => extendWithFaceDetection({}, detection)));\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectAllFaceLandmarksTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n}\n\nexport class DetectSingleFaceTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const faceDetections = await new DetectAllFacesTask(this.input, this.options);\n let faceDetectionWithHighestScore = faceDetections[0];\n faceDetections.forEach((faceDetection) => {\n if (faceDetection.score > faceDetectionWithHighestScore.score) {\n faceDetectionWithHighestScore = faceDetection;\n }\n });\n return faceDetectionWithHighestScore;\n }\n\n private runAndExtendWithFaceDetection(): Promise | undefined> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise | undefined>(async (resolve) => {\n const detection = await this.run();\n resolve(detection ? extendWithFaceDetection<{}>({}, detection) : undefined);\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectSingleFaceLandmarksTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n}\n", "import { TNetInput } from '../dom/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { DetectAllFacesTask, DetectSingleFaceTask } from './DetectFacesTasks';\nimport { FaceDetectionOptions } from './types';\n\nexport function detectSingleFace(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectSingleFaceTask {\n return new DetectSingleFaceTask(input, options);\n}\n\nexport function detectAllFaces(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectAllFacesTask {\n return new DetectAllFacesTask(input, options);\n}\n", "import { TNetInput } from '../dom/index';\nimport { WithFaceDescriptor, WithFaceDetection, WithFaceLandmarks } from '../factories/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';\nimport { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\nimport { detectAllFaces } from './detectFaces';\n\n// export allFaces API for backward compatibility\n\nexport async function allFacesSsdMobilenetv1(\n input: TNetInput,\n minConfidence?: number,\n): Promise>>[]> {\n return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport async function allFacesTinyYolov2(\n input: TNetInput,\n forwardParams: ITinyYolov2Options = {},\n): Promise>>[]> {\n return detectAllFaces(input, new TinyYolov2Options(forwardParams))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport const allFaces = allFacesSsdMobilenetv1;\n", "export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {\n if (arr1.length !== arr2.length) throw new Error('euclideanDistance: arr1.length !== arr2.length');\n\n const desc1 = Array.from(arr1);\n const desc2 = Array.from(arr2);\n\n return Math.sqrt(\n desc1\n .map((val, i) => val - desc2[i])\n .reduce((res, diff) => res + (diff ** 2), 0),\n );\n}\n", "import { FaceMatch } from '../classes/FaceMatch';\nimport { LabeledFaceDescriptors } from '../classes/LabeledFaceDescriptors';\nimport { euclideanDistance } from '../euclideanDistance';\nimport { WithFaceDescriptor } from '../factories/index';\n\nexport class FaceMatcher {\n private _labeledDescriptors: LabeledFaceDescriptors[]\n\n private _distanceThreshold: number\n\n constructor(\n inputs: LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>,\n distanceThreshold: number = 0.6,\n ) {\n this._distanceThreshold = distanceThreshold;\n\n const inputArray = Array.isArray(inputs) ? inputs : [inputs];\n\n if (!inputArray.length) {\n throw new Error('FaceRecognizer.constructor - expected atleast one input');\n }\n\n let count = 1;\n const createUniqueLabel = () => `person ${count++}`;\n\n this._labeledDescriptors = inputArray.map((desc) => {\n if (desc instanceof LabeledFaceDescriptors) {\n return desc;\n }\n\n if (desc instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc]);\n }\n\n if (desc.descriptor && desc.descriptor instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc.descriptor]);\n }\n\n throw new Error('FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>');\n });\n }\n\n public get labeledDescriptors(): LabeledFaceDescriptors[] { return this._labeledDescriptors; }\n\n public get distanceThreshold(): number { return this._distanceThreshold; }\n\n public computeMeanDistance(queryDescriptor: Float32Array, descriptors: Float32Array[]): number {\n return descriptors\n .map((d) => euclideanDistance(d, queryDescriptor))\n .reduce((d1, d2) => d1 + d2, 0)\n / (descriptors.length || 1);\n }\n\n public matchDescriptor(queryDescriptor: Float32Array): FaceMatch {\n return this.labeledDescriptors\n .map(({ descriptors, label }) => new FaceMatch(\n label,\n this.computeMeanDistance(queryDescriptor, descriptors),\n ))\n .reduce((best, curr) => (best.distance < curr.distance ? best : curr));\n }\n\n public findBestMatch(queryDescriptor: Float32Array): FaceMatch {\n const bestMatch = this.matchDescriptor(queryDescriptor);\n return bestMatch.distance < this.distanceThreshold\n ? bestMatch\n : new FaceMatch('unknown', bestMatch.distance);\n }\n\n public toJSON(): any {\n return {\n distanceThreshold: this.distanceThreshold,\n labeledDescriptors: this.labeledDescriptors.map((ld) => ld.toJSON()),\n };\n }\n\n public static fromJSON(json: any): FaceMatcher {\n const labeledDescriptors = json.labeledDescriptors\n .map((ld: any) => LabeledFaceDescriptors.fromJSON(ld));\n return new FaceMatcher(labeledDescriptors, json.distanceThreshold);\n }\n}\n", "import { TinyFaceDetector } from './TinyFaceDetector';\n\nexport * from './TinyFaceDetector';\nexport * from './TinyFaceDetectorOptions';\n\nexport function createTinyFaceDetector(weights: Float32Array) {\n const net = new TinyFaceDetector();\n net.extractWeights(weights);\n return net;\n}\n", "import { Dimensions, IDimensions } from './classes/index';\nimport { FaceDetection } from './classes/FaceDetection';\nimport { FaceLandmarks } from './classes/FaceLandmarks';\nimport { extendWithFaceDetection, isWithFaceDetection } from './factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, isWithFaceLandmarks } from './factories/WithFaceLandmarks';\n\nexport function resizeResults(results: T, dimensions: IDimensions): T {\n const { width, height } = new Dimensions(dimensions.width, dimensions.height);\n\n if (width <= 0 || height <= 0) {\n throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({ width, height })}`);\n }\n\n if (Array.isArray(results)) {\n // return results.map(obj => resizeResults(obj, { width, height })) as any as T\n return (results as Array).map((obj) => resizeResults(obj, { width, height } as IDimensions)) as any as T;\n }\n\n if (isWithFaceLandmarks(results)) {\n const resizedDetection = results.detection.forSize(width, height);\n const resizedLandmarks = results.unshiftedLandmarks.forSize(resizedDetection.box.width, resizedDetection.box.height);\n return extendWithFaceLandmarks(extendWithFaceDetection(results, resizedDetection), resizedLandmarks);\n }\n\n if (isWithFaceDetection(results)) {\n return extendWithFaceDetection(results, results.detection.forSize(width, height));\n }\n\n if (results instanceof FaceLandmarks || results instanceof FaceDetection) {\n return (results as any).forSize(width, height);\n }\n\n return results;\n}\n"], - "mappings": ";;;;;;;wlCAGA,GAAA,GAAc,GAAA,yCCHd,6CAAO,cACL,MAAO,OAAO,SAAW,UACpB,IACA,MAAO,KAAW,aAGlB,MAAO,UAAY,aAAe,CAAC,CAAC,QAAQ,WCNnD,6xFAAA,OAAoB,OCApB,qRCEO,YACL,EACA,EACA,EAAoB,IAUpB,GARA,EAAI,YAEJ,EAAO,MAAM,GAAG,QAAQ,CAAC,CAAE,IAAG,KAAK,KACjC,GAAM,GAAO,EAAO,GACpB,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,KAGZ,GACF,GAAM,GAAO,EAAO,EAAO,OAAS,GAC9B,EAAK,EAAO,GAClB,GAAI,CAAC,GAAQ,CAAC,EACZ,OAGF,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,EAAG,EAAG,GAGtB,EAAI,SC1BN,2RAAA,OAAoB,OCApB,YAYE,YAAY,EAAe,GACzB,GAAI,CAAC,GAAc,IAAU,CAAC,GAAc,GAC1C,KAAM,IAAI,OAAM,wFAAwF,KAAK,UAAU,CAAE,QAAO,cAGlI,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,QAEnC,UACL,MAAO,IAAI,GAAW,EAAI,KAAK,MAAO,EAAI,KAAK,UDrB5C,YAAkB,EAAa,GACpC,MAAO,aAAqB,YAAU,EAAO,MAAM,SAAW,EAGzD,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,WAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAiB,GACtB,MAAO,GAAM,GAAM,EAGd,YAAgB,GACrB,MAAO,GAAM,GAAM,EAGd,YAAe,EAAa,EAAe,GAChD,GAAM,GAAI,IAAM,EAChB,MAAO,MAAK,MAAM,EAAM,GAAK,EAGxB,YAAsB,GAC3B,MAAO,IAAO,EAAI,OAAS,EAAI,OAG1B,YAAmC,CAAE,QAAO,UAAuB,GACxE,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,IAAI,GAAW,KAAK,MAAM,EAAQ,GAAQ,KAAK,MAAM,EAAS,IAGhE,YAAwB,GAC7B,MAAO,GAAI,OAAO,CAAC,EAAK,IAAO,EAAI,IAAI,GAAK,GAAI,GAAM,EAAG,IACtD,IAAI,GAAI,GAAM,EAAI,OAAQ,EAAI,SAG5B,YAAe,EAAa,EAAe,GAChD,MAAO,OAAM,GAAK,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,EAAS,EAAI,GAGhD,YAAuB,GAE5B,MAAO,CAAC,CAAC,GAAQ,IAAQ,UAAc,IAAQ,WAAc,CAAC,OAAO,MAAM,IAAQ,IAAQ,EAGtF,YAA4B,GACjC,MAAO,IAAc,IAAQ,GAAO,GAAK,GAAO,EE9DlD,YAUE,YAAY,EAAW,GACrB,KAAK,GAAK,EACV,KAAK,GAAK,KAGR,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,GAEvB,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,MACL,MAAO,IAAI,GAAM,KAAK,IAAI,KAAK,GAAI,KAAK,IAAI,KAAK,IAG5C,YACL,MAAO,MAAK,KAAM,KAAK,GAAK,EAAM,KAAK,GAAK,GAGvC,QACL,MAAO,IAAI,GAAM,KAAK,MAAM,KAAK,GAAI,KAAK,MAAM,KAAK,MC5CzD,kBAOgB,QAAO,GACnB,MAAO,CAAC,CAAC,GAAQ,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,MAAO,EAAK,QAAQ,MAAM,UAGrD,kBAAiB,EAAU,EAAgB,EAAmC,IAC1F,GAAI,CAAC,EAAI,OAAO,GACd,KAAM,IAAI,OAAM,GAAG,oBAAyB,KAAK,UAAU,2DAG7D,GAAI,CAAC,GAA4B,GAAI,MAAQ,GAAK,EAAI,OAAS,GAC7D,KAAM,IAAI,OAAM,GAAG,cAAmB,EAAI,sBAAsB,EAAI,oCAYxE,YAAY,EAA4B,EAAmC,IACzE,GAAM,GAAO,GAAQ,GAEf,EAAS,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAO,EAAI,QAAQ,MAAM,IAC1D,EAAS,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAAQ,MAAM,IAE3D,GAAI,CAAC,GAAU,CAAC,EACd,KAAM,IAAI,OAAM,2EAA2E,KAAK,UAAU,MAG5G,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,EAC1B,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAC9B,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAQ,EAAI,KAAM,EAAI,OAAS,EAAI,KAE/D,EAAI,iBAAiB,CACnB,IAAG,IAAG,QAAO,UACZ,kBAAmB,GAEtB,KAAK,GAAK,EACV,KAAK,GAAK,EACV,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,MAE1B,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,WAE/B,QAAiB,MAAO,MAAK,KAE7B,OAAgB,MAAO,MAAK,KAE5B,SAAkB,MAAO,MAAK,EAAI,KAAK,SAEvC,UAAmB,MAAO,MAAK,EAAI,KAAK,UAExC,QAAiB,MAAO,MAAK,MAAQ,KAAK,UAE1C,WAAmB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,QAEpD,YAAoB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAEtD,cAAsB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,WAEvD,eAAuB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAE7D,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,WACL,GAAI,CACF,IAAG,IAAG,QAAO,UACX,KACE,EAAO,KAAK,IAAI,EAAQ,GAC9B,MAAI,GAAQ,GACV,IAAM,EAAO,EACb,GAAS,GAEP,EAAS,GACX,IAAM,EAAO,EACb,GAAU,GAGL,GAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QAAQ,GACb,GAAM,GAAS,GAAa,GAAM,EAAkB,MAAQ,EACtD,EAAS,GAAa,GAAM,EAAkB,OAAS,EAC7D,MAAO,IAAI,GAAI,CACb,EAAG,KAAK,EAAI,EACZ,EAAG,KAAK,EAAI,EACZ,MAAO,KAAK,MAAQ,EACpB,OAAQ,KAAK,OAAS,IAInB,IAAI,EAAc,GACvB,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAC5B,KAAK,EAAK,EAAO,EACjB,KAAK,EAAK,EAAO,EACjB,KAAK,MAAQ,EACb,KAAK,OAAS,GAEhB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,mBAAmB,EAAkB,GAC1C,GAAM,CACJ,IAAG,IAAG,QAAO,UACX,KACE,EAAW,KAAK,IAAI,EAAG,GACvB,EAAW,KAAK,IAAI,EAAG,GAEvB,EAAW,EAAQ,EACnB,EAAY,EAAS,EACrB,EAAe,KAAK,IAAI,EAAU,EAAW,GAC7C,EAAgB,KAAK,IAAI,EAAW,EAAY,GAEtD,MAAQ,IAAI,GAAI,CACd,EAAG,EAAU,EAAG,EAAU,MAAO,EAAc,OAAQ,IACrD,QAGC,MAAM,EAAY,GACvB,GAAM,CAAE,QAAO,UAAW,KACpB,EAAI,KAAK,EAAI,EACb,EAAI,KAAK,EAAI,EAEnB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,aAAa,EAAqB,GACvC,GAAM,GAAI,KAAK,MAAQ,EACjB,EAAI,KAAK,OAAS,EAElB,EAAK,EACL,EAAK,EACP,EAAM,EACN,EAAM,EAEN,EAAI,KAAK,KACT,EAAI,KAAK,IACT,EAAK,KAAK,MACV,EAAK,KAAK,OAEd,MAAI,GAAK,GACP,GAAM,CAAC,EAAK,EAAa,EACzB,EAAK,GAEH,EAAK,GACP,GAAM,CAAC,EAAK,EAAc,EAC1B,EAAK,GAEH,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAEF,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAGC,CACL,KAAI,MAAK,KAAI,MAAK,IAAG,KAAI,IAAG,KAAI,IAAG,KAIhC,UAAU,GACf,MAAO,IAAI,GAAI,CACb,KAAM,KAAK,KAAQ,EAAO,KAAO,KAAK,MACtC,IAAK,KAAK,IAAO,EAAO,IAAM,KAAK,OACnC,MAAO,KAAK,MAAS,EAAO,MAAQ,KAAK,MACzC,OAAQ,KAAK,OAAU,EAAO,OAAS,KAAK,SAC3C,WAAW,UC9MlB,oBASiC,GAC/B,YAAY,EAAc,EAAa,EAAe,EAAgB,EAAmC,IACvG,MAAM,CACJ,OAAM,MAAK,QAAO,UACjB,KCbP,aAeE,YACE,EACA,EACA,EACA,EACA,GAEA,KAAK,WAAa,GAAI,GAAW,EAAU,MAAO,EAAU,QAC5D,KAAK,OAAS,EACd,KAAK,YAAc,EACnB,KAAK,WAAa,EAClB,KAAK,KAAO,GAAI,GAAI,GAAa,QAAQ,KAAK,eAGrC,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,eAEnC,aAAsB,MAAO,MAAK,cAElC,OAAa,MAAO,MAAK,QAEzB,aAA0B,MAAO,MAAK,cAEtC,cAAuB,MAAO,MAAK,UAAU,SAE7C,eAAwB,MAAO,MAAK,UAAU,UAE9C,eAAqB,MAAO,IAAI,GAAI,KAAK,MAAM,QAAQ,KAAK,UAAU,WAE1E,QAAQ,EAAe,GAC5B,MAAO,IAAI,IACT,KAAK,MACL,KAAK,WACL,KAAK,UACL,KAAK,YACL,CAAE,QAAO,aCnDf,mBAUmC,IACjC,YACE,EACA,EACA,GAEA,MAAM,EAAO,EAAO,GAAI,EAAa,GAGhC,QAAQ,EAAe,GAC5B,GAAM,CAAE,QAAO,cAAa,aAAc,MAAM,QAAQ,EAAO,GAC/D,MAAO,IAAI,GAAc,EAAO,EAAa,KCnB1C,YAAa,EAAW,EAAW,EAAiB,IACzD,GAAM,GAAQ,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,MAAO,EAAK,OAAS,KAAK,IAAI,EAAK,KAAM,EAAK,OAClF,EAAS,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,OAAQ,EAAK,QAAU,KAAK,IAAI,EAAK,IAAK,EAAK,MACpF,EAAe,EAAQ,EAE7B,MAAO,GACH,EAAgB,GAAK,KAAO,EAAK,KAAO,GACxC,EAAe,KAAK,IAAI,EAAK,KAAM,EAAK,MCPvC,YAAiB,GACtB,GAAM,GAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAExD,MAAO,IAAI,IAAY,EAAM,EAAM,EAAM,GCPpC,YACL,EACA,EACA,EACA,EAAiB,IAEjB,GAAI,GAAuB,EACxB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAC/B,IAAI,AAAC,GAAM,EAAE,UAEV,EAAiB,GAEvB,KAAO,EAAqB,OAAS,IACnC,GAAM,GAAO,EAAqB,MAClC,EAAK,KAAK,GAEV,GAAM,GAAU,EAEV,EAAoB,GAC1B,OAAS,GAAI,EAAG,EAAI,EAAQ,OAAQ,KAClC,GAAM,GAAM,EAAQ,GAEd,EAAU,EAAM,GAChB,EAAS,EAAM,GAErB,EAAQ,KAAK,GAAI,EAAS,EAAQ,IAGpC,EAAuB,EAAqB,OAC1C,CAAC,EAAG,IAAM,EAAQ,IAAM,GAI5B,MAAO,GCrCT,OAAoB,OAEb,YAAmB,EAAgB,GACxC,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAG,EAAG,GAAK,EACZ,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAU,AAAG,UAAO,CAAC,EAAO,EAAO,GAAQ,GAEjD,MAAO,AAAG,QAAI,EAAG,KCVrB,OAAoB,OAUb,YACL,EACA,EAAyB,IAEzB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAQ,GAAS,EAAU,MAAM,MAAM,GAC9C,GAAI,IAAW,EACb,MAAO,GAGT,GAAM,GAAU,KAAK,IAAI,EAAS,GAC5B,EAAgB,KAAK,MAAM,EAAW,GAAgB,GAAM,IAC5D,EAAc,EAAS,EAAQ,EAAI,EAEnC,EAAsB,AAAC,IAC3B,GAAM,GAAqB,EAAU,MAAM,QAC3C,SAAmB,GAAe,EAC3B,AAAG,QAAK,EAAoB,EAAG,YAGlC,EAAsB,EAAoB,GAC1C,EAAyB,EAAW,EAAoB,MAAM,GAM9D,EAAiB,CAJM,GAAiB,EAC1C,EAAoB,GACpB,KAIF,EACA,GAEC,OAAO,AAAC,GAAM,CAAC,CAAC,GAEhB,IAAI,AAAC,GAAiB,AAAG,QAAK,EAAG,YACpC,MAAO,AAAG,WAAO,EAAgB,KC7C9B,YAAsB,GAC3B,GAAM,GAAQ,EAAW,QACzB,OAAS,GAAI,EAAM,OAAS,EAAG,EAAI,EAAG,KACpC,GAAM,GAAI,KAAK,MAAM,KAAK,SAAY,GAAI,IACpC,EAAI,EAAM,GAChB,EAAM,GAAK,EAAM,GACjB,EAAM,GAAK,EAEb,MAAO,GCDF,YAAiB,GACtB,MAAO,GAAK,GAAI,KAAK,IAAI,CAAC,IAGrB,YAAwB,GAC7B,MAAO,MAAK,IAAI,EAAK,GAAI,ICZ3B,oBAS0B,GACxB,YAAY,EAAW,EAAW,EAAe,EAAgB,EAAmC,IAClG,MAAM,CACJ,IAAG,IAAG,QAAO,UACZ,KCHP,GAAM,IAAO,GACP,GAAO,IACP,GAAW,IAZjB,QA0BE,YACE,EACA,EACA,EAAe,GAAI,GAAM,EAAG,IAE5B,GAAM,CAAE,QAAO,UAAW,EAC1B,KAAK,SAAW,GAAI,GAAW,EAAO,GACtC,KAAK,OAAS,EACd,KAAK,WAAa,EAA8B,IAC9C,AAAC,GAAO,EAAG,IAAI,GAAI,GAAM,EAAO,IAAS,IAAI,OAItC,SAAiB,MAAO,IAAI,GAAM,KAAK,OAAO,EAAG,KAAK,OAAO,MAE7D,cAAuB,MAAO,MAAK,SAAS,SAE5C,eAAwB,MAAO,MAAK,SAAS,UAE7C,aAAuB,MAAO,MAAK,cAEnC,qBACT,MAAO,MAAK,WAAW,IACrB,AAAC,GAAO,EAAG,IAAI,KAAK,QAAQ,IAAI,GAAI,GAAM,KAAK,WAAY,KAAK,eAI7D,QAAiC,EAAe,GACrD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,CAAE,QAAO,WAIN,QAAiC,EAAW,GACjD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,KAAK,SACL,GAAI,GAAM,EAAG,IAIV,aAAsC,GAC3C,MAAO,MAAK,QAAQ,EAAG,EAAG,EAAG,GAcxB,MACL,EACA,EAAkE,IAElE,GAAI,GACF,GAAM,GAAM,YAAqB,GAC7B,EAAU,IAAI,QACd,GAAI,GAAI,GAEZ,MAAO,MAAK,QAAQ,EAAI,EAAG,EAAI,GAAG,MAAM,KAAM,GAGhD,GAAM,CAAE,mBAAkB,iBAAkB,CAAE,iBAAkB,GAAO,cAAe,MAAQ,GAE9F,MAAI,GACK,KAAK,YAGP,KAAK,aAAa,GAGnB,YACN,GAAM,GAAU,KAAK,2BAEf,CAAC,EAAe,EAAgB,GAAe,EAC/C,EAAc,AAAC,GAAc,EAAY,IAAI,GAAI,YACjD,EAAkB,GAAY,GAAiB,EAAY,IAAmB,EAE9E,EAAO,KAAK,MAAM,EAAiB,IAEnC,EAAW,GAAe,GAE1B,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAChD,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAEtD,MAAO,IAAI,IAAK,EAAG,EAAG,KAAK,IAAI,EAAM,KAAK,WAAa,GAAI,KAAK,IAAI,EAAM,KAAK,YAAc,IAGvF,aAAa,GACnB,GAAM,GAAM,GAAQ,KAAK,WACzB,MAAO,GAAI,IAAI,EAAI,MAAQ,EAAS,EAAI,OAAS,GAGzC,2BACR,KAAM,IAAI,OAAM,4DC/HpB,oBAIoC,GACxB,2BACR,GAAM,GAAM,KAAK,UACjB,MAAO,CACL,EAAI,GACJ,EAAI,GACJ,GAAe,CAAC,EAAI,GAAI,EAAI,QCVlC,oBAIqC,GAC5B,gBACL,MAAO,MAAK,UAAU,MAAM,EAAG,IAG1B,iBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,kBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,UACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,aACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,cACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,WACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAGxB,2BACR,MAAO,CACL,KAAK,aACL,KAAK,cACL,KAAK,YACL,IAAI,MCtCV,aAYE,YAAY,EAAe,GACzB,KAAK,OAAS,EACd,KAAK,UAAY,KAGR,SAAkB,MAAO,MAAK,UAE9B,YAAqB,MAAO,MAAK,UAErC,SAAS,EAAwB,IACtC,MAAO,GAAG,KAAK,QAAQ,EAAe,KAAK,GAAM,KAAK,aAAe,OCtBzE,oBAKgC,SAChB,yBAAwB,EAAU,GAG9C,GAFA,EAAI,iBAAiB,EAAK,GAEtB,CAAC,GAAc,EAAI,OACrB,KAAM,IAAI,OAAM,GAAG,gCAAqC,EAAI,yBAMhE,YAAY,EAAiC,GAC3C,MAAM,GACN,KAAK,OAAS,KAGL,SAAkB,MAAO,MAAK,SCrB3C,aAKE,YAAY,EAAe,GACzB,GAAM,MAAO,IAAU,SACrB,KAAM,IAAI,OAAM,sEAGlB,GAAI,CAAC,MAAM,QAAQ,IAAgB,EAAY,KAAK,AAAC,GAAS,CAAE,aAAgB,gBAC9E,KAAM,IAAI,OAAM,4FAGlB,KAAK,OAAS,EACd,KAAK,aAAe,KAGX,SAAkB,MAAO,MAAK,UAE9B,eAAgC,MAAO,MAAK,aAEhD,SACL,MAAO,CACL,MAAO,KAAK,MACZ,YAAa,KAAK,YAAY,IAAI,AAAC,GAAM,MAAM,KAAK,WAI1C,UAAS,GACrB,GAAM,GAAc,EAAK,YAAY,IAAI,AAAC,GAAW,GAAI,cAAa,IACtE,MAAO,IAAI,IAAuB,EAAK,MAAO,KC/BlD,oBAKkC,UAClB,2BAA0B,EAAU,GAGhD,GAFA,GAAW,wBAAwB,EAAK,GAGtC,CAAC,GAAmB,EAAI,QACrB,CAAC,GAAmB,EAAI,YAE3B,KAAM,IAAI,OAAM,GAAG,kCAAuC,EAAI,eAAe,EAAI,6CAQrF,YAAY,EAAiC,EAAe,EAAe,GACzE,MAAM,EAAK,GACX,KAAK,OAAS,EACd,KAAK,YAAc,KAGV,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,cCvBzC,YAA6B,GAClC,MAAO,GAAI,oBAAqB,GAG3B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,cCdf,cACL,GAAM,GAAQ,OAAO,MACrB,GAAI,CAAC,EAAO,KAAM,IAAI,OAAM,gEAE5B,GAAM,GAAW,KACf,KAAM,IAAI,OAAM,gEAGlB,MAAO,CACL,OAAQ,kBACR,yBACA,MAAO,iBACP,UACA,MAAO,iBACP,oBAAqB,IAAM,SAAS,cAAc,UAClD,mBAAoB,IAAM,SAAS,cAAc,OACjD,QACA,YCjBG,YAA0B,GAC/B,GAAI,GAAiB,GAErB,GAAI,CAAC,EACH,IAEE,EAAa,oBACN,GACP,EAAiB,EAAI,WAYzB,MAAO,CACL,SATe,EACb,AAAC,GAAqB,GAAI,SAAgB,CAAC,EAAS,KACpD,EAAG,SAAS,EAAU,CAAC,EAAU,IAAoB,EAAM,EAAO,GAAO,EAAQ,MAEjF,KACA,KAAM,IAAI,OAAM,qEAAqE,OCfpF,cAEL,GAAM,GAAS,OAAO,QAAa,OAAO,kBACpC,EAAQ,OAAO,OAAS,OAAO,iBAE/B,EAAsB,KAC1B,GAAI,EAAQ,MAAO,IAAI,GACvB,KAAM,IAAI,OAAM,+EAGZ,EAAqB,KACzB,GAAI,EAAO,MAAO,IAAI,GACtB,KAAM,IAAI,OAAM,6EAGZ,EAAQ,OAAO,MAGf,EAAa,KAEnB,MAAO,CACL,OAAQ,GAAU,QAClB,yBAA0B,OAAO,0BAA4B,QAC7D,MAAO,GAAS,QAChB,UAAW,OAAO,WAAa,QAC/B,MAAO,OAAO,kBAAoB,QAClC,sBACA,qBACA,WACG,GCjCA,cACL,MAAO,OAAO,SAAW,UACpB,MAAO,WAAa,aACpB,MAAO,mBAAqB,aAC5B,MAAO,oBAAsB,aAC7B,MAAO,mBAAqB,aAC5B,MAAO,YAAc,aACrB,MAAO,2BAA6B,YCH3C,OAAyB,QAGrB,EAEJ,cACE,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,yEAElB,MAAO,GAGT,YAAgB,GACd,EAAc,EAGhB,cAGE,MAAI,MAAoB,GAAO,MAC3B,cAAmB,GAAO,MACvB,KAGT,YAAqB,GAKnB,GAJK,GACH,KAGE,CAAC,EACH,KAAM,IAAI,OAAM,8EAGlB,GAAM,CAAE,SAAS,EAAY,OAAQ,QAAQ,EAAY,OAAU,EACnE,EAAY,OAAS,EACrB,EAAY,MAAQ,EACpB,EAAY,oBAAsB,EAAI,qBAAwB,KAAM,GAAI,IACxE,EAAY,mBAAqB,EAAI,oBAAuB,KAAM,GAAI,IAEtE,EAAY,UAAY,EAAI,WAAa,EAAY,UACrD,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,SAAW,EAAI,UAAY,EAAY,SAG9C,GAAM,GAAM,CACjB,UACA,UACA,cACA,oBACA,oBACA,mBACA,eACA,aACA,sBAGF,KC3DO,YAAsB,GAC3B,MAAI,CAAC,EAAI,YAAc,MAAO,IAAQ,SAC7B,SAAS,eAAe,GAE1B,ECHF,WAA6B,GAClC,GAAM,CAAE,SAAQ,4BAA6B,EAAI,SAEjD,GAAI,YAAqB,GACvB,MAAO,GAGT,GAAM,GAAS,GAAa,GAE5B,GAAI,CAAE,aAAkB,IACtB,KAAM,IAAI,OAAM,kEAGlB,GAAM,GAAM,EAAO,WAAW,MAC9B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,GCfF,GAAK,IAAL,UAAK,GAEV,WAAW,WAEX,YAAY,YAEZ,cAAc,cAEd,eAAe,iBARL,aANZ,aAuCE,YAAY,EAAiC,IAC3C,GAAM,CACJ,iBAAgB,kBAAiB,YAAW,WAAU,YAAW,WAC/D,EACJ,KAAK,eAAiB,GAAkB,GAAe,SACvD,KAAK,gBAAkB,GAAmB,qBAC1C,KAAK,UAAY,GAAa,yBAC9B,KAAK,SAAW,GAAY,GAC5B,KAAK,UAAY,GAAa,UAC9B,KAAK,QAAU,GAAW,IAhD9B,SA2DE,YACE,EACA,EACA,EAAiC,IAGjC,KAAK,KAAO,MAAO,IAAS,SACxB,CAAC,GACA,YAAgB,IAAgB,EAAK,KAAO,EACjD,KAAK,OAAS,EACd,KAAK,QAAU,GAAI,IAAqB,GAG1C,aAAa,GACX,GAAM,CAAE,WAAY,KAAK,QACzB,MAAO,MAAK,KAAK,IAAI,AAAC,GAAM,EAAI,YAAY,GAAG,OAAO,OAAO,CAAC,EAAI,IAAQ,EAAK,EAAK,EAAK,EAAK,GAAM,EAAI,EAG1G,gBACE,GAAM,CAAE,WAAU,WAAY,KAAK,QACnC,MAAO,MAAK,KAAK,OAAS,EAAY,EAAI,EAG5C,aAAa,EAA+B,GAC1C,GAAM,CAAE,kBAAmB,KAAK,QAC1B,EAAc,IAAmB,GAAe,cAAgB,IAAmB,GAAe,UAClG,EAAa,IAAmB,GAAe,aAAe,IAAmB,GAAe,aAEhG,EAAiB,KAAK,aAAa,GACnC,EAAkB,KAAK,gBACvB,EAAK,EAAc,KAAK,OAAO,EAAI,EAAiB,KAAK,OAAO,EAChE,EAAI,EAAa,KAAK,OAAO,EAAI,EAAkB,KAAK,OAAO,EAGrE,GAAI,GACF,GAAM,CAAE,QAAO,UAAW,EACpB,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAQ,GAAiB,GACrD,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAS,GAAkB,GAC7D,MAAO,CAAE,EAAG,EAAM,EAAG,GAEvB,MAAO,CAAE,IAAG,KAGd,KAAK,GACH,GAAM,GAAS,GAAa,GACtB,EAAM,EAAoB,GAE1B,CACJ,kBAAiB,YAAW,WAAU,YAAW,WAC/C,KAAK,QAET,EAAI,KAAO,GAAG,OAAc,IAC5B,GAAM,GAAe,KAAK,aAAa,GACjC,EAAa,KAAK,gBAExB,EAAI,UAAY,EAChB,GAAM,GAAY,KAAK,aAAa,EAAK,GACzC,EAAI,SAAS,EAAU,EAAG,EAAU,EAAG,EAAc,GAErD,EAAI,UAAY,EAChB,KAAK,KAAK,QAAQ,CAAC,EAAU,KAC3B,GAAM,GAAI,EAAU,EAAU,EACxB,EAAI,EAAU,EAAU,EAAM,GAAI,GAAK,EAC7C,EAAI,SAAS,EAAU,EAAG,OC1HhC,aAuBE,YAAY,EAA2B,IACrC,GAAM,CACJ,WAAU,YAAW,QAAO,oBAC1B,EACJ,KAAK,SAAW,GAAY,qBAC5B,KAAK,UAAY,GAAa,EAC9B,KAAK,MAAQ,EAEb,GAAM,GAA0B,CAC9B,eAAgB,GAAe,YAC/B,gBAAiB,KAAK,UAExB,KAAK,iBAAmB,GAAI,IAAqB,IAAK,KAA4B,MAnCtF,SA4CE,YACE,EACA,EAA2B,IAE3B,KAAK,IAAM,GAAI,GAAI,GACnB,KAAK,QAAU,GAAI,IAAe,GAGpC,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CAAE,WAAU,aAAc,KAAK,QAE/B,CACJ,IAAG,IAAG,QAAO,UACX,KAAK,IACT,EAAI,YAAc,EAClB,EAAI,UAAY,EAChB,EAAI,WAAW,EAAG,EAAG,EAAO,GAE5B,GAAM,CAAE,SAAU,KAAK,QACvB,AAAI,GACF,GAAI,IAAc,CAAC,GAAQ,CAAE,EAAG,EAAK,EAAY,EAAI,KAAK,KAAK,QAAQ,kBAAkB,KAAK,KC1D7F,YACL,EACA,GAIA,AAFwB,OAAM,QAAQ,GAAc,EAAa,CAAC,IAElD,QAAQ,AAAC,IAEvB,GAAM,GAAQ,YAAe,GACzB,EAAI,MACH,GAAoB,GAAO,EAAI,UAAU,MAAQ,OAGhD,EAAM,YAAe,GACvB,EAAI,IACH,GAAoB,GAAO,EAAI,UAAU,IAAM,GAAI,GAAI,GAEtD,EAAQ,EAAQ,GAAG,GAAM,KAAW,OAC1C,GAAI,IAAQ,EAAK,CAAE,UAAS,KAAK,KC1BrC,OAAoB,OCEb,YAAuB,GAC5B,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAQ,aAAiB,IAAS,EAAM,UAClC,YAAiB,IAAS,EAAM,YAAc,ECH/C,YAA0B,GAE/B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,GAAI,YAAiB,GAAI,SAAS,QAAU,GAAc,GACxD,MAAO,GAAQ,MAGjB,WAAiB,GACf,AAAI,CAAC,EAAE,eAEP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAO,IAGT,WAAgB,GACd,AAAI,CAAC,EAAE,eACP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAQ,IAGV,EAAM,iBAAiB,OAAQ,GAC/B,EAAM,iBAAiB,QAAS,KCxB7B,YAAuB,GAC5B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,AAAM,YAAe,OAAO,EAAO,GAAI,OAAM,qDAC7C,GAAM,GAAS,GAAI,YACnB,EAAO,OAAS,KACd,AAAI,MAAO,GAAO,QAAW,UAAU,EAAO,GAAI,OAAM,qEACxD,GAAM,GAAM,EAAI,SAAS,qBACzB,EAAI,OAAS,IAAM,EAAQ,GAC3B,EAAI,QAAU,EACd,EAAI,IAAM,EAAO,QAEnB,EAAO,QAAU,EACjB,EAAO,cAAc,KCXlB,YAA4B,GACjC,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAI,aAAiB,GACZ,GAAI,GAAW,EAAM,aAAc,EAAM,eAE9C,YAAiB,GACZ,GAAI,GAAW,EAAM,WAAY,EAAM,aAEzC,GAAI,GAAW,EAAM,MAAO,EAAM,QCNpC,YAAsB,CAAE,QAAO,WACpC,GAAM,CAAE,uBAAwB,EAAI,SAC9B,EAAS,IACf,SAAO,MAAQ,EACf,EAAO,OAAS,EACT,EAGF,YAA+B,EAAwD,GAC5F,GAAM,CAAE,aAAc,EAAI,SAE1B,GAAI,CAAE,aAAiB,KAAc,CAAC,GAAc,GAClD,KAAM,IAAI,OAAM,8DAGlB,GAAM,CAAE,QAAO,UAAW,GAAQ,GAAmB,GAC/C,EAAS,GAAa,CAAE,QAAO,WAErC,MAAI,aAAiB,GACnB,EAAoB,GAAQ,aAAa,EAAO,EAAG,GAEnD,EAAoB,GAAQ,UAAU,EAAO,EAAG,EAAG,EAAO,GAErD,EC7BT,OAAoB,OAKpB,kBACE,EACA,GAEA,GAAM,GAAe,GAAU,EAAI,SAAS,sBAEtC,CAAC,EAAQ,EAAO,GAAe,EAAU,MAAM,MAAM,EAAW,GAAa,EAAI,GACjF,EAAc,AAAG,QAAK,IAAM,EAAU,KAAK,EAAQ,EAAO,GAAa,SAC7E,YAAM,AAAG,YAAQ,SAAS,EAAa,GAEvC,EAAY,UAEL,ECfF,YAAwB,GAC7B,GAAM,CAAE,QAAO,SAAQ,SAAU,EAAI,SAErC,MAAO,aAAiB,IACnB,YAAiB,IACjB,YAAiB,GCPxB,MAAoB,OCKb,YAAuB,EAA6C,EAAmB,EAAuB,IACnH,GAAM,CAAE,QAAO,UAAW,EAAI,SAE9B,GAAI,CAAE,aAAiB,IAAS,YAAiB,IAC/C,KAAM,IAAI,OAAM,4EAGlB,GAAM,GAAO,GAAmB,GAC1B,EAAQ,EAAY,KAAK,IAAI,EAAK,OAAQ,EAAK,OAC/C,EAAQ,EAAQ,EAAK,MACrB,EAAS,EAAQ,EAAK,OAEtB,EAAe,GAAa,CAAE,MAAO,EAAW,OAAQ,IACxD,EAAc,YAAiB,GAAS,EAAQ,GAAsB,GAEtE,EAAS,KAAK,IAAI,EAAQ,GAAU,EACpC,EAAK,GAAe,EAAQ,EAAS,EAAS,EAC9C,EAAK,GAAe,EAAS,EAAQ,EAAS,EACpD,SAAoB,GAAc,UAAU,EAAa,EAAI,EAAI,EAAO,GAEjE,EDzBT,aAyBE,YACE,EACA,EAA6B,IAdvB,mBAAkD,GAElD,eAAiC,GAIjC,wBAA8B,GAE9B,sBAA+B,GAQrC,GAAI,CAAC,MAAM,QAAQ,GACjB,KAAM,IAAI,OAAM,4HAA4H,KAG9I,KAAK,mBAAqB,EAC1B,KAAK,WAAa,EAAO,OAEzB,EAAO,QAAQ,CAAC,EAAO,KACrB,GAAI,GAAW,IACb,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAO,EAAM,MACnC,OAGF,GAAI,EAAW,IACb,GAAM,GAAa,EAAc,MAAM,GACvC,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,yCAAyC,8CAG3D,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAQ,EAAc,MAAM,MAAM,GACxD,OAGF,GAAM,GAAU,YAAyB,GAAI,SAAS,OAAS,EAAQ,GAAsB,GAC7F,KAAK,UAAU,GAAO,EACtB,KAAK,iBAAiB,GAAO,CAAC,EAAO,OAAQ,EAAO,MAAO,QAIpD,gBACT,MAAO,MAAK,iBAGH,YACT,MAAO,MAAK,aAGH,gBACT,MAAO,MAAK,UAAY,GAAK,KAAK,sBAGzB,aACT,MAAO,MAAK,cAGH,mBACT,MAAO,MAAK,oBAGH,aACT,MAAO,MAAK,cAGH,2BACT,MAAO,IAAM,KAAK,UAAW,EAAG,GAAG,IACjC,CAAC,EAAG,IAAa,KAAK,2BAA2B,IAI9C,SAAS,GACd,MAAO,MAAK,SAAS,IAAa,KAAK,aAAa,GAG/C,mBAAmB,GACxB,MAAO,MAAK,iBAAiB,GAGxB,eAAe,GACpB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,cAAc,GACnB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,2BAA2B,GAChC,GAAI,MAAO,MAAK,WAAc,SAC5B,KAAM,IAAI,OAAM,yFAGlB,GAAM,GAAQ,KAAK,cAAc,GAC3B,EAAS,KAAK,eAAe,GACnC,MAAO,IAA0B,CAAE,QAAO,UAAU,KAAK,WAYpD,cAAc,EAAmB,EAA0B,IAChE,YAAK,WAAa,EAEX,AAAG,OAAK,KACb,GAAM,GAAe,GAAM,KAAK,UAAW,EAAG,GAAG,IAAI,AAAC,IACpD,GAAM,GAAQ,KAAK,SAAS,GAE5B,GAAI,YAAoB,WAEtB,GAAI,GAAY,EAAW,GAAS,EAAQ,EAAM,aAElD,SAAY,GAAY,EAAW,GAE/B,GAAU,MAAM,KAAO,GAAa,EAAU,MAAM,KAAO,IAC7D,GAAY,AAAG,QAAM,eAAe,EAAW,CAAC,EAAW,KAGtD,EAAU,KAAK,EAAW,EAAW,GAG9C,GAAI,YAAiB,GAAI,SAAS,OAChC,MAAO,AAAG,WAAQ,WAAW,GAAc,EAAO,EAAW,IAG/D,KAAM,IAAI,OAAM,+BAA+B,8FAAqG,OAOtJ,MAHoB,AAAG,SAAM,EAAa,IAAI,AAAC,GAAM,AAAG,OAAK,EAAG,aAAa,KAAK,KAAK,UAAW,EAAW,EAAW,OE3I9H,iBAAiC,GAC/B,GAAI,YAAkB,IACpB,MAAO,GAGT,GAAM,GAAgB,MAAM,QAAQ,GAChC,EACA,CAAC,GAEL,GAAI,CAAC,EAAc,OACjB,KAAM,IAAI,OAAM,4CAGlB,GAAM,GAAa,AAAC,GAAiB,MAAM,QAAQ,GAAU,mBAAmB,KAAS,GAEnF,EAAa,EAAc,IAAI,IAErC,SAAW,QAAQ,CAAC,EAAO,KACzB,GAAI,CAAC,GAAe,IAAU,CAAC,GAAW,IAAU,CAAC,EAAW,GAC9D,KAAI,OAAO,GAAc,IAAO,SACxB,GAAI,OAAM,eAAe,EAAW,sEAAsE,EAAc,MAG1H,GAAI,OAAM,eAAe,EAAW,iIAG5C,GAAI,EAAW,IAEb,GAAM,GAAY,EAAM,MAAM,GAC9B,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,eAAe,EAAW,iCAAiC,iDAMjF,KAAM,SAAQ,IACZ,EAAW,IAAI,AAAC,GAAU,GAAe,IAAU,GAAiB,KAG/D,GAAI,IAAS,EAAY,MAAM,QAAQ,ICtChD,kBACE,EACA,GAEA,GAAM,CAAE,UAAW,EAAI,SAEnB,EAAS,EAEb,GAAI,CAAE,aAAiB,KACrB,GAAM,GAAW,KAAM,GAAW,GAElC,GAAI,EAAS,UAAY,EACvB,KAAM,IAAI,OAAM,8CAGlB,GAAM,GAAiB,EAAS,SAAS,GACzC,EAAS,YAA0B,GAC/B,EACA,KAAM,IAAoB,GAGhC,GAAM,GAAM,EAAoB,GAQhC,MAAO,AAPO,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAO,MAAO,EAAO,QAAQ,IAAI,QAC7C,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAO,MAAO,EAAO,SAE/C,IAAI,CAAC,CAChB,IAAG,IAAG,QAAO,aAEb,GAAM,GAAU,GAAa,CAAE,QAAO,WACtC,SAAoB,GACjB,aAAa,EAAI,aAAa,EAAG,EAAG,EAAO,GAAS,EAAG,GACnD,ICnDX,OAAoB,OAgBpB,kBACE,EACA,GAEA,GAAI,CAAC,GAAW,IAAgB,CAAC,EAAW,GAC1C,KAAM,IAAI,OAAM,6DAGlB,GAAI,EAAW,IAAgB,EAAY,MAAM,GAAK,EACpD,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAW,EAAU,GAAe,EAAY,MAAM,MAAM,EAAW,GAAe,EAAI,GAajG,MAJoB,AAPN,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAU,GAAW,IACjC,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAU,IAEvB,IAAI,CAAC,CAC7B,IAAG,IAAG,QAAO,YACT,AAAG,WAAQ,EAAY,KAAK,EAAW,EAAU,GAAc,CAAC,EAAG,EAAG,GAAI,CAAC,EAAQ,EAAO,OCtCpG,kBACE,EAEA,GAEA,GAAM,CAAE,SAAU,EAAI,SAChB,EAAM,KAAM,GAAM,EAAK,GAC7B,GAAI,CAAE,GAAI,OAAS,KACjB,KAAM,IAAI,OAAM,qBAAqB,EAAI,WAAW,EAAI,yBAAyB,EAAI,OAEvF,MAAO,GCTT,kBAAiC,GAC/B,GAAM,GAAM,KAAM,IAAa,GACzB,EAAO,KAAO,GAAK,OAEzB,GAAI,CAAC,EAAK,KAAK,WAAW,UACxB,KAAM,IAAI,OAAM,wEAAwE,EAAK,kBAAkB,EAAI,OAErH,MAAO,IAAc,GCRvB,kBAAmC,GACjC,MAAQ,MAAM,IAAa,IAAM,OCDnC,kBAAsC,GACpC,MAAO,IAAI,cAAa,KAAO,MAAM,IAAa,IAAM,eCH1D,OAAoB,OCAb,YAAsB,EAAyB,GACpD,GAAM,GAA0B,GAAG,0BAEnC,GAAI,CAAC,EACH,MAAO,CACL,aAAc,GACd,YAAa,GAIjB,GAAI,IAAQ,IACV,MAAO,CACL,aAAc,IACd,YAAa,IAAI,KAIrB,GAAM,GAAW,EAAI,WAAW,WAAa,UAAY,EAAI,WAAW,YAAc,WAAa,GACnG,EAAM,EAAI,QAAQ,EAAU,IAE5B,GAAM,GAAQ,EAAI,MAAM,KAAK,OAAO,AAAC,GAAM,GAErC,EAAe,EAAI,SAAS,SAC9B,EAAM,EAAM,OAAS,GACrB,EAEA,EAAe,EAAY,GAAI,SAAS,SAAW,EAAM,MAAM,EAAG,EAAM,OAAS,GAAK,GAAO,KAAK,KACtG,SAAe,EAAI,WAAW,KAAO,IAAI,IAAiB,EAEnD,CACL,eACA,YAAa,IAAiB,IAAM,IAAI,IAAiB,GAAG,KAAgB,KD1BhF,kBACE,EACA,GAEA,GAAM,CAAE,cAAa,gBAAiB,GAAa,EAAK,GAClD,EAAW,KAAM,IAAuC,GAE9D,MAAO,AAAG,OAAG,YAAY,EAAU,GET9B,YAAyB,EAAoB,EAAwB,EAA8B,IACxG,GAAM,CAAE,QAAO,UAAW,EACtB,GAAmB,GACnB,EACJ,SAAM,MAAQ,EACd,EAAM,OAAS,EACR,CAAE,QAAO,UCTlB,OAAoB,OCApB,OAAoB,OAApB,0BAQY,aAAkC,OAElC,oBAAiC,MAIhC,UAAmC,MAAO,MAAK,WAE/C,iBAAkC,MAAO,MAAK,kBAE9C,YAAsB,MAAO,CAAC,CAAC,KAAK,OAExC,iBAAiB,GACtB,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,MAAO,GAAI,GAGN,sBAAsB,EAAmB,GAC9C,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,EAAI,GAAS,UACb,EAAI,GAAW,EAGV,eACL,MAAO,MAAK,eAAe,IAAI,CAAC,CAAE,eAAiB,EACjD,KAAM,EACN,OAAQ,KAAK,iBAAiB,MAI3B,qBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,EAAM,iBAAqB,cAGnE,kBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,CAAE,GAAM,iBAAqB,eAGrE,WACL,KAAK,kBAAkB,QAAQ,CAAC,CAAE,OAAM,aACtC,KAAK,sBAAsB,EAAM,EAAO,cAIrC,SACL,KAAK,qBAAqB,QAAQ,CAAC,CAAE,OAAM,OAAQ,MACjD,GAAM,GAAS,AAAG,UAAO,EAAS,YAClC,EAAS,UACT,KAAK,sBAAsB,EAAM,KAI9B,QAAQ,EAA4B,IACzC,KAAK,eAAe,QAAQ,AAAC,IAC3B,GAAI,GAAoB,EAAM,OAAO,WACnC,KAAM,IAAI,OAAM,mDAAmD,EAAM,QAE3E,EAAM,OAAO,YAEf,KAAK,QAAU,OAGV,kBACL,MAAO,IAAI,cACT,KAAK,eACF,IAAI,CAAC,CAAE,YAAa,MAAM,KAAK,EAAO,aACtC,OAAO,CAAC,EAAM,IAAQ,EAAK,OAAO,UAI5B,MAAK,GAChB,GAAI,YAAwB,eAC1B,KAAK,eAAe,GACpB,OAGF,KAAM,MAAK,YAAY,QAGZ,aAAY,GACvB,GAAI,GAAO,MAAO,IAAQ,SACxB,KAAM,IAAI,OAAM,GAAG,KAAK,0CAG1B,GAAM,GAAY,KAAM,IAAc,EAAK,KAAK,uBAChD,KAAK,kBAAkB,QAGZ,cAAa,GACxB,GAAI,GAAY,MAAO,IAAa,SAClC,KAAM,IAAI,OAAM,GAAG,KAAK,iDAG1B,GAAM,CAAE,YAAa,EAAI,SAEnB,CAAE,cAAa,gBAAiB,GAAa,EAAU,KAAK,uBAE5D,EAAuB,AAAC,GAAwB,QAAQ,IAC5D,EAAU,IAAI,AAAC,GAAO,EAAS,GAAI,KAAK,AAAC,GAAQ,EAAI,UAEjD,EAAc,AAAG,MAAG,qBAAqB,GACzC,EAAW,KAAK,MAAO,MAAM,GAAS,IAAc,YACpD,EAAY,KAAM,GAAY,EAAU,GAE9C,KAAK,kBAAkB,GAGlB,kBAAkB,GACvB,GAAM,CACJ,gBACA,UACE,KAAK,2BAA2B,GAEpC,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGV,eAAe,GACpB,GAAM,CACJ,gBACA,UACE,KAAK,cAAc,GAEvB,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGT,qBAAqB,GAC3B,GAAI,CAAC,KAAK,OACR,KAAM,IAAI,OAAM,qDAGlB,GAAM,GAAS,EAAU,MAAM,KAAK,OAAO,CAAC,EAAoD,KAE9F,GAAI,CAAC,EAAI,QAAQ,eAAe,GAC9B,KAAM,IAAI,OAAM,wDAAwD,eAAqB,KAG/F,MAAO,CAAE,IAAK,EAAI,QAAS,UAAS,QAAS,EAAI,QAAQ,KACxD,CAAE,QAAS,KAAK,SAEb,CAAE,MAAK,WAAY,EACzB,GAAI,CAAC,GAAO,CAAC,GAAW,CAAE,GAAI,YAAuB,YACnD,KAAM,IAAI,OAAM,8DAA8D,KAGhF,MAAO,CAAE,MAAK,aC1JlB,MAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,iBAAkB,EAAO,iBAAkB,EAAQ,QAC1F,SAAM,AAAG,OAAI,EAAK,EAAO,MAClB,IDNJ,YACL,EACA,EACA,EAAwB,IAExB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,CAAC,EAAG,GAAI,QACrE,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,CAAC,EAAG,KAE7E,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,OAItC,YACL,EACA,EACA,EAAwB,GACxB,EAAuB,IAEvB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,GAAI,QAC5F,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,KAEpG,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAE/D,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,KACxC,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,QEpD1D,OAAoB,OAIb,YACL,EACA,EACA,EAA4B,OAC5B,EAAoB,IAEpB,MAAO,AAAG,SAAK,KACb,GAAM,GAAM,AAAG,OACb,AAAG,UAAO,EAAG,EAAO,QAAS,CAAC,EAAG,GAAI,GACrC,EAAO,MAGT,MAAO,GAAW,AAAG,QAAK,GAAO,ICd9B,WAAoC,EAAgB,GACzD,OAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,AAAK,EAAc,KAAK,AAAC,GAAO,EAAG,eAAiB,IAClD,EAAU,GAAM,YCLtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,EACA,KAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,SCzBtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,KAEA,GAAM,GAAa,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAY,IAChF,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CACL,QAAS,EACT,KAAM,ICvBZ,OAAoB,OCApB,aAsBE,YAES,EAEA,EAEA,GAJA,wBAEA,wBAEA,cDxBJ,YACL,EACA,GAEA,MAAO,CAAC,EAAoB,EAAqB,KAC/C,GAAM,GAAmB,AAAG,YAAS,EAAe,EAAI,EAAI,GAAa,CAAC,EAAG,EAAG,EAAY,IACtF,EAAmB,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAG,EAAG,EAAY,IAC5F,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,WAGX,GAAI,IACT,EACA,EACA,IAKC,YAEL,GAEA,MAAO,AAAC,KACN,GAAM,GAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,IAAI,IACT,EACA,EACA,IEpCC,WAAmC,EAAgB,GACxD,MAAO,CAAC,EAAsB,EAAmB,KAC/C,GAAM,GAAS,EAAU,GAEzB,GAAI,CAAC,GAAS,EAAQ,GACpB,KAAM,IAAI,OAAM,sBAAsB,oBAA+B,oBAA4B,KAGnG,SAAc,KACZ,CAAE,eAAc,UAAW,GAAc,IAGpC,GCfJ,WAA+B,GACpC,GAAI,GAAmB,EAEvB,WAAwB,GACtB,GAAM,GAAM,EAAiB,MAAM,EAAG,GACtC,SAAmB,EAAiB,MAAM,GACnC,EAGT,aACE,MAAO,GAGT,MAAO,CACL,iBACA,uBCPG,YAA2B,EAAwC,GACxE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,GAAQ,EACV,EAAkB,EAAY,EAAa,EAAG,GAAG,WACjD,EAA2B,EAAY,EAAa,GAAG,WACrD,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAChE,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,CAAE,QAAO,QAAO,SAAU,EAAyB,EAAY,EAAa,EAAc,GAC1F,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAC3C,EAAS,EAAyB,IAAK,IAAK,UAElD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CACN,SAAQ,SAAQ,SAAQ,WCvBvB,YAA+B,GACpC,MAAO,AAAC,KACN,GAAM,GAAU,EAAgC,GAAG,YAAkB,GAC/D,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,CAAE,UAAS,SCNf,YAA2B,EAAgB,GAChD,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBhBxBnB,oBAU0C,GACxC,cACE,MAAM,wBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,sDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAE/B,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,+BAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KiBlDzB,OAAoB,OCApB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,IAAM,AAAG,OACtB,AAAG,UAAO,EAAG,EAAO,SACpB,EAAO,OCPJ,YAAuB,EAAuB,EAAoB,GACvE,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAIpB,EAAK,AAFa,GAAuB,EAAgB,GAEpC,EAAY,EAAa,MAEpD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,OCdP,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,EAAgB,OAGtB,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,YAA4B,GACjC,GAAM,GAAyC,GACzC,EAAmC,GAEzC,cAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,GAAM,GAAM,EAAI,WAAW,MAAQ,EAAgB,EACnD,EAAI,GAAO,EAAU,KAGhB,CAAE,sBAAqB,iBJXhC,oBAkBU,GAGR,YAAY,EAAe,GACzB,MAAM,GACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBASP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EACJ,MAAO,IAAoB,EAAmB,KAAK,EAAmB,MAAM,GAAI,IAAK,EAAO,MAIzF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,EAAS,KAAK,0BAA2B,KAAK,4BAG3D,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAM,KAAK,0BACX,EAAO,KAAK,2BACZ,EAAwB,EAAO,EAAO,EAEtC,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KKnFjC,GAAM,IAAyB,CAAC,UAAW,QAAS,MAAO,QAAS,UAAW,YAAa,aAAnG,SAiBE,YAAY,GACV,GAAI,EAAc,SAAW,EAC3B,KAAM,IAAI,OAAM,8EAA8E,EAAc,UAG9G,GAAuB,QAAQ,CAAC,EAAY,KAC1C,KAAK,GAAc,EAAc,KAIrC,gBACE,MAAO,IACJ,IAAI,AAAC,GAAgB,EAAE,aAAY,YAAa,KAAK,MACrD,KAAK,CAAC,EAAI,IAAO,EAAG,YAAc,EAAG,e1C9B5C,oBAQuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGtB,aAAa,GAClB,MAAO,AAAG,SAAK,IAAM,AAAG,WAAQ,KAAK,OAAO,UAGjC,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,oBAAmB,GAC9B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAC9B,EAAsB,KAAM,SAAQ,IAAI,AAAG,WAAQ,GAAK,IAAI,KAAO,KACvE,GAAM,GAAO,KAAM,GAAE,OACrB,SAAE,UACK,KAET,EAAI,UAEJ,GAAM,GAAqB,EACxB,IAAI,AAAC,GAAiB,GAAI,IAAgB,IAE7C,MAAO,GAAS,aACZ,EACA,EAAmB,GAGf,sBACR,MAAO,wBAGC,0BACR,MAAO,KAGC,2BACR,MAAO,K2C1CJ,YAA+B,GACpC,MAAO,GAAI,sBAAuB,IAG7B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,gBCPf,YACL,EACA,EACA,EAAgB,GAChB,GAIA,AAF6B,OAAM,QAAQ,GAAmB,EAAkB,CAAC,IAE5D,QAAQ,AAAC,IAE5B,GAAM,GAAO,YAAa,IACtB,EACC,GAAsB,GAAK,EAAE,YAAc,OAChD,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mHAIlB,GAAM,GAAmB,AADV,EAAK,gBACY,OAAO,AAAC,GAAc,EAAU,YAAc,GAExE,EAAS,GAAoB,GAC/B,EAAE,UAAU,IAAI,WACf,GAAmB,GAAI,GAAM,EAAG,GAMrC,AAJsB,GAAI,IACxB,EAAiB,IAAI,AAAC,GAAc,GAAG,EAAU,eAAe,GAAM,EAAU,iBAChF,GAEY,KAAK,KCxBhB,YAA6B,GAClC,MAAO,IAAoB,IAEtB,EAAI,oBAAwB,IAE5B,EAAI,6BAAiC,IAErC,EAAI,sBAA0B,GAG9B,YAEoD,EAAoB,GAC7E,GAAM,CAAE,IAAK,GAAU,EAAU,UAC3B,EAAY,EAAmB,QAAwB,EAAM,EAAG,EAAM,GAEtE,EAAO,EAAU,QACjB,CAAE,aAAc,EAAU,UAC1B,EAAc,GAAI,GAAc,EAAU,UAAU,MAAO,EAAK,QAAQ,EAAU,WAAY,GAQpG,MAAO,IAAK,KANM,CAChB,YACA,qBACA,gBCpCJ,aA+BE,YAAY,EAAqC,IAC/C,GAAM,CACJ,YAAY,GAAM,aAAa,GAAM,YAAW,YAAW,YAAW,cACpE,EACJ,KAAK,UAAY,EACjB,KAAK,WAAa,EAClB,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,uBAC9B,KAAK,WAAa,GAAc,yBAxCpC,SAiDE,YACE,EACA,EAAqC,IAErC,KAAK,cAAgB,EACrB,KAAK,QAAU,GAAI,IAAyB,GAG9C,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CACJ,YAAW,aAAY,YAAW,YAAW,YAAW,cACtD,KAAK,QAcT,GAZI,GAAa,KAAK,wBAAyB,KAC7C,GAAI,YAAc,EAClB,EAAI,UAAY,EAChB,GAAY,EAAK,KAAK,cAAc,iBACpC,GAAY,EAAK,KAAK,cAAc,kBACpC,GAAY,EAAK,KAAK,cAAc,mBACpC,GAAY,EAAK,KAAK,cAAc,WACpC,GAAY,EAAK,KAAK,cAAc,aAAc,IAClD,GAAY,EAAK,KAAK,cAAc,cAAe,IACnD,GAAY,EAAK,KAAK,cAAc,WAAY,KAG9C,GACF,EAAI,YAAc,EAClB,EAAI,UAAY,EAEhB,GAAM,GAAY,AAAC,IACjB,EAAI,YACJ,EAAI,IAAI,EAAG,EAAG,EAAG,EAAG,EAAW,EAAG,EAAI,KAAK,IAC3C,EAAI,QAEN,KAAK,cAAc,UAAU,QAAQ,MAOpC,YACL,EACA,GAGA,AAD2B,OAAM,QAAQ,GAAiB,EAAgB,CAAC,IACxD,QAAQ,AAAC,IAE1B,GAAM,GAAY,YAAa,GAC3B,EACC,GAAoB,GAAK,EAAE,UAAY,OAC5C,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gIAGlB,GAAI,IAAkB,GAAW,KAAK,qBC1G1C,OAAoB,OCApB,MAAoB,OCKpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAqC,EAAoB,EAAqB,GAC5E,GAAM,GAAkB,EAA2B,EAAY,EAAa,GAAG,qBACzE,EAAkB,EAA2B,EAAa,EAAa,GAAG,qBAC1E,EAAiB,EAAkB,EAAY,EAAa,EAAG,GAAG,oBAExE,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,EAAkB,GAChD,GAAM,GAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBAE1E,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YAAuB,EAAuB,GACnD,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAgB,GAEhC,EAAqB,EAAkB,EAAG,GAAI,EAAG,sBACjD,EAA+B,EAA4B,GAAI,GAAI,gCACnE,EAA+B,EAA4B,GAAI,IAAK,gCAEpE,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,IAAK,0BAA0B,OAG3F,GAAM,GAA4B,EAA4B,IAAK,IAAK,6BAClE,EAA2B,EAA2B,IAAK,IAAK,4BAEhE,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,aAAY,cAAa,cCjEvC,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAqC,GACnC,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAiB,EAAkB,GAAG,oBAE5C,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,GAC9B,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAEtD,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAW,GAE3B,EAAqB,EAAkB,sBACvC,EAA+B,EAA4B,gCAC3D,EAA+B,EAA4B,gCAE3D,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,0BAA0B,OAGtF,GAAM,GAA4B,EAA4B,6BACxD,EAA2B,EAA2B,4BAEtD,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,SAA2B,EAAW,GAE/B,CAAE,OAAQ,CAAE,aAAY,cAAa,aAAa,iBFrE3D,YAAc,EAAgB,EAAoB,GAChD,MAAO,AAAG,OAAI,AAAG,SAAO,EAAG,EAAO,QAAS,EAAQ,QAAS,EAAO,MAGrE,YAAwB,EAAgB,EAA8B,EAA2B,IAC/F,GAAI,GAAM,EAAkB,AAAG,OAAK,GAAK,EACzC,SAAM,EAAuB,EAAK,EAAO,gBAAiB,CAAC,EAAG,IAC9D,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,AAAG,MAAI,EAAK,GAAK,EAAG,EAAO,eAAgB,CAAC,EAAG,KAC9C,EAGT,YAAmB,EAAgB,GACjC,GAAI,GAAM,EAAuB,AAAG,OAAK,GAAI,EAAO,gBAAiB,CAAC,EAAG,IACzE,SAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,MAAI,EAAK,GACX,EA7BT,oBAgCkC,GAGhC,YAAY,GACV,MAAM,gBACN,KAAK,eAAiB,EAGjB,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,8CAGlB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,AAAG,OAAK,GAAK,EAAY,EAAO,WAAW,QAAS,CAAC,EAAG,KAClE,SAAM,GAAe,EAAK,EAAO,WAAW,kBAAmB,IAC/D,EAAM,GAAe,EAAK,EAAO,WAAW,mBAE5C,GAAM,KAAK,eAAgB,EAAG,GAAG,QAAQ,AAAC,IACxC,EAAM,GAAU,EAAK,EAAO,YAAY,cAAc,QAGxD,EAAM,GAAe,EAAK,EAAO,UAAU,iBAC3C,EAAM,AAAG,OAAK,EAAuB,EAAK,EAAO,UAAU,eAAgB,CAAC,EAAG,KACxE,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,sBAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,gBAG1C,cAAc,GACtB,MAAO,IAAc,EAAS,KAAK,kBG5EhC,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAkB,GAAuB,EAAgB,GAEzD,EAAM,EAAgB,IAAK,EAAG,UAC9B,EAAS,EAAgB,IAAK,EAAG,aAEvC,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,GAAI,CAAE,MAAK,YCflB,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,CACF,IAAK,EAAgB,UACrB,OAAQ,EAAgB,eAI5B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,GAAK,IAAL,UAAK,GAEV,SAAS,SAET,OAAO,SAJG,aNLZ,oBAakC,GAGhC,YAAY,EAAqC,GAAI,IAAa,IAChE,MAAM,gBACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBAGP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EAEE,EAAS,AAAG,WAAQ,EAAoB,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAAS,KAAK,EAAmB,MAAM,GAAI,IACnG,EAAM,GAAoB,EAAQ,EAAO,GAAG,KAAK,OACjD,EAAS,GAAoB,EAAQ,EAAO,GAAG,QACrD,MAAO,CAAE,MAAK,YAIX,aAAa,GAClB,MAAO,AAAG,SAAK,KACb,GAAM,CAAE,MAAK,UAAW,KAAK,OAAO,GACpC,MAAO,CAAE,MAAK,OAAQ,AAAG,WAAQ,WAIxB,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,qBAAoB,GAC/B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAE9B,EAAO,AAAG,WAAQ,EAAI,KACtB,EAAU,AAAG,WAAQ,EAAI,QACzB,EAAsB,EAAK,IAAI,CAAC,EAAW,IAAO,EACtD,YACA,aAAc,EAAQ,MAGlB,EAAqB,KAAM,SAAQ,IACvC,EAAoB,IAAI,MAAO,CAAE,YAAW,mBAC1C,GAAM,GAAO,MAAM,GAAU,QAAQ,GAC/B,EAAY,MAAM,GAAa,QAAQ,GACvC,EAAS,EAAW,GACpB,EAAS,EAAS,GAAO,KAAO,GAAO,OACvC,EAAoB,EAAS,EAAY,EAAI,EAEnD,SAAU,UACV,EAAa,UACN,CAAE,MAAK,SAAQ,wBAG1B,SAAI,IAAI,UACR,EAAI,OAAO,UAEJ,EAAS,aAAe,EAAiD,EAAmB,GAG3F,sBACR,MAAO,mBAGF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,GAGb,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAwB,IAAM,EAAI,EAAM,KAAM,EAAI,GAElD,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KOvHxC,MAAoB,OAApB,oBAYU,IACD,YAAY,EAAqB,EAAmB,GACzD,GAAM,GAAkB,EAAmB,IAAI,CAAC,CAAE,QAAO,aACvD,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,CACL,MAAO,EAAQ,EACf,OAAQ,EAAS,KAIf,EAAY,EAAgB,OAElC,MAAO,AAAG,QAAK,KACb,GAAM,GAA0B,CAAC,EAAe,IAAkB,AAAG,QAAM,CAAC,AAAG,OAAK,CAAC,IAAK,EAAO,WAAY,AAAG,OAAK,CAAC,IAAK,EAAO,YAAa,GAAG,KAAK,EAAG,KAAK,OAGzJ,EAAa,CAAC,EAAkB,KACpC,GAAM,CAAE,QAAO,UAAW,EAAgB,GAC1C,MAAO,GAAK,EAAO,GAAU,KAAK,IAAI,EAAQ,GAAU,EAAI,GAGxD,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GACvE,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GAa7E,MAXwB,GACrB,IAAI,AAAG,OAAK,CAAC,EAAW,KAAM,EAAW,YACzC,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAY,GACZ,EAAY,OAEb,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAgB,GAAU,MAC1B,EAAgB,GAAU,aAO3B,aAAa,GAClB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,KAAK,OAAO,GACxB,MAAO,MAAK,YACV,EACA,EAAM,UACN,EAAM,gBAAgB,IAAI,CAAC,CAAC,EAAQ,KAAY,EAAE,SAAQ,mBAKnD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,iBAAgB,GAC3B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAkB,AAAG,OACzB,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAAoB,KAAM,SAAQ,IAAI,EAAgB,IAC1D,MAAO,EAAgB,KACrB,GAAM,GAAiB,MAAM,KAAK,KAAM,GAAe,QACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,GAAO,IACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,CAAC,GAAO,IAExD,MAAO,IAAI,IACT,MAAM,IAAI,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,GAAI,GAAM,EAAQ,GAAc,EAAQ,KACxE,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,QAMtC,SAAgB,QAAQ,AAAC,GAAM,EAAE,WAE1B,EAAS,aAAe,EAAyC,EAAkB,GAGlF,2BACR,MAAO,OC9FX,oBAIuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGnB,sBACR,MAAO,yBAGC,0BACR,MAAO,OCdX,OAAoB,OCMb,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCnBZ,YAA2B,GAChC,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAEjD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,SAAQ,SAAQ,WF1B9B,oBAU8C,GAC5C,cACE,MAAM,4BAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,0DAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,GAAI,IAAK,CAAC,EAAG,GAAI,SAEjC,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,oCAGC,2BAA2B,GACnC,MAAO,IAA+B,GAG9B,cAAc,GACtB,MAAO,IAAkB,KGjD7B,oBAI2C,IACzC,YAAY,EAAiD,GAAI,KAC/D,MAAM,wBAAyB,GAGvB,sBACR,MAAO,8BAGC,0BACR,MAAO,OCdX,oBAKqC,MCLrC,MAAoB,OCApB,OAAoB,OCApB,OAAoB,OAIb,YAAe,EAAgB,GACpC,MAAO,AAAG,QAAI,AAAG,OAAI,EAAG,EAAO,SAAU,EAAO,QDAlD,YACE,EACA,EACA,EACA,EACA,EAA4B,QAE5B,GAAM,CAAE,UAAS,QAAS,EAAO,KAE7B,EAAM,AAAG,UAAO,EAAG,EAAS,EAAS,GACzC,SAAM,AAAG,OAAI,EAAK,GAClB,EAAM,GAAM,EAAK,EAAO,OACjB,EAAW,AAAG,QAAK,GAAO,EAG5B,YAAc,EAAgB,GACnC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAoB,EAAgB,GACzC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAkB,EAAgB,GACvC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,GAAM,SE7B5C,MAAoB,OAUpB,YAA2B,EAAwC,GACjE,WAA6B,EAAyB,EAAoB,GACxE,GAAM,GAAU,EAAe,GACzB,EAAQ,EAAQ,OAAU,GAAa,EAAa,GAE1D,GAAI,GAAQ,GACV,KAAM,IAAI,OAAM,+BAA+B,sBAA0B,EAAQ,uBAAuB,kBAA2B,KAGrI,MAAO,AAAG,QACR,IAAM,AAAG,YACP,AAAG,WAAS,EAAS,CAAC,EAAY,EAAO,EAAY,IACrD,CAAC,EAAG,EAAG,EAAG,KAKhB,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAU,EAAoB,EAAiB,EAAY,GAC3D,EAAO,AAAG,WAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,QAGpB,WAAiC,EAAoB,GACnD,GAAM,GAAU,AAAG,WAAS,EAAe,IACrC,EAAS,AAAG,WAAS,EAAe,IAE1C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,aAGX,CACL,UACA,UAIJ,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAO,EAAkB,EAAiB,EAAY,EAAY,GAAG,UACrE,EAAQ,EAAwB,EAAY,GAAG,WAErD,MAAO,CAAE,OAAM,SAGjB,WACE,EACA,EACA,EACA,EACA,EAAkB,IAElB,GAAM,GAAQ,EAAwB,GAAS,GAAM,GAAK,EAAiB,EAAY,EAAY,GAAG,WAChG,EAAQ,EAAuB,EAAiB,EAAY,EAAY,GAAG,WAEjF,MAAO,CAAE,QAAO,SAGlB,MAAO,CACL,yBACA,8BAIG,YAAuB,GAC5B,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAgB,GAEhC,EAAc,EAAuB,KAAM,GAAI,EAAG,eAClD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YAEnD,EAAc,EAA2B,MAAO,GAAI,EAAG,cAAe,IACtE,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YAEpD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aAEvD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAmB,EAA2B,OAAQ,IAAK,EAAG,oBAE9D,EAAK,AAAG,OACZ,IAAM,AAAG,YAAU,AAAG,WAAS,EAAe,IAAM,KAAM,CAAC,IAAK,MAAO,CAAC,EAAG,KAI7E,GAFA,EAAc,KAAK,CAAE,UAAW,OAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAsB1E,MAAO,CAAE,OAnBM,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGe,iBC9InB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAiC,GAC/B,GAAM,GAAU,EAAmB,GAAG,kBAAwB,GACxD,EAAS,EAAmB,GAAG,iBAAuB,GAE5D,MAAO,CAAE,UAAS,UAGpB,WAAgC,GAC9B,GAAM,GAAU,EAAmB,GAAG,iBAAuB,GACvD,EAAO,EAAmB,GAAG,cAAoB,GACjD,EAAQ,EAAwB,GAEtC,MAAO,CAAE,KAAM,CAAE,UAAS,QAAQ,SAGpC,WAAoC,GAClC,MAAO,CACL,MAAO,EAAuB,GAAG,WACjC,MAAO,EAAuB,GAAG,YAIrC,MAAO,CACL,yBACA,8BAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAW,GAE3B,EAAc,EAAuB,eACrC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAc,EAA2B,eACzC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aAEvC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aACvC,EAAmB,EAA2B,oBAE9C,CAAE,MAAO,EAGf,GAFA,EAAc,KAAK,CAAE,aAAc,KAAM,UAAW,OAEhD,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yDAAyD,KAG3E,GAAM,GAAS,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGF,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBChGnB,MAAoB,OAKb,YAAkB,EAAgB,GACvC,GAAI,GAAM,GAAK,EAAG,EAAO,OACzB,SAAM,GAAW,EAAK,EAAO,OAC7B,EAAM,AAAG,MAAI,EAAK,GAClB,EAAM,AAAG,OAAK,GACP,EAGF,YAAsB,EAAgB,GAC3C,GAAI,GAAM,GAAS,EAAG,EAAO,OAC7B,EAAM,GAAW,EAAK,EAAO,OAE7B,GAAI,GAAS,AAAG,UAAQ,EAAG,EAAG,EAAG,SAC3B,EAAQ,AAAG,QAAkB,EAAO,OACpC,EAAQ,EAAO,MAAM,KAAO,EAAI,MAAM,GAG5C,GAFsB,EAAO,MAAM,KAAO,EAAI,MAAM,IAAM,EAAO,MAAM,KAAO,EAAI,MAAM,IAGtF,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAE/B,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAGjC,SAAS,EAAQ,AAAG,SAAO,CAAC,EAAQ,GAAQ,GAAK,EACjD,EAAM,AAAG,MAAI,EAAQ,GAErB,EAAM,AAAG,OAAK,GACP,ELtCT,oBAWwC,GACtC,cACE,MAAM,sBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,QAAK,KAEb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAGtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,GAAS,EAAY,EAAO,aACtC,EAAM,AAAG,UAAQ,EAAK,EAAG,EAAG,SAE5B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,aAC/B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAa,EAAK,EAAO,kBAE/B,GAAM,GAAY,EAAI,KAAK,CAAC,EAAG,IAG/B,MAFuB,AAAG,UAAO,EAAW,EAAO,WAM1C,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,uBAAsB,GACjC,GAAM,GAAW,KAAM,GAAW,GAE5B,EAAwB,AAAG,OAC/B,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAA0B,KAAM,SAAQ,IAAI,EAAsB,IACtE,AAAC,GAAM,EAAE,SAGX,SAAsB,QAAQ,AAAC,GAAM,EAAE,WAEhC,EAAS,aACZ,EACA,EAAwB,GAGpB,sBACR,MAAO,yBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KMrFlB,YAAkC,GACvC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECHF,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,eCNf,YAAmB,GACxB,MAAO,OAAO,GAAI,KAAQ,SAGrB,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,QCNf,YAAsB,GAC3B,MAAQ,GAAI,SAAW,GAAO,MAAQ,EAAI,SAAW,GAAO,SACvD,GAAmB,EAAI,mBAGvB,YAGL,EACA,EACA,GAGA,MAAO,IAAK,KADM,CAAE,SAAQ,sBCpB9B,OAAoB,OCApB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,WAAoC,EAAqB,GACvD,GAAM,GAAU,AAAG,YAAS,EAAe,EAAI,EAAI,GAAc,CAAC,EAAG,EAAG,EAAa,IAC/E,EAAmB,AAAG,YAAS,EAAe,IAC9C,EAAoB,AAAG,YAAS,EAAe,IAC/C,EAAkB,AAAG,YAAS,EAAe,IAC7C,EAAsB,AAAG,YAAS,EAAe,IAEvD,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,uBAChB,CAAE,UAAW,GAAG,qBAChB,CAAE,UAAW,GAAG,0BAGX,CACL,UACA,mBACA,oBACA,kBACA,uBAIJ,WACE,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,KAAgB,EAAkB,oBAAsB,WAGnE,CAAE,UAAS,QAGpB,WACE,EACA,EACA,EACA,GAEA,GAAM,CACJ,UACA,QACE,EAAkB,EAAY,EAAa,EAAY,EAAc,IAEzE,MAAO,CACL,UACA,kBAAmB,GAIvB,WACE,EACA,EACA,GAEA,GAAM,GAAiB,EAA2B,EAAY,GAAG,oBAC3D,EAAiB,EAA2B,EAAY,EAAa,EAAG,GAAG,oBAEjF,MAAO,CAAE,iBAAgB,kBAG3B,aACE,GAAM,GAAS,EAA2B,EAAG,GAAI,EAAG,sBAE9C,EAAS,EAAsB,GAAI,GAAI,sBACvC,EAAS,EAAsB,GAAI,IAAK,sBACxC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,KAAM,uBAC3C,EAAU,EAAsB,KAAM,KAAM,uBAElD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,UACA,UACA,UACA,WAIJ,aACE,GAAM,GAAS,EAA2B,KAAM,IAAK,EAAG,2BAClD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,GAAI,EAAG,2BAChD,EAAS,EAA2B,GAAI,IAAK,EAAG,2BAEhD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,EAAG,EAAG,oDACjD,EAA2B,EAAkB,KAAM,GAAI,EAAG,2DAC1D,EAAoB,EAAkB,KAAM,GAAI,EAAG,oDACnD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDA2BxD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,gBAlCsB,CACtB,uBAAwB,EACxB,gBAAiB,GAiCjB,gBA/BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA8BjB,gBA5BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA2BjB,gBAzBsB,CACtB,uBAAwB,GACxB,gBAAiB,IAwBjB,gBAtBsB,CACtB,uBAAwB,EACxB,gBAAiB,IAqBjB,gBAnBsB,CACtB,uBAAwB,GACxB,gBAAiB,KAqBrB,MAAO,CACL,2BACA,gCAIG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,2BACA,gCACE,GAAkB,EAAgB,GAEhC,EAAc,IACd,EAAmB,IAKnB,EAAe,CACnB,UALgB,AAAG,YACnB,EAAe,KAAO,GACtB,CAAC,EAAG,KAAM,KAQZ,GAFA,EAAc,KAAK,CAAE,UAAW,2BAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,OAAQ,CACN,cACA,mBACA,gBAEF,iBCvNJ,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAoC,EAAgB,EAAa,GAC/D,GAAM,GAAU,EAAmB,GAAG,YAAiB,sBAAyB,EAAG,GAAG,aAChF,EAAoB,EAAmB,GAAG,YAAiB,oCAAuC,EAAG,GAAG,uBAE9G,MAAO,CAAE,UAAS,qBAGpB,WAA+B,GAC7B,GAAM,GAAe,oBAAoB,IACnC,EAAsB,sBAAsB,cAC5C,EAA4B,GAAG,mBAC/B,EAA4B,GAAG,mBAE/B,EAAU,EAAmB,GAAG,sBAAyC,EAAG,GAAG,aAC/E,EAAmB,EAAmB,GAAG,oBAAuC,EAAG,GAAG,sBACtF,EAAoB,EAAmB,GAAG,mBAAsC,EAAG,GAAG,uBACtF,EAAkB,EAAmB,GAAG,0BAA6C,EAAG,GAAG,qBAC3F,EAAsB,EAAmB,GAAG,8BAAiD,EAAG,GAAG,yBAEzG,MAAO,CACL,eAAgB,CACd,UACA,mBACA,oBACA,kBACA,uBAEF,eAAgB,EAA2B,cAAe,EAAK,IAInE,aACE,MAAO,CACL,OAAQ,EAA2B,cAAe,EAAG,sBACrD,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,KAInC,WAA2B,EAAgB,GACzC,GAAM,GAAU,EAAmB,GAAG,YAAkB,EAAG,GAAG,aACxD,EAAO,EAAmB,GAAG,WAAiB,EAAG,GAAG,UAE1D,MAAO,CAAE,UAAS,QAGpB,WAAmC,GACjC,GAAM,GAAyB,EAC7B,2BAA2B,yBAC3B,kCAAkC,4BAE9B,EAAkB,EACtB,2BAA2B,mBAC3B,kCAAkC,qBAGpC,MAAO,CAAE,yBAAwB,mBAGnC,aACE,MAAO,CACL,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,IAI/C,MAAO,CACL,2BACA,gCAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,2BACA,gCACE,GAAkB,EAAW,GAE3B,EAAY,EAAU,oBAG5B,GAFA,EAAc,KAAK,CAAE,aAAc,mBAAoB,UAAW,2BAE9D,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yEAAyE,KAG3F,GAAM,GAAS,CACb,YAAa,IACb,iBAAkB,IAClB,aAAc,CACZ,cAIJ,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCvInB,OAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,UAAO,EAAG,EAAO,QAAS,EAAS,QAChD,SAAM,AAAG,OAAI,EAAK,EAAO,mBAClB,AAAG,eAAY,EAAK,EAAG,KDPlC,GAAM,IAAU,qBAEhB,YACE,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,QAAS,EAAS,QACzD,SAAM,AAAG,aACP,EACA,EAAO,gBACP,EAAO,oBACP,EAAO,kBACP,EAAO,iBACP,IAEK,AAAG,eAAY,EAAK,EAAG,KAIlC,YAA+B,GAC7B,MAAO,CAAC,EAAG,EAAG,EAAG,IAAI,KAAK,AAAC,GAAQ,IAAQ,GAAY,CAAC,EAAG,GAAK,CAAC,EAAG,GAG/D,YAAqB,EAAgB,GAC1C,MAAO,AAAG,SAAK,KACb,GAAI,GACA,EAAM,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IA4BnD,GAVA,AAhBuB,CACrB,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,QACP,EAAO,QACP,EAAO,QACP,EAAO,SAGM,QAAQ,CAAC,EAAO,KAC7B,GAAM,GAAW,EAAI,EACf,EAAuB,GAAsB,GACnD,EAAM,GAAmB,EAAK,EAAM,eAAgB,GACpD,EAAM,EAAmB,EAAK,EAAM,eAAgB,CAAC,EAAG,IACpD,IAAa,IACf,GAAS,KAIT,IAAW,KACb,KAAM,IAAI,OAAM,iDAGlB,MAAO,CACL,MACA,OAAQ,KEjEd,YAAa,EAAoB,EAAW,GAC1C,GAAM,GAAY,EAAM,YAClB,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAS,GAAQ,GAAU,GAAQ,GACnC,EAAS,GAAQ,GAAU,GAAQ,GACzC,GAAI,GAAS,GAAK,GAAS,EACzB,MAAO,GAET,GAAM,GAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAmB,EAAkB,GACjE,KAAK,IAAI,EAAmB,EAAkB,GACpD,MAAO,GAAoB,GAAQ,EAAQ,GAGtC,YACL,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAW,EAAM,MAAM,GACvB,EAAa,KAAK,IACtB,EACA,GAGI,EAAa,EAChB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,OAAO,AAAC,GAAM,EAAE,MAAQ,GACxB,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAE5B,EAAe,AAAC,GAAe,GAAK,EAAe,EAAI,EAEvD,EAAqB,GAE3B,SAAW,QAAQ,AAAC,IAClB,GAAI,EAAS,QAAU,EACrB,OAEF,GAAM,GAAgB,EAAE,MAExB,OAAS,GAAI,EAAS,OAAS,EAAG,GAAK,EAAG,EAAE,GAC1C,GAAM,GAAM,GAAI,EAAO,EAAE,SAAU,EAAS,IAC5C,GAAI,IAAQ,GACZ,GAAE,OAAS,EAAa,GACpB,EAAE,OAAS,GAAgB,MAEjC,AAAI,IAAkB,EAAE,OACtB,EAAS,KAAK,EAAE,YAIb,ECjET,MAAoB,OAIpB,YAA2C,GACzC,GAAM,GAAM,AAAG,UAAQ,AAAG,YAAU,EAAG,CAAC,EAAG,KAErC,EAAQ,CACZ,AAAG,MAAI,EAAI,GAAI,EAAI,IACnB,AAAG,MAAI,EAAI,GAAI,EAAI,KAGf,EAAU,CACd,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,KAC1C,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,MAG5C,MAAO,CACL,QACA,WAIJ,YAA0B,EAAiB,GACzC,GAAM,CACJ,QACA,WACE,GAAkC,GAEhC,EAAM,AAAG,UAAQ,AAAG,YAAU,EAAI,CAAC,EAAG,KAEtC,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAE3E,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAEjF,MAAO,AAAG,aACR,AAAG,QAAM,CACP,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,KAEnB,CAAC,EAAG,IAID,YACL,EACA,EACA,GAEA,MAAO,AAAG,QAAK,KACb,GAAM,GAAY,EAAe,MAAM,GAEnC,EAAQ,GACV,AAAG,UAAQ,AAAG,OAAK,EAAO,UAAW,CAAC,EAAW,EAAG,IAAK,CAAC,GAAI,IAC9D,AAAG,UAAQ,EAAgB,CAAC,GAAI,KAElC,EAAQ,AAAG,UACT,EACA,CAAC,EAAY,EAAM,MAAM,GAAK,EAAY,IAG5C,GAAM,GAAmB,AAAG,UAAQ,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,MAC/E,EAAS,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,IAE5D,EAAS,AAAG,UACV,EACA,CAAC,EAAW,EAAO,MAAM,KAG3B,GAAM,GAAe,AAAG,UAAQ,GAC1B,EAAgB,AAAG,UAAQ,GAEjC,MAAO,CACL,MAAO,EACP,OAAQ,KC9Ed,OAAoB,OCApB,OAAoB,OAKb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAY,EAAE,MAAM,GAEpB,EAAwB,AAAG,WAC/B,GAAU,EAAG,EAAO,wBACpB,CAAC,EAAW,GAAI,EAAG,IAEf,EAAkB,AAAG,WACzB,GAAU,EAAG,EAAO,iBACpB,CAAC,EAAW,GAAI,IAGlB,MAAO,CACL,wBACA,qBDjBC,YACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAQ,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IACjD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IAErD,EAAiB,GAAmB,EAAQ,EAAO,iBACnD,EAAiB,GAAmB,EAAG,EAAO,iBAC9C,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAElD,EAAiB,AAAG,UAAO,CAC/B,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,uBACd,GAEG,EAAmB,AAAG,UAAO,CACjC,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,iBACd,GAEH,MAAO,CACL,iBACA,sBEhDN,YAYE,YAAY,CAAE,gBAAe,cAAuC,IAN1D,WAAgB,wBAUxB,GAHA,KAAK,eAAiB,GAAiB,GACvC,KAAK,YAAc,GAAc,IAE7B,MAAO,MAAK,gBAAmB,UAAY,KAAK,gBAAkB,GAAK,KAAK,gBAAkB,EAChG,KAAM,IAAI,OAAM,GAAG,KAAK,iEAG1B,GAAI,MAAO,MAAK,aAAgB,SAC9B,KAAM,IAAI,OAAM,GAAG,KAAK,iDAIxB,iBAA0B,MAAO,MAAK,kBAEtC,cAAuB,MAAO,MAAK,cT3BzC,oBAeoC,GAClC,cACE,MAAM,kBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,AAAG,SAAK,KAEb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAQ,WAEvD,EAAI,AAAG,OAAI,AAAG,OAAI,EAAa,AAAG,UAAO,sBAAwB,AAAG,UAAO,IAC3E,EAAW,GAAY,EAAG,EAAO,aAEjC,CACJ,iBACA,oBACE,GAAgB,EAAS,IAAK,EAAS,OAAQ,EAAO,kBAE1D,MAAO,IAAY,EAAgB,EAAkB,EAAO,qBAInD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,aACX,EACA,EAAkC,IAElC,GAAM,CAAE,aAAY,iBAAkB,GAAI,GAAsB,GAE1D,EAAW,KAAM,GAAW,GAE5B,CACJ,MAAO,EACP,OAAQ,GACN,KAAK,aAAa,GAGhB,EAAQ,EAAO,GACf,EAAS,EAAQ,GACvB,OAAS,GAAI,EAAG,EAAI,EAAO,OAAQ,IACjC,EAAO,GAAG,UACV,EAAQ,GAAG,UAIb,GAAM,GAAa,MAAM,KAAK,KAAM,GAAO,QAGrC,EAAU,GACd,EACA,EACA,EAJmB,GAMnB,GAGI,EAAe,EAAS,2BAA2B,GACnD,EAAY,EAAS,UACrB,EAAO,EAAY,EAAa,MAChC,EAAO,EAAY,EAAa,OAEhC,EAAY,EAAM,YAClB,EAAU,EACb,IAAI,AAAC,IACJ,GAAM,CAAC,EAAK,GAAU,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACf,CAAC,GAAM,IAAS,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACrB,MAAO,IAAI,GACT,EAAW,GACX,GAAI,IACF,GACA,EACA,GAAQ,GACR,EAAS,GAEX,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,OAKtC,SAAM,UACN,EAAO,UAEA,EAGC,sBACR,MAAO,wBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KUzHlB,YAA8B,GACnC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,EAGF,YAAgC,GACrC,MAAO,IAAqB,GAZ9B,oBAgBsC,MCd/B,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,QAAU,SACpB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,OAAQ,SAClB,GAAI,GAAM,QAAS,UAGR,GAAwB,CACnC,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAA+C,CAAC,QAAS,QAAS,QAElE,GAAqB,oBACrB,GAAoC,mCCvBjD,MAAoB,OCapB,GAAM,IAAW,AAAC,GAAa,MAAO,IAAQ,SAEvC,YAAwB,GAC7B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mBAAmB,KAGrC,GAAI,MAAO,GAAO,oBAAuB,UACvC,KAAM,IAAI,OAAM,wDAAwD,EAAO,sBAGjF,GAAI,CAAC,GAAS,EAAO,eAAiB,EAAO,aAAe,GAAK,EAAO,aAAe,EACrF,KAAM,IAAI,OAAM,gEAAgE,EAAO,gBAGzF,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,MAAM,AAAC,GAAW,MAAO,IAAM,UAElD,KAAM,IAAI,OAAM,kEAAkE,KAAK,UAAU,EAAO,YAG1G,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,IAAI,AAAC,GAAW,GAAK,IAAI,MAAM,AAAC,GAAW,GAAS,EAAE,IAAM,GAAS,EAAE,IAE1F,KAAM,IAAI,OAAM,wEAAwE,KAAK,UAAU,EAAO,YAGhH,GAAI,EAAO,SACT,EAAC,MAAM,QAAQ,EAAO,UACnB,EAAO,QAAQ,SAAW,GAC1B,CAAC,EAAO,QAAQ,MAAM,KAEzB,KAAM,IAAI,OAAM,8EAA8E,KAAK,UAAU,EAAO,YCjDxH,MAAoB,OCApB,MAAoB,OAEb,YAAe,GACpB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,AAAG,MAAI,EAAG,AAAG,SAAO,qBAChC,MAAO,AAAG,OAAI,AAAG,OAAK,AAAG,MAAI,EAAG,IAAO,KDApC,YAA2B,EAAgB,GAChD,MAAO,AAAG,QAAK,KACb,GAAI,GAAM,AAAG,MAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KAEjD,SAAM,AAAG,SAAO,EAAK,EAAO,KAAK,QAAS,CAAC,EAAG,GAAI,SAClD,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,KAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,SAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,KAAK,MAEvB,GAAM,KEdjB,OAAoB,OAKb,YAAgC,EAAgB,GACrD,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,OAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KAEjD,SAAM,AAAG,mBAAgB,EAAK,EAAO,iBAAkB,EAAO,iBAAkB,CAAC,EAAG,GAAI,SACxF,EAAM,AAAG,OAAI,EAAK,EAAO,MAElB,GAAM,KCZjB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAEnE,WAAgC,EAAc,GAC5C,GAAM,GAAM,AAAG,YAAS,EAAe,IACjC,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,SAChB,CAAE,UAAW,GAAG,cAGX,CAAE,MAAK,WAGhB,WAAwC,EAAoB,EAAqB,GAC/E,GAAM,GAAO,EAAkB,EAAY,EAAa,EAAG,GAAG,UACxD,EAAK,EAAuB,EAAa,GAAG,QAElD,MAAO,CAAE,OAAM,MAEjB,GAAM,GAA6B,GAAkC,EAAgB,GAErF,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,EACA,EACA,GAEA,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAgB,GAElC,EAEJ,GAAI,EAAO,oBACT,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EAEvC,EAAQ,EAAO,mBACjB,EAAkB,EAAI,EAAI,EAAG,SAC7B,EAA2B,EAAI,EAAI,SACjC,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAkB,GAAM,GAAM,EAAI,EAAI,EAAiB,EAAG,SACxE,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,eAG1D,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAAkB,EAAI,EAAI,EAAiB,EAAG,SAC5D,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,UAI5D,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CAAE,SAAQ,iBCvFnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAgC,GAC9B,GAAM,GAAM,EAAmB,GAAG,QAAc,GAC1C,EAAU,EAAmB,GAAG,YAAkB,GACxD,MAAO,CAAE,MAAK,WAGhB,WAA2B,GACzB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,WAAwC,GACtC,GAAM,GAAO,EAAkB,GAAG,UAC5B,EAAK,EAAuB,GAAG,QACrC,MAAO,CAAE,OAAM,MAGjB,GAAM,GAA6B,GAA+B,GAElE,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAW,GAE7B,EAEJ,GAAI,EAAO,oBAET,GAAM,GAAc,EAAO,aAAe,EAAO,YAAY,QAAU,EACvE,EAAS,CACP,MAAO,EAAO,mBAAqB,EAAkB,SAAW,EAA2B,SAC3F,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAkB,cAG3B,GAAS,CACP,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAAkB,UAI7B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCpFnB,aAYE,YAAY,CAAE,YAAW,kBAAuC,IANtD,WAAgB,oBAUxB,GAHA,KAAK,WAAa,GAAa,IAC/B,KAAK,gBAAkB,GAAkB,GAErC,MAAO,MAAK,YAAe,UAAY,KAAK,WAAa,IAAO,EAClE,KAAM,IAAI,OAAM,GAAG,KAAK,6DAG1B,GAAI,MAAO,MAAK,iBAAoB,UAAY,KAAK,iBAAmB,GAAK,KAAK,iBAAmB,EACnG,KAAM,IAAI,OAAM,GAAG,KAAK,qEAIxB,aAAsB,MAAO,MAAK,cAElC,kBAA2B,MAAO,MAAK,kBP3B7C,oBAuBoC,GAOlC,YAAY,GACV,MAAM,cACN,GAAe,GACf,KAAK,QAAU,KAGN,UACT,MAAO,MAAK,WAGH,mBACT,MAAO,MAAK,OAAO,iBAAmB,KAAK,OAAO,QAAQ,OAAS,KAG1D,mBACT,MAAO,GAAK,MAAK,gBAAkB,KAAK,OAAO,QAAQ,OAAS,GAG3D,cAAc,EAAgB,GACnC,GAAI,GAAM,GAAkB,EAAG,EAAO,OACtC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,GAAkB,EAAK,EAAO,OAE7B,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAgB,GAClC,GAAI,GAAM,KAAK,OAAO,mBAClB,GAAM,GAAU,EAAG,EAAO,MAAqB,QAAS,KACxD,GAAuB,EAAG,EAAO,OACrC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EACjE,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EAE1D,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAiB,GACnC,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,4CAGlB,MAAO,AAAG,QAAK,KAEb,GAAI,GAAc,AAAG,OAAK,EAAM,cAAc,EAAW,IAAQ,WACjE,SAAc,KAAK,OAAO,QACtB,GAAU,EAAa,KAAK,OAAO,SACnC,EACJ,EAAc,EAAY,IAAI,AAAG,SAAO,MAEjC,KAAK,OAAO,mBACf,KAAK,aAAa,EAAa,GAC/B,KAAK,cAAc,EAAa,UAI3B,SAAQ,EAAkB,GACrC,MAAO,MAAK,aAAa,KAAM,GAAW,GAAQ,QAGvC,QAAO,EAAkB,EAAoC,IACxE,GAAM,CAAE,YAAW,kBAAmB,GAAI,IAAkB,GAEtD,EAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,EAAU,GACxC,EAAO,AAAG,OAAK,IAAM,AAAG,UAAQ,GAAK,GAAG,cAExC,EAAkB,CACtB,MAAO,EAAS,cAAc,GAC9B,OAAQ,EAAS,eAAe,IAG5B,EAAU,KAAM,MAAK,aAAa,EAAM,EAAS,2BAA2B,GAAI,GACtF,EAAI,UACJ,EAAK,UAEL,GAAM,GAAQ,EAAQ,IAAI,AAAC,GAAQ,EAAI,KACjC,EAAS,EAAQ,IAAI,AAAC,GAAQ,EAAI,OAClC,EAAc,EAAQ,IAAI,AAAC,GAAQ,EAAI,YACvC,EAAa,EAAQ,IAAI,AAAC,GAAQ,KAAK,OAAO,QAAQ,EAAI,QAiBhE,MARmB,AAPH,IACd,EAAM,IAAI,AAAC,GAAQ,EAAI,QAAQ,IAC/B,EACA,KAAK,OAAO,aACZ,IAGyB,IAAI,AAAC,GAAQ,GAAI,IAC1C,EAAO,GACP,EAAY,GACZ,EAAW,GACX,EAAM,GACN,IAMM,sBACR,MAAO,GAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,QAG1C,cAAc,GACtB,GAAM,GAAc,KAAK,OAAO,aAAe,GAAe,qBAExD,EAAa,EAAc,EAAY,OAAS,OACtD,GAAI,IAAe,GAAK,IAAe,GAAK,IAAe,EACzD,KAAM,IAAI,OAAM,oEAAoE,2BAEtF,MAAO,IAAc,EAAS,KAAK,OAAQ,KAAK,gBAAiB,QAGnD,cACd,EACA,EACA,GAEA,GAAM,CAAE,QAAO,UAAW,EACpB,EAAY,KAAK,IAAI,EAAO,GAC5B,EAAoB,EAAY,EAChC,EAAoB,EAAY,EAEhC,EAAW,EAAa,MAAM,GAC9B,EAAW,KAAK,OAAO,QAAQ,OAE/B,CAAC,EAAa,EAAc,GAAqB,AAAG,OAAK,KAC7D,GAAM,GAAW,EAAa,QAAQ,CAAC,EAAU,EAAU,EAAU,KAAK,kBAEpE,EAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACpE,EAAS,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACrE,EAAc,KAAK,gBACrB,AAAG,UAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,KAAK,OAAO,QAAQ,SAAU,GACrG,AAAG,SAAO,GACd,MAAO,CAAC,EAAO,EAAQ,KAGnB,EAAU,GAEV,EAAa,KAAM,GAAa,QAChC,EAAY,KAAM,GAAY,QACpC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAS,EAAG,EAAS,EAAU,KACtC,GAAM,GAAQ,GAAQ,EAAW,GAAK,GAAK,GAAQ,IACnD,GAAI,CAAC,GAAkB,EAAQ,GAC7B,GAAM,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAe,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACvG,EAAgB,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EAExG,GAAK,EAAO,GAAa,EACzB,GAAK,GAAO,EAAc,EAE1B,GAAM,CAAE,MAAK,MAAK,UAClB,CAAE,cAAY,UAAU,KAAK,gBAC/B,KAAM,MAAK,sBAAsB,EAAkC,IACnE,CAAE,WAAY,EAAG,MAAO,GAE5B,EAAQ,KAAK,CACX,IAAK,GAAI,IAAY,GAAG,GAAG,GAAI,GAAY,GAAI,GAC/C,QACA,WAAY,EAAQ,GACpB,YACG,MAOb,SAAY,UACZ,EAAa,UACb,EAAkB,UAEX,OAGK,uBAAsB,EAA4B,GAC9D,GAAM,CAAE,MAAK,MAAK,UAAW,EACvB,EAAc,KAAM,GAAc,QACxC,MAAO,OAAM,KAAK,OAAO,QAAQ,QAAQ,KAAK,GAC3C,IAAI,CAAC,EAAG,IAAM,EAAY,GAAK,GAAK,GAAQ,IAC5C,IAAI,CAAC,EAAY,IAAW,EAC3B,aACA,WAED,OAAO,CAAC,EAAK,IAAU,EAAI,WAAa,EAAK,WAAa,EAAM,KApPvE,MAwBgB,AAxBhB,GAwBgB,qBAAuB,CACnC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,IAAK,KAAM,MQzBxC,oBAiBgC,IAC9B,YAAY,EAA8B,IACxC,GAAM,GAAS,CACb,qBACA,aAAc,GACd,QAAS,CAAC,WACN,EACA,CACA,QAAS,GACT,QAAS,IAET,CACA,QAAS,GACT,gBAAiB,KAIvB,MAAM,MAGG,sBACT,MAAO,MAAK,OAAO,sBAGV,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,MAAK,mBAAqB,GAAoC,GAG7D,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KC9CrC,YAA0B,EAAuB,EAA8B,IACpF,GAAM,GAAM,GAAI,IAAW,GAC3B,SAAI,eAAe,GACZ,ECZT,oBAI6C,IAJ7C,kCAKY,WAAgB,4BCL5B,kBACe,MAEX,GAEA,MAAO,GAAY,KAAM,MAAK,YAGnB,OACX,KAAM,IAAI,OAAM,6CCRpB,OAAoB,OCDpB,OAAoB,OAOpB,kBACE,EACA,EAEA,EACA,EAEA,EAAwF,CAAC,CAAE,iBAAkB,GAE7G,GAAM,GAAY,EAAc,IAAI,AAAC,GAAkB,GAAoB,GACvE,EAAoB,GACpB,EAAa,WACX,EAAgD,GACpD,aAAoB,WAChB,KAAM,IAAmB,EAAO,GAChC,KAAM,IAAa,EAAO,IAG1B,EAAU,KAAM,GAAe,GAErC,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAGT,kBACE,EACA,EAEA,EACA,EAEA,GAEA,MAAO,IACL,CAAC,GACD,EACA,KAAO,IAAU,EAAc,EAAM,IACrC,EACA,GC5CG,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAAqC,CAAC,QAAS,QAAS,QCZrE,oBAUsC,IACpC,cACE,GAAM,GAAS,CACb,mBAAoB,GACpB,aAAc,GACd,QAAS,CAAC,QACV,QAAS,GACT,QAAS,GACT,mBAAoB,GACpB,YAAa,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,MAGzC,MAAM,MAGG,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,2BAGC,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KCvBrC,GAAM,GAAO,CAClB,eAAgB,GAAI,IACpB,iBAAkB,GAAI,IACtB,WAAY,GAAI,IAChB,kBAAmB,GAAI,IACvB,sBAAuB,GAAI,IAC3B,mBAAoB,GAAI,IACxB,kBAAmB,GAAI,IACvB,aAAc,GAAI,KAUP,GAAiB,CAAC,EAAkB,IAA6D,EAAK,eAAe,YAAY,EAAO,GASxI,GAAmB,CAAC,EAAkB,IAA+D,EAAK,iBAAiB,YAAY,EAAO,GAS9I,GAAa,CAAC,EAAkB,IAA0D,EAAK,WAAW,YAAY,EAAO,GAS7H,GAAsB,AAAC,GAAmE,EAAK,kBAAkB,gBAAgB,GAWjI,GAA0B,AAAC,GAAmE,EAAK,sBAAsB,gBAAgB,GAYzI,GAAwB,AAAC,GAA6D,EAAK,mBAAmB,sBAAsB,GASpI,GAA2B,AAAC,GAAmE,EAAK,kBAAkB,mBAAmB,GASzI,GAAsB,AAAC,GAAiF,EAAK,aAAa,oBAAoB,GAE9I,GAA0B,AAAC,GAAgB,EAAK,eAAe,KAAK,GACpE,GAA4B,AAAC,GAAgB,EAAK,iBAAiB,KAAK,GACxE,GAAsB,AAAC,GAAgB,EAAK,WAAW,KAAK,GAC5D,GAAwB,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACrE,GAA4B,AAAC,GAAgB,EAAK,sBAAsB,KAAK,GAC7E,GAA2B,AAAC,GAAgB,EAAK,mBAAmB,KAAK,GACzE,GAA0B,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACvE,GAAqB,AAAC,GAAgB,EAAK,aAAa,KAAK,GAG7D,GAAyB,GACzB,GAAc,GACd,GAAkB,GCpH/B,oBAmB4E,IAC1E,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA1Bd,gBAkCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAwB,KAAM,IAClC,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,KAEtD,KAAK,gBAGP,MAAO,GAAc,IACnB,CAAC,EAAc,IAAM,GAAmC,EAAc,EAAsB,KAIhG,mBACE,MAAO,IAAI,IAA2B,KAAM,KAAK,SArDrD,gBA2DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,GAAkB,KAAM,IAC5B,EACA,KAAK,MACL,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,GACpD,KAAK,gBAGP,MAAO,IAA0B,EAAc,GAGjD,mBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA7ExD,gBAmFU,IACR,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAzFxD,gBA+FU,IACR,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCrG1D,oBAoByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA3Bd,gBAmCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAqB,KAAM,IAC/B,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,aAAa,oBAAoB,KAElD,KAAK,gBAGP,MAAO,GAAc,IAAI,CAAC,EAAc,KACtC,GAAM,CAAE,MAAK,SAAQ,qBAAsB,EAAmB,GAC9D,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,KAIpF,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAvDxD,gBA6DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,MAAK,SAAQ,qBAAsB,KAAM,IAC/C,EACA,KAAK,MACL,AAAC,GAAS,EAAK,aAAa,oBAAoB,GAChD,KAAK,gBAGP,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,GAGlF,sBACE,MAAO,IAAI,IAAiC,KAAM,KAAK,SA/E3D,gBAqFU,IACR,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA3FxD,gBAiGU,IACR,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCvG1D,oBAiB4E,IAC1E,YAEY,EAEA,GAEV,QAJU,kBAEA,eAtBd,gBA8BU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAUjC,MAAO,AARa,MAAM,IACxB,EACA,KAAK,MACL,AAAC,GAAU,QAAQ,IAAI,EAAM,IAAI,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,KACzF,KACA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,OAGxD,IAAI,CAAC,EAAY,IAAM,GAAkC,EAAc,GAAI,IAGhG,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,SAlDtE,gBAwDU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAEF,GAAM,GAAa,KAAM,IACvB,EACA,KAAK,MACL,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,GACxD,KAEA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,MAG3E,MAAO,IAAyB,EAAc,GAGhD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,SP/EzE,oBAqByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,6BAKE,eACZ,MAAO,MAAK,mBACR,EAAK,sBACL,EAAK,oBApCb,gBA0CU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAC3B,EAAa,EAAc,IAAI,AAAC,GAAQ,EAAI,WAE5C,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,GACrC,KAAM,IAAa,KAAK,MAAO,GAE7B,EAAsB,KAAM,SAAQ,IAAI,EAAM,IAClD,AAAC,GAAS,KAAK,YAAY,gBAAgB,KAG7C,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAAc,IAAI,CAAC,EAAc,IAAM,GAAiC,EAAc,EAAoB,KAGnH,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SArExD,gBA2EU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,aAAc,EAChB,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,CAAC,IACtC,KAAM,IAAa,KAAK,MAAO,CAAC,IAE9B,EAAY,KAAM,MAAK,YAAY,gBAAgB,EAAM,IAE/D,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,GAAiC,EAAc,GAGxD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SQvG1D,oBAckD,IAChD,YAEY,EAEA,EAAgC,GAAI,IAE9C,QAJU,aAEA,iBAnBd,gBAyBwC,SACzB,OACX,GAAM,CAAE,QAAO,WAAY,KAGrB,EAAwB,YAAmB,IAE7C,AAAC,GAAqB,EAAK,iBAAiB,YAAY,EAAO,GAG/D,YAAmB,GAEf,AAAC,GAAqB,EAAK,eAAe,YAAY,EAAO,GAE7D,YAAmB,IAEf,AAAC,GAAqB,EAAK,WAAW,YAAY,EAAO,GACzD,KAIZ,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,uIAGlB,MAAO,GAAsB,GAGvB,iCAEN,MAAO,IAAI,SAAiC,KAAO,KACjD,GAAM,GAAa,KAAM,MAAK,MAC9B,EAAQ,EAAW,IAAI,AAAC,GAAc,GAAwB,GAAI,OAItE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,SA/EX,gBAoF0C,SAC3B,OACX,GAAM,GAAiB,KAAM,IAAI,IAAmB,KAAK,MAAO,KAAK,SACjE,EAAgC,EAAe,GACnD,SAAe,QAAQ,AAAC,IACtB,AAAI,EAAc,MAAQ,EAA8B,OACtD,GAAgC,KAG7B,EAGD,gCAEN,MAAO,IAAI,SAA2C,KAAO,KAC3D,GAAM,GAAY,KAAM,MAAK,MAC7B,EAAQ,EAAY,GAA4B,GAAI,GAAa,UAIrE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,SCrHJ,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAqB,EAAO,GAGlC,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAmB,EAAO,GCRvC,kBACE,EACA,GAEA,MAAO,IAAe,EAAO,GAAI,GAAsB,EAAgB,CAAE,iBAAkB,KACxF,oBACA,sBAGL,kBACE,EACA,EAAoC,IAEpC,MAAO,IAAe,EAAO,GAAI,IAAkB,IAChD,oBACA,sBAGE,GAAM,IAAW,GC1BjB,YAA2B,EAA+B,GAC/D,GAAI,EAAK,SAAW,EAAK,OAAQ,KAAM,IAAI,OAAM,kDAEjD,GAAM,GAAQ,MAAM,KAAK,GACnB,EAAQ,MAAM,KAAK,GAEzB,MAAO,MAAK,KACV,EACG,IAAI,CAAC,EAAK,IAAM,EAAM,EAAM,IAC5B,OAAO,CAAC,EAAK,IAAS,EAAO,GAAQ,EAAI,ICThD,aAUE,YACE,EACA,EAA4B,IAE5B,KAAK,mBAAqB,EAE1B,GAAM,GAAa,MAAM,QAAQ,GAAU,EAAS,CAAC,GAErD,GAAI,CAAC,EAAW,OACd,KAAM,IAAI,OAAM,2DAGlB,GAAI,GAAQ,EACN,EAAoB,IAAM,UAAU,MAE1C,KAAK,oBAAsB,EAAW,IAAI,AAAC,IACzC,GAAI,YAAgB,IAClB,MAAO,GAGT,GAAI,YAAgB,cAClB,MAAO,IAAI,IAAuB,IAAqB,CAAC,IAG1D,GAAI,EAAK,YAAc,EAAK,qBAAsB,cAChD,MAAO,IAAI,IAAuB,IAAqB,CAAC,EAAK,aAG/D,KAAM,IAAI,OAAM,4MAIT,sBAAiD,MAAO,MAAK,uBAE7D,qBAA8B,MAAO,MAAK,mBAE9C,oBAAoB,EAA+B,GACxD,MAAO,GACJ,IAAI,AAAC,GAAM,GAAkB,EAAG,IAChC,OAAO,CAAC,EAAI,IAAO,EAAK,EAAI,GACxB,GAAY,QAAU,GAGxB,gBAAgB,GACrB,MAAO,MAAK,mBACT,IAAI,CAAC,CAAE,cAAa,WAAY,GAAI,IACnC,EACA,KAAK,oBAAoB,EAAiB,KAE3C,OAAO,CAAC,EAAM,IAAU,EAAK,SAAW,EAAK,SAAW,EAAO,GAG7D,cAAc,GACnB,GAAM,GAAY,KAAK,gBAAgB,GACvC,MAAO,GAAU,SAAW,KAAK,kBAC7B,EACA,GAAI,IAAU,UAAW,EAAU,UAGlC,SACL,MAAO,CACL,kBAAmB,KAAK,kBACxB,mBAAoB,KAAK,mBAAmB,IAAI,AAAC,GAAO,EAAG,iBAIjD,UAAS,GACrB,GAAM,GAAqB,EAAK,mBAC7B,IAAI,AAAC,GAAY,GAAuB,SAAS,IACpD,MAAO,IAAI,IAAY,EAAoB,EAAK,qBC1E7C,YAAgC,GACrC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECFF,YAA0B,EAAY,GAC3C,GAAM,CAAE,QAAO,UAAW,GAAI,GAAW,EAAW,MAAO,EAAW,QAEtE,GAAI,GAAS,GAAK,GAAU,EAC1B,KAAM,IAAI,OAAM,uCAAuC,KAAK,UAAU,CAAE,QAAO,cAGjF,GAAI,MAAM,QAAQ,GAEhB,MAAQ,GAAuB,IAAI,AAAC,GAAQ,GAAc,EAAK,CAAE,QAAO,YAG1E,GAAI,GAAoB,IACtB,GAAM,GAAmB,EAAQ,UAAU,QAAQ,EAAO,GACpD,EAAmB,EAAQ,mBAAmB,QAAQ,EAAiB,IAAI,MAAO,EAAiB,IAAI,QAC7G,MAAO,IAAwB,GAAwB,EAAS,GAAmB,GAGrF,MAAI,IAAoB,GACf,GAAwB,EAAS,EAAQ,UAAU,QAAQ,EAAO,IAGvE,YAAmB,IAAiB,YAAmB,GACjD,EAAgB,QAAQ,EAAO,GAGlC,EjJRT,GAAM,IAAQ,MAAO,UAAY,YAE3B,GAAW,MAAO,YAAc,aAAiB,MAAO,WAAU,WAAc,YACzE,GAAU,CAAE,QAAa,GAAmB,QAAM", + "sourcesContent": ["/* eslint-disable import/no-extraneous-dependencies */\n/* eslint-disable node/no-unpublished-import */\n\nexport * from '@tensorflow/tfjs-node-gpu';\n", "export function isNodejs(): boolean {\n return typeof global === 'object'\n && typeof require === 'function'\n && typeof module !== 'undefined'\n // issues with gatsby.js: module.exports is undefined\n // && !!module.exports\n && typeof process !== 'undefined' && !!process.version;\n}\n", "import * as tf from '../dist/tfjs.esm';\nimport * as draw from './draw/index';\nimport * as utils from './utils/index';\nimport * as pkg from '../package.json';\n\nexport { tf, draw, utils };\n\nexport * from './ageGenderNet/index';\nexport * from './classes/index';\nexport * from './dom/index';\nexport * from './env/index';\nexport * from './faceExpressionNet/index';\nexport * from './faceLandmarkNet/index';\nexport * from './faceRecognitionNet/index';\nexport * from './factories/index';\nexport * from './globalApi/index';\nexport * from './ops/index';\nexport * from './ssdMobilenetv1/index';\nexport * from './tinyFaceDetector/index';\nexport * from './tinyYolov2/index';\nexport * from './euclideanDistance';\nexport * from './NeuralNetwork';\nexport * from './resizeResults';\n\nconst node = (typeof process !== 'undefined');\nconst browser = (typeof navigator !== 'undefined') && (typeof navigator.userAgent !== 'undefined');\nexport const version = { faceapi: pkg.version as string, node, browser };\n", "export * from './drawContour';\nexport * from './drawDetections';\nexport * from './drawFaceExpressions';\nexport * from './DrawBox';\nexport * from './DrawFaceLandmarks';\nexport * from './DrawTextField';\n", "import { Point } from '../classes/index';\n\nexport function drawContour(\n ctx: CanvasRenderingContext2D,\n points: Point[],\n isClosed: boolean = false,\n) {\n ctx.beginPath();\n\n points.slice(1).forEach(({ x, y }, prevIdx) => {\n const from = points[prevIdx];\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(x, y);\n });\n\n if (isClosed) {\n const from = points[points.length - 1];\n const to = points[0];\n if (!from || !to) {\n return;\n }\n\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(to.x, to.y);\n }\n\n ctx.stroke();\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Point } from '../classes/index';\nimport { Dimensions, IDimensions } from '../classes/Dimensions';\n\nexport function isTensor(tensor: any, dim: number) {\n return tensor instanceof tf.Tensor && tensor.shape.length === dim;\n}\n\nexport function isTensor1D(tensor: any): tensor is tf.Tensor1D {\n return isTensor(tensor, 1);\n}\n\nexport function isTensor2D(tensor: any): tensor is tf.Tensor2D {\n return isTensor(tensor, 2);\n}\n\nexport function isTensor3D(tensor: any): tensor is tf.Tensor3D {\n return isTensor(tensor, 3);\n}\n\nexport function isTensor4D(tensor: any): tensor is tf.Tensor4D {\n return isTensor(tensor, 4);\n}\n\nexport function isFloat(num: number) {\n return num % 1 !== 0;\n}\n\nexport function isEven(num: number) {\n return num % 2 === 0;\n}\n\nexport function round(num: number, prec: number = 2) {\n const f = 10 ** prec;\n return Math.floor(num * f) / f;\n}\n\nexport function isDimensions(obj: any): boolean {\n return obj && obj.width && obj.height;\n}\n\nexport function computeReshapedDimensions({ width, height }: IDimensions, inputSize: number) {\n const scale = inputSize / Math.max(height, width);\n return new Dimensions(Math.round(width * scale), Math.round(height * scale));\n}\n\nexport function getCenterPoint(pts: Point[]): Point {\n return pts.reduce((sum, pt) => sum.add(pt), new Point(0, 0))\n .div(new Point(pts.length, pts.length));\n}\n\nexport function range(num: number, start: number, step: number): number[] {\n return Array(num).fill(0).map((_, i) => start + (i * step));\n}\n\nexport function isValidNumber(num: any) {\n return !!num && (num !== Infinity) && (num !== -Infinity) && !Number.isNaN(num) || num === 0;\n}\n\nexport function isValidProbablitiy(num: any) {\n return isValidNumber(num) && num >= 0 && num <= 1.0;\n}\n", "import { isValidNumber } from '../utils/index';\n\nexport interface IDimensions {\n width: number\n height: number\n}\n\nexport class Dimensions implements IDimensions {\n private _width: number\n\n private _height: number\n\n constructor(width: number, height: number) {\n if (!isValidNumber(width) || !isValidNumber(height)) {\n throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({ width, height })}`);\n }\n\n this._width = width;\n this._height = height;\n }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public reverse(): Dimensions {\n return new Dimensions(1 / this.width, 1 / this.height);\n }\n}\n", "export interface IPoint {\n x: number\n y: number\n}\n\nexport class Point implements IPoint {\n private _x: number\n\n private _y: number\n\n constructor(x: number, y: number) {\n this._x = x;\n this._y = y;\n }\n\n get x(): number { return this._x; }\n\n get y(): number { return this._y; }\n\n public add(pt: IPoint): Point {\n return new Point(this.x + pt.x, this.y + pt.y);\n }\n\n public sub(pt: IPoint): Point {\n return new Point(this.x - pt.x, this.y - pt.y);\n }\n\n public mul(pt: IPoint): Point {\n return new Point(this.x * pt.x, this.y * pt.y);\n }\n\n public div(pt: IPoint): Point {\n return new Point(this.x / pt.x, this.y / pt.y);\n }\n\n public abs(): Point {\n return new Point(Math.abs(this.x), Math.abs(this.y));\n }\n\n public magnitude(): number {\n return Math.sqrt((this.x ** 2) + (this.y ** 2));\n }\n\n public floor(): Point {\n return new Point(Math.floor(this.x), Math.floor(this.y));\n }\n}\n", "import { isDimensions, isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { IDimensions } from './Dimensions';\nimport { Point } from './Point';\nimport { IRect } from './Rect';\n\nexport class Box implements IBoundingBox, IRect {\n public static isRect(rect: any): boolean {\n return !!rect && [rect.x, rect.y, rect.width, rect.height].every(isValidNumber);\n }\n\n public static assertIsValidBox(box: any, callee: string, allowNegativeDimensions: boolean = false) {\n if (!Box.isRect(box)) {\n throw new Error(`${callee} - invalid box: ${JSON.stringify(box)}, expected object with properties x, y, width, height`);\n }\n\n if (!allowNegativeDimensions && (box.width < 0 || box.height < 0)) {\n throw new Error(`${callee} - width (${box.width}) and height (${box.height}) must be positive numbers`);\n }\n }\n\n private _x: number\n\n private _y: number\n\n private _width: number\n\n private _height: number\n\n constructor(_box: IBoundingBox | IRect, allowNegativeDimensions: boolean = true) {\n const box = (_box || {}) as any;\n\n const isBbox = [box.left, box.top, box.right, box.bottom].every(isValidNumber);\n const isRect = [box.x, box.y, box.width, box.height].every(isValidNumber);\n\n if (!isRect && !isBbox) {\n throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(box)}`);\n }\n\n const [x, y, width, height] = isRect\n ? [box.x, box.y, box.width, box.height]\n : [box.left, box.top, box.right - box.left, box.bottom - box.top];\n\n Box.assertIsValidBox({\n x, y, width, height,\n }, 'Box.constructor', allowNegativeDimensions);\n\n this._x = x;\n this._y = y;\n this._width = width;\n this._height = height;\n }\n\n public get x(): number { return this._x; }\n\n public get y(): number { return this._y; }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public get left(): number { return this.x; }\n\n public get top(): number { return this.y; }\n\n public get right(): number { return this.x + this.width; }\n\n public get bottom(): number { return this.y + this.height; }\n\n public get area(): number { return this.width * this.height; }\n\n public get topLeft(): Point { return new Point(this.left, this.top); }\n\n public get topRight(): Point { return new Point(this.right, this.top); }\n\n public get bottomLeft(): Point { return new Point(this.left, this.bottom); }\n\n public get bottomRight(): Point { return new Point(this.right, this.bottom); }\n\n public round(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.round(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public floor(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.floor(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public toSquare(): Box {\n let {\n x, y, width, height,\n } = this;\n const diff = Math.abs(width - height);\n if (width < height) {\n x -= (diff / 2);\n width += diff;\n }\n if (height < width) {\n y -= (diff / 2);\n height += diff;\n }\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public rescale(s: IDimensions | number): Box {\n const scaleX = isDimensions(s) ? (s as IDimensions).width : s as number;\n const scaleY = isDimensions(s) ? (s as IDimensions).height : s as number;\n return new Box({\n x: this.x * scaleX,\n y: this.y * scaleY,\n width: this.width * scaleX,\n height: this.height * scaleY,\n });\n }\n\n public pad(padX: number, padY: number): Box {\n const [x, y, width, height] = [\n this.x - (padX / 2),\n this.y - (padY / 2),\n this.width + padX,\n this.height + padY,\n ];\n return new Box({\n x, y, width, height,\n });\n }\n\n public clipAtImageBorders(imgWidth: number, imgHeight: number): Box {\n const {\n x, y, right, bottom,\n } = this;\n const clippedX = Math.max(x, 0);\n const clippedY = Math.max(y, 0);\n\n const newWidth = right - clippedX;\n const newHeight = bottom - clippedY;\n const clippedWidth = Math.min(newWidth, imgWidth - clippedX);\n const clippedHeight = Math.min(newHeight, imgHeight - clippedY);\n\n return (new Box({\n x: clippedX, y: clippedY, width: clippedWidth, height: clippedHeight,\n })).floor();\n }\n\n public shift(sx: number, sy: number): Box {\n const { width, height } = this;\n const x = this.x + sx;\n const y = this.y + sy;\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public padAtBorders(imageHeight: number, imageWidth: number) {\n const w = this.width + 1;\n const h = this.height + 1;\n\n const dx = 1;\n const dy = 1;\n let edx = w;\n let edy = h;\n\n let x = this.left;\n let y = this.top;\n let ex = this.right;\n let ey = this.bottom;\n\n if (ex > imageWidth) {\n edx = -ex + imageWidth + w;\n ex = imageWidth;\n }\n if (ey > imageHeight) {\n edy = -ey + imageHeight + h;\n ey = imageHeight;\n }\n if (x < 1) {\n edy = 2 - x;\n x = 1;\n }\n if (y < 1) {\n edy = 2 - y;\n y = 1;\n }\n\n return {\n dy, edy, dx, edx, y, ey, x, ex, w, h,\n };\n }\n\n public calibrate(region: Box) {\n return new Box({\n left: this.left + (region.left * this.width),\n top: this.top + (region.top * this.height),\n right: this.right + (region.right * this.width),\n bottom: this.bottom + (region.bottom * this.height),\n }).toSquare().round();\n }\n}\n", "import { Box } from './Box';\n\nexport interface IBoundingBox {\n left: number\n top: number\n right: number\n bottom: number\n}\n\nexport class BoundingBox extends Box implements IBoundingBox {\n constructor(left: number, top: number, right: number, bottom: number, allowNegativeDimensions: boolean = false) {\n super({\n left, top, right, bottom,\n }, allowNegativeDimensions);\n }\n}\n", "import { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { IRect, Rect } from './Rect';\n\nexport class ObjectDetection {\n private _score: number\n\n private _classScore: number\n\n private _className: string\n\n private _box: Rect\n\n private _imageDims: Dimensions\n\n constructor(\n score: number,\n classScore: number,\n className: string,\n relativeBox: IRect,\n imageDims: IDimensions,\n ) {\n this._imageDims = new Dimensions(imageDims.width, imageDims.height);\n this._score = score;\n this._classScore = classScore;\n this._className = className;\n this._box = new Box(relativeBox).rescale(this._imageDims);\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n\n public get className(): string { return this._className; }\n\n public get box(): Box { return this._box; }\n\n public get imageDims(): Dimensions { return this._imageDims; }\n\n public get imageWidth(): number { return this.imageDims.width; }\n\n public get imageHeight(): number { return this.imageDims.height; }\n\n public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()); }\n\n public forSize(width: number, height: number): ObjectDetection {\n return new ObjectDetection(\n this.score,\n this.classScore,\n this.className,\n this.relativeBox,\n { width, height },\n );\n }\n}\n", "import { Box } from './Box';\nimport { IDimensions } from './Dimensions';\nimport { ObjectDetection } from './ObjectDetection';\nimport { Rect } from './Rect';\n\nexport interface IFaceDetecion {\n score: number\n box: Box\n}\n\nexport class FaceDetection extends ObjectDetection implements IFaceDetecion {\n constructor(\n score: number,\n relativeBox: Rect,\n imageDims: IDimensions,\n ) {\n super(score, score, '', relativeBox, imageDims);\n }\n\n public forSize(width: number, height: number): FaceDetection {\n const { score, relativeBox, imageDims } = super.forSize(width, height);\n return new FaceDetection(score, relativeBox, imageDims);\n }\n}\n", "import { Box } from '../classes/Box';\n\nexport function iou(box1: Box, box2: Box, isIOU: boolean = true) {\n const width = Math.max(0.0, Math.min(box1.right, box2.right) - Math.max(box1.left, box2.left));\n const height = Math.max(0.0, Math.min(box1.bottom, box2.bottom) - Math.max(box1.top, box2.top));\n const interSection = width * height;\n\n return isIOU\n ? interSection / (box1.area + box2.area - interSection)\n : interSection / Math.min(box1.area, box2.area);\n}\n", "import { BoundingBox, IPoint } from '../classes/index';\n\nexport function minBbox(pts: IPoint[]): BoundingBox {\n const xs = pts.map((pt) => pt.x);\n const ys = pts.map((pt) => pt.y);\n const minX = xs.reduce((min, x) => (x < min ? x : min), Infinity);\n const minY = ys.reduce((min, y) => (y < min ? y : min), Infinity);\n const maxX = xs.reduce((max, x) => (max < x ? x : max), 0);\n const maxY = ys.reduce((max, y) => (max < y ? y : max), 0);\n\n return new BoundingBox(minX, minY, maxX, maxY);\n}\n", "import { Box } from '../classes/Box';\nimport { iou } from './iou';\n\nexport function nonMaxSuppression(\n boxes: Box[],\n scores: number[],\n iouThreshold: number,\n isIOU: boolean = true,\n): number[] {\n let indicesSortedByScore = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .sort((c1, c2) => c1.score - c2.score)\n .map((c) => c.boxIndex);\n\n const pick: number[] = [];\n\n while (indicesSortedByScore.length > 0) {\n const curr = indicesSortedByScore.pop() as number;\n pick.push(curr);\n\n const indices = indicesSortedByScore;\n\n const outputs: number[] = [];\n for (let i = 0; i < indices.length; i++) {\n const idx = indices[i];\n\n const currBox = boxes[curr];\n const idxBox = boxes[idx];\n\n outputs.push(iou(currBox, idxBox, isIOU));\n }\n\n indicesSortedByScore = indicesSortedByScore.filter(\n (_, j) => outputs[j] <= iouThreshold,\n );\n }\n\n return pick;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function normalize(x: tf.Tensor4D, meanRgb: number[]): tf.Tensor4D {\n return tf.tidy(() => {\n const [r, g, b] = meanRgb;\n const avg_r = tf.fill([...x.shape.slice(0, 3), 1], r, 'float32');\n const avg_g = tf.fill([...x.shape.slice(0, 3), 1], g, 'float32');\n const avg_b = tf.fill([...x.shape.slice(0, 3), 1], b, 'float32');\n const avg_rgb = tf.concat([avg_r, avg_g, avg_b], 3);\n\n return tf.sub(x, avg_rgb);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n/**\n * Pads the smaller dimension of an image tensor with zeros, such that width === height.\n *\n * @param imgTensor The image tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The padded tensor with width === height.\n */\nexport function padToSquare(\n imgTensor: tf.Tensor4D,\n isCenterImage: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const [height, width] = imgTensor.shape.slice(1);\n if (height === width) {\n return imgTensor;\n }\n\n const dimDiff = Math.abs(height - width);\n const paddingAmount = Math.round(dimDiff * (isCenterImage ? 0.5 : 1));\n const paddingAxis = height > width ? 2 : 1;\n\n const createPaddingTensor = (paddingAmountLocal: number): tf.Tensor => {\n const paddingTensorShape = imgTensor.shape.slice();\n paddingTensorShape[paddingAxis] = paddingAmountLocal;\n return tf.fill(paddingTensorShape, 0, 'float32');\n };\n\n const paddingTensorAppend = createPaddingTensor(paddingAmount);\n const remainingPaddingAmount = dimDiff - (paddingTensorAppend.shape[paddingAxis] as number);\n\n const paddingTensorPrepend = isCenterImage && remainingPaddingAmount\n ? createPaddingTensor(remainingPaddingAmount)\n : null;\n\n const tensorsToStack = [\n paddingTensorPrepend,\n imgTensor,\n paddingTensorAppend,\n ]\n .filter((t) => !!t)\n // .map((t: tf.Tensor) => t.toFloat()) as tf.Tensor4D[]\n .map((t: tf.Tensor) => tf.cast(t, 'float32')) as tf.Tensor4D[];\n return tf.concat(tensorsToStack, paddingAxis);\n });\n}\n", "export function shuffleArray(inputArray: any[]) {\n const array = inputArray.slice();\n for (let i = array.length - 1; i > 0; i--) {\n const j = Math.floor(Math.random() * (i + 1));\n const x = array[i];\n array[i] = array[j];\n array[j] = x;\n }\n return array;\n}\n", "export * from './iou';\nexport * from './minBbox';\nexport * from './nonMaxSuppression';\nexport * from './normalize';\nexport * from './padToSquare';\nexport * from './shuffleArray';\n\nexport function sigmoid(x: number) {\n return 1 / (1 + Math.exp(-x));\n}\n\nexport function inverseSigmoid(x: number) {\n return Math.log(x / (1 - x));\n}\n", "import { Box } from './Box';\n\nexport interface IRect {\n x: number\n y: number\n width: number\n height: number\n}\n\nexport class Rect extends Box implements IRect {\n constructor(x: number, y: number, width: number, height: number, allowNegativeDimensions: boolean = false) {\n super({\n x, y, width, height,\n }, allowNegativeDimensions);\n }\n}\n", "import { minBbox } from '../ops/index';\nimport { getCenterPoint } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { FaceDetection } from './FaceDetection';\nimport { Point } from './Point';\nimport { IRect, Rect } from './Rect';\n\n// face alignment constants\nconst relX = 0.5;\nconst relY = 0.43;\nconst relScale = 0.45;\n\nexport interface IFaceLandmarks {\n positions: Point[]\n shift: Point\n}\n\nexport class FaceLandmarks implements IFaceLandmarks {\n protected _shift: Point\n\n protected _positions: Point[]\n\n protected _imgDims: Dimensions\n\n constructor(\n relativeFaceLandmarkPositions: Point[],\n imgDims: IDimensions,\n shift: Point = new Point(0, 0),\n ) {\n const { width, height } = imgDims;\n this._imgDims = new Dimensions(width, height);\n this._shift = shift;\n this._positions = relativeFaceLandmarkPositions.map(\n (pt) => pt.mul(new Point(width, height)).add(shift),\n );\n }\n\n public get shift(): Point { return new Point(this._shift.x, this._shift.y); }\n\n public get imageWidth(): number { return this._imgDims.width; }\n\n public get imageHeight(): number { return this._imgDims.height; }\n\n public get positions(): Point[] { return this._positions; }\n\n public get relativePositions(): Point[] {\n return this._positions.map(\n (pt) => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight)),\n );\n }\n\n public forSize(width: number, height: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n { width, height },\n );\n }\n\n public shiftBy(x: number, y: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n this._imgDims,\n new Point(x, y),\n );\n }\n\n public shiftByPoint(pt: Point): T {\n return this.shiftBy(pt.x, pt.y);\n }\n\n /**\n * Aligns the face landmarks after face detection from the relative positions of the faces\n * bounding box, or it's current shift. This function should be used to align the face images\n * after face detection has been performed, before they are passed to the face recognition net.\n * This will make the computed face descriptor more accurate.\n *\n * @param detection (optional) The bounding box of the face or the face detection result. If\n * no argument was passed the position of the face landmarks are assumed to be relative to\n * it's current shift.\n * @returns The bounding box of the aligned face.\n */\n public align(\n detection?: FaceDetection | IRect | IBoundingBox | null,\n options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { },\n ): Box {\n if (detection) {\n const box = detection instanceof FaceDetection\n ? detection.box.floor()\n : new Box(detection);\n\n return this.shiftBy(box.x, box.y).align(null, options);\n }\n\n const { useDlibAlignment, minBoxPadding } = { useDlibAlignment: false, minBoxPadding: 0.2, ...options };\n\n if (useDlibAlignment) {\n return this.alignDlib();\n }\n\n return this.alignMinBbox(minBoxPadding);\n }\n\n private alignDlib(): Box {\n const centers = this.getRefPointsForAlignment();\n\n const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers;\n const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude();\n const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;\n\n const size = Math.floor(eyeToMouthDist / relScale);\n\n const refPoint = getCenterPoint(centers);\n // TODO: pad in case rectangle is out of image bounds\n const x = Math.floor(Math.max(0, refPoint.x - (relX * size)));\n const y = Math.floor(Math.max(0, refPoint.y - (relY * size)));\n\n return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y));\n }\n\n private alignMinBbox(padding: number): Box {\n const box = minBbox(this.positions);\n return box.pad(box.width * padding, box.height * padding);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n throw new Error('getRefPointsForAlignment not implemented by base class');\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks5 extends FaceLandmarks {\n protected getRefPointsForAlignment(): Point[] {\n const pts = this.positions;\n return [\n pts[0],\n pts[1],\n getCenterPoint([pts[3], pts[4]]),\n ];\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks68 extends FaceLandmarks {\n public getJawOutline(): Point[] {\n return this.positions.slice(0, 17);\n }\n\n public getLeftEyeBrow(): Point[] {\n return this.positions.slice(17, 22);\n }\n\n public getRightEyeBrow(): Point[] {\n return this.positions.slice(22, 27);\n }\n\n public getNose(): Point[] {\n return this.positions.slice(27, 36);\n }\n\n public getLeftEye(): Point[] {\n return this.positions.slice(36, 42);\n }\n\n public getRightEye(): Point[] {\n return this.positions.slice(42, 48);\n }\n\n public getMouth(): Point[] {\n return this.positions.slice(48, 68);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n return [\n this.getLeftEye(),\n this.getRightEye(),\n this.getMouth(),\n ].map(getCenterPoint);\n }\n}\n", "import { round } from '../utils/index';\n\nexport interface IFaceMatch {\n label: string\n distance: number\n}\n\nexport class FaceMatch implements IFaceMatch {\n private _label: string\n\n private _distance: number\n\n constructor(label: string, distance: number) {\n this._label = label;\n this._distance = distance;\n }\n\n public get label(): string { return this._label; }\n\n public get distance(): number { return this._distance; }\n\n public toString(withDistance: boolean = true): string {\n return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`;\n }\n}\n", "import { isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { IRect } from './Rect';\n\nexport class LabeledBox extends Box {\n public static assertIsValidLabeledBox(box: any, callee: string) {\n Box.assertIsValidBox(box, callee);\n\n if (!isValidNumber(box.label)) {\n throw new Error(`${callee} - expected property label (${box.label}) to be a number`);\n }\n }\n\n private _label: number\n\n constructor(box: IBoundingBox | IRect | any, label: number) {\n super(box);\n this._label = label;\n }\n\n public get label(): number { return this._label; }\n}\n", "export class LabeledFaceDescriptors {\n private _label: string\n\n private _descriptors: Float32Array[]\n\n constructor(label: string, descriptors: Float32Array[]) {\n if (!(typeof label === 'string')) {\n throw new Error('LabeledFaceDescriptors - constructor expected label to be a string');\n }\n\n if (!Array.isArray(descriptors) || descriptors.some((desc) => !(desc instanceof Float32Array))) {\n throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array');\n }\n\n this._label = label;\n this._descriptors = descriptors;\n }\n\n public get label(): string { return this._label; }\n\n public get descriptors(): Float32Array[] { return this._descriptors; }\n\n public toJSON(): any {\n return {\n label: this.label,\n descriptors: this.descriptors.map((d) => Array.from(d)),\n };\n }\n\n public static fromJSON(json: any): LabeledFaceDescriptors {\n const descriptors = json.descriptors.map((d: any) => new Float32Array(d));\n return new LabeledFaceDescriptors(json.label, descriptors);\n }\n}\n", "import { isValidProbablitiy } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { LabeledBox } from './LabeledBox';\nimport { IRect } from './Rect';\n\nexport class PredictedBox extends LabeledBox {\n public static assertIsValidPredictedBox(box: any, callee: string) {\n LabeledBox.assertIsValidLabeledBox(box, callee);\n\n if (\n !isValidProbablitiy(box.score)\n || !isValidProbablitiy(box.classScore)\n ) {\n throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`);\n }\n }\n\n private _score: number\n\n private _classScore: number\n\n constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {\n super(box, label);\n this._score = score;\n this._classScore = classScore;\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\n\nexport type WithFaceDetection = TSource & {\n detection: FaceDetection\n}\n\nexport function isWithFaceDetection(obj: any): obj is WithFaceDetection<{}> {\n return obj.detection instanceof FaceDetection;\n}\n\nexport function extendWithFaceDetection<\n TSource\n>(\n sourceObj: TSource,\n detection: FaceDetection,\n): WithFaceDetection {\n const extension = { detection };\n return { ...sourceObj, ...extension };\n}\n", "import { Environment } from './types';\n\nexport function createBrowserEnv(): Environment {\n const fetch = window.fetch;\n if (!fetch) throw new Error('fetch - missing fetch implementation for browser environment');\n\n const readFile = () => {\n throw new Error('readFile - filesystem not available for browser environment');\n };\n\n return {\n Canvas: HTMLCanvasElement,\n CanvasRenderingContext2D,\n Image: HTMLImageElement,\n ImageData,\n Video: HTMLVideoElement,\n createCanvasElement: () => document.createElement('canvas'),\n createImageElement: () => document.createElement('img'),\n fetch,\n readFile,\n };\n}\n", "import { FileSystem } from './types';\n\nexport function createFileSystem(fs?: any): FileSystem {\n let requireFsError = '';\n\n if (!fs) {\n try {\n // eslint-disable-next-line global-require\n fs = require('fs');\n } catch (err) {\n requireFsError = err.toString();\n }\n }\n\n const readFile = fs\n ? (filePath: string) => new Promise((resolve, reject) => {\n fs.readFile(filePath, (err: any, buffer: Buffer) => (err ? reject(err) : resolve(buffer)));\n })\n : () => {\n throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`);\n };\n\n return {\n readFile,\n };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { createFileSystem } from './createFileSystem';\nimport { Environment } from './types';\n\nexport function createNodejsEnv(): Environment {\n // eslint-disable-next-line dot-notation\n const Canvas = global['Canvas'] || global.HTMLCanvasElement;\n const Image = global.Image || global.HTMLImageElement;\n\n const createCanvasElement = () => {\n if (Canvas) return new Canvas();\n throw new Error('createCanvasElement - missing Canvas implementation for nodejs environment');\n };\n\n const createImageElement = () => {\n if (Image) return new Image();\n throw new Error('createImageElement - missing Image implementation for nodejs environment');\n };\n\n const fetch = global.fetch;\n // if (!fetch) throw new Error('fetch - missing fetch implementation for nodejs environment');\n\n const fileSystem = createFileSystem();\n\n return {\n Canvas: Canvas || class {},\n CanvasRenderingContext2D: global.CanvasRenderingContext2D || class {},\n Image: Image || class {},\n ImageData: global.ImageData || class {},\n Video: global.HTMLVideoElement || class {},\n createCanvasElement,\n createImageElement,\n fetch,\n ...fileSystem,\n };\n}\n", "export function isBrowser(): boolean {\n return typeof window === 'object'\n && typeof document !== 'undefined'\n && typeof HTMLImageElement !== 'undefined'\n && typeof HTMLCanvasElement !== 'undefined'\n && typeof HTMLVideoElement !== 'undefined'\n && typeof ImageData !== 'undefined'\n && typeof CanvasRenderingContext2D !== 'undefined';\n}\n", "import { createBrowserEnv } from './createBrowserEnv';\nimport { createFileSystem } from './createFileSystem';\nimport { createNodejsEnv } from './createNodejsEnv';\nimport { isBrowser } from './isBrowser';\nimport { isNodejs } from './isNodejs';\nimport { Environment } from './types';\n\nlet environment: Environment | null;\n\nfunction getEnv(): Environment {\n if (!environment) {\n throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()');\n }\n return environment;\n}\n\nfunction setEnv(env: Environment) {\n environment = env;\n}\n\nfunction initialize() {\n // check for isBrowser() first to prevent electron renderer process\n // to be initialized with wrong environment due to isNodejs() returning true\n if (isBrowser()) return setEnv(createBrowserEnv());\n if (isNodejs()) return setEnv(createNodejsEnv());\n return null;\n}\n\nfunction monkeyPatch(env: Partial) {\n if (!environment) {\n initialize();\n }\n\n if (!environment) {\n throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()');\n }\n\n const { Canvas = environment.Canvas, Image = environment.Image } = env;\n environment.Canvas = Canvas;\n environment.Image = Image;\n environment.createCanvasElement = env.createCanvasElement || (() => new Canvas());\n environment.createImageElement = env.createImageElement || (() => new Image());\n\n environment.ImageData = env.ImageData || environment.ImageData;\n environment.Video = env.Video || environment.Video;\n environment.fetch = env.fetch || environment.fetch;\n environment.readFile = env.readFile || environment.readFile;\n}\n\nexport const env = {\n getEnv,\n setEnv,\n initialize,\n createBrowserEnv,\n createFileSystem,\n createNodejsEnv,\n monkeyPatch,\n isBrowser,\n isNodejs,\n};\n\ninitialize();\n\nexport * from './types';\n", "import { env } from '../env/index';\n\nexport function resolveInput(arg: string | any) {\n if (!env.isNodejs() && typeof arg === 'string') {\n return document.getElementById(arg);\n }\n return arg;\n}\n", "import { env } from '../env/index';\nimport { resolveInput } from './resolveInput';\n\nexport function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {\n const { Canvas, CanvasRenderingContext2D } = env.getEnv();\n\n if (canvasArg instanceof CanvasRenderingContext2D) {\n return canvasArg;\n }\n\n const canvas = resolveInput(canvasArg);\n\n if (!(canvas instanceof Canvas)) {\n throw new Error('resolveContext2d - expected canvas to be of instance of Canvas');\n }\n\n const ctx = canvas.getContext('2d');\n if (!ctx) {\n throw new Error('resolveContext2d - canvas 2d context is null');\n }\n\n return ctx;\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IDimensions, IPoint } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { resolveInput } from '../dom/resolveInput';\n\n// eslint-disable-next-line no-shadow\nexport enum AnchorPosition {\n // eslint-disable-next-line no-unused-vars\n TOP_LEFT = 'TOP_LEFT',\n // eslint-disable-next-line no-unused-vars\n TOP_RIGHT = 'TOP_RIGHT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_LEFT = 'BOTTOM_LEFT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_RIGHT = 'BOTTOM_RIGHT'\n}\n\nexport interface IDrawTextFieldOptions {\n anchorPosition?: AnchorPosition\n backgroundColor?: string\n fontColor?: string\n fontSize?: number\n fontStyle?: string\n padding?: number\n}\n\nexport class DrawTextFieldOptions implements IDrawTextFieldOptions {\n public anchorPosition: AnchorPosition\n\n public backgroundColor: string\n\n public fontColor: string\n\n public fontSize: number\n\n public fontStyle: string\n\n public padding: number\n\n constructor(options: IDrawTextFieldOptions = {}) {\n const {\n anchorPosition, backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = options;\n this.anchorPosition = anchorPosition || AnchorPosition.TOP_LEFT;\n this.backgroundColor = backgroundColor || 'rgba(0, 0, 0, 0.5)';\n this.fontColor = fontColor || 'rgba(255, 255, 255, 1)';\n this.fontSize = fontSize || 14;\n this.fontStyle = fontStyle || 'Georgia';\n this.padding = padding || 4;\n }\n}\n\nexport class DrawTextField {\n public text: string[]\n\n public anchor : IPoint\n\n public options: DrawTextFieldOptions\n\n constructor(\n text: string | string[] | DrawTextField,\n anchor: IPoint,\n options: IDrawTextFieldOptions = {},\n ) {\n // eslint-disable-next-line no-nested-ternary\n this.text = typeof text === 'string'\n ? [text]\n : (text instanceof DrawTextField ? text.text : text);\n this.anchor = anchor;\n this.options = new DrawTextFieldOptions(options);\n }\n\n measureWidth(ctx: CanvasRenderingContext2D): number {\n const { padding } = this.options;\n return this.text.map((l) => ctx.measureText(l).width).reduce((w0, w1) => (w0 < w1 ? w1 : w0), 0) + (2 * padding);\n }\n\n measureHeight(): number {\n const { fontSize, padding } = this.options;\n return this.text.length * fontSize + (2 * padding);\n }\n\n getUpperLeft(ctx: CanvasRenderingContext2D, canvasDims?: IDimensions): IPoint {\n const { anchorPosition } = this.options;\n const isShiftLeft = anchorPosition === AnchorPosition.BOTTOM_RIGHT || anchorPosition === AnchorPosition.TOP_RIGHT;\n const isShiftTop = anchorPosition === AnchorPosition.BOTTOM_LEFT || anchorPosition === AnchorPosition.BOTTOM_RIGHT;\n\n const textFieldWidth = this.measureWidth(ctx);\n const textFieldHeight = this.measureHeight();\n const x = (isShiftLeft ? this.anchor.x - textFieldWidth : this.anchor.x);\n const y = isShiftTop ? this.anchor.y - textFieldHeight : this.anchor.y;\n\n // adjust anchor if text box exceeds canvas borders\n if (canvasDims) {\n const { width, height } = canvasDims;\n const newX = Math.max(Math.min(x, width - textFieldWidth), 0);\n const newY = Math.max(Math.min(y, height - textFieldHeight), 0);\n return { x: newX, y: newY };\n }\n return { x, y };\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const canvas = resolveInput(canvasArg);\n const ctx = getContext2dOrThrow(canvas);\n\n const {\n backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = this.options;\n\n ctx.font = `${fontSize}px ${fontStyle}`;\n const maxTextWidth = this.measureWidth(ctx);\n const textHeight = this.measureHeight();\n\n ctx.fillStyle = backgroundColor;\n const upperLeft = this.getUpperLeft(ctx, canvas);\n ctx.fillRect(upperLeft.x, upperLeft.y, maxTextWidth, textHeight);\n\n ctx.fillStyle = fontColor;\n this.text.forEach((textLine, i) => {\n const x = padding + upperLeft.x;\n const y = padding + upperLeft.y + ((i + 1) * fontSize);\n ctx.fillText(textLine, x, y);\n });\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { Box, IBoundingBox, IRect } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport {\n AnchorPosition, DrawTextField, DrawTextFieldOptions, IDrawTextFieldOptions,\n} from './DrawTextField';\n\nexport interface IDrawBoxOptions {\n boxColor?: string\n lineWidth?: number\n drawLabelOptions?: IDrawTextFieldOptions\n label?: string\n}\n\nexport class DrawBoxOptions {\n public boxColor: string\n\n public lineWidth: number\n\n public drawLabelOptions: DrawTextFieldOptions\n\n public label?: string\n\n constructor(options: IDrawBoxOptions = {}) {\n const {\n boxColor, lineWidth, label, drawLabelOptions,\n } = options;\n this.boxColor = boxColor || 'rgba(0, 0, 255, 1)';\n this.lineWidth = lineWidth || 2;\n this.label = label;\n\n const defaultDrawLabelOptions = {\n anchorPosition: AnchorPosition.BOTTOM_LEFT,\n backgroundColor: this.boxColor,\n };\n this.drawLabelOptions = new DrawTextFieldOptions({ ...defaultDrawLabelOptions, ...drawLabelOptions });\n }\n}\n\nexport class DrawBox {\n public box: Box\n\n public options: DrawBoxOptions\n\n constructor(\n box: IBoundingBox | IRect,\n options: IDrawBoxOptions = {},\n ) {\n this.box = new Box(box);\n this.options = new DrawBoxOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const { boxColor, lineWidth } = this.options;\n\n const {\n x, y, width, height,\n } = this.box;\n ctx.strokeStyle = boxColor;\n ctx.lineWidth = lineWidth;\n ctx.strokeRect(x, y, width, height);\n\n const { label } = this.options;\n if (label) {\n new DrawTextField([label], { x: x - (lineWidth / 2), y }, this.options.drawLabelOptions).draw(canvasArg);\n }\n }\n}\n", "import { Box, IBoundingBox, IRect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { round } from '../utils/index';\nimport { DrawBox } from './DrawBox';\n\nexport type TDrawDetectionsInput = IRect | IBoundingBox | FaceDetection | WithFaceDetection<{}>\n\nexport function drawDetections(\n canvasArg: string | HTMLCanvasElement,\n detections: TDrawDetectionsInput | Array,\n) {\n const detectionsArray = Array.isArray(detections) ? detections : [detections];\n\n detectionsArray.forEach((det) => {\n // eslint-disable-next-line no-nested-ternary\n const score = det instanceof FaceDetection\n ? det.score\n : (isWithFaceDetection(det) ? det.detection.score : undefined);\n\n // eslint-disable-next-line no-nested-ternary\n const box = det instanceof FaceDetection\n ? det.box\n : (isWithFaceDetection(det) ? det.detection.box : new Box(det));\n\n const label = score ? `${round(score)}` : undefined;\n new DrawBox(box, { label }).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { FaceExpressions } from './FaceExpressions';\n\nexport class FaceExpressionNet extends FaceProcessor {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceExpressionNet', faceFeatureExtractor);\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n return tf.tidy(() => tf.softmax(this.runNet(input)));\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictExpressions(input: TNetInput) {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n const probabilitesByBatch = await Promise.all(tf.unstack(out).map(async (t) => {\n const data = await t.data();\n t.dispose();\n return data;\n }));\n out.dispose();\n\n const predictionsByBatch = probabilitesByBatch\n .map((probabilites) => new FaceExpressions(probabilites as Float32Array));\n\n return netInput.isBatchInput\n ? predictionsByBatch\n : predictionsByBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_expression_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n\n protected getClassifierChannelsOut(): number {\n return 7;\n }\n}\n", "import { env } from '../env/index';\n\nexport function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {\n const { Image, Video } = env.getEnv();\n\n return (media instanceof Image && media.complete)\n || (media instanceof Video && media.readyState >= 3);\n}\n", "import { env } from '../env/index';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {\n // eslint-disable-next-line consistent-return\n return new Promise((resolve, reject) => {\n if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {\n return resolve(null);\n }\n\n function onError(e: Event) {\n if (!e.currentTarget) return;\n // eslint-disable-next-line no-use-before-define\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n reject(e);\n }\n\n function onLoad(e: Event) {\n if (!e.currentTarget) return;\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n resolve(e);\n }\n\n media.addEventListener('load', onLoad);\n media.addEventListener('error', onError);\n });\n}\n", "import { env } from '../env/index';\n\nexport function bufferToImage(buf: Blob): Promise {\n return new Promise((resolve, reject) => {\n if (!(buf instanceof Blob)) reject(new Error('bufferToImage - expected buf to be of type: Blob'));\n const reader = new FileReader();\n reader.onload = () => {\n if (typeof reader.result !== 'string') reject(new Error('bufferToImage - expected reader.result to be a string, in onload'));\n const img = env.getEnv().createImageElement();\n img.onload = () => resolve(img);\n img.onerror = reject;\n img.src = reader.result as string;\n };\n reader.onerror = reject;\n reader.readAsDataURL(buf);\n });\n}\n", "import { Dimensions, IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\n\nexport function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {\n const { Image, Video } = env.getEnv();\n\n if (input instanceof Image) {\n return new Dimensions(input.naturalWidth, input.naturalHeight);\n }\n if (input instanceof Video) {\n return new Dimensions(input.videoWidth, input.videoHeight);\n }\n return new Dimensions(input.width, input.height);\n}\n", "import { IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {\n const { createCanvasElement } = env.getEnv();\n const canvas = createCanvasElement();\n canvas.width = width;\n canvas.height = height;\n return canvas;\n}\n\nexport function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {\n const { ImageData } = env.getEnv();\n\n if (!(media instanceof ImageData) && !isMediaLoaded(media)) {\n throw new Error('createCanvasFromMedia - media has not finished loading yet');\n }\n\n const { width, height } = dims || getMediaDimensions(media);\n const canvas = createCanvas({ width, height });\n\n if (media instanceof ImageData) {\n getContext2dOrThrow(canvas).putImageData(media, 0, 0);\n } else {\n getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height);\n }\n return canvas;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { env } from '../env/index';\nimport { isTensor4D } from '../utils/index';\n\nexport async function imageTensorToCanvas(\n imgTensor: tf.Tensor,\n canvas?: HTMLCanvasElement,\n): Promise {\n const targetCanvas = canvas || env.getEnv().createCanvasElement();\n\n const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0);\n const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt());\n await tf.browser.toPixels(imgTensor3D, targetCanvas);\n\n imgTensor3D.dispose();\n\n return targetCanvas;\n}\n", "import { env } from '../env/index';\n\nexport function isMediaElement(input: any) {\n const { Image, Canvas, Video } = env.getEnv();\n\n return input instanceof Image\n || input instanceof Canvas\n || input instanceof Video;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Dimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { padToSquare } from '../ops/padToSquare';\nimport {\n computeReshapedDimensions, isTensor3D, isTensor4D, range,\n} from '../utils/index';\nimport { createCanvasFromMedia } from './createCanvas';\nimport { imageToSquare } from './imageToSquare';\nimport { TResolvedNetInput } from './types';\n\nexport class NetInput {\n private _imageTensors: Array = []\n\n private _canvases: HTMLCanvasElement[] = []\n\n private _batchSize: number\n\n private _treatAsBatchInput: boolean = false\n\n private _inputDimensions: number[][] = []\n\n private _inputSize: number\n\n constructor(\n inputs: Array,\n treatAsBatchInput: boolean = false,\n ) {\n if (!Array.isArray(inputs)) {\n throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`);\n }\n\n this._treatAsBatchInput = treatAsBatchInput;\n this._batchSize = inputs.length;\n\n inputs.forEach((input, idx) => {\n if (isTensor3D(input)) {\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = input.shape;\n return;\n }\n\n if (isTensor4D(input)) {\n const batchSize = (input as any).shape[0];\n if (batchSize !== 1) {\n throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = (input as any).shape.slice(1);\n return;\n }\n\n const canvas = (input as any) instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input);\n this._canvases[idx] = canvas;\n this._inputDimensions[idx] = [canvas.height, canvas.width, 3];\n });\n }\n\n public get imageTensors(): Array {\n return this._imageTensors;\n }\n\n public get canvases(): HTMLCanvasElement[] {\n return this._canvases;\n }\n\n public get isBatchInput(): boolean {\n return this.batchSize > 1 || this._treatAsBatchInput;\n }\n\n public get batchSize(): number {\n return this._batchSize;\n }\n\n public get inputDimensions(): number[][] {\n return this._inputDimensions;\n }\n\n public get inputSize(): number | undefined {\n return this._inputSize;\n }\n\n public get reshapedInputDimensions(): Dimensions[] {\n return range(this.batchSize, 0, 1).map(\n (_, batchIdx) => this.getReshapedInputDimensions(batchIdx),\n );\n }\n\n public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {\n return this.canvases[batchIdx] || this.imageTensors[batchIdx];\n }\n\n public getInputDimensions(batchIdx: number): number[] {\n return this._inputDimensions[batchIdx];\n }\n\n public getInputHeight(batchIdx: number): number {\n return this._inputDimensions[batchIdx][0];\n }\n\n public getInputWidth(batchIdx: number): number {\n return this._inputDimensions[batchIdx][1];\n }\n\n public getReshapedInputDimensions(batchIdx: number): Dimensions {\n if (typeof this.inputSize !== 'number') {\n throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet');\n }\n\n const width = this.getInputWidth(batchIdx);\n const height = this.getInputHeight(batchIdx);\n return computeReshapedDimensions({ width, height }, this.inputSize);\n }\n\n /**\n * Create a batch tensor from all input canvases and tensors\n * with size [batchSize, inputSize, inputSize, 3].\n *\n * @param inputSize Height and width of the tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The batch tensor.\n */\n public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {\n this._inputSize = inputSize;\n\n return tf.tidy(() => {\n const inputTensors = range(this.batchSize, 0, 1).map((batchIdx) => {\n const input = this.getInput(batchIdx);\n\n if (input instanceof tf.Tensor) {\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n let imgTensor = isTensor4D(input) ? input : input.expandDims();\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n imgTensor = padToSquare(imgTensor, isCenterInputs);\n\n if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {\n imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize]);\n }\n\n return imgTensor.as3D(inputSize, inputSize, 3);\n }\n\n if (input instanceof env.getEnv().Canvas) {\n return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs));\n }\n\n throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`);\n });\n\n // const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)\n const batchTensor = tf.stack(inputTensors.map((t) => tf.cast(t, 'float32'))).as4D(this.batchSize, inputSize, inputSize, 3);\n // const batchTensor = tf.stack(inputTensors.map(t => tf.Tensor.as4D(tf.cast(t, 'float32'))), this.batchSize, inputSize, inputSize, 3);\n\n return batchTensor;\n });\n }\n}\n", "import { env } from '../env/index';\nimport { createCanvas, createCanvasFromMedia } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {\n const { Image, Canvas } = env.getEnv();\n\n if (!(input instanceof Image || input instanceof Canvas)) {\n throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement');\n }\n\n const dims = getMediaDimensions(input);\n const scale = inputSize / Math.max(dims.height, dims.width);\n const width = scale * dims.width;\n const height = scale * dims.height;\n\n const targetCanvas = createCanvas({ width: inputSize, height: inputSize });\n const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input);\n\n const offset = Math.abs(width - height) / 2;\n const dx = centerImage && width < height ? offset : 0;\n const dy = centerImage && height < width ? offset : 0;\n getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height);\n\n return targetCanvas;\n}\n", "import { isTensor3D, isTensor4D } from '../utils/index';\nimport { awaitMediaLoaded } from './awaitMediaLoaded';\nimport { isMediaElement } from './isMediaElement';\nimport { NetInput } from './NetInput';\nimport { resolveInput } from './resolveInput';\nimport { TNetInput } from './types';\n\n/**\n * Validates the input to make sure, they are valid net inputs and awaits all media elements\n * to be finished loading.\n *\n * @param input The input, which can be a media element or an array of different media elements.\n * @returns A NetInput instance, which can be passed into one of the neural networks.\n */\nexport async function toNetInput(inputs: TNetInput): Promise {\n if (inputs instanceof NetInput) {\n return inputs;\n }\n\n const inputArgArray = Array.isArray(inputs)\n ? inputs\n : [inputs];\n\n if (!inputArgArray.length) {\n throw new Error('toNetInput - empty array passed as input');\n }\n\n const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');\n\n const inputArray = inputArgArray.map(resolveInput);\n\n inputArray.forEach((input, i) => {\n if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {\n if (typeof inputArgArray[i] === 'string') {\n throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);\n }\n\n throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);\n }\n\n if (isTensor4D(input)) {\n // if tf.Tensor4D is passed in the input array, the batch size has to be 1\n const batchSize = input.shape[0];\n if (batchSize !== 1) {\n throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n }\n });\n\n // wait for all media elements being loaded\n await Promise.all(\n inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),\n );\n\n return new NetInput(inputArray, Array.isArray(inputs));\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { Rect } from '../classes/Rect';\nimport { env } from '../env/index';\nimport { createCanvas } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { imageTensorToCanvas } from './imageTensorToCanvas';\nimport { toNetInput } from './toNetInput';\nimport { TNetInput } from './types';\n\n/**\n * Extracts the image regions containing the detected faces.\n *\n * @param input The image that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns The Canvases of the corresponding image region for each detected face.\n */\nexport async function extractFaces(\n input: TNetInput,\n detections: Array,\n): Promise {\n const { Canvas } = env.getEnv();\n\n let canvas = input as HTMLCanvasElement;\n\n if (!(input instanceof Canvas)) {\n const netInput = await toNetInput(input);\n\n if (netInput.batchSize > 1) {\n throw new Error('extractFaces - batchSize > 1 not supported');\n }\n\n const tensorOrCanvas = netInput.getInput(0);\n canvas = tensorOrCanvas instanceof Canvas\n ? tensorOrCanvas\n : await imageTensorToCanvas(tensorOrCanvas);\n }\n\n const ctx = getContext2dOrThrow(canvas);\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(canvas.width, canvas.height).box.floor()\n : det),\n )\n .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));\n\n return boxes.map(({\n x, y, width, height,\n }) => {\n const faceImg = createCanvas({ width, height });\n getContext2dOrThrow(faceImg)\n .putImageData(ctx.getImageData(x, y, width, height), 0, 0);\n return faceImg;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isTensor3D, isTensor4D } from '../utils/index';\n\n/**\n * Extracts the tensors of the image regions containing the detected faces.\n * Useful if you want to compute the face descriptors for the face images.\n * Using this method is faster then extracting a canvas for each face and\n * converting them to tensors individually.\n *\n * @param imageTensor The image tensor that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns Tensors of the corresponding image region for each detected face.\n */\nexport async function extractFaceTensors(\n imageTensor: tf.Tensor3D | tf.Tensor4D,\n detections: Array,\n): Promise {\n if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {\n throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D');\n }\n\n if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {\n throw new Error('extractFaceTensors - batchSize > 1 not supported');\n }\n\n return tf.tidy(() => {\n const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0);\n\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(imgWidth, imgHeight).box\n : det),\n )\n .map((box) => box.clipAtImageBorders(imgWidth, imgHeight));\n\n const faceTensors = boxes.map(({\n x, y, width, height,\n }) => tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels]));\n\n return faceTensors;\n });\n}\n", "import { env } from '../env/index';\n\nexport async function fetchOrThrow(\n url: string,\n // eslint-disable-next-line no-undef\n init?: RequestInit,\n): Promise {\n const { fetch } = env.getEnv();\n const res = await fetch(url, init);\n if (!(res.status < 400)) {\n throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`);\n }\n return res;\n}\n", "import { bufferToImage } from './bufferToImage';\nimport { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchImage(uri: string): Promise {\n const res = await fetchOrThrow(uri);\n const blob = await (res).blob();\n\n if (!blob.type.startsWith('image/')) {\n throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`);\n }\n return bufferToImage(blob);\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchJson(uri: string): Promise {\n return (await fetchOrThrow(uri)).json();\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchNetWeights(uri: string): Promise {\n return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer());\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { getModelUris } from '../common/getModelUris';\nimport { fetchJson } from './fetchJson';\n\nexport async function loadWeightMap(\n uri: string | undefined,\n defaultModelName: string,\n): Promise {\n const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName);\n const manifest = await fetchJson(manifestUri);\n // if (manifest['weightsManifest']) manifest = manifest['weightsManifest'];\n return tf.io.loadWeights(manifest, modelBaseUri);\n}\n", "export function getModelUris(uri: string | undefined, defaultModelName: string) {\n const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`;\n\n if (!uri) {\n return {\n modelBaseUri: '',\n manifestUri: defaultManifestFilename,\n };\n }\n\n if (uri === '/') {\n return {\n modelBaseUri: '/',\n manifestUri: `/${defaultManifestFilename}`,\n };\n }\n // eslint-disable-next-line no-nested-ternary\n const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';\n uri = uri.replace(protocol, '');\n\n const parts = uri.split('/').filter((s) => s);\n\n const manifestFile = uri.endsWith('.json')\n ? parts[parts.length - 1]\n : defaultManifestFilename;\n\n let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/');\n modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri;\n\n return {\n modelBaseUri,\n manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`,\n };\n}\n", "import { IDimensions } from '../classes/index';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {\n const { width, height } = useMediaDimensions\n ? getMediaDimensions(reference)\n : reference;\n input.width = width;\n input.height = height;\n return { width, height };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock4 } from './denseBlock';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';\n\nexport class FaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('FaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock4(normalized, params.dense0, true);\n out = denseBlock4(out, params.dense1);\n out = denseBlock4(out, params.dense2);\n out = denseBlock4(out, params.dense3);\n out = tf.avgPool(out, [7, 7], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../dist/tfjs.esm';\n\nimport { ParamMapping } from './common/index';\nimport { getModelUris } from './common/getModelUris';\nimport { loadWeightMap } from './dom/index';\nimport { env } from './env/index';\n\nexport abstract class NeuralNetwork {\n constructor(name: string) {\n this._name = name;\n }\n\n protected _params: TNetParams | undefined = undefined\n\n protected _paramMappings: ParamMapping[] = []\n\n public _name: any;\n\n public get params(): TNetParams | undefined { return this._params; }\n\n public get paramMappings(): ParamMapping[] { return this._paramMappings; }\n\n public get isLoaded(): boolean { return !!this.params; }\n\n public getParamFromPath(paramPath: string): tf.Tensor {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n return obj[objProp];\n }\n\n public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n obj[objProp].dispose();\n obj[objProp] = tensor;\n }\n\n public getParamList() {\n return this._paramMappings.map(({ paramPath }) => ({\n path: paramPath,\n tensor: this.getParamFromPath(paramPath),\n }));\n }\n\n public getTrainableParams() {\n return this.getParamList().filter((param) => param.tensor instanceof tf.Variable);\n }\n\n public getFrozenParams() {\n return this.getParamList().filter((param) => !(param.tensor instanceof tf.Variable));\n }\n\n public variable() {\n this.getFrozenParams().forEach(({ path, tensor }) => {\n this.reassignParamFromPath(path, tensor.variable());\n });\n }\n\n public freeze() {\n this.getTrainableParams().forEach(({ path, tensor: variable }) => {\n const tensor = tf.tensor(variable.dataSync());\n variable.dispose();\n this.reassignParamFromPath(path, tensor);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.getParamList().forEach((param) => {\n if (throwOnRedispose && param.tensor.isDisposed) {\n throw new Error(`param tensor has already been disposed for path ${param.path}`);\n }\n param.tensor.dispose();\n });\n this._params = undefined;\n }\n\n public serializeParams(): Float32Array {\n return new Float32Array(\n this.getParamList()\n .map(({ tensor }) => Array.from(tensor.dataSync()) as number[])\n .reduce((flat, arr) => flat.concat(arr)),\n );\n }\n\n public async load(weightsOrUrl: Float32Array | string | undefined): Promise {\n if (weightsOrUrl instanceof Float32Array) {\n this.extractWeights(weightsOrUrl);\n return;\n }\n await this.loadFromUri(weightsOrUrl);\n }\n\n public async loadFromUri(uri: string | undefined) {\n if (uri && typeof uri !== 'string') {\n throw new Error(`${this._name}.loadFromUri - expected model uri`);\n }\n const weightMap = await loadWeightMap(uri, this.getDefaultModelName());\n this.loadFromWeightMap(weightMap);\n }\n\n public async loadFromDisk(filePath: string | undefined) {\n if (filePath && typeof filePath !== 'string') {\n throw new Error(`${this._name}.loadFromDisk - expected model file path`);\n }\n const { readFile } = env.getEnv();\n const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName());\n const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(filePaths.map((fp) => readFile(fp).then((buf) => buf.buffer)));\n const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk);\n const manifest = JSON.parse((await readFile(manifestUri)).toString());\n const weightMap = await loadWeights(manifest, modelBaseUri);\n this.loadFromWeightMap(weightMap);\n }\n\n public loadFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { paramMappings, params } = this.extractParamsFromWeightMap(weightMap);\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n public extractWeights(weights: Float32Array) {\n const { paramMappings, params } = this.extractParams(weights);\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n private traversePropertyPath(paramPath: string) {\n if (!this.params) {\n throw new Error('traversePropertyPath - model has no loaded params');\n }\n\n const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {\n // eslint-disable-next-line no-prototype-builtins\n if (!res.nextObj.hasOwnProperty(objProp)) {\n throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`);\n }\n return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] };\n }, { nextObj: this.params });\n\n const { obj, objProp } = result;\n if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {\n throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`);\n }\n\n return { obj, objProp };\n }\n\n protected abstract getDefaultModelName(): string\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, SeparableConvParams } from '../common/index';\nimport { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function denseBlock3(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock3Params,\n isFirstLayer: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n });\n}\n\nexport function denseBlock4(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock4Params,\n isFirstLayer: boolean = false,\n isScaleDown: boolean = true,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from './types';\n\nexport function depthwiseSeparableConv(\n x: tf.Tensor4D,\n params: SeparableConvParams,\n stride: [number, number],\n): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same');\n out = tf.add(out, params.bias);\n return out;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\nexport function convLayer(\n x: tf.Tensor4D,\n params: ConvParams,\n padding: 'valid' | 'same' = 'same',\n withRelu: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out = tf.add(\n tf.conv2d(x, params.filters, [1, 1], padding),\n params.bias,\n ) as tf.Tensor4D;\n\n return withRelu ? tf.relu(out) : out;\n });\n}\n", "import { ParamMapping } from './types';\n\nexport function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {\n Object.keys(weightMap).forEach((path) => {\n if (!paramMappings.some((pm) => pm.originalPath === path)) {\n weightMap[path].dispose();\n }\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';\n\nexport function extractConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams => {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, FCParams, ParamMapping } from './types';\n\nexport function extractFCParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): FCParams => {\n const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);\n const fc_bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return {\n weights: fc_weights,\n bias: fc_bias,\n };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';\n\nexport function extractSeparableConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams => {\n const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1]);\n const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut]);\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/depthwise_filter` },\n { paramPath: `${mappedPrefix}/pointwise_filter` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n\nexport function loadSeparableConvParamsFactory(\n // eslint-disable-next-line no-unused-vars\n extractWeightEntry: (originalPath: string, paramRank: number) => T,\n) {\n return (prefix: string): SeparableConvParams => {\n const depthwise_filter = extractWeightEntry(`${prefix}/depthwise_filter`, 4);\n const pointwise_filter = extractWeightEntry(`${prefix}/pointwise_filter`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n// eslint-disable-next-line no-unused-vars\nexport type ExtractWeightsFunction = (numWeights: number) => Float32Array\n\nexport type ParamMapping = {\n originalPath?: string\n paramPath: string\n}\n\nexport type ConvParams = {\n filters: tf.Tensor4D\n bias: tf.Tensor1D\n}\n\nexport type FCParams = {\n weights: tf.Tensor2D\n bias: tf.Tensor1D\n}\n\nexport class SeparableConvParams {\n // eslint-disable-next-line no-useless-constructor\n constructor(\n // eslint-disable-next-line no-unused-vars\n public depthwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public pointwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public bias: tf.Tensor1D,\n // eslint-disable-next-line no-empty-function\n ) {}\n}\n", "import { isTensor } from '../utils/index';\nimport { ParamMapping } from './types';\n\nexport function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {\n return (originalPath: string, paramRank: number, mappedPath?: string) => {\n const tensor = weightMap[originalPath];\n\n if (!isTensor(tensor, paramRank)) {\n throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`);\n }\n\n paramMappings.push(\n { originalPath, paramPath: mappedPath || originalPath },\n );\n\n return tensor;\n };\n}\n", "export function extractWeightsFactory(weights: Float32Array) {\n let remainingWeights = weights;\n\n function extractWeights(numWeights: number): Float32Array {\n const ret = remainingWeights.slice(0, numWeights);\n remainingWeights = remainingWeights.slice(numWeights);\n return ret;\n }\n\n function getRemainingWeights(): Float32Array {\n return remainingWeights;\n }\n\n return {\n extractWeights,\n getRemainingWeights,\n };\n}\n", "import {\n extractConvParamsFactory,\n extractSeparableConvParamsFactory,\n ExtractWeightsFunction,\n ParamMapping,\n} from '../common/index';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)\n : extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`);\n const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`);\n const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer);\n const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock4Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock4Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock4Params(64, 128, 'dense2');\n const dense3 = extractDenseBlock4Params(128, 256, 'dense3');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: {\n dense0, dense1, dense2, dense3,\n },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\n// eslint-disable-next-line no-unused-vars\nexport function loadConvParamsFactory(extractWeightEntry: (originalPath: string, paramRank: number) => T) {\n return (prefix: string): ConvParams => {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return { filters, bias };\n };\n}\n", "import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n const conv3 = extractSeparableConvParams(`${prefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock4Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock4Params('dense0', true),\n dense1: extractDenseBlock4Params('dense1'),\n dense2: extractDenseBlock4Params('dense2'),\n dense3: extractDenseBlock4Params('dense3'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { NetInput } from '../dom/index';\nimport {\n FaceFeatureExtractorParams,\n IFaceFeatureExtractor,\n TinyFaceFeatureExtractorParams,\n} from '../faceFeatureExtractor/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { NetParams } from './types';\nimport { seperateWeightMaps } from './util';\n\nexport abstract class FaceProcessor<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends NeuralNetwork {\n protected _faceFeatureExtractor: IFaceFeatureExtractor\n\n constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor) {\n super(_name);\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): IFaceFeatureExtractor {\n return this._faceFeatureExtractor;\n }\n\n protected abstract getDefaultModelName(): string\n\n protected abstract getClassifierChannelsIn(): number\n\n protected abstract getClassifierChannelsOut(): number\n\n public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut());\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const cIn = this.getClassifierChannelsIn();\n const cOut = this.getClassifierChannelsOut();\n const classifierWeightSize = (cOut * cIn) + cOut;\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from './types';\n\nexport function fullyConnectedLayer(\n x: tf.Tensor2D,\n params: FCParams,\n): tf.Tensor2D {\n return tf.tidy(() => tf.add(\n tf.matMul(x, params.weights),\n params.bias,\n ));\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const fc = extractFCParams(channelsIn, channelsOut, 'fc');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: extractFcParams('fc'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function seperateWeightMaps(weightMap: tf.NamedTensorMap) {\n const featureExtractorMap: tf.NamedTensorMap = {};\n const classifierMap: tf.NamedTensorMap = {};\n\n Object.keys(weightMap).forEach((key) => {\n const map = key.startsWith('fc') ? classifierMap : featureExtractorMap;\n map[key] = weightMap[key];\n });\n\n return { featureExtractorMap, classifierMap };\n}\n", "export const FACE_EXPRESSION_LABELS = ['neutral', 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised'];\n\nexport class FaceExpressions {\n public neutral: number\n\n public happy: number\n\n public sad: number\n\n public angry: number\n\n public fearful: number\n\n public disgusted: number\n\n public surprised: number\n\n constructor(probabilities: number[] | Float32Array) {\n if (probabilities.length !== 7) {\n throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${probabilities.length}`);\n }\n\n FACE_EXPRESSION_LABELS.forEach((expression, idx) => {\n this[expression] = probabilities[idx];\n });\n }\n\n asSortedArray() {\n return FACE_EXPRESSION_LABELS\n .map((expression) => ({ expression, probability: this[expression] as number }))\n .sort((e0, e1) => e1.probability - e0.probability);\n }\n}\n", "import { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\n\nexport type WithFaceExpressions = TSource & {\n expressions: FaceExpressions\n}\n\nexport function isWithFaceExpressions(obj: any): obj is WithFaceExpressions<{}> {\n return obj.expressions instanceof FaceExpressions;\n}\n\nexport function extendWithFaceExpressions<\n TSource\n>(\n sourceObj: TSource,\n expressions: FaceExpressions,\n): WithFaceExpressions {\n const extension = { expressions };\n return { ...sourceObj, ...extension };\n}\n", "import { IPoint, Point } from '../classes/index';\nimport { FaceExpressions } from '../faceExpressionNet/index';\nimport { isWithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { round } from '../utils/index';\nimport { DrawTextField } from './DrawTextField';\n\nexport type DrawFaceExpressionsInput = FaceExpressions | WithFaceExpressions<{}>\n\nexport function drawFaceExpressions(\n canvasArg: string | HTMLCanvasElement,\n faceExpressions: DrawFaceExpressionsInput | Array,\n minConfidence = 0.1,\n textFieldAnchor?: IPoint,\n) {\n const faceExpressionsArray = Array.isArray(faceExpressions) ? faceExpressions : [faceExpressions];\n\n faceExpressionsArray.forEach((e) => {\n // eslint-disable-next-line no-nested-ternary\n const expr = e instanceof FaceExpressions\n ? e\n : (isWithFaceExpressions(e) ? e.expressions : undefined);\n if (!expr) {\n throw new Error('drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof');\n }\n\n const sorted = expr.asSortedArray();\n const resultsToDisplay = sorted.filter((exprLocal) => exprLocal.probability > minConfidence);\n\n const anchor = isWithFaceDetection(e)\n ? e.detection.box.bottomLeft\n : (textFieldAnchor || new Point(0, 0));\n\n const drawTextField = new DrawTextField(\n resultsToDisplay.map((exprLocal) => `${exprLocal.expression} (${round(exprLocal.probability)})`),\n anchor,\n );\n drawTextField.draw(canvasArg);\n });\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { isWithFaceDetection, WithFaceDetection } from './WithFaceDetection';\n\nexport type WithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 > = TSource & {\n landmarks: TFaceLandmarks\n unshiftedLandmarks: TFaceLandmarks\n alignedRect: FaceDetection\n }\n\nexport function isWithFaceLandmarks(obj: any): obj is WithFaceLandmarks, FaceLandmarks> {\n return isWithFaceDetection(obj)\n // eslint-disable-next-line dot-notation\n && obj['landmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['unshiftedLandmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['alignedRect'] instanceof FaceDetection;\n}\n\nexport function extendWithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 >(sourceObj: TSource, unshiftedLandmarks: TFaceLandmarks): WithFaceLandmarks {\n const { box: shift } = sourceObj.detection;\n const landmarks = unshiftedLandmarks.shiftBy(shift.x, shift.y);\n\n const rect = landmarks.align();\n const { imageDims } = sourceObj.detection;\n const alignedRect = new FaceDetection(sourceObj.detection.score, rect.rescale(imageDims.reverse()), imageDims);\n\n const extension = {\n landmarks,\n unshiftedLandmarks,\n alignedRect,\n };\n\n return { ...sourceObj, ...extension };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IPoint } from '../classes/index';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { drawContour } from './drawContour';\n\nexport interface IDrawFaceLandmarksOptions {\n drawLines?: boolean\n drawPoints?: boolean\n lineWidth?: number\n pointSize?: number\n lineColor?: string\n pointColor?: string\n}\n\nexport class DrawFaceLandmarksOptions {\n public drawLines: boolean\n\n public drawPoints: boolean\n\n public lineWidth: number\n\n public pointSize: number\n\n public lineColor: string\n\n public pointColor: string\n\n constructor(options: IDrawFaceLandmarksOptions = {}) {\n const {\n drawLines = true, drawPoints = true, lineWidth, lineColor, pointSize, pointColor,\n } = options;\n this.drawLines = drawLines;\n this.drawPoints = drawPoints;\n this.lineWidth = lineWidth || 1;\n this.pointSize = pointSize || 2;\n this.lineColor = lineColor || 'rgba(0, 255, 255, 1)';\n this.pointColor = pointColor || 'rgba(255, 0, 255, 1)';\n }\n}\n\nexport class DrawFaceLandmarks {\n public faceLandmarks: FaceLandmarks\n\n public options: DrawFaceLandmarksOptions\n\n constructor(\n faceLandmarks: FaceLandmarks,\n options: IDrawFaceLandmarksOptions = {},\n ) {\n this.faceLandmarks = faceLandmarks;\n this.options = new DrawFaceLandmarksOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const {\n drawLines, drawPoints, lineWidth, lineColor, pointSize, pointColor,\n } = this.options;\n\n if (drawLines && this.faceLandmarks instanceof FaceLandmarks68) {\n ctx.strokeStyle = lineColor;\n ctx.lineWidth = lineWidth;\n drawContour(ctx, this.faceLandmarks.getJawOutline());\n drawContour(ctx, this.faceLandmarks.getLeftEyeBrow());\n drawContour(ctx, this.faceLandmarks.getRightEyeBrow());\n drawContour(ctx, this.faceLandmarks.getNose());\n drawContour(ctx, this.faceLandmarks.getLeftEye(), true);\n drawContour(ctx, this.faceLandmarks.getRightEye(), true);\n drawContour(ctx, this.faceLandmarks.getMouth(), true);\n }\n\n if (drawPoints) {\n ctx.strokeStyle = pointColor;\n ctx.fillStyle = pointColor;\n\n const drawPoint = (pt: IPoint) => {\n ctx.beginPath();\n ctx.arc(pt.x, pt.y, pointSize, 0, 2 * Math.PI);\n ctx.fill();\n };\n this.faceLandmarks.positions.forEach(drawPoint);\n }\n }\n}\n\nexport type DrawFaceLandmarksInput = FaceLandmarks | WithFaceLandmarks>\n\nexport function drawFaceLandmarks(\n canvasArg: string | HTMLCanvasElement,\n faceLandmarks: DrawFaceLandmarksInput | Array,\n) {\n const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];\n faceLandmarksArray.forEach((f) => {\n // eslint-disable-next-line no-nested-ternary\n const landmarks = f instanceof FaceLandmarks\n ? f\n : (isWithFaceLandmarks(f) ? f.landmarks : undefined);\n if (!landmarks) {\n throw new Error('drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof');\n }\n\n new DrawFaceLandmarks(landmarks).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { seperateWeightMaps } from '../faceProcessor/util';\nimport { TinyXception } from '../xception/TinyXception';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport {\n AgeAndGenderPrediction, Gender, NetOutput, NetParams,\n} from './types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\n\nexport class AgeGenderNet extends NeuralNetwork {\n private _faceFeatureExtractor: TinyXception\n\n constructor(faceFeatureExtractor: TinyXception = new TinyXception(2)) {\n super('AgeGenderNet');\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): TinyXception {\n return this._faceFeatureExtractor;\n }\n\n public runNet(input: NetInput | tf.Tensor4D): NetOutput {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n\n const pooled = tf.avgPool(bottleneckFeatures, [7, 7], [2, 2], 'valid').as2D(bottleneckFeatures.shape[0], -1);\n const age = fullyConnectedLayer(pooled, params.fc.age).as1D();\n const gender = fullyConnectedLayer(pooled, params.fc.gender);\n return { age, gender };\n });\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): NetOutput {\n return tf.tidy(() => {\n const { age, gender } = this.runNet(input);\n return { age, gender: tf.softmax(gender) };\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictAgeAndGender(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n\n const ages = tf.unstack(out.age);\n const genders = tf.unstack(out.gender);\n const ageAndGenderTensors = ages.map((ageTensor, i) => ({\n ageTensor,\n genderTensor: genders[i],\n }));\n\n const predictionsByBatch = await Promise.all(\n ageAndGenderTensors.map(async ({ ageTensor, genderTensor }) => {\n const age = (await ageTensor.data())[0];\n const probMale = (await genderTensor.data())[0];\n const isMale = probMale > 0.5;\n const gender = isMale ? Gender.MALE : Gender.FEMALE;\n const genderProbability = isMale ? probMale : (1 - probMale);\n\n ageTensor.dispose();\n genderTensor.dispose();\n return { age, gender, genderProbability };\n }),\n );\n out.age.dispose();\n out.gender.dispose();\n\n return netInput.isBatchInput ? predictionsByBatch as AgeAndGenderPrediction[] : predictionsByBatch[0] as AgeAndGenderPrediction;\n }\n\n protected getDefaultModelName(): string {\n return 'age_gender_model';\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights);\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const classifierWeightSize = (512 * 1 + 1) + (512 * 2 + 2);\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, depthwiseSeparableConv } from '../common/index';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { range } from '../utils/index';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction conv(x: tf.Tensor4D, params: ConvParams, stride: [number, number]): tf.Tensor4D {\n return tf.add(tf.conv2d(x, params.filters, stride, 'same'), params.bias);\n}\n\nfunction reductionBlock(x: tf.Tensor4D, params: ReductionBlockParams, isActivateInput: boolean = true): tf.Tensor4D {\n let out = isActivateInput ? tf.relu(x) : x;\n out = depthwiseSeparableConv(out, params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = tf.maxPool(out, [3, 3], [2, 2], 'same');\n out = tf.add(out, conv(x, params.expansion_conv, [2, 2]));\n return out;\n}\n\nfunction mainBlock(x: tf.Tensor4D, params: MainBlockParams): tf.Tensor4D {\n let out = depthwiseSeparableConv(tf.relu(x), params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv2, [1, 1]);\n out = tf.add(out, x);\n return out;\n}\n\nexport class TinyXception extends NeuralNetwork {\n private _numMainBlocks: number\n\n constructor(numMainBlocks: number) {\n super('TinyXception');\n this._numMainBlocks = numMainBlocks;\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n if (!params) {\n throw new Error('TinyXception - load model before inference');\n }\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n let out = tf.relu(conv(normalized, params.entry_flow.conv_in, [2, 2]));\n out = reductionBlock(out, params.entry_flow.reduction_block_0, false);\n out = reductionBlock(out, params.entry_flow.reduction_block_1);\n range(this._numMainBlocks, 0, 1).forEach((idx) => {\n out = mainBlock(out, params.middle_flow[`main_block_${idx}`]);\n });\n out = reductionBlock(out, params.exit_flow.reduction_block);\n out = tf.relu(depthwiseSeparableConv(out, params.exit_flow.separable_conv, [1, 1]));\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_xception_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this._numMainBlocks);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights, this._numMainBlocks);\n }\n}\n", "import { extractConvParamsFactory, extractSeparableConvParamsFactory, extractWeightsFactory } from '../common/index';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractReductionBlockParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(channels: number, mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParams(weights: Float32Array, numMainBlocks: number): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const entry_flow_conv_in = extractConvParams(3, 32, 3, 'entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams(32, 64, 'entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams(64, 128, 'entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(128, `middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams(128, 256, 'exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams(256, 512, 'exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { entry_flow, middle_flow, exit_flow },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors,\n extractWeightEntryFactory,\n loadSeparableConvParamsFactory,\n ParamMapping,\n} from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractReductionBlockParams(mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(`${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(`${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n numMainBlocks: number,\n): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const entry_flow_conv_in = extractConvParams('entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams('entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams('entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(`middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams('exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams('exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params: { entry_flow, middle_flow, exit_flow }, paramMappings };\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const age = extractFCParams(512, 1, 'fc/age');\n const gender = extractFCParams(512, 2, 'fc/gender');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc: { age, gender } },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: {\n age: extractFcParams('fc/age'),\n gender: extractFcParams('fc/gender'),\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from '../common/index';\n\n// eslint-disable-next-line no-shadow\nexport enum Gender {\n // eslint-disable-next-line no-unused-vars\n FEMALE = 'female',\n // eslint-disable-next-line no-unused-vars\n MALE = 'male'\n}\n\nexport type AgeAndGenderPrediction = {\n age: number\n gender: Gender\n genderProbability: number\n}\n\nexport type NetOutput = { age: tf.Tensor1D, gender: tf.Tensor2D }\n\nexport type NetParams = {\n fc: {\n age: FCParams\n gender: FCParams\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { IDimensions, Point } from '../classes/index';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { isEven } from '../utils/index';\n\nexport abstract class FaceLandmark68NetBase<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends FaceProcessor {\n public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {\n const inputDimensions = originalDimensions.map(({ width, height }) => {\n const scale = inputSize / Math.max(height, width);\n return {\n width: width * scale,\n height: height * scale,\n };\n });\n\n const batchSize = inputDimensions.length;\n\n return tf.tidy(() => {\n const createInterleavedTensor = (fillX: number, fillY: number) => tf.stack([tf.fill([68], fillX, 'float32'), tf.fill([68], fillY, 'float32')], 1).as2D(1, 136).as1D();\n\n // eslint-disable-next-line no-unused-vars\n const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {\n const { width, height } = inputDimensions[batchIdx];\n return cond(width, height) ? Math.abs(width - height) / 2 : 0;\n };\n\n const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h);\n const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w);\n\n const landmarkTensors = output\n .mul(tf.fill([batchSize, 136], inputSize, 'float32'))\n .sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n getPaddingX(batchIdx),\n getPaddingY(batchIdx),\n ))))\n .div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n inputDimensions[batchIdx].width,\n inputDimensions[batchIdx].height,\n ))));\n\n return landmarkTensors as tf.Tensor2D;\n });\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n return tf.tidy(() => {\n const out = this.runNet(input);\n return this.postProcess(\n out,\n input.inputSize as number,\n input.inputDimensions.map(([height, width]) => ({ height, width })),\n );\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async detectLandmarks(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const landmarkTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const landmarksForBatch = await Promise.all(landmarkTensors.map(\n async (landmarkTensor, batchIdx) => {\n const landmarksArray = Array.from(await landmarkTensor.data());\n const xCoords = landmarksArray.filter((_, i) => isEven(i));\n const yCoords = landmarksArray.filter((_, i) => !isEven(i));\n\n return new FaceLandmarks68(\n Array(68).fill(0).map((_, i) => new Point(xCoords[i] as number, yCoords[i] as number)),\n {\n height: netInput.getInputHeight(batchIdx),\n width: netInput.getInputWidth(batchIdx),\n },\n );\n },\n ));\n\n landmarkTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput ? landmarksForBatch as FaceLandmarks68[] : landmarksForBatch[0] as FaceLandmarks68;\n }\n\n protected getClassifierChannelsOut(): number {\n return 136;\n }\n}\n", "import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68Net extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceLandmark68Net', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock3 } from './denseBlock';\nimport { extractParamsFromWeightMapTiny } from './extractParamsFromWeightMapTiny';\nimport { extractParamsTiny } from './extractParamsTiny';\nimport { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';\n\nexport class TinyFaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('TinyFaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyFaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock3(normalized, params.dense0, true);\n out = denseBlock3(out, params.dense1);\n out = denseBlock3(out, params.dense2);\n out = tf.avgPool(out, [14, 14], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_tiny_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMapTiny(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParamsTiny(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMapTiny(\n weightMap: tf.NamedTensorMap,\n): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock3Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock3Params('dense0', true),\n dense1: extractDenseBlock3Params('dense1'),\n dense2: extractDenseBlock3Params('dense2'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock3Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock3Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock3Params(64, 128, 'dense2');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { dense0, dense1, dense2 },\n };\n}\n", "import { TinyFaceFeatureExtractor } from '../faceFeatureExtractor/TinyFaceFeatureExtractor';\nimport { TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68TinyNet extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: TinyFaceFeatureExtractor = new TinyFaceFeatureExtractor()) {\n super('FaceLandmark68TinyNet', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_tiny_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 128;\n }\n}\n", "import { FaceLandmark68Net } from './FaceLandmark68Net';\n\nexport * from './FaceLandmark68Net';\nexport * from './FaceLandmark68TinyNet';\nexport class FaceLandmarkNet extends FaceLandmark68Net {}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { convDown } from './convLayer';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { residual, residualDown } from './residualLayer';\nimport { NetParams } from './types';\n\nexport class FaceRecognitionNet extends NeuralNetwork {\n constructor() {\n super('FaceRecognitionNet');\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceRecognitionNet - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(150, true), 'float32');\n\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = convDown(normalized, params.conv32_down);\n out = tf.maxPool(out, 3, 2, 'valid');\n\n out = residual(out, params.conv32_1);\n out = residual(out, params.conv32_2);\n out = residual(out, params.conv32_3);\n\n out = residualDown(out, params.conv64_down);\n out = residual(out, params.conv64_1);\n out = residual(out, params.conv64_2);\n out = residual(out, params.conv64_3);\n\n out = residualDown(out, params.conv128_down);\n out = residual(out, params.conv128_1);\n out = residual(out, params.conv128_2);\n\n out = residualDown(out, params.conv256_down);\n out = residual(out, params.conv256_1);\n out = residual(out, params.conv256_2);\n out = residualDown(out, params.conv256_down_out);\n\n const globalAvg = out.mean([1, 2]) as tf.Tensor2D;\n const fullyConnected = tf.matMul(globalAvg, params.fc);\n\n return fullyConnected;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async computeFaceDescriptor(input: TNetInput): Promise {\n if (input?.shape?.some((dim) => dim <= 0)) return new Float32Array(128);\n const netInput = await toNetInput(input);\n const faceDescriptorTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map((t) => t.data())) as Float32Array[];\n faceDescriptorTensors.forEach((t) => t.dispose());\n return netInput.isBatchInput ? faceDescriptorsForBatch : faceDescriptorsForBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_recognition_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { scale } from './scaleLayer';\nimport { ConvLayerParams } from './types';\n\nfunction convLayer(\n x: tf.Tensor4D,\n params: ConvLayerParams,\n strides: [number, number],\n withRelu: boolean,\n padding: 'valid' | 'same' = 'same',\n): tf.Tensor4D {\n const { filters, bias } = params.conv;\n\n let out = tf.conv2d(x, filters, strides, padding);\n out = tf.add(out, bias);\n out = scale(out, params.scale);\n return withRelu ? tf.relu(out) : out;\n}\n\nexport function conv(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], true);\n}\n\nexport function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], false);\n}\n\nexport function convDown(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [2, 2], true, 'valid');\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ScaleLayerParams } from './types';\n\nexport function scale(x: tf.Tensor4D, params: ScaleLayerParams): tf.Tensor4D {\n return tf.add(tf.mul(x, params.weights), params.biases);\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping,\n} from '../common/index';\nimport { isFloat } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {\n const weights = extractWeights(numFilterValues);\n const depth = weights.length / (numFilters * filterSize * filterSize);\n\n if (isFloat(depth)) {\n throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`);\n }\n\n return tf.tidy(\n () => tf.transpose(\n tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),\n [2, 3, 1, 0],\n ),\n );\n }\n\n function extractConvParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams {\n const filters = extractFilterValues(numFilterValues, numFilters, filterSize);\n const bias = tf.tensor1d(extractWeights(numFilters));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n }\n\n function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {\n const weights = tf.tensor1d(extractWeights(numWeights));\n const biases = tf.tensor1d(extractWeights(numWeights));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/biases` },\n );\n\n return {\n weights,\n biases,\n };\n }\n\n function extractConvLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvLayerParams {\n const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`);\n const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`);\n\n return { conv, scale };\n }\n\n function extractResidualLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n isDown: boolean = false,\n ): ResidualLayerParams {\n const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`);\n const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`);\n\n return { conv1, conv2 };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down');\n const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1');\n const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2');\n const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3');\n\n const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true);\n const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1');\n const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2');\n const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3');\n\n const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true);\n const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1');\n const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2');\n\n const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true);\n const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1');\n const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2');\n const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out');\n\n const fc = tf.tidy(\n () => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0]),\n );\n paramMappings.push({ paramPath: 'fc' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common/index';\nimport { isTensor2D } from '../utils/index';\nimport { ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractScaleLayerParams(prefix: string): ScaleLayerParams {\n const weights = extractWeightEntry(`${prefix}/scale/weights`, 1);\n const biases = extractWeightEntry(`${prefix}/scale/biases`, 1);\n\n return { weights, biases };\n }\n\n function extractConvLayerParams(prefix: string): ConvLayerParams {\n const filters = extractWeightEntry(`${prefix}/conv/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/conv/bias`, 1);\n const scale = extractScaleLayerParams(prefix);\n\n return { conv: { filters, bias }, scale };\n }\n\n function extractResidualLayerParams(prefix: string): ResidualLayerParams {\n return {\n conv1: extractConvLayerParams(`${prefix}/conv1`),\n conv2: extractConvLayerParams(`${prefix}/conv2`),\n };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const conv32_down = extractConvLayerParams('conv32_down');\n const conv32_1 = extractResidualLayerParams('conv32_1');\n const conv32_2 = extractResidualLayerParams('conv32_2');\n const conv32_3 = extractResidualLayerParams('conv32_3');\n\n const conv64_down = extractResidualLayerParams('conv64_down');\n const conv64_1 = extractResidualLayerParams('conv64_1');\n const conv64_2 = extractResidualLayerParams('conv64_2');\n const conv64_3 = extractResidualLayerParams('conv64_3');\n\n const conv128_down = extractResidualLayerParams('conv128_down');\n const conv128_1 = extractResidualLayerParams('conv128_1');\n const conv128_2 = extractResidualLayerParams('conv128_2');\n\n const conv256_down = extractResidualLayerParams('conv256_down');\n const conv256_1 = extractResidualLayerParams('conv256_1');\n const conv256_2 = extractResidualLayerParams('conv256_2');\n const conv256_down_out = extractResidualLayerParams('conv256_down_out');\n\n const { fc } = weightMap;\n paramMappings.push({ originalPath: 'fc', paramPath: 'fc' });\n\n if (!isTensor2D(fc)) {\n throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { conv, convDown, convNoRelu } from './convLayer';\nimport { ResidualLayerParams } from './types';\n\nexport function residual(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = conv(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n out = tf.add(out, x);\n out = tf.relu(out);\n return out;\n}\n\nexport function residualDown(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = convDown(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n\n let pooled = tf.avgPool(x, 2, 2, 'valid') as tf.Tensor4D;\n const zeros = tf.zeros(pooled.shape);\n const isPad = pooled.shape[3] !== out.shape[3];\n const isAdjustShape = pooled.shape[1] !== out.shape[1] || pooled.shape[2] !== out.shape[2];\n\n if (isAdjustShape) {\n const padShapeX = [...out.shape] as [number, number, number, number];\n padShapeX[1] = 1;\n const zerosW = tf.zeros(padShapeX);\n out = tf.concat([out, zerosW], 1);\n\n const padShapeY = [...out.shape] as [number, number, number, number];\n padShapeY[2] = 1;\n const zerosH = tf.zeros(padShapeY);\n out = tf.concat([out, zerosH], 2);\n }\n\n pooled = isPad ? tf.concat([pooled, zeros], 3) : pooled;\n out = tf.add(pooled, out) as tf.Tensor4D;\n\n out = tf.relu(out);\n return out;\n}\n", "import { FaceRecognitionNet } from './FaceRecognitionNet';\n\nexport * from './FaceRecognitionNet';\n\nexport function createFaceRecognitionNet(weights: Float32Array) {\n const net = new FaceRecognitionNet();\n net.extractWeights(weights);\n return net;\n}\n", "export type WithFaceDescriptor = TSource & {\n descriptor: Float32Array\n}\n\nexport function extendWithFaceDescriptor<\n TSource\n>(\n sourceObj: TSource,\n descriptor: Float32Array,\n): WithFaceDescriptor {\n const extension = { descriptor };\n return { ...sourceObj, ...extension };\n}\n", "export type WithAge = TSource & {\n age: number\n}\n\nexport function isWithAge(obj: any): obj is WithAge<{}> {\n return typeof obj.age === 'number';\n}\n\nexport function extendWithAge<\n TSource\n>(\n sourceObj: TSource,\n age: number,\n): WithAge {\n const extension = { age };\n return { ...sourceObj, ...extension };\n}\n", "import { Gender } from '../ageGenderNet/types';\nimport { isValidProbablitiy } from '../utils/index';\n\nexport type WithGender = TSource & {\n gender: Gender\n genderProbability: number\n}\n\nexport function isWithGender(obj: any): obj is WithGender<{}> {\n return (obj.gender === Gender.MALE || obj.gender === Gender.FEMALE)\n && isValidProbablitiy(obj.genderProbability);\n}\n\nexport function extendWithGender<\n TSource\n>(\n sourceObj: TSource,\n gender: Gender,\n genderProbability: number,\n): WithGender {\n const extension = { gender, genderProbability };\n return { ...sourceObj, ...extension };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { mobileNetV1 } from './mobileNetV1';\nimport { nonMaxSuppression } from './nonMaxSuppression';\nimport { outputLayer } from './outputLayer';\nimport { predictionLayer } from './predictionLayer';\nimport { ISsdMobilenetv1Options, SsdMobilenetv1Options } from './SsdMobilenetv1Options';\nimport { NetParams } from './types';\n\nexport class SsdMobilenetv1 extends NeuralNetwork {\n constructor() {\n super('SsdMobilenetv1');\n }\n\n public forwardInput(input: NetInput) {\n const { params } = this;\n\n if (!params) {\n throw new Error('SsdMobilenetv1 - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(512, false), 'float32');\n const x = tf.sub(tf.mul(batchTensor, tf.scalar(0.007843137718737125)), tf.scalar(1)) as tf.Tensor4D;\n const features = mobileNetV1(x, params.mobilenetv1);\n\n const {\n boxPredictions,\n classPredictions,\n } = predictionLayer(features.out, features.conv11, params.prediction_layer);\n\n return outputLayer(boxPredictions, classPredictions, params.output_layer);\n });\n }\n\n public async forward(input: TNetInput) {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async locateFaces(\n input: TNetInput,\n options: ISsdMobilenetv1Options = {},\n ): Promise {\n const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);\n\n const netInput = await toNetInput(input);\n\n const {\n boxes: _boxes,\n scores: _scores,\n } = this.forwardInput(netInput);\n\n const boxes = _boxes[0];\n const scores = _scores[0];\n for (let i = 1; i < _boxes.length; i++) {\n _boxes[i].dispose();\n _scores[i].dispose();\n }\n\n const scoresData = Array.from(await scores.data());\n const iouThreshold = 0.5;\n const indices = nonMaxSuppression(\n boxes,\n scoresData as number[],\n maxResults,\n iouThreshold,\n minConfidence,\n );\n\n const reshapedDims = netInput.getReshapedInputDimensions(0);\n const inputSize = netInput.inputSize as number;\n const padX = inputSize / reshapedDims.width;\n const padY = inputSize / reshapedDims.height;\n\n const boxesData = boxes.arraySync();\n const results = indices\n .map((idx) => {\n const [top, bottom] = [\n Math.max(0, boxesData[idx][0]),\n Math.min(1.0, boxesData[idx][2]),\n ].map((val) => val * padY);\n const [left, right] = [\n Math.max(0, boxesData[idx][1]),\n Math.min(1.0, boxesData[idx][3]),\n ].map((val) => val * padX);\n return new FaceDetection(\n scoresData[idx] as number,\n new Rect(\n left,\n top,\n right - left,\n bottom - top,\n ),\n {\n height: netInput.getInputHeight(0),\n width: netInput.getInputWidth(0),\n },\n );\n });\n\n boxes.dispose();\n scores.dispose();\n return results;\n }\n\n protected getDefaultModelName(): string {\n return 'ssd_mobilenetv1_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ExtractWeightsFunction, ParamMapping, ConvParams, extractWeightsFactory,\n} from '../common/index';\nimport {\n MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractDepthwiseConvParams(numChannels: number, mappedPrefix: string): MobileNetV1.DepthwiseConvParams {\n const filters = tf.tensor4d(extractWeights(3 * 3 * numChannels), [3, 3, numChannels, 1]);\n const batch_norm_scale = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_offset = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_mean = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_variance = tf.tensor1d(extractWeights(numChannels));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/batch_norm_scale` },\n { paramPath: `${mappedPrefix}/batch_norm_offset` },\n { paramPath: `${mappedPrefix}/batch_norm_mean` },\n { paramPath: `${mappedPrefix}/batch_norm_variance` },\n );\n\n return {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n };\n }\n\n function extractConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n isPointwiseConv?: boolean,\n ): ConvParams {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/${isPointwiseConv ? 'batch_norm_offset' : 'bias'}` },\n );\n\n return { filters, bias };\n }\n\n function extractPointwiseConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): PointwiseConvParams {\n const {\n filters,\n bias,\n } = extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix, true);\n\n return {\n filters,\n batch_norm_offset: bias,\n };\n }\n\n function extractConvPairParams(\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): MobileNetV1.ConvPairParams {\n const depthwise_conv = extractDepthwiseConvParams(channelsIn, `${mappedPrefix}/depthwise_conv`);\n const pointwise_conv = extractPointwiseConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/pointwise_conv`);\n\n return { depthwise_conv, pointwise_conv };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n const conv_0 = extractPointwiseConvParams(3, 32, 3, 'mobilenetv1/conv_0');\n const conv_1 = extractConvPairParams(32, 64, 'mobilenetv1/conv_1');\n const conv_2 = extractConvPairParams(64, 128, 'mobilenetv1/conv_2');\n const conv_3 = extractConvPairParams(128, 128, 'mobilenetv1/conv_3');\n const conv_4 = extractConvPairParams(128, 256, 'mobilenetv1/conv_4');\n const conv_5 = extractConvPairParams(256, 256, 'mobilenetv1/conv_5');\n const conv_6 = extractConvPairParams(256, 512, 'mobilenetv1/conv_6');\n const conv_7 = extractConvPairParams(512, 512, 'mobilenetv1/conv_7');\n const conv_8 = extractConvPairParams(512, 512, 'mobilenetv1/conv_8');\n const conv_9 = extractConvPairParams(512, 512, 'mobilenetv1/conv_9');\n const conv_10 = extractConvPairParams(512, 512, 'mobilenetv1/conv_10');\n const conv_11 = extractConvPairParams(512, 512, 'mobilenetv1/conv_11');\n const conv_12 = extractConvPairParams(512, 1024, 'mobilenetv1/conv_12');\n const conv_13 = extractConvPairParams(1024, 1024, 'mobilenetv1/conv_13');\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n conv_8,\n conv_9,\n conv_10,\n conv_11,\n conv_12,\n conv_13,\n };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n const conv_0 = extractPointwiseConvParams(1024, 256, 1, 'prediction_layer/conv_0');\n const conv_1 = extractPointwiseConvParams(256, 512, 3, 'prediction_layer/conv_1');\n const conv_2 = extractPointwiseConvParams(512, 128, 1, 'prediction_layer/conv_2');\n const conv_3 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_3');\n const conv_4 = extractPointwiseConvParams(256, 128, 1, 'prediction_layer/conv_4');\n const conv_5 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_5');\n const conv_6 = extractPointwiseConvParams(256, 64, 1, 'prediction_layer/conv_6');\n const conv_7 = extractPointwiseConvParams(64, 128, 3, 'prediction_layer/conv_7');\n const box_encoding_0_predictor = extractConvParams(512, 12, 1, 'prediction_layer/box_predictor_0/box_encoding_predictor');\n const class_predictor_0 = extractConvParams(512, 9, 1, 'prediction_layer/box_predictor_0/class_predictor');\n const box_encoding_1_predictor = extractConvParams(1024, 24, 1, 'prediction_layer/box_predictor_1/box_encoding_predictor');\n const class_predictor_1 = extractConvParams(1024, 18, 1, 'prediction_layer/box_predictor_1/class_predictor');\n const box_encoding_2_predictor = extractConvParams(512, 24, 1, 'prediction_layer/box_predictor_2/box_encoding_predictor');\n const class_predictor_2 = extractConvParams(512, 18, 1, 'prediction_layer/box_predictor_2/class_predictor');\n const box_encoding_3_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_3/box_encoding_predictor');\n const class_predictor_3 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_3/class_predictor');\n const box_encoding_4_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_4/box_encoding_predictor');\n const class_predictor_4 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_4/class_predictor');\n const box_encoding_5_predictor = extractConvParams(128, 24, 1, 'prediction_layer/box_predictor_5/box_encoding_predictor');\n const class_predictor_5 = extractConvParams(128, 18, 1, 'prediction_layer/box_predictor_5/class_predictor');\n\n const box_predictor_0 = {\n box_encoding_predictor: box_encoding_0_predictor,\n class_predictor: class_predictor_0,\n };\n const box_predictor_1 = {\n box_encoding_predictor: box_encoding_1_predictor,\n class_predictor: class_predictor_1,\n };\n const box_predictor_2 = {\n box_encoding_predictor: box_encoding_2_predictor,\n class_predictor: class_predictor_2,\n };\n const box_predictor_3 = {\n box_encoding_predictor: box_encoding_3_predictor,\n class_predictor: class_predictor_3,\n };\n const box_predictor_4 = {\n box_encoding_predictor: box_encoding_4_predictor,\n class_predictor: class_predictor_4,\n };\n const box_predictor_5 = {\n box_encoding_predictor: box_encoding_5_predictor,\n class_predictor: class_predictor_5,\n };\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n box_predictor_0,\n box_predictor_1,\n box_predictor_2,\n box_predictor_3,\n box_predictor_4,\n box_predictor_5,\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n const mobilenetv1 = extractMobilenetV1Params();\n const prediction_layer = extractPredictionLayerParams();\n const extra_dim = tf.tensor3d(\n extractWeights(5118 * 4),\n [1, 5118, 4],\n );\n const output_layer = {\n extra_dim,\n };\n paramMappings.push({ paramPath: 'output_layer/extra_dim' });\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n params: {\n mobilenetv1,\n prediction_layer,\n output_layer,\n },\n paramMappings,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping,\n} from '../common/index';\nimport { isTensor3D } from '../utils/index';\nimport {\n BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractPointwiseConvParams(prefix: string, idx: number, mappedPrefix: string): PointwiseConvParams {\n const filters = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/weights`, 4, `${mappedPrefix}/filters`);\n const batch_norm_offset = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/convolution_bn_offset`, 1, `${mappedPrefix}/batch_norm_offset`);\n return { filters, batch_norm_offset };\n }\n\n function extractConvPairParams(idx: number): MobileNetV1.ConvPairParams {\n const mappedPrefix = `mobilenetv1/conv_${idx}`;\n const prefixDepthwiseConv = `MobilenetV1/Conv2d_${idx}_depthwise`;\n const mappedPrefixDepthwiseConv = `${mappedPrefix}/depthwise_conv`;\n const mappedPrefixPointwiseConv = `${mappedPrefix}/pointwise_conv`;\n\n const filters = extractWeightEntry(`${prefixDepthwiseConv}/depthwise_weights`, 4, `${mappedPrefixDepthwiseConv}/filters`);\n const batch_norm_scale = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/gamma`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_scale`);\n const batch_norm_offset = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/beta`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_offset`);\n const batch_norm_mean = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_mean`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_mean`);\n const batch_norm_variance = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_variance`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_variance`);\n\n return {\n depthwise_conv: {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n },\n pointwise_conv: extractPointwiseConvParams('MobilenetV1', idx, mappedPrefixPointwiseConv),\n };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n return {\n conv_0: extractPointwiseConvParams('MobilenetV1', 0, 'mobilenetv1/conv_0'),\n conv_1: extractConvPairParams(1),\n conv_2: extractConvPairParams(2),\n conv_3: extractConvPairParams(3),\n conv_4: extractConvPairParams(4),\n conv_5: extractConvPairParams(5),\n conv_6: extractConvPairParams(6),\n conv_7: extractConvPairParams(7),\n conv_8: extractConvPairParams(8),\n conv_9: extractConvPairParams(9),\n conv_10: extractConvPairParams(10),\n conv_11: extractConvPairParams(11),\n conv_12: extractConvPairParams(12),\n conv_13: extractConvPairParams(13),\n };\n }\n\n function extractConvParams(prefix: string, mappedPrefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/weights`, 4, `${mappedPrefix}/filters`);\n const bias = extractWeightEntry(`${prefix}/biases`, 1, `${mappedPrefix}/bias`);\n return { filters, bias };\n }\n\n function extractBoxPredictorParams(idx: number): BoxPredictionParams {\n const box_encoding_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/BoxEncodingPredictor`,\n `prediction_layer/box_predictor_${idx}/box_encoding_predictor`,\n );\n const class_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/ClassPredictor`,\n `prediction_layer/box_predictor_${idx}/class_predictor`,\n );\n return { box_encoding_predictor, class_predictor };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n return {\n conv_0: extractPointwiseConvParams('Prediction', 0, 'prediction_layer/conv_0'),\n conv_1: extractPointwiseConvParams('Prediction', 1, 'prediction_layer/conv_1'),\n conv_2: extractPointwiseConvParams('Prediction', 2, 'prediction_layer/conv_2'),\n conv_3: extractPointwiseConvParams('Prediction', 3, 'prediction_layer/conv_3'),\n conv_4: extractPointwiseConvParams('Prediction', 4, 'prediction_layer/conv_4'),\n conv_5: extractPointwiseConvParams('Prediction', 5, 'prediction_layer/conv_5'),\n conv_6: extractPointwiseConvParams('Prediction', 6, 'prediction_layer/conv_6'),\n conv_7: extractPointwiseConvParams('Prediction', 7, 'prediction_layer/conv_7'),\n box_predictor_0: extractBoxPredictorParams(0),\n box_predictor_1: extractBoxPredictorParams(1),\n box_predictor_2: extractBoxPredictorParams(2),\n box_predictor_3: extractBoxPredictorParams(3),\n box_predictor_4: extractBoxPredictorParams(4),\n box_predictor_5: extractBoxPredictorParams(5),\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n const extra_dim = weightMap['Output/extra_dim'];\n paramMappings.push({ originalPath: 'Output/extra_dim', paramPath: 'output_layer/extra_dim' });\n if (!isTensor3D(extra_dim)) {\n throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${extra_dim}`);\n }\n\n const params = {\n mobilenetv1: extractMobilenetV1Params(),\n prediction_layer: extractPredictionLayerParams(),\n output_layer: {\n extra_dim,\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { MobileNetV1 } from './types';\n\nconst epsilon = 0.0010000000474974513;\n\nfunction depthwiseConvLayer(\n x: tf.Tensor4D,\n params: MobileNetV1.DepthwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.depthwiseConv2d(x, params.filters, strides, 'same');\n out = tf.batchNorm(\n out,\n params.batch_norm_mean,\n params.batch_norm_variance,\n params.batch_norm_offset,\n params.batch_norm_scale,\n epsilon,\n );\n return tf.clipByValue(out, 0, 6);\n });\n}\n\nfunction getStridesForLayerIdx(layerIdx: number): [number, number] {\n return [2, 4, 6, 12].some((idx) => idx === layerIdx) ? [2, 2] : [1, 1];\n}\n\nexport function mobileNetV1(x: tf.Tensor4D, params: MobileNetV1.Params) {\n return tf.tidy(() => {\n let conv11;\n let out = pointwiseConvLayer(x, params.conv_0, [2, 2]);\n\n const convPairParams = [\n params.conv_1,\n params.conv_2,\n params.conv_3,\n params.conv_4,\n params.conv_5,\n params.conv_6,\n params.conv_7,\n params.conv_8,\n params.conv_9,\n params.conv_10,\n params.conv_11,\n params.conv_12,\n params.conv_13,\n ];\n\n convPairParams.forEach((param, i) => {\n const layerIdx = i + 1;\n const depthwiseConvStrides = getStridesForLayerIdx(layerIdx);\n out = depthwiseConvLayer(out, param.depthwise_conv, depthwiseConvStrides);\n out = pointwiseConvLayer(out, param.pointwise_conv, [1, 1]);\n if (layerIdx === 11) {\n conv11 = out;\n }\n });\n\n if (conv11 === null) {\n throw new Error('mobileNetV1 - output of conv layer 11 is null');\n }\n\n return {\n out,\n conv11: conv11 as any,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { PointwiseConvParams } from './types';\n\nexport function pointwiseConvLayer(\n x: tf.Tensor4D,\n params: PointwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.conv2d(x, params.filters, strides, 'same');\n out = tf.add(out, params.batch_norm_offset);\n return tf.clipByValue(out, 0, 6);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nfunction IOU(boxes: tf.Tensor2D, i: number, j: number) {\n const boxesData = boxes.arraySync();\n const yminI = Math.min(boxesData[i][0], boxesData[i][2]);\n const xminI = Math.min(boxesData[i][1], boxesData[i][3]);\n const ymaxI = Math.max(boxesData[i][0], boxesData[i][2]);\n const xmaxI = Math.max(boxesData[i][1], boxesData[i][3]);\n const yminJ = Math.min(boxesData[j][0], boxesData[j][2]);\n const xminJ = Math.min(boxesData[j][1], boxesData[j][3]);\n const ymaxJ = Math.max(boxesData[j][0], boxesData[j][2]);\n const xmaxJ = Math.max(boxesData[j][1], boxesData[j][3]);\n const areaI = (ymaxI - yminI) * (xmaxI - xminI);\n const areaJ = (ymaxJ - yminJ) * (xmaxJ - xminJ);\n if (areaI <= 0 || areaJ <= 0) {\n return 0.0;\n }\n const intersectionYmin = Math.max(yminI, yminJ);\n const intersectionXmin = Math.max(xminI, xminJ);\n const intersectionYmax = Math.min(ymaxI, ymaxJ);\n const intersectionXmax = Math.min(xmaxI, xmaxJ);\n const intersectionArea = Math.max(intersectionYmax - intersectionYmin, 0.0)\n * Math.max(intersectionXmax - intersectionXmin, 0.0);\n return intersectionArea / (areaI + areaJ - intersectionArea);\n}\n\nexport function nonMaxSuppression(\n boxes: tf.Tensor2D,\n scores: number[],\n maxOutputSize: number,\n iouThreshold: number,\n scoreThreshold: number,\n): number[] {\n const numBoxes = boxes.shape[0];\n const outputSize = Math.min(\n maxOutputSize,\n numBoxes,\n );\n\n const candidates = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .filter((c) => c.score > scoreThreshold)\n .sort((c1, c2) => c2.score - c1.score);\n\n const suppressFunc = (x: number) => (x <= iouThreshold ? 1 : 0);\n const selected: number[] = [];\n\n candidates.forEach((c) => {\n if (selected.length >= outputSize) return;\n const originalScore = c.score;\n for (let j = selected.length - 1; j >= 0; --j) {\n const iou = IOU(boxes, c.boxIndex, selected[j]);\n if (iou === 0.0) continue;\n c.score *= suppressFunc(iou);\n if (c.score <= scoreThreshold) break;\n }\n if (originalScore === c.score) {\n selected.push(c.boxIndex);\n }\n });\n return selected;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { OutputLayerParams } from './types';\n\nfunction getCenterCoordinatesAndSizesLayer(x: tf.Tensor2D) {\n const vec = tf.unstack(tf.transpose(x, [1, 0]));\n\n const sizes = [\n tf.sub(vec[2], vec[0]),\n tf.sub(vec[3], vec[1]),\n ];\n const centers = [\n tf.add(vec[0], tf.div(sizes[0], tf.scalar(2))),\n tf.add(vec[1], tf.div(sizes[1], tf.scalar(2))),\n ];\n return {\n sizes,\n centers,\n };\n}\n\nfunction decodeBoxesLayer(x0: tf.Tensor2D, x1: tf.Tensor2D) {\n const {\n sizes,\n centers,\n } = getCenterCoordinatesAndSizesLayer(x0);\n\n const vec = tf.unstack(tf.transpose(x1, [1, 0]));\n const div0_out = tf.div(tf.mul(tf.exp(tf.div(vec[2], tf.scalar(5))), sizes[0]), tf.scalar(2));\n const add0_out = tf.add(tf.mul(tf.div(vec[0], tf.scalar(10)), sizes[0]), centers[0]);\n const div1_out = tf.div(tf.mul(tf.exp(tf.div(vec[3], tf.scalar(5))), sizes[1]), tf.scalar(2));\n const add1_out = tf.add(tf.mul(tf.div(vec[1], tf.scalar(10)), sizes[1]), centers[1]);\n\n return tf.transpose(\n tf.stack([\n tf.sub(add0_out, div0_out),\n tf.sub(add1_out, div1_out),\n tf.add(add0_out, div0_out),\n tf.add(add1_out, div1_out),\n ]),\n [1, 0],\n );\n}\n\nexport function outputLayer(\n boxPredictions: tf.Tensor4D,\n classPredictions: tf.Tensor4D,\n params: OutputLayerParams,\n) {\n return tf.tidy(() => {\n const batchSize = boxPredictions.shape[0];\n\n let boxes = decodeBoxesLayer(\n tf.reshape(tf.tile(params.extra_dim, [batchSize, 1, 1]), [-1, 4]) as tf.Tensor2D,\n tf.reshape(boxPredictions, [-1, 4]) as tf.Tensor2D,\n );\n boxes = tf.reshape(\n boxes,\n [batchSize, (boxes.shape[0] / batchSize), 4],\n );\n\n const scoresAndClasses = tf.sigmoid(tf.slice(classPredictions, [0, 0, 1], [-1, -1, -1]));\n let scores = tf.slice(scoresAndClasses, [0, 0, 0], [-1, -1, 1]) as tf.Tensor;\n\n scores = tf.reshape(\n scores,\n [batchSize, scores.shape[1] as number],\n );\n\n const boxesByBatch = tf.unstack(boxes) as tf.Tensor2D[];\n const scoresByBatch = tf.unstack(scores) as tf.Tensor1D[];\n\n return {\n boxes: boxesByBatch,\n scores: scoresByBatch,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { boxPredictionLayer } from './boxPredictionLayer';\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { PredictionLayerParams } from './types';\n\nexport function predictionLayer(\n x: tf.Tensor4D,\n conv11: tf.Tensor4D,\n params: PredictionLayerParams,\n) {\n return tf.tidy(() => {\n const conv0 = pointwiseConvLayer(x, params.conv_0, [1, 1]);\n const conv1 = pointwiseConvLayer(conv0, params.conv_1, [2, 2]);\n const conv2 = pointwiseConvLayer(conv1, params.conv_2, [1, 1]);\n const conv3 = pointwiseConvLayer(conv2, params.conv_3, [2, 2]);\n const conv4 = pointwiseConvLayer(conv3, params.conv_4, [1, 1]);\n const conv5 = pointwiseConvLayer(conv4, params.conv_5, [2, 2]);\n const conv6 = pointwiseConvLayer(conv5, params.conv_6, [1, 1]);\n const conv7 = pointwiseConvLayer(conv6, params.conv_7, [2, 2]);\n\n const boxPrediction0 = boxPredictionLayer(conv11, params.box_predictor_0);\n const boxPrediction1 = boxPredictionLayer(x, params.box_predictor_1);\n const boxPrediction2 = boxPredictionLayer(conv1, params.box_predictor_2);\n const boxPrediction3 = boxPredictionLayer(conv3, params.box_predictor_3);\n const boxPrediction4 = boxPredictionLayer(conv5, params.box_predictor_4);\n const boxPrediction5 = boxPredictionLayer(conv7, params.box_predictor_5);\n\n const boxPredictions = tf.concat([\n boxPrediction0.boxPredictionEncoding,\n boxPrediction1.boxPredictionEncoding,\n boxPrediction2.boxPredictionEncoding,\n boxPrediction3.boxPredictionEncoding,\n boxPrediction4.boxPredictionEncoding,\n boxPrediction5.boxPredictionEncoding,\n ], 1) as tf.Tensor4D;\n\n const classPredictions = tf.concat([\n boxPrediction0.classPrediction,\n boxPrediction1.classPrediction,\n boxPrediction2.classPrediction,\n boxPrediction3.classPrediction,\n boxPrediction4.classPrediction,\n boxPrediction5.classPrediction,\n ], 1) as tf.Tensor4D;\n\n return {\n boxPredictions,\n classPredictions,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { convLayer } from '../common/index';\nimport { BoxPredictionParams } from './types';\n\nexport function boxPredictionLayer(\n x: tf.Tensor4D,\n params: BoxPredictionParams,\n) {\n return tf.tidy(() => {\n const batchSize = x.shape[0];\n const boxPredictionEncoding = tf.reshape(\n convLayer(x, params.box_encoding_predictor),\n [batchSize, -1, 1, 4],\n );\n const classPrediction = tf.reshape(\n convLayer(x, params.class_predictor),\n [batchSize, -1, 3],\n );\n return { boxPredictionEncoding, classPrediction };\n });\n}\n", "export interface ISsdMobilenetv1Options {\n minConfidence?: number\n maxResults?: number\n}\n\nexport class SsdMobilenetv1Options {\n protected _name: string = 'SsdMobilenetv1Options'\n\n private _minConfidence: number\n\n private _maxResults: number\n\n constructor({ minConfidence, maxResults }: ISsdMobilenetv1Options = {}) {\n this._minConfidence = minConfidence || 0.5;\n this._maxResults = maxResults || 100;\n\n if (typeof this._minConfidence !== 'number' || this._minConfidence <= 0 || this._minConfidence >= 1) {\n throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);\n }\n\n if (typeof this._maxResults !== 'number') {\n throw new Error(`${this._name} - expected maxResults to be a number`);\n }\n }\n\n get minConfidence(): number { return this._minConfidence; }\n\n get maxResults(): number { return this._maxResults; }\n}\n", "import { SsdMobilenetv1 } from './SsdMobilenetv1';\n\nexport * from './SsdMobilenetv1';\nexport * from './SsdMobilenetv1Options';\n\nexport function createSsdMobilenetv1(weights: Float32Array) {\n const net = new SsdMobilenetv1();\n net.extractWeights(weights);\n return net;\n}\n\nexport function createFaceDetectionNet(weights: Float32Array) {\n return createSsdMobilenetv1(weights);\n}\n\n// alias for backward compatibily\nexport class FaceDetectionNet extends SsdMobilenetv1 {}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(0.738768, 0.874946),\n new Point(2.42204, 2.65704),\n new Point(4.30971, 7.04493),\n new Point(10.246, 4.59428),\n new Point(12.6868, 11.8741),\n];\n\nexport const BOX_ANCHORS_SEPARABLE = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB_SEPARABLE: [number, number, number] = [117.001, 114.697, 97.404];\n\nexport const DEFAULT_MODEL_NAME = 'tiny_yolov2_model';\nexport const DEFAULT_MODEL_NAME_SEPARABLE_CONV = 'tiny_yolov2_separable_conv_model';\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { BoundingBox } from '../classes/BoundingBox';\nimport { Dimensions } from '../classes/Dimensions';\nimport { ObjectDetection } from '../classes/ObjectDetection';\nimport { convLayer } from '../common/index';\nimport { ConvParams, SeparableConvParams } from '../common/types';\nimport { toNetInput } from '../dom/index';\nimport { NetInput } from '../dom/NetInput';\nimport { TNetInput } from '../dom/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { sigmoid } from '../ops/index';\nimport { nonMaxSuppression } from '../ops/nonMaxSuppression';\nimport { normalize } from '../ops/normalize';\nimport { TinyYolov2Config, validateConfig } from './config';\nimport { convWithBatchNorm } from './convWithBatchNorm';\nimport { depthwiseSeparableConv } from './depthwiseSeparableConv';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { leaky } from './leaky';\nimport { ITinyYolov2Options, TinyYolov2Options } from './TinyYolov2Options';\nimport { DefaultTinyYolov2NetParams, MobilenetParams, TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2Base extends NeuralNetwork {\n public static DEFAULT_FILTER_SIZES = [3, 16, 32, 64, 128, 256, 512, 1024, 1024];\n\n private _config: TinyYolov2Config\n\n constructor(config: TinyYolov2Config) {\n super('TinyYolov2');\n validateConfig(config);\n this._config = config;\n }\n\n public get config(): TinyYolov2Config {\n return this._config;\n }\n\n public get withClassScores(): boolean {\n return this.config.withClassScores || this.config.classes.length > 1;\n }\n\n public get boxEncodingSize(): number {\n return 5 + (this.withClassScores ? this.config.classes.length : 0);\n }\n\n public runTinyYolov2(x: tf.Tensor4D, params: DefaultTinyYolov2NetParams): tf.Tensor4D {\n let out = convWithBatchNorm(x, params.conv0);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = convWithBatchNorm(out, params.conv6);\n out = convWithBatchNorm(out, params.conv7);\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public runMobilenet(x: tf.Tensor4D, params: MobilenetParams): tf.Tensor4D {\n let out = this.config.isFirstLayerConv2d\n ? leaky(convLayer(x, params.conv0 as ConvParams, 'valid', false))\n : depthwiseSeparableConv(x, params.conv0 as SeparableConvParams);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = params.conv6 ? depthwiseSeparableConv(out, params.conv6) : out;\n out = params.conv7 ? depthwiseSeparableConv(out, params.conv7) : out;\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public forwardInput(input: NetInput, inputSize: number): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyYolov2 - load model before inference');\n }\n\n return tf.tidy(() => {\n let batchTensor = tf.cast(input.toBatchTensor(inputSize, false), 'float32');\n batchTensor = this.config.meanRgb\n ? normalize(batchTensor, this.config.meanRgb)\n : batchTensor;\n batchTensor = batchTensor.div(tf.scalar(256)) as tf.Tensor4D;\n return this.config.withSeparableConvs\n ? this.runMobilenet(batchTensor, params as MobilenetParams)\n : this.runTinyYolov2(batchTensor, params as DefaultTinyYolov2NetParams);\n });\n }\n\n public async forward(input: TNetInput, inputSize: number): Promise {\n return this.forwardInput(await toNetInput(input), inputSize);\n }\n\n public async detect(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise {\n const { inputSize, scoreThreshold } = new TinyYolov2Options(forwardParams);\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput, inputSize);\n const out0 = tf.tidy(() => tf.unstack(out)[0].expandDims()) as tf.Tensor4D;\n const inputDimensions = {\n width: netInput.getInputWidth(0),\n height: netInput.getInputHeight(0),\n };\n\n const results = await this.extractBoxes(out0, netInput.getReshapedInputDimensions(0), scoreThreshold);\n out.dispose();\n out0.dispose();\n\n const boxes = results.map((res) => res.box);\n const scores = results.map((res) => res.score);\n const classScores = results.map((res) => res.classScore);\n const classNames = results.map((res) => this.config.classes[res.label]);\n\n const indices = nonMaxSuppression(\n boxes.map((box) => box.rescale(inputSize)),\n scores,\n this.config.iouThreshold,\n true,\n );\n\n const detections = indices.map((idx) => new ObjectDetection(\n scores[idx],\n classScores[idx],\n classNames[idx],\n boxes[idx],\n inputDimensions,\n ));\n return detections;\n }\n\n protected getDefaultModelName(): string {\n return '';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this.config);\n }\n\n protected extractParams(weights: Float32Array) {\n const filterSizes = this.config.filterSizes || TinyYolov2Base.DEFAULT_FILTER_SIZES;\n\n const numFilters = filterSizes ? filterSizes.length : undefined;\n if (numFilters !== 7 && numFilters !== 8 && numFilters !== 9) {\n throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${numFilters} filterSizes in config`);\n }\n return extractParams(weights, this.config, this.boxEncodingSize, filterSizes);\n }\n\n protected async extractBoxes(\n outputTensor: tf.Tensor4D,\n inputBlobDimensions: Dimensions,\n scoreThreshold?: number,\n ) {\n const { width, height } = inputBlobDimensions;\n const inputSize = Math.max(width, height);\n const correctionFactorX = inputSize / width;\n const correctionFactorY = inputSize / height;\n\n const numCells = outputTensor.shape[1];\n const numBoxes = this.config.anchors.length;\n\n const [boxesTensor, scoresTensor, classScoresTensor] = tf.tidy(() => {\n const reshaped = outputTensor.reshape([numCells, numCells, numBoxes, this.boxEncodingSize]);\n\n const boxes = reshaped.slice([0, 0, 0, 0], [numCells, numCells, numBoxes, 4]);\n const scores = reshaped.slice([0, 0, 0, 4], [numCells, numCells, numBoxes, 1]);\n const classScores = this.withClassScores\n ? tf.softmax(reshaped.slice([0, 0, 0, 5], [numCells, numCells, numBoxes, this.config.classes.length]), 3)\n : tf.scalar(0);\n return [boxes, scores, classScores];\n });\n\n const results = [] as any;\n const scoresData = await scoresTensor.array();\n const boxesData = await boxesTensor.array();\n for (let row = 0; row < numCells; row++) {\n for (let col = 0; col < numCells; col++) {\n for (let anchor = 0; anchor < numBoxes; anchor++) {\n const score = sigmoid(scoresData[row][col][anchor][0]);\n if (!scoreThreshold || score > scoreThreshold) {\n const ctX = ((col + sigmoid(boxesData[row][col][anchor][0])) / numCells) * correctionFactorX;\n const ctY = ((row + sigmoid(boxesData[row][col][anchor][1])) / numCells) * correctionFactorY;\n const widthLocal = ((Math.exp(boxesData[row][col][anchor][2]) * this.config.anchors[anchor].x) / numCells) * correctionFactorX;\n const heightLocal = ((Math.exp(boxesData[row][col][anchor][3]) * this.config.anchors[anchor].y) / numCells) * correctionFactorY;\n const x = (ctX - (widthLocal / 2));\n const y = (ctY - (heightLocal / 2));\n const pos = { row, col, anchor };\n const { classScore, label } = this.withClassScores\n ? await this.extractPredictedClass(classScoresTensor as tf.Tensor4D, pos)\n : { classScore: 1, label: 0 };\n results.push({\n box: new BoundingBox(x, y, x + widthLocal, y + heightLocal),\n score,\n classScore: score * classScore,\n label,\n ...pos,\n });\n }\n }\n }\n }\n\n boxesTensor.dispose();\n scoresTensor.dispose();\n classScoresTensor.dispose();\n return results;\n }\n\n private async extractPredictedClass(classesTensor: tf.Tensor4D, pos: { row: number, col: number, anchor: number }) {\n const { row, col, anchor } = pos;\n const classesData = await classesTensor.array();\n return Array(this.config.classes.length).fill(0)\n .map((_, i) => classesData[row][col][anchor][i])\n .map((classScore, label) => ({\n classScore,\n label,\n }))\n .reduce((max, curr) => (max.classScore > curr.classScore ? max : curr));\n }\n}\n", "import { Point } from '../classes/Point';\n\nexport type TinyYolov2Config = {\n withSeparableConvs: boolean\n iouThreshold: number\n anchors: Point[]\n classes: string[]\n meanRgb?: [number, number, number]\n withClassScores?: boolean,\n filterSizes?: number[]\n isFirstLayerConv2d?: boolean\n}\n\nconst isNumber = (arg: any) => typeof arg === 'number';\n\nexport function validateConfig(config: any) {\n if (!config) {\n throw new Error(`invalid config: ${config}`);\n }\n\n if (typeof config.withSeparableConvs !== 'boolean') {\n throw new Error(`config.withSeparableConvs has to be a boolean, have: ${config.withSeparableConvs}`);\n }\n\n if (!isNumber(config.iouThreshold) || config.iouThreshold < 0 || config.iouThreshold > 1.0) {\n throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${config.iouThreshold}`);\n }\n\n if (\n !Array.isArray(config.classes)\n || !config.classes.length\n || !config.classes.every((c: any) => typeof c === 'string')\n ) {\n throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(config.classes)}`);\n }\n\n if (\n !Array.isArray(config.anchors)\n || !config.anchors.length\n || !config.anchors.map((a: any) => a || {}).every((a: any) => isNumber(a.x) && isNumber(a.y))\n ) {\n throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(config.anchors)}`);\n }\n\n if (config.meanRgb && (\n !Array.isArray(config.meanRgb)\n || config.meanRgb.length !== 3\n || !config.meanRgb.every(isNumber)\n )) {\n throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(config.meanRgb)}`);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { leaky } from './leaky';\nimport { ConvWithBatchNorm } from './types';\n\nexport function convWithBatchNorm(x: tf.Tensor4D, params: ConvWithBatchNorm): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n out = tf.conv2d(out, params.conv.filters, [1, 1], 'valid');\n out = tf.sub(out, params.bn.sub);\n out = tf.mul(out, params.bn.truediv);\n out = tf.add(out, params.conv.bias);\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function leaky(x: tf.Tensor4D): tf.Tensor4D {\n return tf.tidy(() => {\n const min = tf.mul(x, tf.scalar(0.10000000149011612));\n return tf.add(tf.relu(tf.sub(x, min)), min);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from '../common/types';\nimport { leaky } from './leaky';\n\nexport function depthwiseSeparableConv(x: tf.Tensor4D, params: SeparableConvParams): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n out = tf.separableConv2d(out, params.depthwise_filter, params.pointwise_filter, [1, 1], 'valid');\n out = tf.add(out, params.bias);\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { extractConvParamsFactory } from '../common/index';\nimport { extractSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightsFactory } from '../common/extractWeightsFactory';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n\n function extractBatchNormParams(size: number, mappedPrefix: string): BatchNorm {\n const sub = tf.tensor1d(extractWeights(size));\n const truediv = tf.tensor1d(extractWeights(size));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/sub` },\n { paramPath: `${mappedPrefix}/truediv` },\n );\n return { sub, truediv };\n }\n\n function extractConvWithBatchNormParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv`);\n const bn = extractBatchNormParams(channelsOut, `${mappedPrefix}/bn`);\n return { conv, bn };\n }\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParams(\n weights: Float32Array,\n config: TinyYolov2Config,\n boxEncodingSize: number,\n filterSizes: number[],\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(extractWeights, paramMappings);\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = config.isFirstLayerConv2d\n ? extractConvParams(s0, s1, 3, 'conv0')\n : extractSeparableConvParams(s0, s1, 'conv0');\n const conv1 = extractSeparableConvParams(s1, s2, 'conv1');\n const conv2 = extractSeparableConvParams(s2, s3, 'conv2');\n const conv3 = extractSeparableConvParams(s3, s4, 'conv3');\n const conv4 = extractSeparableConvParams(s4, s5, 'conv4');\n const conv5 = extractSeparableConvParams(s5, s6, 'conv5');\n const conv6 = s7 ? extractSeparableConvParams(s6, s7, 'conv6') : undefined;\n const conv7 = s8 ? extractSeparableConvParams(s7, s8, 'conv7') : undefined;\n const conv8 = extractConvParams(s8 || s7 || s6, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n } else {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = extractConvWithBatchNormParams(s0, s1, 'conv0');\n const conv1 = extractConvWithBatchNormParams(s1, s2, 'conv1');\n const conv2 = extractConvWithBatchNormParams(s2, s3, 'conv2');\n const conv3 = extractConvWithBatchNormParams(s3, s4, 'conv3');\n const conv4 = extractConvWithBatchNormParams(s4, s5, 'conv4');\n const conv5 = extractConvWithBatchNormParams(s5, s6, 'conv5');\n const conv6 = extractConvWithBatchNormParams(s6, s7, 'conv6');\n const conv7 = extractConvWithBatchNormParams(s7, s8, 'conv7');\n const conv8 = extractConvParams(s8, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n }\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from '../common/index';\nimport { disposeUnusedWeightTensors } from '../common/disposeUnusedWeightTensors';\nimport { loadSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightEntryFactory } from '../common/extractWeightEntryFactory';\nimport { ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractBatchNormParams(prefix: string): BatchNorm {\n const sub = extractWeightEntry(`${prefix}/sub`, 1);\n const truediv = extractWeightEntry(`${prefix}/truediv`, 1);\n return { sub, truediv };\n }\n\n function extractConvParams(prefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { filters, bias };\n }\n\n function extractConvWithBatchNormParams(prefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(`${prefix}/conv`);\n const bn = extractBatchNormParams(`${prefix}/bn`);\n return { conv, bn };\n }\n\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n config: TinyYolov2Config,\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n // eslint-disable-next-line no-mixed-operators\n const numFilters = (config.filterSizes && config.filterSizes.length || 9);\n params = {\n conv0: config.isFirstLayerConv2d ? extractConvParams('conv0') : extractSeparableConvParams('conv0'),\n conv1: extractSeparableConvParams('conv1'),\n conv2: extractSeparableConvParams('conv2'),\n conv3: extractSeparableConvParams('conv3'),\n conv4: extractSeparableConvParams('conv4'),\n conv5: extractSeparableConvParams('conv5'),\n conv6: numFilters > 7 ? extractSeparableConvParams('conv6') : undefined,\n conv7: numFilters > 8 ? extractSeparableConvParams('conv7') : undefined,\n conv8: extractConvParams('conv8'),\n };\n } else {\n params = {\n conv0: extractConvWithBatchNormParams('conv0'),\n conv1: extractConvWithBatchNormParams('conv1'),\n conv2: extractConvWithBatchNormParams('conv2'),\n conv3: extractConvWithBatchNormParams('conv3'),\n conv4: extractConvWithBatchNormParams('conv4'),\n conv5: extractConvWithBatchNormParams('conv5'),\n conv6: extractConvWithBatchNormParams('conv6'),\n conv7: extractConvWithBatchNormParams('conv7'),\n conv8: extractConvParams('conv8'),\n };\n }\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n return { params, paramMappings };\n}\n", "export interface ITinyYolov2Options {\n inputSize?: number\n scoreThreshold?: number\n}\n\nexport class TinyYolov2Options {\n protected _name: string = 'TinyYolov2Options'\n\n private _inputSize: number\n\n private _scoreThreshold: number\n\n constructor({ inputSize, scoreThreshold }: ITinyYolov2Options = {}) {\n this._inputSize = inputSize || 416;\n this._scoreThreshold = scoreThreshold || 0.5;\n\n if (typeof this._inputSize !== 'number' || this._inputSize % 32 !== 0) {\n throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);\n }\n\n if (typeof this._scoreThreshold !== 'number' || this._scoreThreshold <= 0 || this._scoreThreshold >= 1) {\n throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`);\n }\n }\n\n get inputSize(): number { return this._inputSize; }\n\n get scoreThreshold(): number { return this._scoreThreshold; }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/types';\nimport { TNetInput } from '../dom/types';\nimport {\n BOX_ANCHORS,\n BOX_ANCHORS_SEPARABLE,\n DEFAULT_MODEL_NAME,\n DEFAULT_MODEL_NAME_SEPARABLE_CONV,\n IOU_THRESHOLD,\n MEAN_RGB_SEPARABLE,\n} from './const';\nimport { TinyYolov2Base } from './TinyYolov2Base';\nimport { ITinyYolov2Options } from './TinyYolov2Options';\nimport { TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2 extends TinyYolov2Base {\n constructor(withSeparableConvs: boolean = true) {\n const config = {\n withSeparableConvs,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n ...(withSeparableConvs\n ? {\n anchors: BOX_ANCHORS_SEPARABLE,\n meanRgb: MEAN_RGB_SEPARABLE,\n }\n : {\n anchors: BOX_ANCHORS,\n withClassScores: true,\n }),\n };\n\n super(config);\n }\n\n public get withSeparableConvs(): boolean {\n return this.config.withSeparableConvs;\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return this.withSeparableConvs ? DEFAULT_MODEL_NAME_SEPARABLE_CONV : DEFAULT_MODEL_NAME;\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { TinyYolov2 } from './TinyYolov2';\n\nexport * from './TinyYolov2Options';\nexport * from './config';\nexport * from './types';\nexport { TinyYolov2 };\n\nexport function createTinyYolov2(weights: Float32Array, withSeparableConvs: boolean = true) {\n const net = new TinyYolov2(withSeparableConvs);\n net.extractWeights(weights);\n return net;\n}\n", "import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\n\nexport interface ITinyFaceDetectorOptions extends ITinyYolov2Options {}\n\nexport class TinyFaceDetectorOptions extends TinyYolov2Options {\n protected _name: string = 'TinyFaceDetectorOptions'\n}\n", "export class ComposableTask {\n public async then(\n // eslint-disable-next-line no-unused-vars\n onfulfilled: (value: T) => T | PromiseLike,\n ): Promise {\n return onfulfilled(await this.run());\n }\n\n public async run(): Promise {\n throw new Error('ComposableTask - run is not implemented');\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class DetectFaceLandmarksTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected useTinyLandmarkNet: boolean,\n ) {\n super();\n }\n\n protected get landmarkNet(): FaceLandmark68Net | FaceLandmark68TinyNet {\n return this.useTinyLandmarkNet\n ? nets.faceLandmark68TinyNet\n : nets.faceLandmark68Net;\n }\n}\n\nexport class DetectAllFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n const detections = parentResults.map((res) => res.detection);\n\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, detections)\n : await extractFaces(this.input, detections);\n\n const faceLandmarksByFace = await Promise.all(faces.map(\n (face) => this.landmarkNet.detectLandmarks(face),\n )) as FaceLandmarks68[];\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return parentResults.map((parentResult, i) => extendWithFaceLandmarks(parentResult, faceLandmarksByFace[i]));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class DetectSingleFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { detection } = parentResult;\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, [detection])\n : await extractFaces(this.input, [detection]);\n\n const landmarks = await this.landmarkNet.detectLandmarks(faces[0]) as FaceLandmarks68;\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return extendWithFaceLandmarks(parentResult, landmarks);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\n\nexport async function extractAllFacesAndComputeResults, TResult>(\n parentResults: TSource[],\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResults: (faces: Array) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment: (parentResult: WithFaceLandmarks) => FaceDetection = ({ alignedRect }) => alignedRect,\n) {\n const faceBoxes = parentResults.map((parentResult) => (isWithFaceLandmarks(parentResult)\n ? getRectForAlignment(parentResult)\n : parentResult.detection));\n const faces: Array = extractedFaces || (\n input instanceof tf.Tensor\n ? await extractFaceTensors(input, faceBoxes)\n : await extractFaces(input, faceBoxes)\n );\n\n const results = await computeResults(faces);\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return results;\n}\n\nexport async function extractSingleFaceAndComputeResult, TResult>(\n parentResult: TSource,\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResult: (face: HTMLCanvasElement | tf.Tensor3D) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment?: (parentResultLocal: WithFaceLandmarks) => FaceDetection,\n) {\n return extractAllFacesAndComputeResults(\n [parentResult],\n input,\n async (faces) => computeResult(faces[0]),\n extractedFaces,\n getRectForAlignment,\n );\n}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB: [number, number, number] = [117.001, 114.697, 97.404];\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/index';\nimport { TNetInput } from '../dom/index';\nimport { ITinyYolov2Options } from '../tinyYolov2/index';\nimport { TinyYolov2Base } from '../tinyYolov2/TinyYolov2Base';\nimport { TinyYolov2NetParams } from '../tinyYolov2/types';\nimport { BOX_ANCHORS, IOU_THRESHOLD, MEAN_RGB } from './const';\n\nexport class TinyFaceDetector extends TinyYolov2Base {\n constructor() {\n const config = {\n withSeparableConvs: true,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n anchors: BOX_ANCHORS,\n meanRgb: MEAN_RGB,\n isFirstLayerConv2d: true,\n filterSizes: [3, 16, 32, 64, 128, 256, 512],\n };\n\n super(config);\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_face_detector_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { AgeGenderNet } from '../ageGenderNet/AgeGenderNet';\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressionNet } from '../faceExpressionNet/FaceExpressionNet';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { FaceRecognitionNet } from '../faceRecognitionNet/FaceRecognitionNet';\nimport { SsdMobilenetv1 } from '../ssdMobilenetv1/SsdMobilenetv1';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetector } from '../tinyFaceDetector/TinyFaceDetector';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { ITinyYolov2Options, TinyYolov2 } from '../tinyYolov2/index';\n\nexport const nets = {\n ssdMobilenetv1: new SsdMobilenetv1(),\n tinyFaceDetector: new TinyFaceDetector(),\n tinyYolov2: new TinyYolov2(),\n faceLandmark68Net: new FaceLandmark68Net(),\n faceLandmark68TinyNet: new FaceLandmark68TinyNet(),\n faceRecognitionNet: new FaceRecognitionNet(),\n faceExpressionNet: new FaceExpressionNet(),\n ageGenderNet: new AgeGenderNet(),\n};\n\n/**\n * Attempts to detect all faces in an image using SSD Mobilenetv1 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see SsdMobilenetv1Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const ssdMobilenetv1 = (input: TNetInput, options: SsdMobilenetv1Options): Promise => nets.ssdMobilenetv1.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Face Detector.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyFaceDetectorOptions constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyFaceDetector = (input: TNetInput, options: TinyFaceDetectorOptions): Promise => nets.tinyFaceDetector.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Yolov2 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyYolov2Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyYolov2 = (input: TNetInput, options: ITinyYolov2Options): Promise => nets.tinyYolov2.locateFaces(input, options);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarks = (input: TNetInput): Promise => nets.faceLandmark68Net.detectLandmarks(input);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image\n * using a tinier version of the 68 point face landmark model, which is slightly\n * faster at inference, but also slightly less accurate.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarksTiny = (input: TNetInput): Promise => nets.faceLandmark68TinyNet.detectLandmarks(input);\n\n/**\n * Computes a 128 entry vector (face descriptor / face embeddings) from the face shown in an image,\n * which uniquely represents the features of that persons face. The computed face descriptor can\n * be used to measure the similarity between faces, by computing the euclidean distance of two\n * face descriptors.\n *\n * @param inputs The face image extracted from the aligned bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Face descriptor with 128 entries or array thereof in case of batch input.\n */\nexport const computeFaceDescriptor = (input: TNetInput): Promise => nets.faceRecognitionNet.computeFaceDescriptor(input);\n\n/**\n * Recognizes the facial expressions from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Facial expressions with corresponding probabilities or array thereof in case of batch input.\n */\nexport const recognizeFaceExpressions = (input: TNetInput): Promise => nets.faceExpressionNet.predictExpressions(input);\n\n/**\n * Predicts age and gender from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Predictions with age, gender and gender probability or array thereof in case of batch input.\n */\nexport const predictAgeAndGender = (input: TNetInput): Promise => nets.ageGenderNet.predictAgeAndGender(input);\n\nexport const loadSsdMobilenetv1Model = (url: string) => nets.ssdMobilenetv1.load(url);\nexport const loadTinyFaceDetectorModel = (url: string) => nets.tinyFaceDetector.load(url);\nexport const loadTinyYolov2Model = (url: string) => nets.tinyYolov2.load(url);\nexport const loadFaceLandmarkModel = (url: string) => nets.faceLandmark68Net.load(url);\nexport const loadFaceLandmarkTinyModel = (url: string) => nets.faceLandmark68TinyNet.load(url);\nexport const loadFaceRecognitionModel = (url: string) => nets.faceRecognitionNet.load(url);\nexport const loadFaceExpressionModel = (url: string) => nets.faceExpressionNet.load(url);\nexport const loadAgeGenderModel = (url: string) => nets.ageGenderNet.load(url);\n\n// backward compatibility\nexport const loadFaceDetectionModel = loadSsdMobilenetv1Model;\nexport const locateFaces = ssdMobilenetv1;\nexport const detectLandmarks = detectFaceLandmarks;\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderTask,\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\n\nexport class PredictFaceExpressionsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const faceExpressionsByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map(\n (parentResult, i) => extendWithFaceExpressions(parentResult, faceExpressionsByFace[i]),\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const faceExpressions = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithFaceExpressions(parentResult, faceExpressions);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictAllFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { TNetInput } from '../dom/index';\nimport { extendWithAge, WithAge } from '../factories/WithAge';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { extendWithGender, WithGender } from '../factories/WithGender';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllFaceExpressionsTask,\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class PredictAgeAndGenderTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase>[], TSource[]> {\n public async run(): Promise>[]> {\n const parentResults = await this.parentTask;\n\n const ageAndGenderByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map((parentResult, i) => {\n const { age, gender, genderProbability } = ageAndGenderByFace[i];\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n });\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase> | undefined, TSource | undefined> {\n public async run(): Promise> | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { age, gender, genderProbability } = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictAllAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDescriptor, WithFaceDescriptor } from '../factories/WithFaceDescriptor';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class ComputeFaceDescriptorsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n ) {\n super();\n }\n}\n\nexport class ComputeAllFaceDescriptorsTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const descriptors = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n (faces) => Promise.all(faces.map((face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise)),\n null,\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return descriptors.map((descriptor, i) => extendWithFaceDescriptor(parentResults[i], descriptor));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n\nexport class ComputeSingleFaceDescriptorTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n const descriptor = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise,\n null,\n // eslint-disable-next-line no-shadow\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return extendWithFaceDescriptor(parentResult, descriptor);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { TinyYolov2Options } from '../tinyYolov2/index';\nimport { ComposableTask } from './ComposableTask';\nimport { DetectAllFaceLandmarksTask, DetectSingleFaceLandmarksTask } from './DetectFaceLandmarksTasks';\nimport { nets } from './nets';\nimport { PredictAllAgeAndGenderTask, PredictSingleAgeAndGenderTask } from './PredictAgeAndGenderTask';\nimport { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from './PredictFaceExpressionsTask';\nimport { FaceDetectionOptions } from './types';\n\nexport class DetectFacesTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n ) {\n super();\n }\n}\n\nexport class DetectAllFacesTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const { input, options } = this;\n\n // eslint-disable-next-line no-nested-ternary\n const faceDetectionFunction = options instanceof TinyFaceDetectorOptions\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyFaceDetector.locateFaces(input, options)\n : (\n // eslint-disable-next-line no-nested-ternary\n options instanceof SsdMobilenetv1Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.ssdMobilenetv1.locateFaces(input, options)\n : (\n options instanceof TinyYolov2Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyYolov2.locateFaces(input, options)\n : null\n )\n );\n\n if (!faceDetectionFunction) {\n throw new Error('detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options');\n }\n\n return faceDetectionFunction(input);\n }\n\n private runAndExtendWithFaceDetections(): Promise[]> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise[]>(async (resolve) => {\n const detections = await this.run();\n resolve(detections.map((detection) => extendWithFaceDetection({}, detection)));\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectAllFaceLandmarksTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n}\n\nexport class DetectSingleFaceTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const faceDetections = await new DetectAllFacesTask(this.input, this.options);\n let faceDetectionWithHighestScore = faceDetections[0];\n faceDetections.forEach((faceDetection) => {\n if (faceDetection.score > faceDetectionWithHighestScore.score) {\n faceDetectionWithHighestScore = faceDetection;\n }\n });\n return faceDetectionWithHighestScore;\n }\n\n private runAndExtendWithFaceDetection(): Promise | undefined> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise | undefined>(async (resolve) => {\n const detection = await this.run();\n resolve(detection ? extendWithFaceDetection<{}>({}, detection) : undefined);\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectSingleFaceLandmarksTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n}\n", "import { TNetInput } from '../dom/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { DetectAllFacesTask, DetectSingleFaceTask } from './DetectFacesTasks';\nimport { FaceDetectionOptions } from './types';\n\nexport function detectSingleFace(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectSingleFaceTask {\n return new DetectSingleFaceTask(input, options);\n}\n\nexport function detectAllFaces(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectAllFacesTask {\n return new DetectAllFacesTask(input, options);\n}\n", "import { TNetInput } from '../dom/index';\nimport { WithFaceDescriptor, WithFaceDetection, WithFaceLandmarks } from '../factories/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';\nimport { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\nimport { detectAllFaces } from './detectFaces';\n\n// export allFaces API for backward compatibility\n\nexport async function allFacesSsdMobilenetv1(\n input: TNetInput,\n minConfidence?: number,\n): Promise>>[]> {\n return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport async function allFacesTinyYolov2(\n input: TNetInput,\n forwardParams: ITinyYolov2Options = {},\n): Promise>>[]> {\n return detectAllFaces(input, new TinyYolov2Options(forwardParams))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport const allFaces = allFacesSsdMobilenetv1;\n", "export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {\n if (arr1.length !== arr2.length) throw new Error('euclideanDistance: arr1.length !== arr2.length');\n\n const desc1 = Array.from(arr1);\n const desc2 = Array.from(arr2);\n\n return Math.sqrt(\n desc1\n .map((val, i) => val - desc2[i])\n .reduce((res, diff) => res + (diff ** 2), 0),\n );\n}\n", "import { FaceMatch } from '../classes/FaceMatch';\nimport { LabeledFaceDescriptors } from '../classes/LabeledFaceDescriptors';\nimport { euclideanDistance } from '../euclideanDistance';\nimport { WithFaceDescriptor } from '../factories/index';\n\nexport class FaceMatcher {\n private _labeledDescriptors: LabeledFaceDescriptors[]\n\n private _distanceThreshold: number\n\n constructor(\n inputs: LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>,\n distanceThreshold: number = 0.6,\n ) {\n this._distanceThreshold = distanceThreshold;\n\n const inputArray = Array.isArray(inputs) ? inputs : [inputs];\n\n if (!inputArray.length) {\n throw new Error('FaceRecognizer.constructor - expected atleast one input');\n }\n\n let count = 1;\n const createUniqueLabel = () => `person ${count++}`;\n\n this._labeledDescriptors = inputArray.map((desc) => {\n if (desc instanceof LabeledFaceDescriptors) {\n return desc;\n }\n\n if (desc instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc]);\n }\n\n if (desc.descriptor && desc.descriptor instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc.descriptor]);\n }\n\n throw new Error('FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>');\n });\n }\n\n public get labeledDescriptors(): LabeledFaceDescriptors[] { return this._labeledDescriptors; }\n\n public get distanceThreshold(): number { return this._distanceThreshold; }\n\n public computeMeanDistance(queryDescriptor: Float32Array, descriptors: Float32Array[]): number {\n return descriptors\n .map((d) => euclideanDistance(d, queryDescriptor))\n .reduce((d1, d2) => d1 + d2, 0)\n / (descriptors.length || 1);\n }\n\n public matchDescriptor(queryDescriptor: Float32Array): FaceMatch {\n return this.labeledDescriptors\n .map(({ descriptors, label }) => new FaceMatch(\n label,\n this.computeMeanDistance(queryDescriptor, descriptors),\n ))\n .reduce((best, curr) => (best.distance < curr.distance ? best : curr));\n }\n\n public findBestMatch(queryDescriptor: Float32Array): FaceMatch {\n const bestMatch = this.matchDescriptor(queryDescriptor);\n return bestMatch.distance < this.distanceThreshold\n ? bestMatch\n : new FaceMatch('unknown', bestMatch.distance);\n }\n\n public toJSON(): any {\n return {\n distanceThreshold: this.distanceThreshold,\n labeledDescriptors: this.labeledDescriptors.map((ld) => ld.toJSON()),\n };\n }\n\n public static fromJSON(json: any): FaceMatcher {\n const labeledDescriptors = json.labeledDescriptors\n .map((ld: any) => LabeledFaceDescriptors.fromJSON(ld));\n return new FaceMatcher(labeledDescriptors, json.distanceThreshold);\n }\n}\n", "import { TinyFaceDetector } from './TinyFaceDetector';\n\nexport * from './TinyFaceDetector';\nexport * from './TinyFaceDetectorOptions';\n\nexport function createTinyFaceDetector(weights: Float32Array) {\n const net = new TinyFaceDetector();\n net.extractWeights(weights);\n return net;\n}\n", "import { Dimensions, IDimensions } from './classes/index';\nimport { FaceDetection } from './classes/FaceDetection';\nimport { FaceLandmarks } from './classes/FaceLandmarks';\nimport { extendWithFaceDetection, isWithFaceDetection } from './factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, isWithFaceLandmarks } from './factories/WithFaceLandmarks';\n\nexport function resizeResults(results: T, dimensions: IDimensions): T {\n const { width, height } = new Dimensions(dimensions.width, dimensions.height);\n\n if (width <= 0 || height <= 0) {\n throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({ width, height })}`);\n }\n\n if (Array.isArray(results)) {\n // return results.map(obj => resizeResults(obj, { width, height })) as any as T\n return (results as Array).map((obj) => resizeResults(obj, { width, height } as IDimensions)) as any as T;\n }\n\n if (isWithFaceLandmarks(results)) {\n const resizedDetection = results.detection.forSize(width, height);\n const resizedLandmarks = results.unshiftedLandmarks.forSize(resizedDetection.box.width, resizedDetection.box.height);\n return extendWithFaceLandmarks(extendWithFaceDetection(results, resizedDetection), resizedLandmarks);\n }\n\n if (isWithFaceDetection(results)) {\n return extendWithFaceDetection(results, results.detection.forSize(width, height));\n }\n\n if (results instanceof FaceLandmarks || results instanceof FaceDetection) {\n return (results as any).forSize(width, height);\n }\n\n return results;\n}\n"], + "mappings": ";;;;;;;wlCAGA,GAAA,GAAc,GAAA,yCCHd,6CAAO,cACL,MAAO,OAAO,SAAW,UACpB,IACA,MAAO,KAAW,aAGlB,MAAO,UAAY,aAAe,CAAC,CAAC,QAAQ,WCNnD,6xFAAA,OAAoB,OCApB,qRCEO,YACL,EACA,EACA,EAAoB,IAUpB,GARA,EAAI,YAEJ,EAAO,MAAM,GAAG,QAAQ,CAAC,CAAE,IAAG,KAAK,KACjC,GAAM,GAAO,EAAO,GACpB,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,KAGZ,GACF,GAAM,GAAO,EAAO,EAAO,OAAS,GAC9B,EAAK,EAAO,GAClB,GAAI,CAAC,GAAQ,CAAC,EACZ,OAGF,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,EAAG,EAAG,GAGtB,EAAI,SC1BN,2RAAA,OAAoB,OCApB,YAYE,YAAY,EAAe,GACzB,GAAI,CAAC,GAAc,IAAU,CAAC,GAAc,GAC1C,KAAM,IAAI,OAAM,wFAAwF,KAAK,UAAU,CAAE,QAAO,cAGlI,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,QAEnC,UACL,MAAO,IAAI,GAAW,EAAI,KAAK,MAAO,EAAI,KAAK,UDrB5C,YAAkB,EAAa,GACpC,MAAO,aAAqB,YAAU,EAAO,MAAM,SAAW,EAGzD,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,WAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAiB,GACtB,MAAO,GAAM,GAAM,EAGd,YAAgB,GACrB,MAAO,GAAM,GAAM,EAGd,YAAe,EAAa,EAAe,GAChD,GAAM,GAAI,IAAM,EAChB,MAAO,MAAK,MAAM,EAAM,GAAK,EAGxB,YAAsB,GAC3B,MAAO,IAAO,EAAI,OAAS,EAAI,OAG1B,YAAmC,CAAE,QAAO,UAAuB,GACxE,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,IAAI,GAAW,KAAK,MAAM,EAAQ,GAAQ,KAAK,MAAM,EAAS,IAGhE,YAAwB,GAC7B,MAAO,GAAI,OAAO,CAAC,EAAK,IAAO,EAAI,IAAI,GAAK,GAAI,GAAM,EAAG,IACtD,IAAI,GAAI,GAAM,EAAI,OAAQ,EAAI,SAG5B,YAAe,EAAa,EAAe,GAChD,MAAO,OAAM,GAAK,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,EAAS,EAAI,GAGhD,YAAuB,GAC5B,MAAO,CAAC,CAAC,GAAQ,IAAQ,UAAc,IAAQ,WAAc,CAAC,OAAO,MAAM,IAAQ,IAAQ,EAGtF,YAA4B,GACjC,MAAO,IAAc,IAAQ,GAAO,GAAK,GAAO,EE7DlD,YAUE,YAAY,EAAW,GACrB,KAAK,GAAK,EACV,KAAK,GAAK,KAGR,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,GAEvB,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,MACL,MAAO,IAAI,GAAM,KAAK,IAAI,KAAK,GAAI,KAAK,IAAI,KAAK,IAG5C,YACL,MAAO,MAAK,KAAM,KAAK,GAAK,EAAM,KAAK,GAAK,GAGvC,QACL,MAAO,IAAI,GAAM,KAAK,MAAM,KAAK,GAAI,KAAK,MAAM,KAAK,MC5CzD,kBAOgB,QAAO,GACnB,MAAO,CAAC,CAAC,GAAQ,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,MAAO,EAAK,QAAQ,MAAM,UAGrD,kBAAiB,EAAU,EAAgB,EAAmC,IAC1F,GAAI,CAAC,EAAI,OAAO,GACd,KAAM,IAAI,OAAM,GAAG,oBAAyB,KAAK,UAAU,2DAG7D,GAAI,CAAC,GAA4B,GAAI,MAAQ,GAAK,EAAI,OAAS,GAC7D,KAAM,IAAI,OAAM,GAAG,cAAmB,EAAI,sBAAsB,EAAI,oCAYxE,YAAY,EAA4B,EAAmC,IACzE,GAAM,GAAO,GAAQ,GAEf,EAAS,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAO,EAAI,QAAQ,MAAM,IAC1D,EAAS,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAAQ,MAAM,IAE3D,GAAI,CAAC,GAAU,CAAC,EACd,KAAM,IAAI,OAAM,2EAA2E,KAAK,UAAU,MAG5G,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,EAC1B,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAC9B,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAQ,EAAI,KAAM,EAAI,OAAS,EAAI,KAE/D,EAAI,iBAAiB,CACnB,IAAG,IAAG,QAAO,UACZ,kBAAmB,GAEtB,KAAK,GAAK,EACV,KAAK,GAAK,EACV,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,MAE1B,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,WAE/B,QAAiB,MAAO,MAAK,KAE7B,OAAgB,MAAO,MAAK,KAE5B,SAAkB,MAAO,MAAK,EAAI,KAAK,SAEvC,UAAmB,MAAO,MAAK,EAAI,KAAK,UAExC,QAAiB,MAAO,MAAK,MAAQ,KAAK,UAE1C,WAAmB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,QAEpD,YAAoB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAEtD,cAAsB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,WAEvD,eAAuB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAE7D,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,WACL,GAAI,CACF,IAAG,IAAG,QAAO,UACX,KACE,EAAO,KAAK,IAAI,EAAQ,GAC9B,MAAI,GAAQ,GACV,IAAM,EAAO,EACb,GAAS,GAEP,EAAS,GACX,IAAM,EAAO,EACb,GAAU,GAGL,GAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QAAQ,GACb,GAAM,GAAS,GAAa,GAAM,EAAkB,MAAQ,EACtD,EAAS,GAAa,GAAM,EAAkB,OAAS,EAC7D,MAAO,IAAI,GAAI,CACb,EAAG,KAAK,EAAI,EACZ,EAAG,KAAK,EAAI,EACZ,MAAO,KAAK,MAAQ,EACpB,OAAQ,KAAK,OAAS,IAInB,IAAI,EAAc,GACvB,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAC5B,KAAK,EAAK,EAAO,EACjB,KAAK,EAAK,EAAO,EACjB,KAAK,MAAQ,EACb,KAAK,OAAS,GAEhB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,mBAAmB,EAAkB,GAC1C,GAAM,CACJ,IAAG,IAAG,QAAO,UACX,KACE,EAAW,KAAK,IAAI,EAAG,GACvB,EAAW,KAAK,IAAI,EAAG,GAEvB,EAAW,EAAQ,EACnB,EAAY,EAAS,EACrB,EAAe,KAAK,IAAI,EAAU,EAAW,GAC7C,EAAgB,KAAK,IAAI,EAAW,EAAY,GAEtD,MAAQ,IAAI,GAAI,CACd,EAAG,EAAU,EAAG,EAAU,MAAO,EAAc,OAAQ,IACrD,QAGC,MAAM,EAAY,GACvB,GAAM,CAAE,QAAO,UAAW,KACpB,EAAI,KAAK,EAAI,EACb,EAAI,KAAK,EAAI,EAEnB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,aAAa,EAAqB,GACvC,GAAM,GAAI,KAAK,MAAQ,EACjB,EAAI,KAAK,OAAS,EAElB,EAAK,EACL,EAAK,EACP,EAAM,EACN,EAAM,EAEN,EAAI,KAAK,KACT,EAAI,KAAK,IACT,EAAK,KAAK,MACV,EAAK,KAAK,OAEd,MAAI,GAAK,GACP,GAAM,CAAC,EAAK,EAAa,EACzB,EAAK,GAEH,EAAK,GACP,GAAM,CAAC,EAAK,EAAc,EAC1B,EAAK,GAEH,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAEF,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAGC,CACL,KAAI,MAAK,KAAI,MAAK,IAAG,KAAI,IAAG,KAAI,IAAG,KAIhC,UAAU,GACf,MAAO,IAAI,GAAI,CACb,KAAM,KAAK,KAAQ,EAAO,KAAO,KAAK,MACtC,IAAK,KAAK,IAAO,EAAO,IAAM,KAAK,OACnC,MAAO,KAAK,MAAS,EAAO,MAAQ,KAAK,MACzC,OAAQ,KAAK,OAAU,EAAO,OAAS,KAAK,SAC3C,WAAW,UC9MlB,oBASiC,GAC/B,YAAY,EAAc,EAAa,EAAe,EAAgB,EAAmC,IACvG,MAAM,CACJ,OAAM,MAAK,QAAO,UACjB,KCbP,aAeE,YACE,EACA,EACA,EACA,EACA,GAEA,KAAK,WAAa,GAAI,GAAW,EAAU,MAAO,EAAU,QAC5D,KAAK,OAAS,EACd,KAAK,YAAc,EACnB,KAAK,WAAa,EAClB,KAAK,KAAO,GAAI,GAAI,GAAa,QAAQ,KAAK,eAGrC,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,eAEnC,aAAsB,MAAO,MAAK,cAElC,OAAa,MAAO,MAAK,QAEzB,aAA0B,MAAO,MAAK,cAEtC,cAAuB,MAAO,MAAK,UAAU,SAE7C,eAAwB,MAAO,MAAK,UAAU,UAE9C,eAAqB,MAAO,IAAI,GAAI,KAAK,MAAM,QAAQ,KAAK,UAAU,WAE1E,QAAQ,EAAe,GAC5B,MAAO,IAAI,IACT,KAAK,MACL,KAAK,WACL,KAAK,UACL,KAAK,YACL,CAAE,QAAO,aCnDf,mBAUmC,IACjC,YACE,EACA,EACA,GAEA,MAAM,EAAO,EAAO,GAAI,EAAa,GAGhC,QAAQ,EAAe,GAC5B,GAAM,CAAE,QAAO,cAAa,aAAc,MAAM,QAAQ,EAAO,GAC/D,MAAO,IAAI,GAAc,EAAO,EAAa,KCnB1C,YAAa,EAAW,EAAW,EAAiB,IACzD,GAAM,GAAQ,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,MAAO,EAAK,OAAS,KAAK,IAAI,EAAK,KAAM,EAAK,OAClF,EAAS,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,OAAQ,EAAK,QAAU,KAAK,IAAI,EAAK,IAAK,EAAK,MACpF,EAAe,EAAQ,EAE7B,MAAO,GACH,EAAgB,GAAK,KAAO,EAAK,KAAO,GACxC,EAAe,KAAK,IAAI,EAAK,KAAM,EAAK,MCPvC,YAAiB,GACtB,GAAM,GAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAExD,MAAO,IAAI,IAAY,EAAM,EAAM,EAAM,GCPpC,YACL,EACA,EACA,EACA,EAAiB,IAEjB,GAAI,GAAuB,EACxB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAC/B,IAAI,AAAC,GAAM,EAAE,UAEV,EAAiB,GAEvB,KAAO,EAAqB,OAAS,IACnC,GAAM,GAAO,EAAqB,MAClC,EAAK,KAAK,GAEV,GAAM,GAAU,EAEV,EAAoB,GAC1B,OAAS,GAAI,EAAG,EAAI,EAAQ,OAAQ,KAClC,GAAM,GAAM,EAAQ,GAEd,EAAU,EAAM,GAChB,EAAS,EAAM,GAErB,EAAQ,KAAK,GAAI,EAAS,EAAQ,IAGpC,EAAuB,EAAqB,OAC1C,CAAC,EAAG,IAAM,EAAQ,IAAM,GAI5B,MAAO,GCrCT,OAAoB,OAEb,YAAmB,EAAgB,GACxC,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAG,EAAG,GAAK,EACZ,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAU,AAAG,UAAO,CAAC,EAAO,EAAO,GAAQ,GAEjD,MAAO,AAAG,QAAI,EAAG,KCVrB,OAAoB,OAUb,YACL,EACA,EAAyB,IAEzB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAQ,GAAS,EAAU,MAAM,MAAM,GAC9C,GAAI,IAAW,EACb,MAAO,GAGT,GAAM,GAAU,KAAK,IAAI,EAAS,GAC5B,EAAgB,KAAK,MAAM,EAAW,GAAgB,GAAM,IAC5D,EAAc,EAAS,EAAQ,EAAI,EAEnC,EAAsB,AAAC,IAC3B,GAAM,GAAqB,EAAU,MAAM,QAC3C,SAAmB,GAAe,EAC3B,AAAG,QAAK,EAAoB,EAAG,YAGlC,EAAsB,EAAoB,GAC1C,EAAyB,EAAW,EAAoB,MAAM,GAM9D,EAAiB,CAJM,GAAiB,EAC1C,EAAoB,GACpB,KAIF,EACA,GAEC,OAAO,AAAC,GAAM,CAAC,CAAC,GAEhB,IAAI,AAAC,GAAiB,AAAG,QAAK,EAAG,YACpC,MAAO,AAAG,WAAO,EAAgB,KC7C9B,YAAsB,GAC3B,GAAM,GAAQ,EAAW,QACzB,OAAS,GAAI,EAAM,OAAS,EAAG,EAAI,EAAG,KACpC,GAAM,GAAI,KAAK,MAAM,KAAK,SAAY,GAAI,IACpC,EAAI,EAAM,GAChB,EAAM,GAAK,EAAM,GACjB,EAAM,GAAK,EAEb,MAAO,GCDF,YAAiB,GACtB,MAAO,GAAK,GAAI,KAAK,IAAI,CAAC,IAGrB,YAAwB,GAC7B,MAAO,MAAK,IAAI,EAAK,GAAI,ICZ3B,oBAS0B,GACxB,YAAY,EAAW,EAAW,EAAe,EAAgB,EAAmC,IAClG,MAAM,CACJ,IAAG,IAAG,QAAO,UACZ,KCHP,GAAM,IAAO,GACP,GAAO,IACP,GAAW,IAZjB,QA0BE,YACE,EACA,EACA,EAAe,GAAI,GAAM,EAAG,IAE5B,GAAM,CAAE,QAAO,UAAW,EAC1B,KAAK,SAAW,GAAI,GAAW,EAAO,GACtC,KAAK,OAAS,EACd,KAAK,WAAa,EAA8B,IAC9C,AAAC,GAAO,EAAG,IAAI,GAAI,GAAM,EAAO,IAAS,IAAI,OAItC,SAAiB,MAAO,IAAI,GAAM,KAAK,OAAO,EAAG,KAAK,OAAO,MAE7D,cAAuB,MAAO,MAAK,SAAS,SAE5C,eAAwB,MAAO,MAAK,SAAS,UAE7C,aAAuB,MAAO,MAAK,cAEnC,qBACT,MAAO,MAAK,WAAW,IACrB,AAAC,GAAO,EAAG,IAAI,KAAK,QAAQ,IAAI,GAAI,GAAM,KAAK,WAAY,KAAK,eAI7D,QAAiC,EAAe,GACrD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,CAAE,QAAO,WAIN,QAAiC,EAAW,GACjD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,KAAK,SACL,GAAI,GAAM,EAAG,IAIV,aAAsC,GAC3C,MAAO,MAAK,QAAQ,EAAG,EAAG,EAAG,GAcxB,MACL,EACA,EAAkE,IAElE,GAAI,GACF,GAAM,GAAM,YAAqB,GAC7B,EAAU,IAAI,QACd,GAAI,GAAI,GAEZ,MAAO,MAAK,QAAQ,EAAI,EAAG,EAAI,GAAG,MAAM,KAAM,GAGhD,GAAM,CAAE,mBAAkB,iBAAkB,CAAE,iBAAkB,GAAO,cAAe,MAAQ,GAE9F,MAAI,GACK,KAAK,YAGP,KAAK,aAAa,GAGnB,YACN,GAAM,GAAU,KAAK,2BAEf,CAAC,EAAe,EAAgB,GAAe,EAC/C,EAAc,AAAC,GAAc,EAAY,IAAI,GAAI,YACjD,EAAkB,GAAY,GAAiB,EAAY,IAAmB,EAE9E,EAAO,KAAK,MAAM,EAAiB,IAEnC,EAAW,GAAe,GAE1B,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAChD,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAEtD,MAAO,IAAI,IAAK,EAAG,EAAG,KAAK,IAAI,EAAM,KAAK,WAAa,GAAI,KAAK,IAAI,EAAM,KAAK,YAAc,IAGvF,aAAa,GACnB,GAAM,GAAM,GAAQ,KAAK,WACzB,MAAO,GAAI,IAAI,EAAI,MAAQ,EAAS,EAAI,OAAS,GAGzC,2BACR,KAAM,IAAI,OAAM,4DC/HpB,oBAIoC,GACxB,2BACR,GAAM,GAAM,KAAK,UACjB,MAAO,CACL,EAAI,GACJ,EAAI,GACJ,GAAe,CAAC,EAAI,GAAI,EAAI,QCVlC,oBAIqC,GAC5B,gBACL,MAAO,MAAK,UAAU,MAAM,EAAG,IAG1B,iBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,kBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,UACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,aACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,cACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,WACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAGxB,2BACR,MAAO,CACL,KAAK,aACL,KAAK,cACL,KAAK,YACL,IAAI,MCtCV,aAYE,YAAY,EAAe,GACzB,KAAK,OAAS,EACd,KAAK,UAAY,KAGR,SAAkB,MAAO,MAAK,UAE9B,YAAqB,MAAO,MAAK,UAErC,SAAS,EAAwB,IACtC,MAAO,GAAG,KAAK,QAAQ,EAAe,KAAK,GAAM,KAAK,aAAe,OCtBzE,oBAKgC,SAChB,yBAAwB,EAAU,GAG9C,GAFA,EAAI,iBAAiB,EAAK,GAEtB,CAAC,GAAc,EAAI,OACrB,KAAM,IAAI,OAAM,GAAG,gCAAqC,EAAI,yBAMhE,YAAY,EAAiC,GAC3C,MAAM,GACN,KAAK,OAAS,KAGL,SAAkB,MAAO,MAAK,SCrB3C,aAKE,YAAY,EAAe,GACzB,GAAM,MAAO,IAAU,SACrB,KAAM,IAAI,OAAM,sEAGlB,GAAI,CAAC,MAAM,QAAQ,IAAgB,EAAY,KAAK,AAAC,GAAS,CAAE,aAAgB,gBAC9E,KAAM,IAAI,OAAM,4FAGlB,KAAK,OAAS,EACd,KAAK,aAAe,KAGX,SAAkB,MAAO,MAAK,UAE9B,eAAgC,MAAO,MAAK,aAEhD,SACL,MAAO,CACL,MAAO,KAAK,MACZ,YAAa,KAAK,YAAY,IAAI,AAAC,GAAM,MAAM,KAAK,WAI1C,UAAS,GACrB,GAAM,GAAc,EAAK,YAAY,IAAI,AAAC,GAAW,GAAI,cAAa,IACtE,MAAO,IAAI,IAAuB,EAAK,MAAO,KC/BlD,oBAKkC,UAClB,2BAA0B,EAAU,GAGhD,GAFA,GAAW,wBAAwB,EAAK,GAGtC,CAAC,GAAmB,EAAI,QACrB,CAAC,GAAmB,EAAI,YAE3B,KAAM,IAAI,OAAM,GAAG,kCAAuC,EAAI,eAAe,EAAI,6CAQrF,YAAY,EAAiC,EAAe,EAAe,GACzE,MAAM,EAAK,GACX,KAAK,OAAS,EACd,KAAK,YAAc,KAGV,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,cCvBzC,YAA6B,GAClC,MAAO,GAAI,oBAAqB,GAG3B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,cCdf,cACL,GAAM,GAAQ,OAAO,MACrB,GAAI,CAAC,EAAO,KAAM,IAAI,OAAM,gEAE5B,GAAM,GAAW,KACf,KAAM,IAAI,OAAM,gEAGlB,MAAO,CACL,OAAQ,kBACR,yBACA,MAAO,iBACP,UACA,MAAO,iBACP,oBAAqB,IAAM,SAAS,cAAc,UAClD,mBAAoB,IAAM,SAAS,cAAc,OACjD,QACA,YCjBG,YAA0B,GAC/B,GAAI,GAAiB,GAErB,GAAI,CAAC,EACH,IAEE,EAAa,oBACN,GACP,EAAiB,EAAI,WAYzB,MAAO,CACL,SATe,EACb,AAAC,GAAqB,GAAI,SAAgB,CAAC,EAAS,KACpD,EAAG,SAAS,EAAU,CAAC,EAAU,IAAoB,EAAM,EAAO,GAAO,EAAQ,MAEjF,KACA,KAAM,IAAI,OAAM,qEAAqE,OCfpF,cAEL,GAAM,GAAS,OAAO,QAAa,OAAO,kBACpC,EAAQ,OAAO,OAAS,OAAO,iBAE/B,EAAsB,KAC1B,GAAI,EAAQ,MAAO,IAAI,GACvB,KAAM,IAAI,OAAM,+EAGZ,EAAqB,KACzB,GAAI,EAAO,MAAO,IAAI,GACtB,KAAM,IAAI,OAAM,6EAGZ,EAAQ,OAAO,MAGf,EAAa,KAEnB,MAAO,CACL,OAAQ,GAAU,QAClB,yBAA0B,OAAO,0BAA4B,QAC7D,MAAO,GAAS,QAChB,UAAW,OAAO,WAAa,QAC/B,MAAO,OAAO,kBAAoB,QAClC,sBACA,qBACA,WACG,GCjCA,cACL,MAAO,OAAO,SAAW,UACpB,MAAO,WAAa,aACpB,MAAO,mBAAqB,aAC5B,MAAO,oBAAsB,aAC7B,MAAO,mBAAqB,aAC5B,MAAO,YAAc,aACrB,MAAO,2BAA6B,YCH3C,OAAyB,QAGrB,EAEJ,cACE,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,yEAElB,MAAO,GAGT,YAAgB,GACd,EAAc,EAGhB,cAGE,MAAI,MAAoB,GAAO,MAC3B,cAAmB,GAAO,MACvB,KAGT,YAAqB,GAKnB,GAJK,GACH,KAGE,CAAC,EACH,KAAM,IAAI,OAAM,8EAGlB,GAAM,CAAE,SAAS,EAAY,OAAQ,QAAQ,EAAY,OAAU,EACnE,EAAY,OAAS,EACrB,EAAY,MAAQ,EACpB,EAAY,oBAAsB,EAAI,qBAAwB,KAAM,GAAI,IACxE,EAAY,mBAAqB,EAAI,oBAAuB,KAAM,GAAI,IAEtE,EAAY,UAAY,EAAI,WAAa,EAAY,UACrD,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,SAAW,EAAI,UAAY,EAAY,SAG9C,GAAM,GAAM,CACjB,UACA,UACA,cACA,oBACA,oBACA,mBACA,eACA,aACA,sBAGF,KC3DO,YAAsB,GAC3B,MAAI,CAAC,EAAI,YAAc,MAAO,IAAQ,SAC7B,SAAS,eAAe,GAE1B,ECHF,WAA6B,GAClC,GAAM,CAAE,SAAQ,4BAA6B,EAAI,SAEjD,GAAI,YAAqB,GACvB,MAAO,GAGT,GAAM,GAAS,GAAa,GAE5B,GAAI,CAAE,aAAkB,IACtB,KAAM,IAAI,OAAM,kEAGlB,GAAM,GAAM,EAAO,WAAW,MAC9B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,GCfF,GAAK,IAAL,UAAK,GAEV,WAAW,WAEX,YAAY,YAEZ,cAAc,cAEd,eAAe,iBARL,aANZ,aAuCE,YAAY,EAAiC,IAC3C,GAAM,CACJ,iBAAgB,kBAAiB,YAAW,WAAU,YAAW,WAC/D,EACJ,KAAK,eAAiB,GAAkB,GAAe,SACvD,KAAK,gBAAkB,GAAmB,qBAC1C,KAAK,UAAY,GAAa,yBAC9B,KAAK,SAAW,GAAY,GAC5B,KAAK,UAAY,GAAa,UAC9B,KAAK,QAAU,GAAW,IAhD9B,SA2DE,YACE,EACA,EACA,EAAiC,IAGjC,KAAK,KAAO,MAAO,IAAS,SACxB,CAAC,GACA,YAAgB,IAAgB,EAAK,KAAO,EACjD,KAAK,OAAS,EACd,KAAK,QAAU,GAAI,IAAqB,GAG1C,aAAa,GACX,GAAM,CAAE,WAAY,KAAK,QACzB,MAAO,MAAK,KAAK,IAAI,AAAC,GAAM,EAAI,YAAY,GAAG,OAAO,OAAO,CAAC,EAAI,IAAQ,EAAK,EAAK,EAAK,EAAK,GAAM,EAAI,EAG1G,gBACE,GAAM,CAAE,WAAU,WAAY,KAAK,QACnC,MAAO,MAAK,KAAK,OAAS,EAAY,EAAI,EAG5C,aAAa,EAA+B,GAC1C,GAAM,CAAE,kBAAmB,KAAK,QAC1B,EAAc,IAAmB,GAAe,cAAgB,IAAmB,GAAe,UAClG,EAAa,IAAmB,GAAe,aAAe,IAAmB,GAAe,aAEhG,EAAiB,KAAK,aAAa,GACnC,EAAkB,KAAK,gBACvB,EAAK,EAAc,KAAK,OAAO,EAAI,EAAiB,KAAK,OAAO,EAChE,EAAI,EAAa,KAAK,OAAO,EAAI,EAAkB,KAAK,OAAO,EAGrE,GAAI,GACF,GAAM,CAAE,QAAO,UAAW,EACpB,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAQ,GAAiB,GACrD,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAS,GAAkB,GAC7D,MAAO,CAAE,EAAG,EAAM,EAAG,GAEvB,MAAO,CAAE,IAAG,KAGd,KAAK,GACH,GAAM,GAAS,GAAa,GACtB,EAAM,EAAoB,GAE1B,CACJ,kBAAiB,YAAW,WAAU,YAAW,WAC/C,KAAK,QAET,EAAI,KAAO,GAAG,OAAc,IAC5B,GAAM,GAAe,KAAK,aAAa,GACjC,EAAa,KAAK,gBAExB,EAAI,UAAY,EAChB,GAAM,GAAY,KAAK,aAAa,EAAK,GACzC,EAAI,SAAS,EAAU,EAAG,EAAU,EAAG,EAAc,GAErD,EAAI,UAAY,EAChB,KAAK,KAAK,QAAQ,CAAC,EAAU,KAC3B,GAAM,GAAI,EAAU,EAAU,EACxB,EAAI,EAAU,EAAU,EAAM,GAAI,GAAK,EAC7C,EAAI,SAAS,EAAU,EAAG,OC1HhC,aAuBE,YAAY,EAA2B,IACrC,GAAM,CACJ,WAAU,YAAW,QAAO,oBAC1B,EACJ,KAAK,SAAW,GAAY,qBAC5B,KAAK,UAAY,GAAa,EAC9B,KAAK,MAAQ,EAEb,GAAM,GAA0B,CAC9B,eAAgB,GAAe,YAC/B,gBAAiB,KAAK,UAExB,KAAK,iBAAmB,GAAI,IAAqB,IAAK,KAA4B,MAnCtF,SA4CE,YACE,EACA,EAA2B,IAE3B,KAAK,IAAM,GAAI,GAAI,GACnB,KAAK,QAAU,GAAI,IAAe,GAGpC,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CAAE,WAAU,aAAc,KAAK,QAE/B,CACJ,IAAG,IAAG,QAAO,UACX,KAAK,IACT,EAAI,YAAc,EAClB,EAAI,UAAY,EAChB,EAAI,WAAW,EAAG,EAAG,EAAO,GAE5B,GAAM,CAAE,SAAU,KAAK,QACvB,AAAI,GACF,GAAI,IAAc,CAAC,GAAQ,CAAE,EAAG,EAAK,EAAY,EAAI,KAAK,KAAK,QAAQ,kBAAkB,KAAK,KC1D7F,YACL,EACA,GAIA,AAFwB,OAAM,QAAQ,GAAc,EAAa,CAAC,IAElD,QAAQ,AAAC,IAEvB,GAAM,GAAQ,YAAe,GACzB,EAAI,MACH,GAAoB,GAAO,EAAI,UAAU,MAAQ,OAGhD,EAAM,YAAe,GACvB,EAAI,IACH,GAAoB,GAAO,EAAI,UAAU,IAAM,GAAI,GAAI,GAEtD,EAAQ,EAAQ,GAAG,GAAM,KAAW,OAC1C,GAAI,IAAQ,EAAK,CAAE,UAAS,KAAK,KC1BrC,OAAoB,OCEb,YAAuB,GAC5B,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAQ,aAAiB,IAAS,EAAM,UAClC,YAAiB,IAAS,EAAM,YAAc,ECH/C,YAA0B,GAE/B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,GAAI,YAAiB,GAAI,SAAS,QAAU,GAAc,GACxD,MAAO,GAAQ,MAGjB,WAAiB,GACf,AAAI,CAAC,EAAE,eAEP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAO,IAGT,WAAgB,GACd,AAAI,CAAC,EAAE,eACP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAQ,IAGV,EAAM,iBAAiB,OAAQ,GAC/B,EAAM,iBAAiB,QAAS,KCxB7B,YAAuB,GAC5B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,AAAM,YAAe,OAAO,EAAO,GAAI,OAAM,qDAC7C,GAAM,GAAS,GAAI,YACnB,EAAO,OAAS,KACd,AAAI,MAAO,GAAO,QAAW,UAAU,EAAO,GAAI,OAAM,qEACxD,GAAM,GAAM,EAAI,SAAS,qBACzB,EAAI,OAAS,IAAM,EAAQ,GAC3B,EAAI,QAAU,EACd,EAAI,IAAM,EAAO,QAEnB,EAAO,QAAU,EACjB,EAAO,cAAc,KCXlB,YAA4B,GACjC,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAI,aAAiB,GACZ,GAAI,GAAW,EAAM,aAAc,EAAM,eAE9C,YAAiB,GACZ,GAAI,GAAW,EAAM,WAAY,EAAM,aAEzC,GAAI,GAAW,EAAM,MAAO,EAAM,QCNpC,YAAsB,CAAE,QAAO,WACpC,GAAM,CAAE,uBAAwB,EAAI,SAC9B,EAAS,IACf,SAAO,MAAQ,EACf,EAAO,OAAS,EACT,EAGF,YAA+B,EAAwD,GAC5F,GAAM,CAAE,aAAc,EAAI,SAE1B,GAAI,CAAE,aAAiB,KAAc,CAAC,GAAc,GAClD,KAAM,IAAI,OAAM,8DAGlB,GAAM,CAAE,QAAO,UAAW,GAAQ,GAAmB,GAC/C,EAAS,GAAa,CAAE,QAAO,WAErC,MAAI,aAAiB,GACnB,EAAoB,GAAQ,aAAa,EAAO,EAAG,GAEnD,EAAoB,GAAQ,UAAU,EAAO,EAAG,EAAG,EAAO,GAErD,EC7BT,OAAoB,OAKpB,kBACE,EACA,GAEA,GAAM,GAAe,GAAU,EAAI,SAAS,sBAEtC,CAAC,EAAQ,EAAO,GAAe,EAAU,MAAM,MAAM,EAAW,GAAa,EAAI,GACjF,EAAc,AAAG,QAAK,IAAM,EAAU,KAAK,EAAQ,EAAO,GAAa,SAC7E,YAAM,AAAG,YAAQ,SAAS,EAAa,GAEvC,EAAY,UAEL,ECfF,YAAwB,GAC7B,GAAM,CAAE,QAAO,SAAQ,SAAU,EAAI,SAErC,MAAO,aAAiB,IACnB,YAAiB,IACjB,YAAiB,GCPxB,MAAoB,OCKb,YAAuB,EAA6C,EAAmB,EAAuB,IACnH,GAAM,CAAE,QAAO,UAAW,EAAI,SAE9B,GAAI,CAAE,aAAiB,IAAS,YAAiB,IAC/C,KAAM,IAAI,OAAM,4EAGlB,GAAM,GAAO,GAAmB,GAC1B,EAAQ,EAAY,KAAK,IAAI,EAAK,OAAQ,EAAK,OAC/C,EAAQ,EAAQ,EAAK,MACrB,EAAS,EAAQ,EAAK,OAEtB,EAAe,GAAa,CAAE,MAAO,EAAW,OAAQ,IACxD,EAAc,YAAiB,GAAS,EAAQ,GAAsB,GAEtE,EAAS,KAAK,IAAI,EAAQ,GAAU,EACpC,EAAK,GAAe,EAAQ,EAAS,EAAS,EAC9C,EAAK,GAAe,EAAS,EAAQ,EAAS,EACpD,SAAoB,GAAc,UAAU,EAAa,EAAI,EAAI,EAAO,GAEjE,EDzBT,aAyBE,YACE,EACA,EAA6B,IAdvB,mBAAkD,GAElD,eAAiC,GAIjC,wBAA8B,GAE9B,sBAA+B,GAQrC,GAAI,CAAC,MAAM,QAAQ,GACjB,KAAM,IAAI,OAAM,4HAA4H,KAG9I,KAAK,mBAAqB,EAC1B,KAAK,WAAa,EAAO,OAEzB,EAAO,QAAQ,CAAC,EAAO,KACrB,GAAI,GAAW,IACb,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAO,EAAM,MACnC,OAGF,GAAI,EAAW,IACb,GAAM,GAAa,EAAc,MAAM,GACvC,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,yCAAyC,8CAG3D,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAQ,EAAc,MAAM,MAAM,GACxD,OAGF,GAAM,GAAU,YAAyB,GAAI,SAAS,OAAS,EAAQ,GAAsB,GAC7F,KAAK,UAAU,GAAO,EACtB,KAAK,iBAAiB,GAAO,CAAC,EAAO,OAAQ,EAAO,MAAO,QAIpD,gBACT,MAAO,MAAK,iBAGH,YACT,MAAO,MAAK,aAGH,gBACT,MAAO,MAAK,UAAY,GAAK,KAAK,sBAGzB,aACT,MAAO,MAAK,cAGH,mBACT,MAAO,MAAK,oBAGH,aACT,MAAO,MAAK,cAGH,2BACT,MAAO,IAAM,KAAK,UAAW,EAAG,GAAG,IACjC,CAAC,EAAG,IAAa,KAAK,2BAA2B,IAI9C,SAAS,GACd,MAAO,MAAK,SAAS,IAAa,KAAK,aAAa,GAG/C,mBAAmB,GACxB,MAAO,MAAK,iBAAiB,GAGxB,eAAe,GACpB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,cAAc,GACnB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,2BAA2B,GAChC,GAAI,MAAO,MAAK,WAAc,SAC5B,KAAM,IAAI,OAAM,yFAGlB,GAAM,GAAQ,KAAK,cAAc,GAC3B,EAAS,KAAK,eAAe,GACnC,MAAO,IAA0B,CAAE,QAAO,UAAU,KAAK,WAYpD,cAAc,EAAmB,EAA0B,IAChE,YAAK,WAAa,EAEX,AAAG,OAAK,KACb,GAAM,GAAe,GAAM,KAAK,UAAW,EAAG,GAAG,IAAI,AAAC,IACpD,GAAM,GAAQ,KAAK,SAAS,GAE5B,GAAI,YAAoB,WAEtB,GAAI,GAAY,EAAW,GAAS,EAAQ,EAAM,aAElD,SAAY,GAAY,EAAW,GAE/B,GAAU,MAAM,KAAO,GAAa,EAAU,MAAM,KAAO,IAC7D,GAAY,AAAG,QAAM,eAAe,EAAW,CAAC,EAAW,KAGtD,EAAU,KAAK,EAAW,EAAW,GAG9C,GAAI,YAAiB,GAAI,SAAS,OAChC,MAAO,AAAG,WAAQ,WAAW,GAAc,EAAO,EAAW,IAG/D,KAAM,IAAI,OAAM,+BAA+B,8FAAqG,OAOtJ,MAHoB,AAAG,SAAM,EAAa,IAAI,AAAC,GAAM,AAAG,OAAK,EAAG,aAAa,KAAK,KAAK,UAAW,EAAW,EAAW,OE3I9H,iBAAiC,GAC/B,GAAI,YAAkB,IACpB,MAAO,GAGT,GAAM,GAAgB,MAAM,QAAQ,GAChC,EACA,CAAC,GAEL,GAAI,CAAC,EAAc,OACjB,KAAM,IAAI,OAAM,4CAGlB,GAAM,GAAa,AAAC,GAAiB,MAAM,QAAQ,GAAU,mBAAmB,KAAS,GAEnF,EAAa,EAAc,IAAI,IAErC,SAAW,QAAQ,CAAC,EAAO,KACzB,GAAI,CAAC,GAAe,IAAU,CAAC,GAAW,IAAU,CAAC,EAAW,GAC9D,KAAI,OAAO,GAAc,IAAO,SACxB,GAAI,OAAM,eAAe,EAAW,sEAAsE,EAAc,MAG1H,GAAI,OAAM,eAAe,EAAW,iIAG5C,GAAI,EAAW,IAEb,GAAM,GAAY,EAAM,MAAM,GAC9B,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,eAAe,EAAW,iCAAiC,iDAMjF,KAAM,SAAQ,IACZ,EAAW,IAAI,AAAC,GAAU,GAAe,IAAU,GAAiB,KAG/D,GAAI,IAAS,EAAY,MAAM,QAAQ,ICtChD,kBACE,EACA,GAEA,GAAM,CAAE,UAAW,EAAI,SAEnB,EAAS,EAEb,GAAI,CAAE,aAAiB,KACrB,GAAM,GAAW,KAAM,GAAW,GAElC,GAAI,EAAS,UAAY,EACvB,KAAM,IAAI,OAAM,8CAGlB,GAAM,GAAiB,EAAS,SAAS,GACzC,EAAS,YAA0B,GAC/B,EACA,KAAM,IAAoB,GAGhC,GAAM,GAAM,EAAoB,GAQhC,MAAO,AAPO,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAO,MAAO,EAAO,QAAQ,IAAI,QAC7C,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAO,MAAO,EAAO,SAE/C,IAAI,CAAC,CAChB,IAAG,IAAG,QAAO,aAEb,GAAM,GAAU,GAAa,CAAE,QAAO,WACtC,SAAoB,GACjB,aAAa,EAAI,aAAa,EAAG,EAAG,EAAO,GAAS,EAAG,GACnD,ICnDX,OAAoB,OAgBpB,kBACE,EACA,GAEA,GAAI,CAAC,GAAW,IAAgB,CAAC,EAAW,GAC1C,KAAM,IAAI,OAAM,6DAGlB,GAAI,EAAW,IAAgB,EAAY,MAAM,GAAK,EACpD,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAW,EAAU,GAAe,EAAY,MAAM,MAAM,EAAW,GAAe,EAAI,GAajG,MAJoB,AAPN,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAU,GAAW,IACjC,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAU,IAEvB,IAAI,CAAC,CAC7B,IAAG,IAAG,QAAO,YACT,AAAG,WAAQ,EAAY,KAAK,EAAW,EAAU,GAAc,CAAC,EAAG,EAAG,GAAI,CAAC,EAAQ,EAAO,OCtCpG,kBACE,EAEA,GAEA,GAAM,CAAE,SAAU,EAAI,SAChB,EAAM,KAAM,GAAM,EAAK,GAC7B,GAAI,CAAE,GAAI,OAAS,KACjB,KAAM,IAAI,OAAM,qBAAqB,EAAI,WAAW,EAAI,yBAAyB,EAAI,OAEvF,MAAO,GCTT,kBAAiC,GAC/B,GAAM,GAAM,KAAM,IAAa,GACzB,EAAO,KAAO,GAAK,OAEzB,GAAI,CAAC,EAAK,KAAK,WAAW,UACxB,KAAM,IAAI,OAAM,wEAAwE,EAAK,kBAAkB,EAAI,OAErH,MAAO,IAAc,GCRvB,kBAAmC,GACjC,MAAQ,MAAM,IAAa,IAAM,OCDnC,kBAAsC,GACpC,MAAO,IAAI,cAAa,KAAO,MAAM,IAAa,IAAM,eCH1D,OAAoB,OCAb,YAAsB,EAAyB,GACpD,GAAM,GAA0B,GAAG,0BAEnC,GAAI,CAAC,EACH,MAAO,CACL,aAAc,GACd,YAAa,GAIjB,GAAI,IAAQ,IACV,MAAO,CACL,aAAc,IACd,YAAa,IAAI,KAIrB,GAAM,GAAW,EAAI,WAAW,WAAa,UAAY,EAAI,WAAW,YAAc,WAAa,GACnG,EAAM,EAAI,QAAQ,EAAU,IAE5B,GAAM,GAAQ,EAAI,MAAM,KAAK,OAAO,AAAC,GAAM,GAErC,EAAe,EAAI,SAAS,SAC9B,EAAM,EAAM,OAAS,GACrB,EAEA,EAAe,EAAY,GAAI,SAAS,SAAW,EAAM,MAAM,EAAG,EAAM,OAAS,GAAK,GAAO,KAAK,KACtG,SAAe,EAAI,WAAW,KAAO,IAAI,IAAiB,EAEnD,CACL,eACA,YAAa,IAAiB,IAAM,IAAI,IAAiB,GAAG,KAAgB,KD1BhF,kBACE,EACA,GAEA,GAAM,CAAE,cAAa,gBAAiB,GAAa,EAAK,GAClD,EAAW,KAAM,IAAuC,GAE9D,MAAO,AAAG,OAAG,YAAY,EAAU,GET9B,YAAyB,EAAoB,EAAwB,EAA8B,IACxG,GAAM,CAAE,QAAO,UAAW,EACtB,GAAmB,GACnB,EACJ,SAAM,MAAQ,EACd,EAAM,OAAS,EACR,CAAE,QAAO,UCTlB,OAAoB,OCApB,OAAoB,OAApB,YAQE,YAAY,GAIF,aAAkC,OAElC,oBAAiC,GALzC,KAAK,MAAQ,KASJ,UAAmC,MAAO,MAAK,WAE/C,iBAAkC,MAAO,MAAK,kBAE9C,YAAsB,MAAO,CAAC,CAAC,KAAK,OAExC,iBAAiB,GACtB,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,MAAO,GAAI,GAGN,sBAAsB,EAAmB,GAC9C,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,EAAI,GAAS,UACb,EAAI,GAAW,EAGV,eACL,MAAO,MAAK,eAAe,IAAI,CAAC,CAAE,eAAiB,EACjD,KAAM,EACN,OAAQ,KAAK,iBAAiB,MAI3B,qBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,EAAM,iBAAqB,cAGnE,kBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,CAAE,GAAM,iBAAqB,eAGrE,WACL,KAAK,kBAAkB,QAAQ,CAAC,CAAE,OAAM,aACtC,KAAK,sBAAsB,EAAM,EAAO,cAIrC,SACL,KAAK,qBAAqB,QAAQ,CAAC,CAAE,OAAM,OAAQ,MACjD,GAAM,GAAS,AAAG,UAAO,EAAS,YAClC,EAAS,UACT,KAAK,sBAAsB,EAAM,KAI9B,QAAQ,EAA4B,IACzC,KAAK,eAAe,QAAQ,AAAC,IAC3B,GAAI,GAAoB,EAAM,OAAO,WACnC,KAAM,IAAI,OAAM,mDAAmD,EAAM,QAE3E,EAAM,OAAO,YAEf,KAAK,QAAU,OAGV,kBACL,MAAO,IAAI,cACT,KAAK,eACF,IAAI,CAAC,CAAE,YAAa,MAAM,KAAK,EAAO,aACtC,OAAO,CAAC,EAAM,IAAQ,EAAK,OAAO,UAI5B,MAAK,GAChB,GAAI,YAAwB,eAC1B,KAAK,eAAe,GACpB,OAEF,KAAM,MAAK,YAAY,QAGZ,aAAY,GACvB,GAAI,GAAO,MAAO,IAAQ,SACxB,KAAM,IAAI,OAAM,GAAG,KAAK,0CAE1B,GAAM,GAAY,KAAM,IAAc,EAAK,KAAK,uBAChD,KAAK,kBAAkB,QAGZ,cAAa,GACxB,GAAI,GAAY,MAAO,IAAa,SAClC,KAAM,IAAI,OAAM,GAAG,KAAK,iDAE1B,GAAM,CAAE,YAAa,EAAI,SACnB,CAAE,cAAa,gBAAiB,GAAa,EAAU,KAAK,uBAC5D,EAAuB,AAAC,GAAwB,QAAQ,IAAI,EAAU,IAAI,AAAC,GAAO,EAAS,GAAI,KAAK,AAAC,GAAQ,EAAI,UACjH,EAAc,AAAG,MAAG,qBAAqB,GACzC,EAAW,KAAK,MAAO,MAAM,GAAS,IAAc,YACpD,EAAY,KAAM,GAAY,EAAU,GAC9C,KAAK,kBAAkB,GAGlB,kBAAkB,GACvB,GAAM,CAAE,gBAAe,UAAW,KAAK,2BAA2B,GAClE,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGV,eAAe,GACpB,GAAM,CAAE,gBAAe,UAAW,KAAK,cAAc,GACrD,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGT,qBAAqB,GAC3B,GAAI,CAAC,KAAK,OACR,KAAM,IAAI,OAAM,qDAGlB,GAAM,GAAS,EAAU,MAAM,KAAK,OAAO,CAAC,EAAoD,KAE9F,GAAI,CAAC,EAAI,QAAQ,eAAe,GAC9B,KAAM,IAAI,OAAM,wDAAwD,eAAqB,KAE/F,MAAO,CAAE,IAAK,EAAI,QAAS,UAAS,QAAS,EAAI,QAAQ,KACxD,CAAE,QAAS,KAAK,SAEb,CAAE,MAAK,WAAY,EACzB,GAAI,CAAC,GAAO,CAAC,GAAW,CAAE,GAAI,YAAuB,YACnD,KAAM,IAAI,OAAM,8DAA8D,KAGhF,MAAO,CAAE,MAAK,aC7IlB,MAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,iBAAkB,EAAO,iBAAkB,EAAQ,QAC1F,SAAM,AAAG,OAAI,EAAK,EAAO,MAClB,IDNJ,YACL,EACA,EACA,EAAwB,IAExB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,CAAC,EAAG,GAAI,QACrE,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,CAAC,EAAG,KAE7E,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,OAItC,YACL,EACA,EACA,EAAwB,GACxB,EAAuB,IAEvB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,GAAI,QAC5F,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,KAEpG,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAE/D,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,KACxC,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,QEpD1D,OAAoB,OAIb,YACL,EACA,EACA,EAA4B,OAC5B,EAAoB,IAEpB,MAAO,AAAG,SAAK,KACb,GAAM,GAAM,AAAG,OACb,AAAG,UAAO,EAAG,EAAO,QAAS,CAAC,EAAG,GAAI,GACrC,EAAO,MAGT,MAAO,GAAW,AAAG,QAAK,GAAO,ICd9B,WAAoC,EAAgB,GACzD,OAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,AAAK,EAAc,KAAK,AAAC,GAAO,EAAG,eAAiB,IAClD,EAAU,GAAM,YCLtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,EACA,KAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,SCzBtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,KAEA,GAAM,GAAa,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAY,IAChF,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CACL,QAAS,EACT,KAAM,ICvBZ,OAAoB,OCApB,aAsBE,YAES,EAEA,EAEA,GAJA,wBAEA,wBAEA,cDxBJ,YACL,EACA,GAEA,MAAO,CAAC,EAAoB,EAAqB,KAC/C,GAAM,GAAmB,AAAG,YAAS,EAAe,EAAI,EAAI,GAAa,CAAC,EAAG,EAAG,EAAY,IACtF,EAAmB,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAG,EAAG,EAAY,IAC5F,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,WAGX,GAAI,IACT,EACA,EACA,IAKC,YAEL,GAEA,MAAO,AAAC,KACN,GAAM,GAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,IAAI,IACT,EACA,EACA,IEpCC,WAAmC,EAAgB,GACxD,MAAO,CAAC,EAAsB,EAAmB,KAC/C,GAAM,GAAS,EAAU,GAEzB,GAAI,CAAC,GAAS,EAAQ,GACpB,KAAM,IAAI,OAAM,sBAAsB,oBAA+B,oBAA4B,KAGnG,SAAc,KACZ,CAAE,eAAc,UAAW,GAAc,IAGpC,GCfJ,WAA+B,GACpC,GAAI,GAAmB,EAEvB,WAAwB,GACtB,GAAM,GAAM,EAAiB,MAAM,EAAG,GACtC,SAAmB,EAAiB,MAAM,GACnC,EAGT,aACE,MAAO,GAGT,MAAO,CACL,iBACA,uBCPG,YAA2B,EAAwC,GACxE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,GAAQ,EACV,EAAkB,EAAY,EAAa,EAAG,GAAG,WACjD,EAA2B,EAAY,EAAa,GAAG,WACrD,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAChE,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,CAAE,QAAO,QAAO,SAAU,EAAyB,EAAY,EAAa,EAAc,GAC1F,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAC3C,EAAS,EAAyB,IAAK,IAAK,UAElD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CACN,SAAQ,SAAQ,SAAQ,WCvBvB,YAA+B,GACpC,MAAO,AAAC,KACN,GAAM,GAAU,EAAgC,GAAG,YAAkB,GAC/D,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,CAAE,UAAS,SCNf,YAA2B,EAAgB,GAChD,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBhBxBnB,oBAU0C,GACxC,cACE,MAAM,wBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,sDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAE/B,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,+BAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KiBlDzB,OAAoB,OCApB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,IAAM,AAAG,OACtB,AAAG,UAAO,EAAG,EAAO,SACpB,EAAO,OCPJ,YAAuB,EAAuB,EAAoB,GACvE,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAIpB,EAAK,AAFa,GAAuB,EAAgB,GAEpC,EAAY,EAAa,MAEpD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,OCdP,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,EAAgB,OAGtB,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,YAA4B,GACjC,GAAM,GAAyC,GACzC,EAAmC,GAEzC,cAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,GAAM,GAAM,EAAI,WAAW,MAAQ,EAAgB,EACnD,EAAI,GAAO,EAAU,KAGhB,CAAE,sBAAqB,iBJXhC,oBAkBU,GAGR,YAAY,EAAe,GACzB,MAAM,GACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBASP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EACJ,MAAO,IAAoB,EAAmB,KAAK,EAAmB,MAAM,GAAI,IAAK,EAAO,MAIzF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,EAAS,KAAK,0BAA2B,KAAK,4BAG3D,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAM,KAAK,0BACX,EAAO,KAAK,2BACZ,EAAwB,EAAO,EAAO,EAEtC,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KKnFjC,GAAM,IAAyB,CAAC,UAAW,QAAS,MAAO,QAAS,UAAW,YAAa,aAAnG,SAiBE,YAAY,GACV,GAAI,EAAc,SAAW,EAC3B,KAAM,IAAI,OAAM,8EAA8E,EAAc,UAG9G,GAAuB,QAAQ,CAAC,EAAY,KAC1C,KAAK,GAAc,EAAc,KAIrC,gBACE,MAAO,IACJ,IAAI,AAAC,GAAgB,EAAE,aAAY,YAAa,KAAK,MACrD,KAAK,CAAC,EAAI,IAAO,EAAG,YAAc,EAAG,e1C9B5C,oBAQuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGtB,aAAa,GAClB,MAAO,AAAG,SAAK,IAAM,AAAG,WAAQ,KAAK,OAAO,UAGjC,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,oBAAmB,GAC9B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAC9B,EAAsB,KAAM,SAAQ,IAAI,AAAG,WAAQ,GAAK,IAAI,KAAO,KACvE,GAAM,GAAO,KAAM,GAAE,OACrB,SAAE,UACK,KAET,EAAI,UAEJ,GAAM,GAAqB,EACxB,IAAI,AAAC,GAAiB,GAAI,IAAgB,IAE7C,MAAO,GAAS,aACZ,EACA,EAAmB,GAGf,sBACR,MAAO,wBAGC,0BACR,MAAO,KAGC,2BACR,MAAO,K2C1CJ,YAA+B,GACpC,MAAO,GAAI,sBAAuB,IAG7B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,gBCPf,YACL,EACA,EACA,EAAgB,GAChB,GAIA,AAF6B,OAAM,QAAQ,GAAmB,EAAkB,CAAC,IAE5D,QAAQ,AAAC,IAE5B,GAAM,GAAO,YAAa,IACtB,EACC,GAAsB,GAAK,EAAE,YAAc,OAChD,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mHAIlB,GAAM,GAAmB,AADV,EAAK,gBACY,OAAO,AAAC,GAAc,EAAU,YAAc,GAExE,EAAS,GAAoB,GAC/B,EAAE,UAAU,IAAI,WACf,GAAmB,GAAI,GAAM,EAAG,GAMrC,AAJsB,GAAI,IACxB,EAAiB,IAAI,AAAC,GAAc,GAAG,EAAU,eAAe,GAAM,EAAU,iBAChF,GAEY,KAAK,KCxBhB,YAA6B,GAClC,MAAO,IAAoB,IAEtB,EAAI,oBAAwB,IAE5B,EAAI,6BAAiC,IAErC,EAAI,sBAA0B,GAG9B,YAEoD,EAAoB,GAC7E,GAAM,CAAE,IAAK,GAAU,EAAU,UAC3B,EAAY,EAAmB,QAAwB,EAAM,EAAG,EAAM,GAEtE,EAAO,EAAU,QACjB,CAAE,aAAc,EAAU,UAC1B,EAAc,GAAI,GAAc,EAAU,UAAU,MAAO,EAAK,QAAQ,EAAU,WAAY,GAQpG,MAAO,IAAK,KANM,CAChB,YACA,qBACA,gBCpCJ,aA+BE,YAAY,EAAqC,IAC/C,GAAM,CACJ,YAAY,GAAM,aAAa,GAAM,YAAW,YAAW,YAAW,cACpE,EACJ,KAAK,UAAY,EACjB,KAAK,WAAa,EAClB,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,uBAC9B,KAAK,WAAa,GAAc,yBAxCpC,SAiDE,YACE,EACA,EAAqC,IAErC,KAAK,cAAgB,EACrB,KAAK,QAAU,GAAI,IAAyB,GAG9C,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CACJ,YAAW,aAAY,YAAW,YAAW,YAAW,cACtD,KAAK,QAcT,GAZI,GAAa,KAAK,wBAAyB,KAC7C,GAAI,YAAc,EAClB,EAAI,UAAY,EAChB,GAAY,EAAK,KAAK,cAAc,iBACpC,GAAY,EAAK,KAAK,cAAc,kBACpC,GAAY,EAAK,KAAK,cAAc,mBACpC,GAAY,EAAK,KAAK,cAAc,WACpC,GAAY,EAAK,KAAK,cAAc,aAAc,IAClD,GAAY,EAAK,KAAK,cAAc,cAAe,IACnD,GAAY,EAAK,KAAK,cAAc,WAAY,KAG9C,GACF,EAAI,YAAc,EAClB,EAAI,UAAY,EAEhB,GAAM,GAAY,AAAC,IACjB,EAAI,YACJ,EAAI,IAAI,EAAG,EAAG,EAAG,EAAG,EAAW,EAAG,EAAI,KAAK,IAC3C,EAAI,QAEN,KAAK,cAAc,UAAU,QAAQ,MAOpC,YACL,EACA,GAGA,AAD2B,OAAM,QAAQ,GAAiB,EAAgB,CAAC,IACxD,QAAQ,AAAC,IAE1B,GAAM,GAAY,YAAa,GAC3B,EACC,GAAoB,GAAK,EAAE,UAAY,OAC5C,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gIAGlB,GAAI,IAAkB,GAAW,KAAK,qBC1G1C,OAAoB,OCApB,MAAoB,OCKpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAqC,EAAoB,EAAqB,GAC5E,GAAM,GAAkB,EAA2B,EAAY,EAAa,GAAG,qBACzE,EAAkB,EAA2B,EAAa,EAAa,GAAG,qBAC1E,EAAiB,EAAkB,EAAY,EAAa,EAAG,GAAG,oBAExE,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,EAAkB,GAChD,GAAM,GAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBAE1E,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YAAuB,EAAuB,GACnD,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAgB,GAEhC,EAAqB,EAAkB,EAAG,GAAI,EAAG,sBACjD,EAA+B,EAA4B,GAAI,GAAI,gCACnE,EAA+B,EAA4B,GAAI,IAAK,gCAEpE,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,IAAK,0BAA0B,OAG3F,GAAM,GAA4B,EAA4B,IAAK,IAAK,6BAClE,EAA2B,EAA2B,IAAK,IAAK,4BAEhE,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,aAAY,cAAa,cCjEvC,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAqC,GACnC,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAiB,EAAkB,GAAG,oBAE5C,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,GAC9B,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAEtD,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAW,GAE3B,EAAqB,EAAkB,sBACvC,EAA+B,EAA4B,gCAC3D,EAA+B,EAA4B,gCAE3D,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,0BAA0B,OAGtF,GAAM,GAA4B,EAA4B,6BACxD,EAA2B,EAA2B,4BAEtD,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,SAA2B,EAAW,GAE/B,CAAE,OAAQ,CAAE,aAAY,cAAa,aAAa,iBFrE3D,YAAc,EAAgB,EAAoB,GAChD,MAAO,AAAG,OAAI,AAAG,SAAO,EAAG,EAAO,QAAS,EAAQ,QAAS,EAAO,MAGrE,YAAwB,EAAgB,EAA8B,EAA2B,IAC/F,GAAI,GAAM,EAAkB,AAAG,OAAK,GAAK,EACzC,SAAM,EAAuB,EAAK,EAAO,gBAAiB,CAAC,EAAG,IAC9D,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,AAAG,MAAI,EAAK,GAAK,EAAG,EAAO,eAAgB,CAAC,EAAG,KAC9C,EAGT,YAAmB,EAAgB,GACjC,GAAI,GAAM,EAAuB,AAAG,OAAK,GAAI,EAAO,gBAAiB,CAAC,EAAG,IACzE,SAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,MAAI,EAAK,GACX,EA7BT,oBAgCkC,GAGhC,YAAY,GACV,MAAM,gBACN,KAAK,eAAiB,EAGjB,aAAa,GAClB,GAAM,CAAE,UAAW,KACnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,8CAElB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAC7D,EAAM,AAAG,OAAK,GAAK,EAAY,EAAO,WAAW,QAAS,CAAC,EAAG,KAClE,SAAM,GAAe,EAAK,EAAO,WAAW,kBAAmB,IAC/D,EAAM,GAAe,EAAK,EAAO,WAAW,mBAC5C,GAAM,KAAK,eAAgB,EAAG,GAAG,QAAQ,AAAC,IACxC,EAAM,GAAU,EAAK,EAAO,YAAY,cAAc,QAExD,EAAM,GAAe,EAAK,EAAO,UAAU,iBAC3C,EAAM,AAAG,OAAK,EAAuB,EAAK,EAAO,UAAU,eAAgB,CAAC,EAAG,KACxE,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,sBAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,gBAG1C,cAAc,GACtB,MAAO,IAAc,EAAS,KAAK,kBGvEhC,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAkB,GAAuB,EAAgB,GAEzD,EAAM,EAAgB,IAAK,EAAG,UAC9B,EAAS,EAAgB,IAAK,EAAG,aAEvC,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,GAAI,CAAE,MAAK,YCflB,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,CACF,IAAK,EAAgB,UACrB,OAAQ,EAAgB,eAI5B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,GAAK,IAAL,UAAK,GAEV,SAAS,SAET,OAAO,SAJG,aNLZ,oBAakC,GAGhC,YAAY,EAAqC,GAAI,IAAa,IAChE,MAAM,gBACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBAGP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EAEE,EAAS,AAAG,WAAQ,EAAoB,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAAS,KAAK,EAAmB,MAAM,GAAI,IACnG,EAAM,GAAoB,EAAQ,EAAO,GAAG,KAAK,OACjD,EAAS,GAAoB,EAAQ,EAAO,GAAG,QACrD,MAAO,CAAE,MAAK,YAIX,aAAa,GAClB,MAAO,AAAG,SAAK,KACb,GAAM,CAAE,MAAK,UAAW,KAAK,OAAO,GACpC,MAAO,CAAE,MAAK,OAAQ,AAAG,WAAQ,WAIxB,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,qBAAoB,GAC/B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAE9B,EAAO,AAAG,WAAQ,EAAI,KACtB,EAAU,AAAG,WAAQ,EAAI,QACzB,EAAsB,EAAK,IAAI,CAAC,EAAW,IAAO,EACtD,YACA,aAAc,EAAQ,MAGlB,EAAqB,KAAM,SAAQ,IACvC,EAAoB,IAAI,MAAO,CAAE,YAAW,mBAC1C,GAAM,GAAO,MAAM,GAAU,QAAQ,GAC/B,EAAY,MAAM,GAAa,QAAQ,GACvC,EAAS,EAAW,GACpB,EAAS,EAAS,GAAO,KAAO,GAAO,OACvC,EAAoB,EAAS,EAAY,EAAI,EAEnD,SAAU,UACV,EAAa,UACN,CAAE,MAAK,SAAQ,wBAG1B,SAAI,IAAI,UACR,EAAI,OAAO,UAEJ,EAAS,aAAe,EAAiD,EAAmB,GAG3F,sBACR,MAAO,mBAGF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,GAGb,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAwB,IAAM,EAAI,EAAM,KAAM,EAAI,GAElD,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KOvHxC,MAAoB,OAApB,oBAYU,IACD,YAAY,EAAqB,EAAmB,GACzD,GAAM,GAAkB,EAAmB,IAAI,CAAC,CAAE,QAAO,aACvD,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,CACL,MAAO,EAAQ,EACf,OAAQ,EAAS,KAIf,EAAY,EAAgB,OAElC,MAAO,AAAG,QAAK,KACb,GAAM,GAA0B,CAAC,EAAe,IAAkB,AAAG,QAAM,CAAC,AAAG,OAAK,CAAC,IAAK,EAAO,WAAY,AAAG,OAAK,CAAC,IAAK,EAAO,YAAa,GAAG,KAAK,EAAG,KAAK,OAGzJ,EAAa,CAAC,EAAkB,KACpC,GAAM,CAAE,QAAO,UAAW,EAAgB,GAC1C,MAAO,GAAK,EAAO,GAAU,KAAK,IAAI,EAAQ,GAAU,EAAI,GAGxD,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GACvE,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GAa7E,MAXwB,GACrB,IAAI,AAAG,OAAK,CAAC,EAAW,KAAM,EAAW,YACzC,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAY,GACZ,EAAY,OAEb,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAgB,GAAU,MAC1B,EAAgB,GAAU,aAO3B,aAAa,GAClB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,KAAK,OAAO,GACxB,MAAO,MAAK,YACV,EACA,EAAM,UACN,EAAM,gBAAgB,IAAI,CAAC,CAAC,EAAQ,KAAY,EAAE,SAAQ,mBAKnD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,iBAAgB,GAC3B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAkB,AAAG,OACzB,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAAoB,KAAM,SAAQ,IAAI,EAAgB,IAC1D,MAAO,EAAgB,KACrB,GAAM,GAAiB,MAAM,KAAK,KAAM,GAAe,QACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,GAAO,IACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,CAAC,GAAO,IAExD,MAAO,IAAI,IACT,MAAM,IAAI,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,GAAI,GAAM,EAAQ,GAAc,EAAQ,KACxE,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,QAMtC,SAAgB,QAAQ,AAAC,GAAM,EAAE,WAE1B,EAAS,aAAe,EAAyC,EAAkB,GAGlF,2BACR,MAAO,OC9FX,oBAIuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGnB,sBACR,MAAO,yBAGC,0BACR,MAAO,OCdX,OAAoB,OCMb,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCnBZ,YAA2B,GAChC,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAEjD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,SAAQ,SAAQ,WF1B9B,oBAU8C,GAC5C,cACE,MAAM,4BAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,0DAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,GAAI,IAAK,CAAC,EAAG,GAAI,SAEjC,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,oCAGC,2BAA2B,GACnC,MAAO,IAA+B,GAG9B,cAAc,GACtB,MAAO,IAAkB,KGjD7B,oBAI2C,IACzC,YAAY,EAAiD,GAAI,KAC/D,MAAM,wBAAyB,GAGvB,sBACR,MAAO,8BAGC,0BACR,MAAO,OCdX,oBAIqC,MCJrC,MAAoB,OCApB,OAAoB,OCApB,OAAoB,OAIb,YAAe,EAAgB,GACpC,MAAO,AAAG,QAAI,AAAG,OAAI,EAAG,EAAO,SAAU,EAAO,QDAlD,YACE,EACA,EACA,EACA,EACA,EAA4B,QAE5B,GAAM,CAAE,UAAS,QAAS,EAAO,KAE7B,EAAM,AAAG,UAAO,EAAG,EAAS,EAAS,GACzC,SAAM,AAAG,OAAI,EAAK,GAClB,EAAM,GAAM,EAAK,EAAO,OACjB,EAAW,AAAG,QAAK,GAAO,EAG5B,YAAc,EAAgB,GACnC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAoB,EAAgB,GACzC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAkB,EAAgB,GACvC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,GAAM,SE7B5C,MAAoB,OAUpB,YAA2B,EAAwC,GACjE,WAA6B,EAAyB,EAAoB,GACxE,GAAM,GAAU,EAAe,GACzB,EAAQ,EAAQ,OAAU,GAAa,EAAa,GAE1D,GAAI,GAAQ,GACV,KAAM,IAAI,OAAM,+BAA+B,sBAA0B,EAAQ,uBAAuB,kBAA2B,KAGrI,MAAO,AAAG,QACR,IAAM,AAAG,YACP,AAAG,WAAS,EAAS,CAAC,EAAY,EAAO,EAAY,IACrD,CAAC,EAAG,EAAG,EAAG,KAKhB,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAU,EAAoB,EAAiB,EAAY,GAC3D,EAAO,AAAG,WAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,QAGpB,WAAiC,EAAoB,GACnD,GAAM,GAAU,AAAG,WAAS,EAAe,IACrC,EAAS,AAAG,WAAS,EAAe,IAE1C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,aAGX,CACL,UACA,UAIJ,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAO,EAAkB,EAAiB,EAAY,EAAY,GAAG,UACrE,EAAQ,EAAwB,EAAY,GAAG,WAErD,MAAO,CAAE,OAAM,SAGjB,WACE,EACA,EACA,EACA,EACA,EAAkB,IAElB,GAAM,GAAQ,EAAwB,GAAS,GAAM,GAAK,EAAiB,EAAY,EAAY,GAAG,WAChG,EAAQ,EAAuB,EAAiB,EAAY,EAAY,GAAG,WAEjF,MAAO,CAAE,QAAO,SAGlB,MAAO,CACL,yBACA,8BAIG,YAAuB,GAC5B,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAgB,GAEhC,EAAc,EAAuB,KAAM,GAAI,EAAG,eAClD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YAEnD,EAAc,EAA2B,MAAO,GAAI,EAAG,cAAe,IACtE,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YAEpD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aAEvD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAmB,EAA2B,OAAQ,IAAK,EAAG,oBAE9D,EAAK,AAAG,OACZ,IAAM,AAAG,YAAU,AAAG,WAAS,EAAe,IAAM,KAAM,CAAC,IAAK,MAAO,CAAC,EAAG,KAI7E,GAFA,EAAc,KAAK,CAAE,UAAW,OAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAsB1E,MAAO,CAAE,OAnBM,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGe,iBChJnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAiC,GAC/B,GAAM,GAAU,EAAmB,GAAG,kBAAwB,GACxD,EAAS,EAAmB,GAAG,iBAAuB,GAE5D,MAAO,CAAE,UAAS,UAGpB,WAAgC,GAC9B,GAAM,GAAU,EAAmB,GAAG,iBAAuB,GACvD,EAAO,EAAmB,GAAG,cAAoB,GACjD,EAAQ,EAAwB,GAEtC,MAAO,CAAE,KAAM,CAAE,UAAS,QAAQ,SAGpC,WAAoC,GAClC,MAAO,CACL,MAAO,EAAuB,GAAG,WACjC,MAAO,EAAuB,GAAG,YAIrC,MAAO,CACL,yBACA,8BAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAW,GAE3B,EAAc,EAAuB,eACrC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAc,EAA2B,eACzC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aAEvC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aACvC,EAAmB,EAA2B,oBAE9C,CAAE,MAAO,EAGf,GAFA,EAAc,KAAK,CAAE,aAAc,KAAM,UAAW,OAEhD,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yDAAyD,KAG3E,GAAM,GAAS,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGF,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBC9FnB,MAAoB,OAKb,YAAkB,EAAgB,GACvC,GAAI,GAAM,GAAK,EAAG,EAAO,OACzB,SAAM,GAAW,EAAK,EAAO,OAC7B,EAAM,AAAG,MAAI,EAAK,GAClB,EAAM,AAAG,OAAK,GACP,EAGF,YAAsB,EAAgB,GAC3C,GAAI,GAAM,GAAS,EAAG,EAAO,OAC7B,EAAM,GAAW,EAAK,EAAO,OAE7B,GAAI,GAAS,AAAG,UAAQ,EAAG,EAAG,EAAG,SAC3B,EAAQ,AAAG,QAAkB,EAAO,OACpC,EAAQ,EAAO,MAAM,KAAO,EAAI,MAAM,GAG5C,GAFsB,EAAO,MAAM,KAAO,EAAI,MAAM,IAAM,EAAO,MAAM,KAAO,EAAI,MAAM,IAGtF,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAE/B,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAGjC,SAAS,EAAQ,AAAG,SAAO,CAAC,EAAQ,GAAQ,GAAK,EACjD,EAAM,AAAG,MAAI,EAAQ,GAErB,EAAM,AAAG,OAAK,GACP,ELtCT,oBAWwC,GACtC,cACE,MAAM,sBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAGtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,GAAS,EAAY,EAAO,aACtC,EAAM,AAAG,UAAQ,EAAK,EAAG,EAAG,SAE5B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,aAC/B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAa,EAAK,EAAO,kBAE/B,GAAM,GAAY,EAAI,KAAK,CAAC,EAAG,IAG/B,MAFuB,AAAG,UAAO,EAAW,EAAO,WAM1C,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,uBAAsB,GA7DrC,MA8DI,GAAI,oBAAO,QAAP,cAAc,KAAK,AAAC,GAAQ,GAAO,GAAI,MAAO,IAAI,cAAa,KACnE,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAwB,AAAG,OAC/B,IAAM,AAAG,UAAQ,KAAK,aAAa,KAE/B,EAA0B,KAAM,SAAQ,IAAI,EAAsB,IAAI,AAAC,GAAM,EAAE,SACrF,SAAsB,QAAQ,AAAC,GAAM,EAAE,WAChC,EAAS,aAAe,EAA0B,EAAwB,GAGzE,sBACR,MAAO,yBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KM7ElB,YAAkC,GACvC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECHF,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,eCNf,YAAmB,GACxB,MAAO,OAAO,GAAI,KAAQ,SAGrB,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,QCNf,YAAsB,GAC3B,MAAQ,GAAI,SAAW,GAAO,MAAQ,EAAI,SAAW,GAAO,SACvD,GAAmB,EAAI,mBAGvB,YAGL,EACA,EACA,GAGA,MAAO,IAAK,KADM,CAAE,SAAQ,sBCpB9B,OAAoB,OCApB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,WAAoC,EAAqB,GACvD,GAAM,GAAU,AAAG,YAAS,EAAe,EAAI,EAAI,GAAc,CAAC,EAAG,EAAG,EAAa,IAC/E,EAAmB,AAAG,YAAS,EAAe,IAC9C,EAAoB,AAAG,YAAS,EAAe,IAC/C,EAAkB,AAAG,YAAS,EAAe,IAC7C,EAAsB,AAAG,YAAS,EAAe,IAEvD,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,uBAChB,CAAE,UAAW,GAAG,qBAChB,CAAE,UAAW,GAAG,0BAGX,CACL,UACA,mBACA,oBACA,kBACA,uBAIJ,WACE,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,KAAgB,EAAkB,oBAAsB,WAGnE,CAAE,UAAS,QAGpB,WACE,EACA,EACA,EACA,GAEA,GAAM,CACJ,UACA,QACE,EAAkB,EAAY,EAAa,EAAY,EAAc,IAEzE,MAAO,CACL,UACA,kBAAmB,GAIvB,WACE,EACA,EACA,GAEA,GAAM,GAAiB,EAA2B,EAAY,GAAG,oBAC3D,EAAiB,EAA2B,EAAY,EAAa,EAAG,GAAG,oBAEjF,MAAO,CAAE,iBAAgB,kBAG3B,aACE,GAAM,GAAS,EAA2B,EAAG,GAAI,EAAG,sBAC9C,EAAS,EAAsB,GAAI,GAAI,sBACvC,EAAS,EAAsB,GAAI,IAAK,sBACxC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,KAAM,uBAC3C,EAAU,EAAsB,KAAM,KAAM,uBAClD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,UACA,UACA,UACA,WAIJ,aACE,GAAM,GAAS,EAA2B,KAAM,IAAK,EAAG,2BAClD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,GAAI,EAAG,2BAChD,EAAS,EAA2B,GAAI,IAAK,EAAG,2BAChD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,EAAG,EAAG,oDACjD,EAA2B,EAAkB,KAAM,GAAI,EAAG,2DAC1D,EAAoB,EAAkB,KAAM,GAAI,EAAG,oDACnD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDA0BxD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,gBAjCsB,CACtB,uBAAwB,EACxB,gBAAiB,GAgCjB,gBA9BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA6BjB,gBA3BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA0BjB,gBAxBsB,CACtB,uBAAwB,GACxB,gBAAiB,IAuBjB,gBArBsB,CACtB,uBAAwB,EACxB,gBAAiB,IAoBjB,gBAlBsB,CACtB,uBAAwB,GACxB,gBAAiB,KAoBrB,MAAO,CACL,2BACA,gCAIG,YAAuB,GAC5B,GAAM,GAAgC,GAChC,CACJ,iBACA,uBACE,EAAsB,GACpB,CACJ,2BACA,gCACE,GAAkB,EAAgB,GAChC,EAAc,IACd,EAAmB,IAKnB,EAAe,CACnB,UALgB,AAAG,YACnB,EAAe,KAAO,GACtB,CAAC,EAAG,KAAM,KAMZ,GADA,EAAc,KAAK,CAAE,UAAW,2BAC5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,OAAQ,CACN,cACA,mBACA,gBAEF,iBC9MJ,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAoC,EAAgB,EAAa,GAC/D,GAAM,GAAU,EAAmB,GAAG,YAAiB,sBAAyB,EAAG,GAAG,aAChF,EAAoB,EAAmB,GAAG,YAAiB,oCAAuC,EAAG,GAAG,uBAC9G,MAAO,CAAE,UAAS,qBAGpB,WAA+B,GAC7B,GAAM,GAAe,oBAAoB,IACnC,EAAsB,sBAAsB,cAC5C,EAA4B,GAAG,mBAC/B,EAA4B,GAAG,mBAE/B,EAAU,EAAmB,GAAG,sBAAyC,EAAG,GAAG,aAC/E,EAAmB,EAAmB,GAAG,oBAAuC,EAAG,GAAG,sBACtF,EAAoB,EAAmB,GAAG,mBAAsC,EAAG,GAAG,uBACtF,EAAkB,EAAmB,GAAG,0BAA6C,EAAG,GAAG,qBAC3F,EAAsB,EAAmB,GAAG,8BAAiD,EAAG,GAAG,yBAEzG,MAAO,CACL,eAAgB,CACd,UACA,mBACA,oBACA,kBACA,uBAEF,eAAgB,EAA2B,cAAe,EAAK,IAInE,aACE,MAAO,CACL,OAAQ,EAA2B,cAAe,EAAG,sBACrD,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,KAInC,WAA2B,EAAgB,GACzC,GAAM,GAAU,EAAmB,GAAG,YAAkB,EAAG,GAAG,aACxD,EAAO,EAAmB,GAAG,WAAiB,EAAG,GAAG,UAC1D,MAAO,CAAE,UAAS,QAGpB,WAAmC,GACjC,GAAM,GAAyB,EAC7B,2BAA2B,yBAC3B,kCAAkC,4BAE9B,EAAkB,EACtB,2BAA2B,mBAC3B,kCAAkC,qBAEpC,MAAO,CAAE,yBAAwB,mBAGnC,aACE,MAAO,CACL,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,IAI/C,MAAO,CACL,2BACA,gCAIG,YACL,GAEA,GAAM,GAAgC,GAChC,CACJ,2BACA,gCACE,GAAkB,EAAW,GAC3B,EAAY,EAAU,oBAE5B,GADA,EAAc,KAAK,CAAE,aAAc,mBAAoB,UAAW,2BAC9D,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yEAAyE,KAG3F,GAAM,GAAS,CACb,YAAa,IACb,iBAAkB,IAClB,aAAc,CACZ,cAIJ,SAA2B,EAAW,GAC/B,CAAE,SAAQ,iBChInB,OAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,UAAO,EAAG,EAAO,QAAS,EAAS,QAChD,SAAM,AAAG,OAAI,EAAK,EAAO,mBAClB,AAAG,eAAY,EAAK,EAAG,KDPlC,GAAM,IAAU,qBAEhB,YACE,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,QAAS,EAAS,QACzD,SAAM,AAAG,aACP,EACA,EAAO,gBACP,EAAO,oBACP,EAAO,kBACP,EAAO,iBACP,IAEK,AAAG,eAAY,EAAK,EAAG,KAIlC,YAA+B,GAC7B,MAAO,CAAC,EAAG,EAAG,EAAG,IAAI,KAAK,AAAC,GAAQ,IAAQ,GAAY,CAAC,EAAG,GAAK,CAAC,EAAG,GAG/D,YAAqB,EAAgB,GAC1C,MAAO,AAAG,SAAK,KACb,GAAI,GACA,EAAM,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IA4BnD,GAVA,AAhBuB,CACrB,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,QACP,EAAO,QACP,EAAO,QACP,EAAO,SAGM,QAAQ,CAAC,EAAO,KAC7B,GAAM,GAAW,EAAI,EACf,EAAuB,GAAsB,GACnD,EAAM,GAAmB,EAAK,EAAM,eAAgB,GACpD,EAAM,EAAmB,EAAK,EAAM,eAAgB,CAAC,EAAG,IACpD,IAAa,IACf,GAAS,KAIT,IAAW,KACb,KAAM,IAAI,OAAM,iDAGlB,MAAO,CACL,MACA,OAAQ,KEjEd,YAAa,EAAoB,EAAW,GAC1C,GAAM,GAAY,EAAM,YAClB,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAS,GAAQ,GAAU,GAAQ,GACnC,EAAS,GAAQ,GAAU,GAAQ,GACzC,GAAI,GAAS,GAAK,GAAS,EACzB,MAAO,GAET,GAAM,GAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAmB,EAAkB,GACjE,KAAK,IAAI,EAAmB,EAAkB,GACpD,MAAO,GAAoB,GAAQ,EAAQ,GAGtC,YACL,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAW,EAAM,MAAM,GACvB,EAAa,KAAK,IACtB,EACA,GAGI,EAAa,EAChB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,OAAO,AAAC,GAAM,EAAE,MAAQ,GACxB,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAE5B,EAAe,AAAC,GAAe,GAAK,EAAe,EAAI,EACvD,EAAqB,GAE3B,SAAW,QAAQ,AAAC,IAClB,GAAI,EAAS,QAAU,EAAY,OACnC,GAAM,GAAgB,EAAE,MACxB,OAAS,GAAI,EAAS,OAAS,EAAG,GAAK,EAAG,EAAE,GAC1C,GAAM,GAAM,GAAI,EAAO,EAAE,SAAU,EAAS,IAC5C,GAAI,IAAQ,GACZ,GAAE,OAAS,EAAa,GACpB,EAAE,OAAS,GAAgB,MAEjC,AAAI,IAAkB,EAAE,OACtB,EAAS,KAAK,EAAE,YAGb,EC5DT,MAAoB,OAIpB,YAA2C,GACzC,GAAM,GAAM,AAAG,UAAQ,AAAG,YAAU,EAAG,CAAC,EAAG,KAErC,EAAQ,CACZ,AAAG,MAAI,EAAI,GAAI,EAAI,IACnB,AAAG,MAAI,EAAI,GAAI,EAAI,KAEf,EAAU,CACd,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,KAC1C,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,MAE5C,MAAO,CACL,QACA,WAIJ,YAA0B,EAAiB,GACzC,GAAM,CACJ,QACA,WACE,GAAkC,GAEhC,EAAM,AAAG,UAAQ,AAAG,YAAU,EAAI,CAAC,EAAG,KACtC,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAC3E,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAEjF,MAAO,AAAG,aACR,AAAG,QAAM,CACP,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,KAEnB,CAAC,EAAG,IAID,YACL,EACA,EACA,GAEA,MAAO,AAAG,QAAK,KACb,GAAM,GAAY,EAAe,MAAM,GAEnC,EAAQ,GACV,AAAG,UAAQ,AAAG,OAAK,EAAO,UAAW,CAAC,EAAW,EAAG,IAAK,CAAC,GAAI,IAC9D,AAAG,UAAQ,EAAgB,CAAC,GAAI,KAElC,EAAQ,AAAG,UACT,EACA,CAAC,EAAY,EAAM,MAAM,GAAK,EAAY,IAG5C,GAAM,GAAmB,AAAG,UAAQ,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,MAC/E,EAAS,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,IAE5D,EAAS,AAAG,UACV,EACA,CAAC,EAAW,EAAO,MAAM,KAG3B,GAAM,GAAe,AAAG,UAAQ,GAC1B,EAAgB,AAAG,UAAQ,GAEjC,MAAO,CACL,MAAO,EACP,OAAQ,KC1Ed,OAAoB,OCApB,OAAoB,OAKb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAY,EAAE,MAAM,GACpB,EAAwB,AAAG,WAC/B,GAAU,EAAG,EAAO,wBACpB,CAAC,EAAW,GAAI,EAAG,IAEf,EAAkB,AAAG,WACzB,GAAU,EAAG,EAAO,iBACpB,CAAC,EAAW,GAAI,IAElB,MAAO,CAAE,wBAAuB,qBDb7B,YACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAQ,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IACjD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IAErD,EAAiB,GAAmB,EAAQ,EAAO,iBACnD,EAAiB,GAAmB,EAAG,EAAO,iBAC9C,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAElD,EAAiB,AAAG,UAAO,CAC/B,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,uBACd,GAEG,EAAmB,AAAG,UAAO,CACjC,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,iBACd,GAEH,MAAO,CACL,iBACA,sBEhDN,YAYE,YAAY,CAAE,gBAAe,cAAuC,IAN1D,WAAgB,wBAUxB,GAHA,KAAK,eAAiB,GAAiB,GACvC,KAAK,YAAc,GAAc,IAE7B,MAAO,MAAK,gBAAmB,UAAY,KAAK,gBAAkB,GAAK,KAAK,gBAAkB,EAChG,KAAM,IAAI,OAAM,GAAG,KAAK,iEAG1B,GAAI,MAAO,MAAK,aAAgB,SAC9B,KAAM,IAAI,OAAM,GAAG,KAAK,iDAIxB,iBAA0B,MAAO,MAAK,kBAEtC,cAAuB,MAAO,MAAK,cT3BzC,oBAeoC,GAClC,cACE,MAAM,kBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAQ,WACvD,EAAI,AAAG,OAAI,AAAG,OAAI,EAAa,AAAG,UAAO,sBAAwB,AAAG,UAAO,IAC3E,EAAW,GAAY,EAAG,EAAO,aAEjC,CACJ,iBACA,oBACE,GAAgB,EAAS,IAAK,EAAS,OAAQ,EAAO,kBAE1D,MAAO,IAAY,EAAgB,EAAkB,EAAO,qBAInD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,aACX,EACA,EAAkC,IAElC,GAAM,CAAE,aAAY,iBAAkB,GAAI,GAAsB,GAE1D,EAAW,KAAM,GAAW,GAE5B,CACJ,MAAO,EACP,OAAQ,GACN,KAAK,aAAa,GAEhB,EAAQ,EAAO,GACf,EAAS,EAAQ,GACvB,OAAS,GAAI,EAAG,EAAI,EAAO,OAAQ,IACjC,EAAO,GAAG,UACV,EAAQ,GAAG,UAGb,GAAM,GAAa,MAAM,KAAK,KAAM,GAAO,QAErC,EAAU,GACd,EACA,EACA,EAJmB,GAMnB,GAGI,EAAe,EAAS,2BAA2B,GACnD,EAAY,EAAS,UACrB,EAAO,EAAY,EAAa,MAChC,EAAO,EAAY,EAAa,OAEhC,EAAY,EAAM,YAClB,EAAU,EACb,IAAI,AAAC,IACJ,GAAM,CAAC,EAAK,GAAU,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACf,CAAC,GAAM,IAAS,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACrB,MAAO,IAAI,GACT,EAAW,GACX,GAAI,IACF,GACA,EACA,GAAQ,GACR,EAAS,GAEX,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,OAKtC,SAAM,UACN,EAAO,UACA,EAGC,sBACR,MAAO,wBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KUnHlB,YAA8B,GACnC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,EAGF,YAAgC,GACrC,MAAO,IAAqB,GAZ9B,oBAgBsC,MCd/B,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,QAAU,SACpB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,OAAQ,SAClB,GAAI,GAAM,QAAS,UAGR,GAAwB,CACnC,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAA+C,CAAC,QAAS,QAAS,QAElE,GAAqB,oBACrB,GAAoC,mCCvBjD,MAAoB,OCapB,GAAM,IAAW,AAAC,GAAa,MAAO,IAAQ,SAEvC,YAAwB,GAC7B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mBAAmB,KAGrC,GAAI,MAAO,GAAO,oBAAuB,UACvC,KAAM,IAAI,OAAM,wDAAwD,EAAO,sBAGjF,GAAI,CAAC,GAAS,EAAO,eAAiB,EAAO,aAAe,GAAK,EAAO,aAAe,EACrF,KAAM,IAAI,OAAM,gEAAgE,EAAO,gBAGzF,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,MAAM,AAAC,GAAW,MAAO,IAAM,UAElD,KAAM,IAAI,OAAM,kEAAkE,KAAK,UAAU,EAAO,YAG1G,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,IAAI,AAAC,GAAW,GAAK,IAAI,MAAM,AAAC,GAAW,GAAS,EAAE,IAAM,GAAS,EAAE,IAE1F,KAAM,IAAI,OAAM,wEAAwE,KAAK,UAAU,EAAO,YAGhH,GAAI,EAAO,SACT,EAAC,MAAM,QAAQ,EAAO,UACnB,EAAO,QAAQ,SAAW,GAC1B,CAAC,EAAO,QAAQ,MAAM,KAEzB,KAAM,IAAI,OAAM,8EAA8E,KAAK,UAAU,EAAO,YCjDxH,MAAoB,OCApB,MAAoB,OAEb,YAAe,GACpB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,AAAG,MAAI,EAAG,AAAG,SAAO,qBAChC,MAAO,AAAG,OAAI,AAAG,OAAK,AAAG,MAAI,EAAG,IAAO,KDApC,YAA2B,EAAgB,GAChD,MAAO,AAAG,QAAK,KACb,GAAI,GAAM,AAAG,MAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KACjD,SAAM,AAAG,SAAO,EAAK,EAAO,KAAK,QAAS,CAAC,EAAG,GAAI,SAClD,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,KAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,SAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,KAAK,MACvB,GAAM,KEZjB,OAAoB,OAKb,YAAgC,EAAgB,GACrD,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,OAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KACjD,SAAM,AAAG,mBAAgB,EAAK,EAAO,iBAAkB,EAAO,iBAAkB,CAAC,EAAG,GAAI,SACxF,EAAM,AAAG,OAAI,EAAK,EAAO,MAClB,GAAM,KCVjB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAEnE,WAAgC,EAAc,GAC5C,GAAM,GAAM,AAAG,YAAS,EAAe,IACjC,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,SAChB,CAAE,UAAW,GAAG,cAEX,CAAE,MAAK,WAGhB,WAAwC,EAAoB,EAAqB,GAC/E,GAAM,GAAO,EAAkB,EAAY,EAAa,EAAG,GAAG,UACxD,EAAK,EAAuB,EAAa,GAAG,QAClD,MAAO,CAAE,OAAM,MAEjB,GAAM,GAA6B,GAAkC,EAAgB,GAErF,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,EACA,EACA,GAEA,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAChC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAgB,GAClC,EAEJ,GAAI,EAAO,oBACT,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAAO,mBACjB,EAAkB,EAAI,EAAI,EAAG,SAC7B,EAA2B,EAAI,EAAI,SACjC,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAkB,GAAM,GAAM,EAAI,EAAI,EAAiB,EAAG,SACxE,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,eAG1D,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAAkB,EAAI,EAAI,EAAiB,EAAG,SAC5D,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,UAG5D,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAE1E,MAAO,CAAE,SAAQ,iBChFnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAgC,GAC9B,GAAM,GAAM,EAAmB,GAAG,QAAc,GAC1C,EAAU,EAAmB,GAAG,YAAkB,GACxD,MAAO,CAAE,MAAK,WAGhB,WAA2B,GACzB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,WAAwC,GACtC,GAAM,GAAO,EAAkB,GAAG,UAC5B,EAAK,EAAuB,GAAG,QACrC,MAAO,CAAE,OAAM,MAGjB,GAAM,GAA6B,GAA+B,GAClE,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAW,GAE7B,EAEJ,GAAI,EAAO,oBAET,GAAM,GAAc,EAAO,aAAe,EAAO,YAAY,QAAU,EACvE,EAAS,CACP,MAAO,EAAO,mBAAqB,EAAkB,SAAW,EAA2B,SAC3F,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAkB,cAG3B,GAAS,CACP,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAAkB,UAI7B,SAA2B,EAAW,GAC/B,CAAE,SAAQ,iBClFnB,aAYE,YAAY,CAAE,YAAW,kBAAuC,IANtD,WAAgB,oBAUxB,GAHA,KAAK,WAAa,GAAa,IAC/B,KAAK,gBAAkB,GAAkB,GAErC,MAAO,MAAK,YAAe,UAAY,KAAK,WAAa,IAAO,EAClE,KAAM,IAAI,OAAM,GAAG,KAAK,6DAG1B,GAAI,MAAO,MAAK,iBAAoB,UAAY,KAAK,iBAAmB,GAAK,KAAK,iBAAmB,EACnG,KAAM,IAAI,OAAM,GAAG,KAAK,qEAIxB,aAAsB,MAAO,MAAK,cAElC,kBAA2B,MAAO,MAAK,kBP3B7C,oBAuBoC,GAKlC,YAAY,GACV,MAAM,cACN,GAAe,GACf,KAAK,QAAU,KAGN,UACT,MAAO,MAAK,WAGH,mBACT,MAAO,MAAK,OAAO,iBAAmB,KAAK,OAAO,QAAQ,OAAS,KAG1D,mBACT,MAAO,GAAK,MAAK,gBAAkB,KAAK,OAAO,QAAQ,OAAS,GAG3D,cAAc,EAAgB,GACnC,GAAI,GAAM,GAAkB,EAAG,EAAO,OACtC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,GAAkB,EAAK,EAAO,OAC7B,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAgB,GAClC,GAAI,GAAM,KAAK,OAAO,mBAClB,GAAM,GAAU,EAAG,EAAO,MAAqB,QAAS,KACxD,GAAuB,EAAG,EAAO,OACrC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EACjE,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EAC1D,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAiB,GACnC,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,4CAGlB,MAAO,AAAG,QAAK,KACb,GAAI,GAAc,AAAG,OAAK,EAAM,cAAc,EAAW,IAAQ,WACjE,SAAc,KAAK,OAAO,QACtB,GAAU,EAAa,KAAK,OAAO,SACnC,EACJ,EAAc,EAAY,IAAI,AAAG,SAAO,MACjC,KAAK,OAAO,mBACf,KAAK,aAAa,EAAa,GAC/B,KAAK,cAAc,EAAa,UAI3B,SAAQ,EAAkB,GACrC,MAAO,MAAK,aAAa,KAAM,GAAW,GAAQ,QAGvC,QAAO,EAAkB,EAAoC,IACxE,GAAM,CAAE,YAAW,kBAAmB,GAAI,IAAkB,GACtD,EAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,EAAU,GACxC,EAAO,AAAG,OAAK,IAAM,AAAG,UAAQ,GAAK,GAAG,cACxC,EAAkB,CACtB,MAAO,EAAS,cAAc,GAC9B,OAAQ,EAAS,eAAe,IAG5B,EAAU,KAAM,MAAK,aAAa,EAAM,EAAS,2BAA2B,GAAI,GACtF,EAAI,UACJ,EAAK,UAEL,GAAM,GAAQ,EAAQ,IAAI,AAAC,GAAQ,EAAI,KACjC,EAAS,EAAQ,IAAI,AAAC,GAAQ,EAAI,OAClC,EAAc,EAAQ,IAAI,AAAC,GAAQ,EAAI,YACvC,EAAa,EAAQ,IAAI,AAAC,GAAQ,KAAK,OAAO,QAAQ,EAAI,QAgBhE,MAPmB,AAPH,IACd,EAAM,IAAI,AAAC,GAAQ,EAAI,QAAQ,IAC/B,EACA,KAAK,OAAO,aACZ,IAGyB,IAAI,AAAC,GAAQ,GAAI,IAC1C,EAAO,GACP,EAAY,GACZ,EAAW,GACX,EAAM,GACN,IAKM,sBACR,MAAO,GAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,QAG1C,cAAc,GACtB,GAAM,GAAc,KAAK,OAAO,aAAe,GAAe,qBAExD,EAAa,EAAc,EAAY,OAAS,OACtD,GAAI,IAAe,GAAK,IAAe,GAAK,IAAe,EACzD,KAAM,IAAI,OAAM,oEAAoE,2BAEtF,MAAO,IAAc,EAAS,KAAK,OAAQ,KAAK,gBAAiB,QAGnD,cACd,EACA,EACA,GAEA,GAAM,CAAE,QAAO,UAAW,EACpB,EAAY,KAAK,IAAI,EAAO,GAC5B,EAAoB,EAAY,EAChC,EAAoB,EAAY,EAEhC,EAAW,EAAa,MAAM,GAC9B,EAAW,KAAK,OAAO,QAAQ,OAE/B,CAAC,EAAa,EAAc,GAAqB,AAAG,OAAK,KAC7D,GAAM,GAAW,EAAa,QAAQ,CAAC,EAAU,EAAU,EAAU,KAAK,kBAEpE,EAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACpE,EAAS,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACrE,EAAc,KAAK,gBACrB,AAAG,UAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,KAAK,OAAO,QAAQ,SAAU,GACrG,AAAG,SAAO,GACd,MAAO,CAAC,EAAO,EAAQ,KAGnB,EAAU,GACV,EAAa,KAAM,GAAa,QAChC,EAAY,KAAM,GAAY,QACpC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAS,EAAG,EAAS,EAAU,KACtC,GAAM,GAAQ,GAAQ,EAAW,GAAK,GAAK,GAAQ,IACnD,GAAI,CAAC,GAAkB,EAAQ,GAC7B,GAAM,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAe,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACvG,EAAgB,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACxG,GAAK,EAAO,GAAa,EACzB,GAAK,GAAO,EAAc,EAC1B,GAAM,CAAE,MAAK,MAAK,UAClB,CAAE,cAAY,UAAU,KAAK,gBAC/B,KAAM,MAAK,sBAAsB,EAAkC,IACnE,CAAE,WAAY,EAAG,MAAO,GAC5B,EAAQ,KAAK,CACX,IAAK,GAAI,IAAY,GAAG,GAAG,GAAI,GAAY,GAAI,GAC/C,QACA,WAAY,EAAQ,GACpB,YACG,MAOb,SAAY,UACZ,EAAa,UACb,EAAkB,UACX,OAGK,uBAAsB,EAA4B,GAC9D,GAAM,CAAE,MAAK,MAAK,UAAW,EACvB,EAAc,KAAM,GAAc,QACxC,MAAO,OAAM,KAAK,OAAO,QAAQ,QAAQ,KAAK,GAC3C,IAAI,CAAC,EAAG,IAAM,EAAY,GAAK,GAAK,GAAQ,IAC5C,IAAI,CAAC,EAAY,IAAW,EAC3B,aACA,WAED,OAAO,CAAC,EAAK,IAAU,EAAI,WAAa,EAAK,WAAa,EAAM,KAtOvE,MAwBgB,AAxBhB,GAwBgB,qBAAuB,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,IAAK,KAAM,MQxB5E,oBAiBgC,IAC9B,YAAY,EAA8B,IACxC,GAAM,GAAS,CACb,qBACA,aAAc,GACd,QAAS,CAAC,WACN,EACA,CACA,QAAS,GACT,QAAS,IAET,CACA,QAAS,GACT,gBAAiB,KAIvB,MAAM,MAGG,sBACT,MAAO,MAAK,OAAO,sBAGV,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,MAAK,mBAAqB,GAAoC,GAG7D,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KChDrC,YAA0B,EAAuB,EAA8B,IACpF,GAAM,GAAM,GAAI,IAAW,GAC3B,SAAI,eAAe,GACZ,ECVT,oBAI6C,IAJ7C,kCAKY,WAAgB,4BCL5B,kBACe,MAEX,GAEA,MAAO,GAAY,KAAM,MAAK,YAGnB,OACX,KAAM,IAAI,OAAM,6CCRpB,OAAoB,OCDpB,OAAoB,OAOpB,kBACE,EACA,EAEA,EACA,EAEA,EAAwF,CAAC,CAAE,iBAAkB,GAE7G,GAAM,GAAY,EAAc,IAAI,AAAC,GAAkB,GAAoB,GACvE,EAAoB,GACpB,EAAa,WACX,EAAgD,GACpD,aAAoB,WAChB,KAAM,IAAmB,EAAO,GAChC,KAAM,IAAa,EAAO,IAG1B,EAAU,KAAM,GAAe,GAErC,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAGT,kBACE,EACA,EAEA,EACA,EAEA,GAEA,MAAO,IACL,CAAC,GACD,EACA,KAAO,IAAU,EAAc,EAAM,IACrC,EACA,GC5CG,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAAqC,CAAC,QAAS,QAAS,QCZrE,oBAUsC,IACpC,cACE,GAAM,GAAS,CACb,mBAAoB,GACpB,aAAc,GACd,QAAS,CAAC,QACV,QAAS,GACT,QAAS,GACT,mBAAoB,GACpB,YAAa,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,MAGzC,MAAM,MAGG,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,2BAGC,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KCvBrC,GAAM,GAAO,CAClB,eAAgB,GAAI,IACpB,iBAAkB,GAAI,IACtB,WAAY,GAAI,IAChB,kBAAmB,GAAI,IACvB,sBAAuB,GAAI,IAC3B,mBAAoB,GAAI,IACxB,kBAAmB,GAAI,IACvB,aAAc,GAAI,KAUP,GAAiB,CAAC,EAAkB,IAA6D,EAAK,eAAe,YAAY,EAAO,GASxI,GAAmB,CAAC,EAAkB,IAA+D,EAAK,iBAAiB,YAAY,EAAO,GAS9I,GAAa,CAAC,EAAkB,IAA0D,EAAK,WAAW,YAAY,EAAO,GAS7H,GAAsB,AAAC,GAAmE,EAAK,kBAAkB,gBAAgB,GAWjI,GAA0B,AAAC,GAAmE,EAAK,sBAAsB,gBAAgB,GAYzI,GAAwB,AAAC,GAA6D,EAAK,mBAAmB,sBAAsB,GASpI,GAA2B,AAAC,GAAmE,EAAK,kBAAkB,mBAAmB,GASzI,GAAsB,AAAC,GAAiF,EAAK,aAAa,oBAAoB,GAE9I,GAA0B,AAAC,GAAgB,EAAK,eAAe,KAAK,GACpE,GAA4B,AAAC,GAAgB,EAAK,iBAAiB,KAAK,GACxE,GAAsB,AAAC,GAAgB,EAAK,WAAW,KAAK,GAC5D,GAAwB,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACrE,GAA4B,AAAC,GAAgB,EAAK,sBAAsB,KAAK,GAC7E,GAA2B,AAAC,GAAgB,EAAK,mBAAmB,KAAK,GACzE,GAA0B,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACvE,GAAqB,AAAC,GAAgB,EAAK,aAAa,KAAK,GAG7D,GAAyB,GACzB,GAAc,GACd,GAAkB,GCpH/B,oBAmB4E,IAC1E,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA1Bd,gBAkCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAwB,KAAM,IAClC,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,KAEtD,KAAK,gBAGP,MAAO,GAAc,IACnB,CAAC,EAAc,IAAM,GAAmC,EAAc,EAAsB,KAIhG,mBACE,MAAO,IAAI,IAA2B,KAAM,KAAK,SArDrD,gBA2DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,GAAkB,KAAM,IAC5B,EACA,KAAK,MACL,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,GACpD,KAAK,gBAGP,MAAO,IAA0B,EAAc,GAGjD,mBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA7ExD,gBAmFU,IACR,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAzFxD,gBA+FU,IACR,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCrG1D,oBAoByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA3Bd,gBAmCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAqB,KAAM,IAC/B,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,aAAa,oBAAoB,KAElD,KAAK,gBAGP,MAAO,GAAc,IAAI,CAAC,EAAc,KACtC,GAAM,CAAE,MAAK,SAAQ,qBAAsB,EAAmB,GAC9D,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,KAIpF,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAvDxD,gBA6DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,MAAK,SAAQ,qBAAsB,KAAM,IAC/C,EACA,KAAK,MACL,AAAC,GAAS,EAAK,aAAa,oBAAoB,GAChD,KAAK,gBAGP,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,GAGlF,sBACE,MAAO,IAAI,IAAiC,KAAM,KAAK,SA/E3D,gBAqFU,IACR,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA3FxD,gBAiGU,IACR,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCvG1D,oBAiB4E,IAC1E,YAEY,EAEA,GAEV,QAJU,kBAEA,eAtBd,gBA8BU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAUjC,MAAO,AARa,MAAM,IACxB,EACA,KAAK,MACL,AAAC,GAAU,QAAQ,IAAI,EAAM,IAAI,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,KACzF,KACA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,OAGxD,IAAI,CAAC,EAAY,IAAM,GAAkC,EAAc,GAAI,IAGhG,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,SAlDtE,gBAwDU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAEF,GAAM,GAAa,KAAM,IACvB,EACA,KAAK,MACL,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,GACxD,KAEA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,MAG3E,MAAO,IAAyB,EAAc,GAGhD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,SP/EzE,oBAqByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,6BAKE,eACZ,MAAO,MAAK,mBACR,EAAK,sBACL,EAAK,oBApCb,gBA0CU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAC3B,EAAa,EAAc,IAAI,AAAC,GAAQ,EAAI,WAE5C,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,GACrC,KAAM,IAAa,KAAK,MAAO,GAE7B,EAAsB,KAAM,SAAQ,IAAI,EAAM,IAClD,AAAC,GAAS,KAAK,YAAY,gBAAgB,KAG7C,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAAc,IAAI,CAAC,EAAc,IAAM,GAAiC,EAAc,EAAoB,KAGnH,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SArExD,gBA2EU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,aAAc,EAChB,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,CAAC,IACtC,KAAM,IAAa,KAAK,MAAO,CAAC,IAE9B,EAAY,KAAM,MAAK,YAAY,gBAAgB,EAAM,IAE/D,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,GAAiC,EAAc,GAGxD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SQvG1D,oBAckD,IAChD,YAEY,EAEA,EAAgC,GAAI,IAE9C,QAJU,aAEA,iBAnBd,gBAyBwC,SACzB,OACX,GAAM,CAAE,QAAO,WAAY,KAGrB,EAAwB,YAAmB,IAE7C,AAAC,GAAqB,EAAK,iBAAiB,YAAY,EAAO,GAG/D,YAAmB,GAEf,AAAC,GAAqB,EAAK,eAAe,YAAY,EAAO,GAE7D,YAAmB,IAEf,AAAC,GAAqB,EAAK,WAAW,YAAY,EAAO,GACzD,KAIZ,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,uIAGlB,MAAO,GAAsB,GAGvB,iCAEN,MAAO,IAAI,SAAiC,KAAO,KACjD,GAAM,GAAa,KAAM,MAAK,MAC9B,EAAQ,EAAW,IAAI,AAAC,GAAc,GAAwB,GAAI,OAItE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,SA/EX,gBAoF0C,SAC3B,OACX,GAAM,GAAiB,KAAM,IAAI,IAAmB,KAAK,MAAO,KAAK,SACjE,EAAgC,EAAe,GACnD,SAAe,QAAQ,AAAC,IACtB,AAAI,EAAc,MAAQ,EAA8B,OACtD,GAAgC,KAG7B,EAGD,gCAEN,MAAO,IAAI,SAA2C,KAAO,KAC3D,GAAM,GAAY,KAAM,MAAK,MAC7B,EAAQ,EAAY,GAA4B,GAAI,GAAa,UAIrE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,SCrHJ,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAqB,EAAO,GAGlC,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAmB,EAAO,GCRvC,kBACE,EACA,GAEA,MAAO,IAAe,EAAO,GAAI,GAAsB,EAAgB,CAAE,iBAAkB,KACxF,oBACA,sBAGL,kBACE,EACA,EAAoC,IAEpC,MAAO,IAAe,EAAO,GAAI,IAAkB,IAChD,oBACA,sBAGE,GAAM,IAAW,GC1BjB,YAA2B,EAA+B,GAC/D,GAAI,EAAK,SAAW,EAAK,OAAQ,KAAM,IAAI,OAAM,kDAEjD,GAAM,GAAQ,MAAM,KAAK,GACnB,EAAQ,MAAM,KAAK,GAEzB,MAAO,MAAK,KACV,EACG,IAAI,CAAC,EAAK,IAAM,EAAM,EAAM,IAC5B,OAAO,CAAC,EAAK,IAAS,EAAO,GAAQ,EAAI,ICThD,aAUE,YACE,EACA,EAA4B,IAE5B,KAAK,mBAAqB,EAE1B,GAAM,GAAa,MAAM,QAAQ,GAAU,EAAS,CAAC,GAErD,GAAI,CAAC,EAAW,OACd,KAAM,IAAI,OAAM,2DAGlB,GAAI,GAAQ,EACN,EAAoB,IAAM,UAAU,MAE1C,KAAK,oBAAsB,EAAW,IAAI,AAAC,IACzC,GAAI,YAAgB,IAClB,MAAO,GAGT,GAAI,YAAgB,cAClB,MAAO,IAAI,IAAuB,IAAqB,CAAC,IAG1D,GAAI,EAAK,YAAc,EAAK,qBAAsB,cAChD,MAAO,IAAI,IAAuB,IAAqB,CAAC,EAAK,aAG/D,KAAM,IAAI,OAAM,4MAIT,sBAAiD,MAAO,MAAK,uBAE7D,qBAA8B,MAAO,MAAK,mBAE9C,oBAAoB,EAA+B,GACxD,MAAO,GACJ,IAAI,AAAC,GAAM,GAAkB,EAAG,IAChC,OAAO,CAAC,EAAI,IAAO,EAAK,EAAI,GACxB,GAAY,QAAU,GAGxB,gBAAgB,GACrB,MAAO,MAAK,mBACT,IAAI,CAAC,CAAE,cAAa,WAAY,GAAI,IACnC,EACA,KAAK,oBAAoB,EAAiB,KAE3C,OAAO,CAAC,EAAM,IAAU,EAAK,SAAW,EAAK,SAAW,EAAO,GAG7D,cAAc,GACnB,GAAM,GAAY,KAAK,gBAAgB,GACvC,MAAO,GAAU,SAAW,KAAK,kBAC7B,EACA,GAAI,IAAU,UAAW,EAAU,UAGlC,SACL,MAAO,CACL,kBAAmB,KAAK,kBACxB,mBAAoB,KAAK,mBAAmB,IAAI,AAAC,GAAO,EAAG,iBAIjD,UAAS,GACrB,GAAM,GAAqB,EAAK,mBAC7B,IAAI,AAAC,GAAY,GAAuB,SAAS,IACpD,MAAO,IAAI,IAAY,EAAoB,EAAK,qBC1E7C,YAAgC,GACrC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECFF,YAA0B,EAAY,GAC3C,GAAM,CAAE,QAAO,UAAW,GAAI,GAAW,EAAW,MAAO,EAAW,QAEtE,GAAI,GAAS,GAAK,GAAU,EAC1B,KAAM,IAAI,OAAM,uCAAuC,KAAK,UAAU,CAAE,QAAO,cAGjF,GAAI,MAAM,QAAQ,GAEhB,MAAQ,GAAuB,IAAI,AAAC,GAAQ,GAAc,EAAK,CAAE,QAAO,YAG1E,GAAI,GAAoB,IACtB,GAAM,GAAmB,EAAQ,UAAU,QAAQ,EAAO,GACpD,EAAmB,EAAQ,mBAAmB,QAAQ,EAAiB,IAAI,MAAO,EAAiB,IAAI,QAC7G,MAAO,IAAwB,GAAwB,EAAS,GAAmB,GAGrF,MAAI,IAAoB,GACf,GAAwB,EAAS,EAAQ,UAAU,QAAQ,EAAO,IAGvE,YAAmB,IAAiB,YAAmB,GACjD,EAAgB,QAAQ,EAAO,GAGlC,EjJRT,GAAM,IAAQ,MAAO,UAAY,YAC3B,GAAW,MAAO,YAAc,aAAiB,MAAO,WAAU,WAAc,YACzE,GAAU,CAAE,QAAa,GAAmB,QAAM", "names": [] } diff --git a/dist/face-api.node-gpu.json b/dist/face-api.node-gpu.json index 091d87e..180ac58 100644 --- a/dist/face-api.node-gpu.json +++ b/dist/face-api.node-gpu.json @@ -18,7 +18,7 @@ ] }, "src/utils/index.ts": { - "bytes": 1842, + "bytes": 1793, "imports": [ { "path": "dist/tfjs.esm.js", @@ -843,7 +843,7 @@ ] }, "src/NeuralNetwork.ts": { - "bytes": 5289, + "bytes": 5291, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1326,7 +1326,7 @@ ] }, "src/xception/TinyXception.ts": { - "bytes": 3148, + "bytes": 3143, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1553,7 +1553,7 @@ ] }, "src/faceLandmarkNet/index.ts": { - "bytes": 195, + "bytes": 194, "imports": [ { "path": "src/faceLandmarkNet/FaceLandmark68Net.ts", @@ -1609,7 +1609,7 @@ ] }, "src/faceRecognitionNet/extractParamsFromWeightMap.ts": { - "bytes": 3101, + "bytes": 3098, "imports": [ { "path": "src/common/index.ts", @@ -1635,7 +1635,7 @@ ] }, "src/faceRecognitionNet/FaceRecognitionNet.ts": { - "bytes": 2981, + "bytes": 2959, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1735,7 +1735,7 @@ ] }, "src/ssdMobilenetv1/extractParams.ts": { - "bytes": 8339, + "bytes": 8330, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1748,7 +1748,7 @@ ] }, "src/ssdMobilenetv1/extractParamsFromWeightMap.ts": { - "bytes": 5782, + "bytes": 5775, "imports": [ { "path": "src/common/index.ts", @@ -1783,11 +1783,11 @@ ] }, "src/ssdMobilenetv1/nonMaxSuppression.ts": { - "bytes": 2187, + "bytes": 2170, "imports": [] }, "src/ssdMobilenetv1/outputLayer.ts": { - "bytes": 2187, + "bytes": 2183, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1796,7 +1796,7 @@ ] }, "src/ssdMobilenetv1/boxPredictionLayer.ts": { - "bytes": 617, + "bytes": 598, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1830,7 +1830,7 @@ "imports": [] }, "src/ssdMobilenetv1/SsdMobilenetv1.ts": { - "bytes": 3826, + "bytes": 3675, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1913,7 +1913,7 @@ "imports": [] }, "src/tinyYolov2/leaky.ts": { - "bytes": 271, + "bytes": 238, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1922,7 +1922,7 @@ ] }, "src/tinyYolov2/convWithBatchNorm.ts": { - "bytes": 532, + "bytes": 530, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1935,7 +1935,7 @@ ] }, "src/tinyYolov2/depthwiseSeparableConv.ts": { - "bytes": 502, + "bytes": 500, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1948,7 +1948,7 @@ ] }, "src/tinyYolov2/extractParams.ts": { - "bytes": 3918, + "bytes": 3911, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1969,7 +1969,7 @@ ] }, "src/tinyYolov2/extractParamsFromWeightMap.ts": { - "bytes": 3284, + "bytes": 3282, "imports": [ { "path": "src/common/disposeUnusedWeightTensors.ts", @@ -1990,7 +1990,7 @@ "imports": [] }, "src/tinyYolov2/TinyYolov2Base.ts": { - "bytes": 9700, + "bytes": 9606, "imports": [ { "path": "dist/tfjs.esm.js", @@ -2080,7 +2080,7 @@ "imports": [] }, "src/tinyYolov2/index.ts": { - "bytes": 349, + "bytes": 347, "imports": [ { "path": "src/tinyYolov2/TinyYolov2.ts", @@ -2501,7 +2501,7 @@ ] }, "src/index.ts": { - "bytes": 1024, + "bytes": 987, "imports": [ { "path": "dist/tfjs.esm.js", @@ -2590,7 +2590,7 @@ "dist/face-api.node-gpu.js.map": { "imports": [], "inputs": {}, - "bytes": 310112 + "bytes": 309649 }, "dist/face-api.node-gpu.js": { "imports": [], @@ -2780,7 +2780,7 @@ "bytesInOutput": 621 }, "src/NeuralNetwork.ts": { - "bytesInOutput": 2640 + "bytesInOutput": 2654 }, "src/faceFeatureExtractor/denseBlock.ts": { "bytesInOutput": 568 @@ -2912,7 +2912,7 @@ "bytesInOutput": 176 }, "src/faceRecognitionNet/FaceRecognitionNet.ts": { - "bytesInOutput": 1062 + "bytesInOutput": 1156 }, "src/faceRecognitionNet/convLayer.ts": { "bytesInOutput": 277 @@ -3065,7 +3065,7 @@ "bytesInOutput": 443 } }, - "bytes": 82583 + "bytes": 82691 } } } diff --git a/dist/face-api.node.js b/dist/face-api.node.js index a606d4b..61a2f70 100644 --- a/dist/face-api.node.js +++ b/dist/face-api.node.js @@ -5,5 +5,5 @@ author: ' */ -var ln=Object.create,Ye=Object.defineProperty,fn=Object.getPrototypeOf,hn=Object.prototype.hasOwnProperty,xn=Object.getOwnPropertyNames,bn=Object.getOwnPropertyDescriptor;var fo=o=>Ye(o,"__esModule",{value:!0});var ho=(o,t)=>()=>(t||(t={exports:{}},o(t.exports,t)),t.exports),Ge=(o,t)=>{fo(o);for(var e in t)Ye(o,e,{get:t[e],enumerable:!0})},gn=(o,t,e)=>{if(fo(o),t&&typeof t=="object"||typeof t=="function")for(let r of xn(t))!hn.call(o,r)&&r!=="default"&&Ye(o,r,{get:()=>t[r],enumerable:!(e=bn(t,r))||e.enumerable});return o},b=o=>o&&o.__esModule?o:gn(Ye(o!=null?ln(fn(o)):{},"default",{value:o,enumerable:!0}),o);var g=ho(xo=>{var vn=Object.create,Er=Object.defineProperty,yn=Object.getPrototypeOf,Fn=Object.prototype.hasOwnProperty,Tn=Object.getOwnPropertyNames,Pn=Object.getOwnPropertyDescriptor,_n=o=>Er(o,"__esModule",{value:!0}),bo=(o,t,e)=>{if(_n(o),t&&typeof t=="object"||typeof t=="function")for(let r of Tn(t))!Fn.call(o,r)&&r!=="default"&&Er(o,r,{get:()=>t[r],enumerable:!(e=Pn(t,r))||e.enumerable});return o},wn=o=>o&&o.__esModule?o:bo(Er(o!=null?vn(yn(o)):{},"default",{value:o,enumerable:!0}),o);bo(xo,wn(require("@tensorflow/tfjs-node")))});var To=ho((Ln,Fo)=>{Ge(Ln,{isNodejs:()=>kn});function kn(){return typeof global=="object"&&!0&&typeof Fo!="undefined"&&typeof process!="undefined"&&!!process.version}});Ge(exports,{AgeGenderNet:()=>pr,BoundingBox:()=>ee,Box:()=>D,ComposableTask:()=>tt,ComputeAllFaceDescriptorsTask:()=>At,ComputeFaceDescriptorsTaskBase:()=>vr,ComputeSingleFaceDescriptorTask:()=>Wt,DetectAllFaceLandmarksTask:()=>Fr,DetectAllFacesTask:()=>He,DetectFaceLandmarksTaskBase:()=>yr,DetectFacesTaskBase:()=>Pr,DetectSingleFaceLandmarksTask:()=>Tr,DetectSingleFaceTask:()=>_r,Dimensions:()=>A,FACE_EXPRESSION_LABELS:()=>Jr,FaceDetection:()=>M,FaceDetectionNet:()=>Jo,FaceExpressionNet:()=>cr,FaceExpressions:()=>It,FaceLandmark68Net:()=>fe,FaceLandmark68TinyNet:()=>dr,FaceLandmarkNet:()=>Bo,FaceLandmarks:()=>V,FaceLandmarks5:()=>vo,FaceLandmarks68:()=>oe,FaceMatch:()=>Ee,FaceMatcher:()=>Dr,FaceRecognitionNet:()=>xe,Gender:()=>vt,LabeledBox:()=>Me,LabeledFaceDescriptors:()=>xt,NetInput:()=>bt,NeuralNetwork:()=>S,ObjectDetection:()=>Dt,Point:()=>x,PredictedBox:()=>yo,Rect:()=>re,SsdMobilenetv1:()=>Ut,SsdMobilenetv1Options:()=>Z,TinyFaceDetector:()=>Fe,TinyFaceDetectorOptions:()=>gr,TinyYolov2:()=>ve,TinyYolov2Options:()=>lt,allFaces:()=>Da,allFacesSsdMobilenetv1:()=>dn,allFacesTinyYolov2:()=>wa,awaitMediaLoaded:()=>Yr,bufferToImage:()=>Gr,computeFaceDescriptor:()=>da,createCanvas:()=>ne,createCanvasFromMedia:()=>Ie,createFaceDetectionNet:()=>na,createFaceRecognitionNet:()=>Un,createSsdMobilenetv1:()=>Xo,createTinyFaceDetector:()=>Ea,createTinyYolov2:()=>ia,detectAllFaces:()=>wr,detectFaceLandmarks:()=>mn,detectFaceLandmarksTiny:()=>pa,detectLandmarks:()=>Pa,detectSingleFace:()=>_a,draw:()=>Qr,env:()=>w,euclideanDistance:()=>uo,extendWithAge:()=>hr,extendWithFaceDescriptor:()=>fr,extendWithFaceDetection:()=>$t,extendWithFaceExpressions:()=>mr,extendWithFaceLandmarks:()=>le,extendWithGender:()=>xr,extractFaceTensors:()=>se,extractFaces:()=>ae,fetchImage:()=>Bn,fetchJson:()=>Ur,fetchNetWeights:()=>Rn,fetchOrThrow:()=>Yt,getContext2dOrThrow:()=>O,getMediaDimensions:()=>Ht,imageTensorToCanvas:()=>zr,imageToSquare:()=>Vr,inverseSigmoid:()=>Mn,iou:()=>Lr,isMediaElement:()=>qe,isMediaLoaded:()=>Ne,isWithAge:()=>Xn,isWithFaceDetection:()=>pt,isWithFaceExpressions:()=>qr,isWithFaceLandmarks:()=>zt,isWithGender:()=>Jn,loadAgeGenderModel:()=>ya,loadFaceDetectionModel:()=>Fa,loadFaceExpressionModel:()=>va,loadFaceLandmarkModel:()=>xa,loadFaceLandmarkTinyModel:()=>ba,loadFaceRecognitionModel:()=>ga,loadSsdMobilenetv1Model:()=>pn,loadTinyFaceDetectorModel:()=>fa,loadTinyYolov2Model:()=>ha,loadWeightMap:()=>Xr,locateFaces:()=>Ta,matchDimensions:()=>On,minBbox:()=>kr,nets:()=>P,nonMaxSuppression:()=>Sr,normalize:()=>ot,padToSquare:()=>Ar,predictAgeAndGender:()=>la,recognizeFaceExpressions:()=>ua,resizeResults:()=>un,resolveInput:()=>jt,shuffleArray:()=>En,sigmoid:()=>De,ssdMobilenetv1:()=>cn,tf:()=>Ma,tinyFaceDetector:()=>ca,tinyYolov2:()=>ma,toNetInput:()=>E,utils:()=>Mr,validateConfig:()=>ao,version:()=>Ia});var Ma=b(g());var Qr={};Ge(Qr,{AnchorPosition:()=>dt,DrawBox:()=>Xe,DrawBoxOptions:()=>Hr,DrawFaceLandmarks:()=>Kr,DrawFaceLandmarksOptions:()=>Zr,DrawTextField:()=>Mt,DrawTextFieldOptions:()=>Ce,drawContour:()=>ft,drawDetections:()=>Wn,drawFaceExpressions:()=>$n,drawFaceLandmarks:()=>jn});function ft(o,t,e=!1){if(o.beginPath(),t.slice(1).forEach(({x:r,y:n},a)=>{let s=t[a];o.moveTo(s.x,s.y),o.lineTo(r,n)}),e){let r=t[t.length-1],n=t[0];if(!r||!n)return;o.moveTo(r.x,r.y),o.lineTo(n.x,n.y)}o.stroke()}var Mr={};Ge(Mr,{computeReshapedDimensions:()=>Ir,getCenterPoint:()=>Ot,isDimensions:()=>Ve,isEven:()=>ze,isFloat:()=>Nr,isTensor:()=>Bt,isTensor1D:()=>Dn,isTensor2D:()=>Cr,isTensor3D:()=>ht,isTensor4D:()=>z,isValidNumber:()=>rt,isValidProbablitiy:()=>te,range:()=>ct,round:()=>Rt});var go=b(g());var A=class{constructor(t,e){if(!rt(t)||!rt(e))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:e})}`);this._width=t,this._height=e}get width(){return this._width}get height(){return this._height}reverse(){return new A(1/this.width,1/this.height)}};function Bt(o,t){return o instanceof go.Tensor&&o.shape.length===t}function Dn(o){return Bt(o,1)}function Cr(o){return Bt(o,2)}function ht(o){return Bt(o,3)}function z(o){return Bt(o,4)}function Nr(o){return o%1!=0}function ze(o){return o%2==0}function Rt(o,t=2){let e=10**t;return Math.floor(o*e)/e}function Ve(o){return o&&o.width&&o.height}function Ir({width:o,height:t},e){let r=e/Math.max(t,o);return new A(Math.round(o*r),Math.round(t*r))}function Ot(o){return o.reduce((t,e)=>t.add(e),new x(0,0)).div(new x(o.length,o.length))}function ct(o,t,e){return Array(o).fill(0).map((r,n)=>t+n*e)}function rt(o){return!!o&&o!==Infinity&&o!==-Infinity&&!Number.isNaN(o)||o===0}function te(o){return rt(o)&&o>=0&&o<=1}var x=class{constructor(t,e){this._x=t,this._y=e}get x(){return this._x}get y(){return this._y}add(t){return new x(this.x+t.x,this.y+t.y)}sub(t){return new x(this.x-t.x,this.y-t.y)}mul(t){return new x(this.x*t.x,this.y*t.y)}div(t){return new x(this.x/t.x,this.y/t.y)}abs(){return new x(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new x(Math.floor(this.x),Math.floor(this.y))}};var D=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(rt)}static assertIsValidBox(t,e,r=!1){if(!D.isRect(t))throw new Error(`${e} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!r&&(t.width<0||t.height<0))throw new Error(`${e} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,e=!0){let r=t||{},n=[r.left,r.top,r.right,r.bottom].every(rt),a=[r.x,r.y,r.width,r.height].every(rt);if(!a&&!n)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(r)}`);let[s,i,c,m]=a?[r.x,r.y,r.width,r.height]:[r.left,r.top,r.right-r.left,r.bottom-r.top];D.assertIsValidBox({x:s,y:i,width:c,height:m},"Box.constructor",e),this._x=s,this._y=i,this._width=c,this._height=m}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new x(this.left,this.top)}get topRight(){return new x(this.right,this.top)}get bottomLeft(){return new x(this.left,this.bottom)}get bottomRight(){return new x(this.right,this.bottom)}round(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.round(a));return new D({x:t,y:e,width:r,height:n})}floor(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.floor(a));return new D({x:t,y:e,width:r,height:n})}toSquare(){let{x:t,y:e,width:r,height:n}=this,a=Math.abs(r-n);return re&&(i=-d+e+r,d=e),u>t&&(c=-u+t+n,u=t),m<1&&(c=2-m,m=1),p<1&&(c=2-p,p=1),{dy:s,edy:c,dx:a,edx:i,y:p,ey:u,x:m,ex:d,w:r,h:n}}calibrate(t){return new D({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var ee=class extends D{constructor(t,e,r,n,a=!1){super({left:t,top:e,right:r,bottom:n},a)}};var Dt=class{constructor(t,e,r,n,a){this._imageDims=new A(a.width,a.height),this._score=t,this._classScore=e,this._className=r,this._box=new D(n).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new D(this._box).rescale(this.imageDims.reverse())}forSize(t,e){return new Dt(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:e})}};var M=class extends Dt{constructor(t,e,r){super(t,t,"",e,r)}forSize(t,e){let{score:r,relativeBox:n,imageDims:a}=super.forSize(t,e);return new M(r,n,a)}};function Lr(o,t,e=!0){let r=Math.max(0,Math.min(o.right,t.right)-Math.max(o.left,t.left)),n=Math.max(0,Math.min(o.bottom,t.bottom)-Math.max(o.top,t.top)),a=r*n;return e?a/(o.area+t.area-a):a/Math.min(o.area,t.area)}function kr(o){let t=o.map(i=>i.x),e=o.map(i=>i.y),r=t.reduce((i,c)=>ccii({score:s,boxIndex:i})).sort((s,i)=>s.score-i.score).map(s=>s.boxIndex),a=[];for(;n.length>0;){let s=n.pop();a.push(s);let i=n,c=[];for(let m=0;mc[p]<=e)}return a}var mt=b(g());function ot(o,t){return mt.tidy(()=>{let[e,r,n]=t,a=mt.fill([...o.shape.slice(0,3),1],e,"float32"),s=mt.fill([...o.shape.slice(0,3),1],r,"float32"),i=mt.fill([...o.shape.slice(0,3),1],n,"float32"),c=mt.concat([a,s,i],3);return mt.sub(o,c)})}var Et=b(g());function Ar(o,t=!1){return Et.tidy(()=>{let[e,r]=o.shape.slice(1);if(e===r)return o;let n=Math.abs(e-r),a=Math.round(n*(t?.5:1)),s=e>r?2:1,i=u=>{let l=o.shape.slice();return l[s]=u,Et.fill(l,0,"float32")},c=i(a),m=n-c.shape[s],d=[t&&m?i(m):null,o,c].filter(u=>!!u).map(u=>Et.cast(u,"float32"));return Et.concat(d,s)})}function En(o){let t=o.slice();for(let e=t.length-1;e>0;e--){let r=Math.floor(Math.random()*(e+1)),n=t[e];t[e]=t[r],t[r]=n}return t}function De(o){return 1/(1+Math.exp(-o))}function Mn(o){return Math.log(o/(1-o))}var re=class extends D{constructor(t,e,r,n,a=!1){super({x:t,y:e,width:r,height:n},a)}};var Cn=.5,Nn=.43,In=.45,V=class{constructor(t,e,r=new x(0,0)){let{width:n,height:a}=e;this._imgDims=new A(n,a),this._shift=r,this._positions=t.map(s=>s.mul(new x(n,a)).add(r))}get shift(){return new x(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new x(this.imageWidth,this.imageHeight)))}forSize(t,e){return new this.constructor(this.relativePositions,{width:t,height:e})}shiftBy(t,e){return new this.constructor(this.relativePositions,this._imgDims,new x(t,e))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,e={}){if(t){let a=t instanceof M?t.box.floor():new D(t);return this.shiftBy(a.x,a.y).align(null,e)}let{useDlibAlignment:r,minBoxPadding:n}={useDlibAlignment:!1,minBoxPadding:.2,...e};return r?this.alignDlib():this.alignMinBbox(n)}alignDlib(){let t=this.getRefPointsForAlignment(),[e,r,n]=t,a=d=>n.sub(d).magnitude(),s=(a(e)+a(r))/2,i=Math.floor(s/In),c=Ot(t),m=Math.floor(Math.max(0,c.x-Cn*i)),p=Math.floor(Math.max(0,c.y-Nn*i));return new re(m,p,Math.min(i,this.imageWidth+m),Math.min(i,this.imageHeight+p))}alignMinBbox(t){let e=kr(this.positions);return e.pad(e.width*t,e.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var vo=class extends V{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Ot([t[3],t[4]])]}};var oe=class extends V{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Ot)}};var Ee=class{constructor(t,e){this._label=t,this._distance=e}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${Rt(this.distance)})`:""}`}};var Me=class extends D{static assertIsValidLabeledBox(t,e){if(D.assertIsValidBox(t,e),!rt(t.label))throw new Error(`${e} - expected property label (${t.label}) to be a number`)}constructor(t,e){super(t);this._label=e}get label(){return this._label}};var xt=class{constructor(t,e){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(e)||e.some(r=>!(r instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=e}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let e=t.descriptors.map(r=>new Float32Array(r));return new xt(t.label,e)}};var yo=class extends Me{static assertIsValidPredictedBox(t,e){if(Me.assertIsValidLabeledBox(t,e),!te(t.score)||!te(t.classScore))throw new Error(`${e} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,e,r,n){super(t,e);this._score=r,this._classScore=n}get score(){return this._score}get classScore(){return this._classScore}};function pt(o){return o.detection instanceof M}function $t(o,t){return{...o,...{detection:t}}}function Wr(){let o=window.fetch;if(!o)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:o,readFile:t}}function Ue(o){let t="";if(!o)try{o=require("fs")}catch(r){t=r.toString()}return{readFile:o?r=>new Promise((n,a)=>{o.readFile(r,(s,i)=>s?a(s):n(i))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function Br(){let o=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,e=()=>{if(o)return new o;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},r=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},n=global.fetch,a=Ue();return{Canvas:o||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:e,createImageElement:r,fetch:n,...a}}function Rr(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var Or=b(To()),k;function Sn(){if(!k)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return k}function $r(o){k=o}function jr(){return Rr()?$r(Wr()):Or.isNodejs()?$r(Br()):null}function An(o){if(k||jr(),!k)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=k.Canvas,Image:e=k.Image}=o;k.Canvas=t,k.Image=e,k.createCanvasElement=o.createCanvasElement||(()=>new t),k.createImageElement=o.createImageElement||(()=>new e),k.ImageData=o.ImageData||k.ImageData,k.Video=o.Video||k.Video,k.fetch=o.fetch||k.fetch,k.readFile=o.readFile||k.readFile}var w={getEnv:Sn,setEnv:$r,initialize:jr,createBrowserEnv:Wr,createFileSystem:Ue,createNodejsEnv:Br,monkeyPatch:An,isBrowser:Rr,isNodejs:Or.isNodejs};jr();function jt(o){return!w.isNodejs()&&typeof o=="string"?document.getElementById(o):o}function O(o){let{Canvas:t,CanvasRenderingContext2D:e}=w.getEnv();if(o instanceof e)return o;let r=jt(o);if(!(r instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let n=r.getContext("2d");if(!n)throw new Error("resolveContext2d - canvas 2d context is null");return n}var dt;(function(o){o.TOP_LEFT="TOP_LEFT",o.TOP_RIGHT="TOP_RIGHT",o.BOTTOM_LEFT="BOTTOM_LEFT",o.BOTTOM_RIGHT="BOTTOM_RIGHT"})(dt||(dt={}));var Ce=class{constructor(t={}){let{anchorPosition:e,backgroundColor:r,fontColor:n,fontSize:a,fontStyle:s,padding:i}=t;this.anchorPosition=e||dt.TOP_LEFT,this.backgroundColor=r||"rgba(0, 0, 0, 0.5)",this.fontColor=n||"rgba(255, 255, 255, 1)",this.fontSize=a||14,this.fontStyle=s||"Georgia",this.padding=i||4}},Mt=class{constructor(t,e,r={}){this.text=typeof t=="string"?[t]:t instanceof Mt?t.text:t,this.anchor=e,this.options=new Ce(r)}measureWidth(t){let{padding:e}=this.options;return this.text.map(r=>t.measureText(r).width).reduce((r,n)=>r{let v=c+d.x,_=c+d.y+(l+1)*s;r.fillText(u,v,_)})}};var Hr=class{constructor(t={}){let{boxColor:e,lineWidth:r,label:n,drawLabelOptions:a}=t;this.boxColor=e||"rgba(0, 0, 255, 1)",this.lineWidth=r||2,this.label=n;let s={anchorPosition:dt.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Ce({...s,...a})}},Xe=class{constructor(t,e={}){this.box=new D(t),this.options=new Hr(e)}draw(t){let e=O(t),{boxColor:r,lineWidth:n}=this.options,{x:a,y:s,width:i,height:c}=this.box;e.strokeStyle=r,e.lineWidth=n,e.strokeRect(a,s,i,c);let{label:m}=this.options;m&&new Mt([m],{x:a-n/2,y:s},this.options.drawLabelOptions).draw(t)}};function Wn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof M?r.score:pt(r)?r.detection.score:void 0,a=r instanceof M?r.box:pt(r)?r.detection.box:new D(r),s=n?`${Rt(n)}`:void 0;new Xe(a,{label:s}).draw(o)})}var ue=b(g());function Ne(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t&&o.complete||o instanceof e&&o.readyState>=3}function Yr(o){return new Promise((t,e)=>{if(o instanceof w.getEnv().Canvas||Ne(o))return t(null);function r(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),e(a))}function n(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),t(a))}o.addEventListener("load",n),o.addEventListener("error",r)})}function Gr(o){return new Promise((t,e)=>{o instanceof Blob||e(new Error("bufferToImage - expected buf to be of type: Blob"));let r=new FileReader;r.onload=()=>{typeof r.result!="string"&&e(new Error("bufferToImage - expected reader.result to be a string, in onload"));let n=w.getEnv().createImageElement();n.onload=()=>t(n),n.onerror=e,n.src=r.result},r.onerror=e,r.readAsDataURL(o)})}function Ht(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t?new A(o.naturalWidth,o.naturalHeight):o instanceof e?new A(o.videoWidth,o.videoHeight):new A(o.width,o.height)}function ne({width:o,height:t}){let{createCanvasElement:e}=w.getEnv(),r=e();return r.width=o,r.height=t,r}function Ie(o,t){let{ImageData:e}=w.getEnv();if(!(o instanceof e)&&!Ne(o))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:r,height:n}=t||Ht(o),a=ne({width:r,height:n});return o instanceof e?O(a).putImageData(o,0,0):O(a).drawImage(o,0,0,r,n),a}var Je=b(g());async function zr(o,t){let e=t||w.getEnv().createCanvasElement(),[r,n,a]=o.shape.slice(z(o)?1:0),s=Je.tidy(()=>o.as3D(r,n,a).toInt());return await Je.browser.toPixels(s,e),s.dispose(),e}function qe(o){let{Image:t,Canvas:e,Video:r}=w.getEnv();return o instanceof t||o instanceof e||o instanceof r}var J=b(g());function Vr(o,t,e=!1){let{Image:r,Canvas:n}=w.getEnv();if(!(o instanceof r||o instanceof n))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let a=Ht(o),s=t/Math.max(a.height,a.width),i=s*a.width,c=s*a.height,m=ne({width:t,height:t}),p=o instanceof n?o:Ie(o),d=Math.abs(i-c)/2,u=e&&i{if(ht(r)){this._imageTensors[n]=r,this._inputDimensions[n]=r.shape;return}if(z(r)){let s=r.shape[0];if(s!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${s} passed, but not supported in input array`);this._imageTensors[n]=r,this._inputDimensions[n]=r.shape.slice(1);return}let a=r instanceof w.getEnv().Canvas?r:Ie(r);this._canvases[n]=a,this._inputDimensions[n]=[a.height,a.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ct(this.batchSize,0,1).map((t,e)=>this.getReshapedInputDimensions(e))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let e=this.getInputWidth(t),r=this.getInputHeight(t);return Ir({width:e,height:r},this.inputSize)}toBatchTensor(t,e=!0){return this._inputSize=t,J.tidy(()=>{let r=ct(this.batchSize,0,1).map(a=>{let s=this.getInput(a);if(s instanceof J.Tensor){let i=z(s)?s:s.expandDims();return i=Ar(i,e),(i.shape[1]!==t||i.shape[2]!==t)&&(i=J.image.resizeBilinear(i,[t,t])),i.as3D(t,t,3)}if(s instanceof w.getEnv().Canvas)return J.browser.fromPixels(Vr(s,t,e));throw new Error(`toBatchTensor - at batchIdx ${a}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${s}`)});return J.stack(r.map(a=>J.cast(a,"float32"))).as4D(this.batchSize,t,t,3)})}};async function E(o){if(o instanceof bt)return o;let t=Array.isArray(o)?o:[o];if(!t.length)throw new Error("toNetInput - empty array passed as input");let e=n=>Array.isArray(o)?` at input index ${n}:`:"",r=t.map(jt);return r.forEach((n,a)=>{if(!qe(n)&&!ht(n)&&!z(n))throw typeof t[a]=="string"?new Error(`toNetInput -${e(a)} string passed, but could not resolve HTMLElement for element id ${t[a]}`):new Error(`toNetInput -${e(a)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(z(n)){let s=n.shape[0];if(s!==1)throw new Error(`toNetInput -${e(a)} tf.Tensor4D with batchSize ${s} passed, but not supported in input array`)}}),await Promise.all(r.map(n=>qe(n)&&Yr(n))),new bt(r,Array.isArray(o))}async function ae(o,t){let{Canvas:e}=w.getEnv(),r=o;if(!(o instanceof e)){let s=await E(o);if(s.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let i=s.getInput(0);r=i instanceof e?i:await zr(i)}let n=O(r);return t.map(s=>s instanceof M?s.forSize(r.width,r.height).box.floor():s).map(s=>s.clipAtImageBorders(r.width,r.height)).map(({x:s,y:i,width:c,height:m})=>{let p=ne({width:c,height:m});return O(p).putImageData(n.getImageData(s,i,c,m),0,0),p})}var Ze=b(g());async function se(o,t){if(!ht(o)&&!z(o))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(z(o)&&o.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return Ze.tidy(()=>{let[e,r,n]=o.shape.slice(z(o)?1:0);return t.map(i=>i instanceof M?i.forSize(r,e).box:i).map(i=>i.clipAtImageBorders(r,e)).map(({x:i,y:c,width:m,height:p})=>Ze.slice3d(o.as3D(e,r,n),[c,i,0],[p,m,n]))})}async function Yt(o,t){let{fetch:e}=w.getEnv(),r=await e(o,t);if(!(r.status<400))throw new Error(`failed to fetch: (${r.status}) ${r.statusText}, from url: ${r.url}`);return r}async function Bn(o){let t=await Yt(o),e=await t.blob();if(!e.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${e.type}, for url: ${t.url}`);return Gr(e)}async function Ur(o){return(await Yt(o)).json()}async function Rn(o){return new Float32Array(await(await Yt(o)).arrayBuffer())}var Po=b(g());function Ke(o,t){let e=`${t}-weights_manifest.json`;if(!o)return{modelBaseUri:"",manifestUri:e};if(o==="/")return{modelBaseUri:"/",manifestUri:`/${e}`};let r=o.startsWith("http://")?"http://":o.startsWith("https://")?"https://":"";o=o.replace(r,"");let n=o.split("/").filter(i=>i),a=o.endsWith(".json")?n[n.length-1]:e,s=r+(o.endsWith(".json")?n.slice(0,n.length-1):n).join("/");return s=o.startsWith("/")?`/${s}`:s,{modelBaseUri:s,manifestUri:s==="/"?`/${a}`:`${s}/${a}`}}async function Xr(o,t){let{manifestUri:e,modelBaseUri:r}=Ke(o,t),n=await Ur(e);return Po.io.loadWeights(n,r)}function On(o,t,e=!1){let{width:r,height:n}=e?Ht(t):t;return o.width=r,o.height=n,{width:r,height:n}}var Nt=b(g());var gt=b(g());var S=class{constructor(){this._params=void 0;this._paramMappings=[]}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:e,objProp:r}=this.traversePropertyPath(t);return e[r]}reassignParamFromPath(t,e){let{obj:r,objProp:n}=this.traversePropertyPath(t);r[n].dispose(),r[n]=e}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof gt.Variable)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof gt.Variable))}variable(){this.getFrozenParams().forEach(({path:t,tensor:e})=>{this.reassignParamFromPath(t,e.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:e})=>{let r=gt.tensor(e.dataSync());e.dispose(),this.reassignParamFromPath(t,r)})}dispose(t=!0){this.getParamList().forEach(e=>{if(t&&e.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${e.path}`);e.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,e)=>t.concat(e)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let e=await Xr(t,this.getDefaultModelName());this.loadFromWeightMap(e)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:e}=w.getEnv(),{manifestUri:r,modelBaseUri:n}=Ke(t,this.getDefaultModelName()),a=m=>Promise.all(m.map(p=>e(p).then(d=>d.buffer))),s=gt.io.weightsLoaderFactory(a),i=JSON.parse((await e(r)).toString()),c=await s(i,n);this.loadFromWeightMap(c)}loadFromWeightMap(t){let{paramMappings:e,params:r}=this.extractParamsFromWeightMap(t);this._paramMappings=e,this._params=r}extractWeights(t){let{paramMappings:e,params:r}=this.extractParams(t);this._paramMappings=e,this._params=r}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let e=t.split("/").reduce((a,s)=>{if(!a.nextObj.hasOwnProperty(s))throw new Error(`traversePropertyPath - object does not have property ${s}, for path ${t}`);return{obj:a.nextObj,objProp:s,nextObj:a.nextObj[s]}},{nextObj:this.params}),{obj:r,objProp:n}=e;if(!r||!n||!(r[n]instanceof gt.Tensor))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:r,objProp:n}}};var C=b(g());var ie=b(g());function $(o,t,e){return ie.tidy(()=>{let r=ie.separableConv2d(o,t.depthwise_filter,t.pointwise_filter,e,"same");return r=ie.add(r,t.bias),r})}function Qe(o,t,e=!1){return C.tidy(()=>{let r=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,[2,2],"same"),t.conv0.bias):$(o,t.conv0,[2,2])),n=$(r,t.conv1,[1,1]),a=C.relu(C.add(r,n)),s=$(a,t.conv2,[1,1]);return C.relu(C.add(r,C.add(n,s)))})}function Le(o,t,e=!1,r=!0){return C.tidy(()=>{let n=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,r?[2,2]:[1,1],"same"),t.conv0.bias):$(o,t.conv0,r?[2,2]:[1,1])),a=$(n,t.conv1,[1,1]),s=C.relu(C.add(n,a)),i=$(s,t.conv2,[1,1]),c=C.relu(C.add(n,C.add(a,i))),m=$(c,t.conv3,[1,1]);return C.relu(C.add(n,C.add(a,C.add(i,m))))})}var Ct=b(g());function Gt(o,t,e="same",r=!1){return Ct.tidy(()=>{let n=Ct.add(Ct.conv2d(o,t.filters,[1,1],e),t.bias);return r?Ct.relu(n):n})}function W(o,t){Object.keys(o).forEach(e=>{t.some(r=>r.originalPath===e)||o[e].dispose()})}var tr=b(g());function ce(o,t){return(e,r,n,a)=>{let s=tr.tensor4d(o(e*r*n*n),[n,n,e,r]),i=tr.tensor1d(o(r));return t.push({paramPath:`${a}/filters`},{paramPath:`${a}/bias`}),{filters:s,bias:i}}}var er=b(g());function rr(o,t){return(e,r,n)=>{let a=er.tensor2d(o(e*r),[e,r]),s=er.tensor1d(o(r));return t.push({paramPath:`${n}/weights`},{paramPath:`${n}/bias`}),{weights:a,bias:s}}}var ke=b(g());var or=class{constructor(t,e,r){this.depthwise_filter=t;this.pointwise_filter=e;this.bias=r}};function me(o,t){return(e,r,n)=>{let a=ke.tensor4d(o(3*3*e),[3,3,e,1]),s=ke.tensor4d(o(e*r),[1,1,e,r]),i=ke.tensor1d(o(r));return t.push({paramPath:`${n}/depthwise_filter`},{paramPath:`${n}/pointwise_filter`},{paramPath:`${n}/bias`}),new or(a,s,i)}}function pe(o){return t=>{let e=o(`${t}/depthwise_filter`,4),r=o(`${t}/pointwise_filter`,4),n=o(`${t}/bias`,1);return new or(e,r,n)}}function j(o,t){return(e,r,n)=>{let a=o[e];if(!Bt(a,r))throw new Error(`expected weightMap[${e}] to be a Tensor${r}D, instead have ${a}`);return t.push({originalPath:e,paramPath:n||e}),a}}function B(o){let t=o;function e(n){let a=t.slice(0,n);return t=t.slice(n),a}function r(){return t}return{extractWeights:e,getRemainingWeights:r}}function nr(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c,m=!1){let p=m?e(s,i,3,`${c}/conv0`):r(s,i,`${c}/conv0`),d=r(i,i,`${c}/conv1`),u=r(i,i,`${c}/conv2`);return{conv0:p,conv1:d,conv2:u}}function a(s,i,c,m=!1){let{conv0:p,conv1:d,conv2:u}=n(s,i,c,m),l=r(i,i,`${c}/conv3`);return{conv0:p,conv1:d,conv2:u,conv3:l}}return{extractDenseBlock3Params:n,extractDenseBlock4Params:a}}function _o(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock4Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2"),c=n(128,256,"dense3");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i,dense3:c}}}function ar(o){return t=>{let e=o(`${t}/filters`,4),r=o(`${t}/bias`,1);return{filters:e,bias:r}}}function sr(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`);return{conv0:m,conv1:p,conv2:d}}function s(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`),u=n(`${i}/conv3`);return{conv0:m,conv1:p,conv2:d,conv3:u}}return{extractDenseBlock3Params:a,extractDenseBlock4Params:s}}function wo(o){let t=[],{extractDenseBlock4Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2"),dense3:e("dense3")};return W(o,t),{params:r,paramMappings:t}}var Se=class extends S{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceFeatureExtractor - load model before inference");return Nt.tidy(()=>{let r=Nt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Nt.scalar(255)),s=Le(a,e.dense0,!0);return s=Le(s,e.dense1),s=Le(s,e.dense2),s=Le(s,e.dense3),s=Nt.avgPool(s,[7,7],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return wo(t)}extractParams(t){return _o(t)}};var Mo=b(g());var de=b(g());function Ae(o,t){return de.tidy(()=>de.add(de.matMul(o,t.weights),t.bias))}function Do(o,t,e){let r=[],{extractWeights:n,getRemainingWeights:a}=B(o),i=rr(n,r)(t,e,"fc");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:r,params:{fc:i}}}function Eo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:r("fc")};return W(o,t),{params:n,paramMappings:t}}function ir(o){let t={},e={};return Object.keys(o).forEach(r=>{let n=r.startsWith("fc")?e:t;n[r]=o[r]}),{featureExtractorMap:t,classifierMap:e}}var We=class extends S{constructor(t,e){super(t);this._faceFeatureExtractor=e}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return Mo.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t;return Ae(r.as2D(r.shape[0],-1),e.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return Do(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),Eo(r)}extractParams(t){let e=this.getClassifierChannelsIn(),r=this.getClassifierChannelsOut(),n=r*e+r,a=t.slice(0,t.length-n),s=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(s)}};var Jr=["neutral","happy","sad","angry","fearful","disgusted","surprised"],It=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Jr.forEach((e,r)=>{this[e]=t[r]})}asSortedArray(){return Jr.map(t=>({expression:t,probability:this[t]})).sort((t,e)=>e.probability-t.probability)}};var cr=class extends We{constructor(t=new Se){super("FaceExpressionNet",t)}forwardInput(t){return ue.tidy(()=>ue.softmax(this.runNet(t)))}async forward(t){return this.forwardInput(await E(t))}async predictExpressions(t){let e=await E(t),r=await this.forwardInput(e),n=await Promise.all(ue.unstack(r).map(async s=>{let i=await s.data();return s.dispose(),i}));r.dispose();let a=n.map(s=>new It(s));return e.isBatchInput?a:a[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function qr(o){return o.expressions instanceof It}function mr(o,t){return{...o,...{expressions:t}}}function $n(o,t,e=.1,r){(Array.isArray(t)?t:[t]).forEach(a=>{let s=a instanceof It?a:qr(a)?a.expressions:void 0;if(!s)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let c=s.asSortedArray().filter(d=>d.probability>e),m=pt(a)?a.detection.box.bottomLeft:r||new x(0,0);new Mt(c.map(d=>`${d.expression} (${Rt(d.probability)})`),m).draw(o)})}function zt(o){return pt(o)&&o.landmarks instanceof V&&o.unshiftedLandmarks instanceof V&&o.alignedRect instanceof M}function le(o,t){let{box:e}=o.detection,r=t.shiftBy(e.x,e.y),n=r.align(),{imageDims:a}=o.detection,s=new M(o.detection.score,n.rescale(a.reverse()),a);return{...o,...{landmarks:r,unshiftedLandmarks:t,alignedRect:s}}}var Zr=class{constructor(t={}){let{drawLines:e=!0,drawPoints:r=!0,lineWidth:n,lineColor:a,pointSize:s,pointColor:i}=t;this.drawLines=e,this.drawPoints=r,this.lineWidth=n||1,this.pointSize=s||2,this.lineColor=a||"rgba(0, 255, 255, 1)",this.pointColor=i||"rgba(255, 0, 255, 1)"}},Kr=class{constructor(t,e={}){this.faceLandmarks=t,this.options=new Zr(e)}draw(t){let e=O(t),{drawLines:r,drawPoints:n,lineWidth:a,lineColor:s,pointSize:i,pointColor:c}=this.options;if(r&&this.faceLandmarks instanceof oe&&(e.strokeStyle=s,e.lineWidth=a,ft(e,this.faceLandmarks.getJawOutline()),ft(e,this.faceLandmarks.getLeftEyeBrow()),ft(e,this.faceLandmarks.getRightEyeBrow()),ft(e,this.faceLandmarks.getNose()),ft(e,this.faceLandmarks.getLeftEye(),!0),ft(e,this.faceLandmarks.getRightEye(),!0),ft(e,this.faceLandmarks.getMouth(),!0)),n){e.strokeStyle=c,e.fillStyle=c;let m=p=>{e.beginPath(),e.arc(p.x,p.y,i,0,2*Math.PI),e.fill()};this.faceLandmarks.positions.forEach(m)}}};function jn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof V?r:zt(r)?r.landmarks:void 0;if(!n)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new Kr(n).draw(o)})}var Co="0.11.4";var ut=b(g());var I=b(g());function Hn(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c){let m=r(s,i,`${c}/separable_conv0`),p=r(i,i,`${c}/separable_conv1`),d=e(s,i,1,`${c}/expansion_conv`);return{separable_conv0:m,separable_conv1:p,expansion_conv:d}}function a(s,i){let c=r(s,s,`${i}/separable_conv0`),m=r(s,s,`${i}/separable_conv1`),p=r(s,s,`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:e,extractSeparableConvParams:r,extractReductionBlockParams:n,extractMainBlockParams:a}}function No(o,t){let e=[],{extractWeights:r,getRemainingWeights:n}=B(o),{extractConvParams:a,extractSeparableConvParams:s,extractReductionBlockParams:i,extractMainBlockParams:c}=Hn(r,e),m=a(3,32,3,"entry_flow/conv_in"),p=i(32,64,"entry_flow/reduction_block_0"),d=i(64,128,"entry_flow/reduction_block_1"),u={conv_in:m,reduction_block_0:p,reduction_block_1:d},l={};ct(t,0,1).forEach(y=>{l[`main_block_${y}`]=c(128,`middle_flow/main_block_${y}`)});let v=i(128,256,"exit_flow/reduction_block"),_=s(256,512,"exit_flow/separable_conv"),h={reduction_block:v,separable_conv:_};if(n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{paramMappings:e,params:{entry_flow:u,middle_flow:l,exit_flow:h}}}function Yn(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=r(`${i}/expansion_conv`);return{separable_conv0:c,separable_conv1:m,expansion_conv:p}}function s(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=n(`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}}function Io(o,t){let e=[],{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}=Yn(o,e),i=r("entry_flow/conv_in"),c=a("entry_flow/reduction_block_0"),m=a("entry_flow/reduction_block_1"),p={conv_in:i,reduction_block_0:c,reduction_block_1:m},d={};ct(t,0,1).forEach(_=>{d[`main_block_${_}`]=s(`middle_flow/main_block_${_}`)});let u=a("exit_flow/reduction_block"),l=n("exit_flow/separable_conv"),v={reduction_block:u,separable_conv:l};return W(o,e),{params:{entry_flow:p,middle_flow:d,exit_flow:v},paramMappings:e}}function Lo(o,t,e){return I.add(I.conv2d(o,t.filters,e,"same"),t.bias)}function to(o,t,e=!0){let r=e?I.relu(o):o;return r=$(r,t.separable_conv0,[1,1]),r=$(I.relu(r),t.separable_conv1,[1,1]),r=I.maxPool(r,[3,3],[2,2],"same"),r=I.add(r,Lo(o,t.expansion_conv,[2,2])),r}function Gn(o,t){let e=$(I.relu(o),t.separable_conv0,[1,1]);return e=$(I.relu(e),t.separable_conv1,[1,1]),e=$(I.relu(e),t.separable_conv2,[1,1]),e=I.add(e,o),e}var eo=class extends S{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyXception - load model before inference");return I.tidy(()=>{let r=I.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(I.scalar(256)),s=I.relu(Lo(a,e.entry_flow.conv_in,[2,2]));return s=to(s,e.entry_flow.reduction_block_0,!1),s=to(s,e.entry_flow.reduction_block_1),ct(this._numMainBlocks,0,1).forEach(i=>{s=Gn(s,e.middle_flow[`main_block_${i}`])}),s=to(s,e.exit_flow.reduction_block),s=I.relu($(s,e.exit_flow.separable_conv,[1,1])),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return Io(t,this._numMainBlocks)}extractParams(t){return No(t,this._numMainBlocks)}};function ko(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),n=rr(e,t),a=n(512,1,"fc/age"),s=n(512,2,"fc/gender");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{fc:{age:a,gender:s}}}}function So(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:{age:r("fc/age"),gender:r("fc/gender")}};return W(o,t),{params:n,paramMappings:t}}var vt;(function(o){o.FEMALE="female",o.MALE="male"})(vt||(vt={}));var pr=class extends S{constructor(t=new eo(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return ut.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t,n=ut.avgPool(r,[7,7],[2,2],"valid").as2D(r.shape[0],-1),a=Ae(n,e.fc.age).as1D(),s=Ae(n,e.fc.gender);return{age:a,gender:s}})}forwardInput(t){return ut.tidy(()=>{let{age:e,gender:r}=this.runNet(t);return{age:e,gender:ut.softmax(r)}})}async forward(t){return this.forwardInput(await E(t))}async predictAgeAndGender(t){let e=await E(t),r=await this.forwardInput(e),n=ut.unstack(r.age),a=ut.unstack(r.gender),s=n.map((c,m)=>({ageTensor:c,genderTensor:a[m]})),i=await Promise.all(s.map(async({ageTensor:c,genderTensor:m})=>{let p=(await c.data())[0],d=(await m.data())[0],u=d>.5,l=u?vt.MALE:vt.FEMALE,v=u?d:1-d;return c.dispose(),m.dispose(),{age:p,gender:l,genderProbability:v}}));return r.age.dispose(),r.gender.dispose(),e.isBatchInput?i:i[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return ko(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),So(r)}extractParams(t){let e=512*1+1+(512*2+2),r=t.slice(0,t.length-e),n=t.slice(t.length-e);return this.faceFeatureExtractor.extractWeights(r),this.extractClassifierParams(n)}};var H=b(g());var Be=class extends We{postProcess(t,e,r){let n=r.map(({width:s,height:i})=>{let c=e/Math.max(i,s);return{width:s*c,height:i*c}}),a=n.length;return H.tidy(()=>{let s=(d,u)=>H.stack([H.fill([68],d,"float32"),H.fill([68],u,"float32")],1).as2D(1,136).as1D(),i=(d,u)=>{let{width:l,height:v}=n[d];return u(l,v)?Math.abs(l-v)/2:0},c=d=>i(d,(u,l)=>ui(d,(u,l)=>ls(c(u),m(u))))).div(H.stack(Array.from(Array(a),(d,u)=>s(n[u].width,n[u].height))))})}forwardInput(t){return H.tidy(()=>{let e=this.runNet(t);return this.postProcess(e,t.inputSize,t.inputDimensions.map(([r,n])=>({height:r,width:n})))})}async forward(t){return this.forwardInput(await E(t))}async detectLandmarks(t){let e=await E(t),r=H.tidy(()=>H.unstack(this.forwardInput(e))),n=await Promise.all(r.map(async(a,s)=>{let i=Array.from(await a.data()),c=i.filter((p,d)=>ze(d)),m=i.filter((p,d)=>!ze(d));return new oe(Array(68).fill(0).map((p,d)=>new x(c[d],m[d])),{height:e.getInputHeight(s),width:e.getInputWidth(s)})}));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getClassifierChannelsOut(){return 136}};var fe=class extends Be{constructor(t=new Se){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};var Lt=b(g());function Ao(o){let t=[],{extractDenseBlock3Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2")};return W(o,t),{params:r,paramMappings:t}}function Wo(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock3Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i}}}var ro=class extends S{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyFaceFeatureExtractor - load model before inference");return Lt.tidy(()=>{let r=Lt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Lt.scalar(255)),s=Qe(a,e.dense0,!0);return s=Qe(s,e.dense1),s=Qe(s,e.dense2),s=Lt.avgPool(s,[14,14],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return Ao(t)}extractParams(t){return Wo(t)}};var dr=class extends Be{constructor(t=new ro){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Bo=class extends fe{};var U=b(g());var he=b(g());var ur=b(g());function Ro(o,t){return ur.add(ur.mul(o,t.weights),t.biases)}function oo(o,t,e,r,n="same"){let{filters:a,bias:s}=t.conv,i=he.conv2d(o,a,e,n);return i=he.add(i,s),i=Ro(i,t.scale),r?he.relu(i):i}function Oo(o,t){return oo(o,t,[1,1],!0)}function no(o,t){return oo(o,t,[1,1],!1)}function lr(o,t){return oo(o,t,[2,2],!0,"valid")}var Y=b(g());function zn(o,t){function e(i,c,m){let p=o(i),d=p.length/(c*m*m);if(Nr(d))throw new Error(`depth has to be an integer: ${d}, weights.length: ${p.length}, numFilters: ${c}, filterSize: ${m}`);return Y.tidy(()=>Y.transpose(Y.tensor4d(p,[c,d,m,m]),[2,3,1,0]))}function r(i,c,m,p){let d=e(i,c,m),u=Y.tensor1d(o(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/bias`}),{filters:d,bias:u}}function n(i,c){let m=Y.tensor1d(o(i)),p=Y.tensor1d(o(i));return t.push({paramPath:`${c}/weights`},{paramPath:`${c}/biases`}),{weights:m,biases:p}}function a(i,c,m,p){let d=r(i,c,m,`${p}/conv`),u=n(c,`${p}/scale`);return{conv:d,scale:u}}function s(i,c,m,p,d=!1){let u=a((d?.5:1)*i,c,m,`${p}/conv1`),l=a(i,c,m,`${p}/conv2`);return{conv1:u,conv2:l}}return{extractConvLayerParams:a,extractResidualLayerParams:s}}function $o(o){let{extractWeights:t,getRemainingWeights:e}=B(o),r=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=zn(t,r),s=n(4704,32,7,"conv32_down"),i=a(9216,32,3,"conv32_1"),c=a(9216,32,3,"conv32_2"),m=a(9216,32,3,"conv32_3"),p=a(36864,64,3,"conv64_down",!0),d=a(36864,64,3,"conv64_1"),u=a(36864,64,3,"conv64_2"),l=a(36864,64,3,"conv64_3"),v=a(147456,128,3,"conv128_down",!0),_=a(147456,128,3,"conv128_1"),h=a(147456,128,3,"conv128_2"),y=a(589824,256,3,"conv256_down",!0),T=a(589824,256,3,"conv256_1"),F=a(589824,256,3,"conv256_2"),L=a(589824,256,3,"conv256_down_out"),G=Y.tidy(()=>Y.transpose(Y.tensor2d(t(256*128),[128,256]),[1,0]));if(r.push({paramPath:"fc"}),e().length!==0)throw new Error(`weights remaing after extract: ${e().length}`);return{params:{conv32_down:s,conv32_1:i,conv32_2:c,conv32_3:m,conv64_down:p,conv64_1:d,conv64_2:u,conv64_3:l,conv128_down:v,conv128_1:_,conv128_2:h,conv256_down:y,conv256_1:T,conv256_2:F,conv256_down_out:L,fc:G},paramMappings:r}}function Vn(o,t){let e=j(o,t);function r(s){let i=e(`${s}/scale/weights`,1),c=e(`${s}/scale/biases`,1);return{weights:i,biases:c}}function n(s){let i=e(`${s}/conv/filters`,4),c=e(`${s}/conv/bias`,1),m=r(s);return{conv:{filters:i,bias:c},scale:m}}function a(s){return{conv1:n(`${s}/conv1`),conv2:n(`${s}/conv2`)}}return{extractConvLayerParams:n,extractResidualLayerParams:a}}function jo(o){let t=[],{extractConvLayerParams:e,extractResidualLayerParams:r}=Vn(o,t),n=e("conv32_down"),a=r("conv32_1"),s=r("conv32_2"),i=r("conv32_3"),c=r("conv64_down"),m=r("conv64_1"),p=r("conv64_2"),d=r("conv64_3"),u=r("conv128_down"),l=r("conv128_1"),v=r("conv128_2"),_=r("conv256_down"),h=r("conv256_1"),y=r("conv256_2"),T=r("conv256_down_out"),{fc:F}=o;if(t.push({originalPath:"fc",paramPath:"fc"}),!Cr(F))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${F}`);let L={conv32_down:n,conv32_1:a,conv32_2:s,conv32_3:i,conv64_down:c,conv64_1:m,conv64_2:p,conv64_3:d,conv128_down:u,conv128_1:l,conv128_2:v,conv256_down:_,conv256_1:h,conv256_2:y,conv256_down_out:T,fc:F};return W(o,t),{params:L,paramMappings:t}}var R=b(g());function nt(o,t){let e=Oo(o,t.conv1);return e=no(e,t.conv2),e=R.add(e,o),e=R.relu(e),e}function Re(o,t){let e=lr(o,t.conv1);e=no(e,t.conv2);let r=R.avgPool(o,2,2,"valid"),n=R.zeros(r.shape),a=r.shape[3]!==e.shape[3];if(r.shape[1]!==e.shape[1]||r.shape[2]!==e.shape[2]){let i=[...e.shape];i[1]=1;let c=R.zeros(i);e=R.concat([e,c],1);let m=[...e.shape];m[2]=1;let p=R.zeros(m);e=R.concat([e,p],2)}return r=a?R.concat([r,n],3):r,e=R.add(r,e),e=R.relu(e),e}var xe=class extends S{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceRecognitionNet - load model before inference");return U.tidy(()=>{let r=U.cast(t.toBatchTensor(150,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(U.scalar(256)),s=lr(a,e.conv32_down);s=U.maxPool(s,3,2,"valid"),s=nt(s,e.conv32_1),s=nt(s,e.conv32_2),s=nt(s,e.conv32_3),s=Re(s,e.conv64_down),s=nt(s,e.conv64_1),s=nt(s,e.conv64_2),s=nt(s,e.conv64_3),s=Re(s,e.conv128_down),s=nt(s,e.conv128_1),s=nt(s,e.conv128_2),s=Re(s,e.conv256_down),s=nt(s,e.conv256_1),s=nt(s,e.conv256_2),s=Re(s,e.conv256_down_out);let i=s.mean([1,2]);return U.matMul(i,e.fc)})}async forward(t){return this.forwardInput(await E(t))}async computeFaceDescriptor(t){let e=await E(t),r=U.tidy(()=>U.unstack(this.forwardInput(e))),n=await Promise.all(r.map(a=>a.data()));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return jo(t)}extractParams(t){return $o(t)}};function Un(o){let t=new xe;return t.extractWeights(o),t}function fr(o,t){return{...o,...{descriptor:t}}}function Xn(o){return typeof o.age=="number"}function hr(o,t){return{...o,...{age:t}}}function Jn(o){return(o.gender===vt.MALE||o.gender===vt.FEMALE)&&te(o.genderProbability)}function xr(o,t,e){return{...o,...{gender:t,genderProbability:e}}}var st=b(g());var at=b(g());function qn(o,t){function e(c,m){let p=at.tensor4d(o(3*3*c),[3,3,c,1]),d=at.tensor1d(o(c)),u=at.tensor1d(o(c)),l=at.tensor1d(o(c)),v=at.tensor1d(o(c));return t.push({paramPath:`${m}/filters`},{paramPath:`${m}/batch_norm_scale`},{paramPath:`${m}/batch_norm_offset`},{paramPath:`${m}/batch_norm_mean`},{paramPath:`${m}/batch_norm_variance`}),{filters:p,batch_norm_scale:d,batch_norm_offset:u,batch_norm_mean:l,batch_norm_variance:v}}function r(c,m,p,d,u){let l=at.tensor4d(o(c*m*p*p),[p,p,c,m]),v=at.tensor1d(o(m));return t.push({paramPath:`${d}/filters`},{paramPath:`${d}/${u?"batch_norm_offset":"bias"}`}),{filters:l,bias:v}}function n(c,m,p,d){let{filters:u,bias:l}=r(c,m,p,d,!0);return{filters:u,batch_norm_offset:l}}function a(c,m,p){let d=e(c,`${p}/depthwise_conv`),u=n(c,m,1,`${p}/pointwise_conv`);return{depthwise_conv:d,pointwise_conv:u}}function s(){let c=n(3,32,3,"mobilenetv1/conv_0"),m=a(32,64,"mobilenetv1/conv_1"),p=a(64,128,"mobilenetv1/conv_2"),d=a(128,128,"mobilenetv1/conv_3"),u=a(128,256,"mobilenetv1/conv_4"),l=a(256,256,"mobilenetv1/conv_5"),v=a(256,512,"mobilenetv1/conv_6"),_=a(512,512,"mobilenetv1/conv_7"),h=a(512,512,"mobilenetv1/conv_8"),y=a(512,512,"mobilenetv1/conv_9"),T=a(512,512,"mobilenetv1/conv_10"),F=a(512,512,"mobilenetv1/conv_11"),L=a(512,1024,"mobilenetv1/conv_12"),G=a(1024,1024,"mobilenetv1/conv_13");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,conv_8:h,conv_9:y,conv_10:T,conv_11:F,conv_12:L,conv_13:G}}function i(){let c=n(1024,256,1,"prediction_layer/conv_0"),m=n(256,512,3,"prediction_layer/conv_1"),p=n(512,128,1,"prediction_layer/conv_2"),d=n(128,256,3,"prediction_layer/conv_3"),u=n(256,128,1,"prediction_layer/conv_4"),l=n(128,256,3,"prediction_layer/conv_5"),v=n(256,64,1,"prediction_layer/conv_6"),_=n(64,128,3,"prediction_layer/conv_7"),h=r(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=r(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),T=r(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),F=r(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),L=r(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),G=r(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),et=r(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),it=r(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),X=r(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),Pt=r(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),_t=r(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),wt=r(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,box_predictor_0:{box_encoding_predictor:h,class_predictor:y},box_predictor_1:{box_encoding_predictor:T,class_predictor:F},box_predictor_2:{box_encoding_predictor:L,class_predictor:G},box_predictor_3:{box_encoding_predictor:et,class_predictor:it},box_predictor_4:{box_encoding_predictor:X,class_predictor:Pt},box_predictor_5:{box_encoding_predictor:_t,class_predictor:wt}}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:i}}function Ho(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=qn(e,t),s=n(),i=a(),m={extra_dim:at.tensor3d(e(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{params:{mobilenetv1:s,prediction_layer:i,output_layer:m},paramMappings:t}}function Zn(o,t){let e=j(o,t);function r(m,p,d){let u=e(`${m}/Conv2d_${p}_pointwise/weights`,4,`${d}/filters`),l=e(`${m}/Conv2d_${p}_pointwise/convolution_bn_offset`,1,`${d}/batch_norm_offset`);return{filters:u,batch_norm_offset:l}}function n(m){let p=`mobilenetv1/conv_${m}`,d=`MobilenetV1/Conv2d_${m}_depthwise`,u=`${p}/depthwise_conv`,l=`${p}/pointwise_conv`,v=e(`${d}/depthwise_weights`,4,`${u}/filters`),_=e(`${d}/BatchNorm/gamma`,1,`${u}/batch_norm_scale`),h=e(`${d}/BatchNorm/beta`,1,`${u}/batch_norm_offset`),y=e(`${d}/BatchNorm/moving_mean`,1,`${u}/batch_norm_mean`),T=e(`${d}/BatchNorm/moving_variance`,1,`${u}/batch_norm_variance`);return{depthwise_conv:{filters:v,batch_norm_scale:_,batch_norm_offset:h,batch_norm_mean:y,batch_norm_variance:T},pointwise_conv:r("MobilenetV1",m,l)}}function a(){return{conv_0:r("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:n(1),conv_2:n(2),conv_3:n(3),conv_4:n(4),conv_5:n(5),conv_6:n(6),conv_7:n(7),conv_8:n(8),conv_9:n(9),conv_10:n(10),conv_11:n(11),conv_12:n(12),conv_13:n(13)}}function s(m,p){let d=e(`${m}/weights`,4,`${p}/filters`),u=e(`${m}/biases`,1,`${p}/bias`);return{filters:d,bias:u}}function i(m){let p=s(`Prediction/BoxPredictor_${m}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${m}/box_encoding_predictor`),d=s(`Prediction/BoxPredictor_${m}/ClassPredictor`,`prediction_layer/box_predictor_${m}/class_predictor`);return{box_encoding_predictor:p,class_predictor:d}}function c(){return{conv_0:r("Prediction",0,"prediction_layer/conv_0"),conv_1:r("Prediction",1,"prediction_layer/conv_1"),conv_2:r("Prediction",2,"prediction_layer/conv_2"),conv_3:r("Prediction",3,"prediction_layer/conv_3"),conv_4:r("Prediction",4,"prediction_layer/conv_4"),conv_5:r("Prediction",5,"prediction_layer/conv_5"),conv_6:r("Prediction",6,"prediction_layer/conv_6"),conv_7:r("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:i(0),box_predictor_1:i(1),box_predictor_2:i(2),box_predictor_3:i(3),box_predictor_4:i(4),box_predictor_5:i(5)}}return{extractMobilenetV1Params:a,extractPredictionLayerParams:c}}function Yo(o){let t=[],{extractMobilenetV1Params:e,extractPredictionLayerParams:r}=Zn(o,t),n=o["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!ht(n))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${n}`);let a={mobilenetv1:e(),prediction_layer:r(),output_layer:{extra_dim:n}};return W(o,t),{params:a,paramMappings:t}}var yt=b(g());var kt=b(g());function q(o,t,e){return kt.tidy(()=>{let r=kt.conv2d(o,t.filters,e,"same");return r=kt.add(r,t.batch_norm_offset),kt.clipByValue(r,0,6)})}var Kn=.0010000000474974513;function Qn(o,t,e){return yt.tidy(()=>{let r=yt.depthwiseConv2d(o,t.filters,e,"same");return r=yt.batchNorm(r,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Kn),yt.clipByValue(r,0,6)})}function ta(o){return[2,4,6,12].some(t=>t===o)?[2,2]:[1,1]}function Go(o,t){return yt.tidy(()=>{let e,r=q(o,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((a,s)=>{let i=s+1,c=ta(i);r=Qn(r,a.depthwise_conv,c),r=q(r,a.pointwise_conv,[1,1]),i===11&&(e=r)}),e===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:r,conv11:e}})}function ea(o,t,e){let r=o.arraySync(),n=Math.min(r[t][0],r[t][2]),a=Math.min(r[t][1],r[t][3]),s=Math.max(r[t][0],r[t][2]),i=Math.max(r[t][1],r[t][3]),c=Math.min(r[e][0],r[e][2]),m=Math.min(r[e][1],r[e][3]),p=Math.max(r[e][0],r[e][2]),d=Math.max(r[e][1],r[e][3]),u=(s-n)*(i-a),l=(p-c)*(d-m);if(u<=0||l<=0)return 0;let v=Math.max(n,c),_=Math.max(a,m),h=Math.min(s,p),y=Math.min(i,d),T=Math.max(h-v,0)*Math.max(y-_,0);return T/(u+l-T)}function zo(o,t,e,r,n){let a=o.shape[0],s=Math.min(e,a),i=t.map((p,d)=>({score:p,boxIndex:d})).filter(p=>p.score>n).sort((p,d)=>d.score-p.score),c=p=>p<=r?1:0,m=[];return i.forEach(p=>{if(m.length>=s)return;let d=p.score;for(let u=m.length-1;u>=0;--u){let l=ea(o,p.boxIndex,m[u]);if(l!==0&&(p.score*=c(l),p.score<=n))break}d===p.score&&m.push(p.boxIndex)}),m}var f=b(g());function ra(o){let t=f.unstack(f.transpose(o,[1,0])),e=[f.sub(t[2],t[0]),f.sub(t[3],t[1])],r=[f.add(t[0],f.div(e[0],f.scalar(2))),f.add(t[1],f.div(e[1],f.scalar(2)))];return{sizes:e,centers:r}}function oa(o,t){let{sizes:e,centers:r}=ra(o),n=f.unstack(f.transpose(t,[1,0])),a=f.div(f.mul(f.exp(f.div(n[2],f.scalar(5))),e[0]),f.scalar(2)),s=f.add(f.mul(f.div(n[0],f.scalar(10)),e[0]),r[0]),i=f.div(f.mul(f.exp(f.div(n[3],f.scalar(5))),e[1]),f.scalar(2)),c=f.add(f.mul(f.div(n[1],f.scalar(10)),e[1]),r[1]);return f.transpose(f.stack([f.sub(s,a),f.sub(c,i),f.add(s,a),f.add(c,i)]),[1,0])}function Vo(o,t,e){return f.tidy(()=>{let r=o.shape[0],n=oa(f.reshape(f.tile(e.extra_dim,[r,1,1]),[-1,4]),f.reshape(o,[-1,4]));n=f.reshape(n,[r,n.shape[0]/r,4]);let a=f.sigmoid(f.slice(t,[0,0,1],[-1,-1,-1])),s=f.slice(a,[0,0,0],[-1,-1,1]);s=f.reshape(s,[r,s.shape[1]]);let i=f.unstack(n),c=f.unstack(s);return{boxes:i,scores:c}})}var $e=b(g());var Oe=b(g());function Vt(o,t){return Oe.tidy(()=>{let e=o.shape[0],r=Oe.reshape(Gt(o,t.box_encoding_predictor),[e,-1,1,4]),n=Oe.reshape(Gt(o,t.class_predictor),[e,-1,3]);return{boxPredictionEncoding:r,classPrediction:n}})}function Uo(o,t,e){return $e.tidy(()=>{let r=q(o,e.conv_0,[1,1]),n=q(r,e.conv_1,[2,2]),a=q(n,e.conv_2,[1,1]),s=q(a,e.conv_3,[2,2]),i=q(s,e.conv_4,[1,1]),c=q(i,e.conv_5,[2,2]),m=q(c,e.conv_6,[1,1]),p=q(m,e.conv_7,[2,2]),d=Vt(t,e.box_predictor_0),u=Vt(o,e.box_predictor_1),l=Vt(n,e.box_predictor_2),v=Vt(s,e.box_predictor_3),_=Vt(c,e.box_predictor_4),h=Vt(p,e.box_predictor_5),y=$e.concat([d.boxPredictionEncoding,u.boxPredictionEncoding,l.boxPredictionEncoding,v.boxPredictionEncoding,_.boxPredictionEncoding,h.boxPredictionEncoding],1),T=$e.concat([d.classPrediction,u.classPrediction,l.classPrediction,v.classPrediction,_.classPrediction,h.classPrediction],1);return{boxPredictions:y,classPredictions:T}})}var Z=class{constructor({minConfidence:t,maxResults:e}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=e||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Ut=class extends S{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("SsdMobilenetv1 - load model before inference");return st.tidy(()=>{let r=st.cast(t.toBatchTensor(512,!1),"float32"),n=st.sub(st.mul(r,st.scalar(.007843137718737125)),st.scalar(1)),a=Go(n,e.mobilenetv1),{boxPredictions:s,classPredictions:i}=Uo(a.out,a.conv11,e.prediction_layer);return Vo(s,i,e.output_layer)})}async forward(t){return this.forwardInput(await E(t))}async locateFaces(t,e={}){let{maxResults:r,minConfidence:n}=new Z(e),a=await E(t),{boxes:s,scores:i}=this.forwardInput(a),c=s[0],m=i[0];for(let F=1;F{let[L,G]=[Math.max(0,y[F][0]),Math.min(1,y[F][2])].map(X=>X*h),[et,it]=[Math.max(0,y[F][1]),Math.min(1,y[F][3])].map(X=>X*_);return new M(p[F],new re(et,L,it-et,G-L),{height:a.getInputHeight(0),width:a.getInputWidth(0)})});return c.dispose(),m.dispose(),T}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return Yo(t)}extractParams(t){return Ho(t)}};function Xo(o){let t=new Ut;return t.extractWeights(o),t}function na(o){return Xo(o)}var Jo=class extends Ut{};var qo=.4,Zo=[new x(.738768,.874946),new x(2.42204,2.65704),new x(4.30971,7.04493),new x(10.246,4.59428),new x(12.6868,11.8741)],Ko=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],Qo=[117.001,114.697,97.404],tn="tiny_yolov2_model",en="tiny_yolov2_separable_conv_model";var N=b(g());var br=o=>typeof o=="number";function ao(o){if(!o)throw new Error(`invalid config: ${o}`);if(typeof o.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${o.withSeparableConvs}`);if(!br(o.iouThreshold)||o.iouThreshold<0||o.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${o.iouThreshold}`);if(!Array.isArray(o.classes)||!o.classes.length||!o.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(o.classes)}`);if(!Array.isArray(o.anchors)||!o.anchors.length||!o.anchors.map(t=>t||{}).every(t=>br(t.x)&&br(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(o.anchors)}`);if(o.meanRgb&&(!Array.isArray(o.meanRgb)||o.meanRgb.length!==3||!o.meanRgb.every(br)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(o.meanRgb)}`)}var Q=b(g());var K=b(g());function be(o){return K.tidy(()=>{let t=K.mul(o,K.scalar(.10000000149011612));return K.add(K.relu(K.sub(o,t)),t)})}function Ft(o,t){return Q.tidy(()=>{let e=Q.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=Q.conv2d(e,t.conv.filters,[1,1],"valid"),e=Q.sub(e,t.bn.sub),e=Q.mul(e,t.bn.truediv),e=Q.add(e,t.conv.bias),be(e)})}var St=b(g());function Tt(o,t){return St.tidy(()=>{let e=St.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=St.separableConv2d(e,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),e=St.add(e,t.bias),be(e)})}var so=b(g());function aa(o,t){let e=ce(o,t);function r(s,i){let c=so.tensor1d(o(s)),m=so.tensor1d(o(s));return t.push({paramPath:`${i}/sub`},{paramPath:`${i}/truediv`}),{sub:c,truediv:m}}function n(s,i,c){let m=e(s,i,3,`${c}/conv`),p=r(i,`${c}/bn`);return{conv:m,bn:p}}let a=me(o,t);return{extractConvParams:e,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}}function rn(o,t,e,r){let{extractWeights:n,getRemainingWeights:a}=B(o),s=[],{extractConvParams:i,extractConvWithBatchNormParams:c,extractSeparableConvParams:m}=aa(n,s),p;if(t.withSeparableConvs){let[d,u,l,v,_,h,y,T,F]=r,L=t.isFirstLayerConv2d?i(d,u,3,"conv0"):m(d,u,"conv0"),G=m(u,l,"conv1"),et=m(l,v,"conv2"),it=m(v,_,"conv3"),X=m(_,h,"conv4"),Pt=m(h,y,"conv5"),_t=T?m(y,T,"conv6"):void 0,wt=F?m(T,F,"conv7"):void 0,Qt=i(F||T||y,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}else{let[d,u,l,v,_,h,y,T,F]=r,L=c(d,u,"conv0"),G=c(u,l,"conv1"),et=c(l,v,"conv2"),it=c(v,_,"conv3"),X=c(_,h,"conv4"),Pt=c(h,y,"conv5"),_t=c(y,T,"conv6"),wt=c(T,F,"conv7"),Qt=i(F,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:p,paramMappings:s}}function sa(o,t){let e=j(o,t);function r(i){let c=e(`${i}/sub`,1),m=e(`${i}/truediv`,1);return{sub:c,truediv:m}}function n(i){let c=e(`${i}/filters`,4),m=e(`${i}/bias`,1);return{filters:c,bias:m}}function a(i){let c=n(`${i}/conv`),m=r(`${i}/bn`);return{conv:c,bn:m}}let s=pe(e);return{extractConvParams:n,extractConvWithBatchNormParams:a,extractSeparableConvParams:s}}function on(o,t){let e=[],{extractConvParams:r,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}=sa(o,e),s;if(t.withSeparableConvs){let i=t.filterSizes&&t.filterSizes.length||9;s={conv0:t.isFirstLayerConv2d?r("conv0"):a("conv0"),conv1:a("conv1"),conv2:a("conv2"),conv3:a("conv3"),conv4:a("conv4"),conv5:a("conv5"),conv6:i>7?a("conv6"):void 0,conv7:i>8?a("conv7"):void 0,conv8:r("conv8")}}else s={conv0:n("conv0"),conv1:n("conv1"),conv2:n("conv2"),conv3:n("conv3"),conv4:n("conv4"),conv5:n("conv5"),conv6:n("conv6"),conv7:n("conv7"),conv8:r("conv8")};return W(o,e),{params:s,paramMappings:e}}var lt=class{constructor({inputSize:t,scoreThreshold:e}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=e||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var io=class extends S{constructor(t){super("TinyYolov2");ao(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,e){let r=Ft(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=Ft(r,e.conv6),r=Ft(r,e.conv7),Gt(r,e.conv8,"valid",!1)}runMobilenet(t,e){let r=this.config.isFirstLayerConv2d?be(Gt(t,e.conv0,"valid",!1)):Tt(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=e.conv6?Tt(r,e.conv6):r,r=e.conv7?Tt(r,e.conv7):r,Gt(r,e.conv8,"valid",!1)}forwardInput(t,e){let{params:r}=this;if(!r)throw new Error("TinyYolov2 - load model before inference");return N.tidy(()=>{let n=N.cast(t.toBatchTensor(e,!1),"float32");return n=this.config.meanRgb?ot(n,this.config.meanRgb):n,n=n.div(N.scalar(256)),this.config.withSeparableConvs?this.runMobilenet(n,r):this.runTinyYolov2(n,r)})}async forward(t,e){return this.forwardInput(await E(t),e)}async detect(t,e={}){let{inputSize:r,scoreThreshold:n}=new lt(e),a=await E(t),s=await this.forwardInput(a,r),i=N.tidy(()=>N.unstack(s)[0].expandDims()),c={width:a.getInputWidth(0),height:a.getInputHeight(0)},m=await this.extractBoxes(i,a.getReshapedInputDimensions(0),n);s.dispose(),i.dispose();let p=m.map(h=>h.box),d=m.map(h=>h.score),u=m.map(h=>h.classScore),l=m.map(h=>this.config.classes[h.label]);return Sr(p.map(h=>h.rescale(r)),d,this.config.iouThreshold,!0).map(h=>new Dt(d[h],u[h],l[h],p[h],c))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return on(t,this.config)}extractParams(t){let e=this.config.filterSizes||io.DEFAULT_FILTER_SIZES,r=e?e.length:void 0;if(r!==7&&r!==8&&r!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${r} filterSizes in config`);return rn(t,this.config,this.boxEncodingSize,e)}async extractBoxes(t,e,r){let{width:n,height:a}=e,s=Math.max(n,a),i=s/n,c=s/a,m=t.shape[1],p=this.config.anchors.length,[d,u,l]=N.tidy(()=>{let y=t.reshape([m,m,p,this.boxEncodingSize]),T=y.slice([0,0,0,0],[m,m,p,4]),F=y.slice([0,0,0,4],[m,m,p,1]),L=this.withClassScores?N.softmax(y.slice([0,0,0,5],[m,m,p,this.config.classes.length]),3):N.scalar(0);return[T,F,L]}),v=[],_=await u.array(),h=await d.array();for(let y=0;yr){let G=(T+De(h[y][T][F][0]))/m*i,et=(y+De(h[y][T][F][1]))/m*c,it=Math.exp(h[y][T][F][2])*this.config.anchors[F].x/m*i,X=Math.exp(h[y][T][F][3])*this.config.anchors[F].y/m*c,Pt=G-it/2,_t=et-X/2,wt={row:y,col:T,anchor:F},{classScore:Qt,label:lo}=this.withClassScores?await this.extractPredictedClass(l,wt):{classScore:1,label:0};v.push({box:new ee(Pt,_t,Pt+it,_t+X),score:L,classScore:L*Qt,label:lo,...wt})}}return d.dispose(),u.dispose(),l.dispose(),v}async extractPredictedClass(t,e){let{row:r,col:n,anchor:a}=e,s=await t.array();return Array(this.config.classes.length).fill(0).map((i,c)=>s[r][n][a][c]).map((i,c)=>({classScore:i,label:c})).reduce((i,c)=>i.classScore>c.classScore?i:c)}},ge=io;ge.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var ve=class extends ge{constructor(t=!0){let e={withSeparableConvs:t,iouThreshold:qo,classes:["face"],...t?{anchors:Ko,meanRgb:Qo}:{anchors:Zo,withClassScores:!0}};super(e)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?en:tn}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function ia(o,t=!0){let e=new ve(t);return e.extractWeights(o),e}var gr=class extends lt{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var tt=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};var je=b(g());var co=b(g());async function Xt(o,t,e,r,n=({alignedRect:a})=>a){let a=o.map(c=>zt(c)?n(c):c.detection),s=r||(t instanceof co.Tensor?await se(t,a):await ae(t,a)),i=await e(s);return s.forEach(c=>c instanceof co.Tensor&&c.dispose()),i}async function ye(o,t,e,r,n){return Xt([o],t,async a=>e(a[0]),r,n)}var nn=.4,an=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],sn=[117.001,114.697,97.404];var Fe=class extends ge{constructor(){let t={withSeparableConvs:!0,iouThreshold:nn,classes:["face"],anchors:an,meanRgb:sn,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var P={ssdMobilenetv1:new Ut,tinyFaceDetector:new Fe,tinyYolov2:new ve,faceLandmark68Net:new fe,faceLandmark68TinyNet:new dr,faceRecognitionNet:new xe,faceExpressionNet:new cr,ageGenderNet:new pr},cn=(o,t)=>P.ssdMobilenetv1.locateFaces(o,t),ca=(o,t)=>P.tinyFaceDetector.locateFaces(o,t),ma=(o,t)=>P.tinyYolov2.locateFaces(o,t),mn=o=>P.faceLandmark68Net.detectLandmarks(o),pa=o=>P.faceLandmark68TinyNet.detectLandmarks(o),da=o=>P.faceRecognitionNet.computeFaceDescriptor(o),ua=o=>P.faceExpressionNet.predictExpressions(o),la=o=>P.ageGenderNet.predictAgeAndGender(o),pn=o=>P.ssdMobilenetv1.load(o),fa=o=>P.tinyFaceDetector.load(o),ha=o=>P.tinyYolov2.load(o),xa=o=>P.faceLandmark68Net.load(o),ba=o=>P.faceLandmark68TinyNet.load(o),ga=o=>P.faceRecognitionNet.load(o),va=o=>P.faceExpressionNet.load(o),ya=o=>P.ageGenderNet.load(o),Fa=pn,Ta=cn,Pa=mn;var mo=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},_e=class extends mo{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.faceExpressionNet.predictExpressions(n))),this.extractedFaces);return t.map((r,n)=>mr(r,e[n]))}withAgeAndGender(){return new Te(this,this.input)}},we=class extends mo{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceExpressionNet.predictExpressions(r),this.extractedFaces);return mr(t,e)}withAgeAndGender(){return new Pe(this,this.input)}},Zt=class extends _e{withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Kt=class extends we{withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var po=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},Te=class extends po{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.ageGenderNet.predictAgeAndGender(n))),this.extractedFaces);return t.map((r,n)=>{let{age:a,gender:s,genderProbability:i}=e[n];return hr(xr(r,s,i),a)})}withFaceExpressions(){return new _e(this,this.input)}},Pe=class extends po{async run(){let t=await this.parentTask;if(!t)return;let{age:e,gender:r,genderProbability:n}=await ye(t,this.input,a=>P.ageGenderNet.predictAgeAndGender(a),this.extractedFaces);return hr(xr(t,r,n),e)}withFaceExpressions(){return new we(this,this.input)}},Jt=class extends Te{withFaceExpressions(){return new Zt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},qt=class extends Pe{withFaceExpressions(){return new Kt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var vr=class extends tt{constructor(t,e){super();this.parentTask=t;this.input=e}},At=class extends vr{async run(){let t=await this.parentTask;return(await Xt(t,this.input,r=>Promise.all(r.map(n=>P.faceRecognitionNet.computeFaceDescriptor(n))),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}))).map((r,n)=>fr(t[n],r))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}},Wt=class extends vr{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceRecognitionNet.computeFaceDescriptor(r),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}));return fr(t,e)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}};var yr=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.useTinyLandmarkNet=r}get landmarkNet(){return this.useTinyLandmarkNet?P.faceLandmark68TinyNet:P.faceLandmark68Net}},Fr=class extends yr{async run(){let t=await this.parentTask,e=t.map(a=>a.detection),r=this.input instanceof je.Tensor?await se(this.input,e):await ae(this.input,e),n=await Promise.all(r.map(a=>this.landmarkNet.detectLandmarks(a)));return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),t.map((a,s)=>le(a,n[s]))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Tr=class extends yr{async run(){let t=await this.parentTask;if(!t)return;let{detection:e}=t,r=this.input instanceof je.Tensor?await se(this.input,[e]):await ae(this.input,[e]),n=await this.landmarkNet.detectLandmarks(r[0]);return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),le(t,n)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var Pr=class extends tt{constructor(t,e=new Z){super();this.input=t;this.options=e}},He=class extends Pr{async run(){let{input:t,options:e}=this,r=e instanceof gr?n=>P.tinyFaceDetector.locateFaces(n,e):e instanceof Z?n=>P.ssdMobilenetv1.locateFaces(n,e):e instanceof lt?n=>P.tinyYolov2.locateFaces(n,e):null;if(!r)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return r(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let e=await this.run();t(e.map(r=>$t({},r)))})}withFaceLandmarks(t=!1){return new Fr(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new _e(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Te(this.runAndExtendWithFaceDetections(),this.input)}},_r=class extends Pr{async run(){let t=await new He(this.input,this.options),e=t[0];return t.forEach(r=>{r.score>e.score&&(e=r)}),e}runAndExtendWithFaceDetection(){return new Promise(async t=>{let e=await this.run();t(e?$t({},e):void 0)})}withFaceLandmarks(t=!1){return new Tr(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new we(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Pe(this.runAndExtendWithFaceDetection(),this.input)}};function _a(o,t=new Z){return new _r(o,t)}function wr(o,t=new Z){return new He(o,t)}async function dn(o,t){return wr(o,new Z(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function wa(o,t={}){return wr(o,new lt(t)).withFaceLandmarks().withFaceDescriptors()}var Da=dn;function uo(o,t){if(o.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let e=Array.from(o),r=Array.from(t);return Math.sqrt(e.map((n,a)=>n-r[a]).reduce((n,a)=>n+a**2,0))}var Dr=class{constructor(t,e=.6){this._distanceThreshold=e;let r=Array.isArray(t)?t:[t];if(!r.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let n=1,a=()=>`person ${n++}`;this._labeledDescriptors=r.map(s=>{if(s instanceof xt)return s;if(s instanceof Float32Array)return new xt(a(),[s]);if(s.descriptor&&s.descriptor instanceof Float32Array)return new xt(a(),[s.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,e){return e.map(r=>uo(r,t)).reduce((r,n)=>r+n,0)/(e.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:e,label:r})=>new Ee(r,this.computeMeanDistance(t,e))).reduce((e,r)=>e.distancet.toJSON())}}static fromJSON(t){let e=t.labeledDescriptors.map(r=>xt.fromJSON(r));return new Dr(e,t.distanceThreshold)}};function Ea(o){let t=new Fe;return t.extractWeights(o),t}function un(o,t){let{width:e,height:r}=new A(t.width,t.height);if(e<=0||r<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:e,height:r})}`);if(Array.isArray(o))return o.map(n=>un(n,{width:e,height:r}));if(zt(o)){let n=o.detection.forSize(e,r),a=o.unshiftedLandmarks.forSize(n.box.width,n.box.height);return le($t(o,n),a)}return pt(o)?$t(o,o.detection.forSize(e,r)):o instanceof V||o instanceof M?o.forSize(e,r):o}var Ca=typeof process!="undefined",Na=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Ia={faceapi:Co,node:Ca,browser:Na}; +var ln=Object.create,Ye=Object.defineProperty,fn=Object.getPrototypeOf,hn=Object.prototype.hasOwnProperty,xn=Object.getOwnPropertyNames,bn=Object.getOwnPropertyDescriptor;var fo=o=>Ye(o,"__esModule",{value:!0});var ho=(o,t)=>()=>(t||(t={exports:{}},o(t.exports,t)),t.exports),Ge=(o,t)=>{fo(o);for(var e in t)Ye(o,e,{get:t[e],enumerable:!0})},gn=(o,t,e)=>{if(fo(o),t&&typeof t=="object"||typeof t=="function")for(let r of xn(t))!hn.call(o,r)&&r!=="default"&&Ye(o,r,{get:()=>t[r],enumerable:!(e=bn(t,r))||e.enumerable});return o},b=o=>o&&o.__esModule?o:gn(Ye(o!=null?ln(fn(o)):{},"default",{value:o,enumerable:!0}),o);var g=ho(xo=>{var vn=Object.create,Er=Object.defineProperty,yn=Object.getPrototypeOf,Fn=Object.prototype.hasOwnProperty,Tn=Object.getOwnPropertyNames,Pn=Object.getOwnPropertyDescriptor,_n=o=>Er(o,"__esModule",{value:!0}),bo=(o,t,e)=>{if(_n(o),t&&typeof t=="object"||typeof t=="function")for(let r of Tn(t))!Fn.call(o,r)&&r!=="default"&&Er(o,r,{get:()=>t[r],enumerable:!(e=Pn(t,r))||e.enumerable});return o},wn=o=>o&&o.__esModule?o:bo(Er(o!=null?vn(yn(o)):{},"default",{value:o,enumerable:!0}),o);bo(xo,wn(require("@tensorflow/tfjs-node")))});var To=ho((Ln,Fo)=>{Ge(Ln,{isNodejs:()=>kn});function kn(){return typeof global=="object"&&!0&&typeof Fo!="undefined"&&typeof process!="undefined"&&!!process.version}});Ge(exports,{AgeGenderNet:()=>pr,BoundingBox:()=>ee,Box:()=>D,ComposableTask:()=>tt,ComputeAllFaceDescriptorsTask:()=>At,ComputeFaceDescriptorsTaskBase:()=>vr,ComputeSingleFaceDescriptorTask:()=>Wt,DetectAllFaceLandmarksTask:()=>Fr,DetectAllFacesTask:()=>He,DetectFaceLandmarksTaskBase:()=>yr,DetectFacesTaskBase:()=>Pr,DetectSingleFaceLandmarksTask:()=>Tr,DetectSingleFaceTask:()=>_r,Dimensions:()=>A,FACE_EXPRESSION_LABELS:()=>Jr,FaceDetection:()=>M,FaceDetectionNet:()=>Jo,FaceExpressionNet:()=>cr,FaceExpressions:()=>It,FaceLandmark68Net:()=>fe,FaceLandmark68TinyNet:()=>dr,FaceLandmarkNet:()=>Bo,FaceLandmarks:()=>V,FaceLandmarks5:()=>vo,FaceLandmarks68:()=>oe,FaceMatch:()=>Ee,FaceMatcher:()=>Dr,FaceRecognitionNet:()=>xe,Gender:()=>vt,LabeledBox:()=>Me,LabeledFaceDescriptors:()=>xt,NetInput:()=>bt,NeuralNetwork:()=>S,ObjectDetection:()=>Dt,Point:()=>x,PredictedBox:()=>yo,Rect:()=>re,SsdMobilenetv1:()=>Ut,SsdMobilenetv1Options:()=>Z,TinyFaceDetector:()=>Fe,TinyFaceDetectorOptions:()=>gr,TinyYolov2:()=>ve,TinyYolov2Options:()=>lt,allFaces:()=>Da,allFacesSsdMobilenetv1:()=>dn,allFacesTinyYolov2:()=>wa,awaitMediaLoaded:()=>Yr,bufferToImage:()=>Gr,computeFaceDescriptor:()=>da,createCanvas:()=>ne,createCanvasFromMedia:()=>Ie,createFaceDetectionNet:()=>na,createFaceRecognitionNet:()=>Un,createSsdMobilenetv1:()=>Xo,createTinyFaceDetector:()=>Ea,createTinyYolov2:()=>ia,detectAllFaces:()=>wr,detectFaceLandmarks:()=>mn,detectFaceLandmarksTiny:()=>pa,detectLandmarks:()=>Pa,detectSingleFace:()=>_a,draw:()=>Qr,env:()=>w,euclideanDistance:()=>uo,extendWithAge:()=>hr,extendWithFaceDescriptor:()=>fr,extendWithFaceDetection:()=>$t,extendWithFaceExpressions:()=>mr,extendWithFaceLandmarks:()=>le,extendWithGender:()=>xr,extractFaceTensors:()=>se,extractFaces:()=>ae,fetchImage:()=>Bn,fetchJson:()=>Ur,fetchNetWeights:()=>Rn,fetchOrThrow:()=>Yt,getContext2dOrThrow:()=>O,getMediaDimensions:()=>Ht,imageTensorToCanvas:()=>zr,imageToSquare:()=>Vr,inverseSigmoid:()=>Mn,iou:()=>Lr,isMediaElement:()=>qe,isMediaLoaded:()=>Ne,isWithAge:()=>Xn,isWithFaceDetection:()=>pt,isWithFaceExpressions:()=>qr,isWithFaceLandmarks:()=>zt,isWithGender:()=>Jn,loadAgeGenderModel:()=>ya,loadFaceDetectionModel:()=>Fa,loadFaceExpressionModel:()=>va,loadFaceLandmarkModel:()=>xa,loadFaceLandmarkTinyModel:()=>ba,loadFaceRecognitionModel:()=>ga,loadSsdMobilenetv1Model:()=>pn,loadTinyFaceDetectorModel:()=>fa,loadTinyYolov2Model:()=>ha,loadWeightMap:()=>Xr,locateFaces:()=>Ta,matchDimensions:()=>On,minBbox:()=>kr,nets:()=>P,nonMaxSuppression:()=>Sr,normalize:()=>ot,padToSquare:()=>Ar,predictAgeAndGender:()=>la,recognizeFaceExpressions:()=>ua,resizeResults:()=>un,resolveInput:()=>jt,shuffleArray:()=>En,sigmoid:()=>De,ssdMobilenetv1:()=>cn,tf:()=>Ma,tinyFaceDetector:()=>ca,tinyYolov2:()=>ma,toNetInput:()=>E,utils:()=>Mr,validateConfig:()=>ao,version:()=>Ia});var Ma=b(g());var Qr={};Ge(Qr,{AnchorPosition:()=>dt,DrawBox:()=>Xe,DrawBoxOptions:()=>Hr,DrawFaceLandmarks:()=>Kr,DrawFaceLandmarksOptions:()=>Zr,DrawTextField:()=>Mt,DrawTextFieldOptions:()=>Ce,drawContour:()=>ft,drawDetections:()=>Wn,drawFaceExpressions:()=>$n,drawFaceLandmarks:()=>jn});function ft(o,t,e=!1){if(o.beginPath(),t.slice(1).forEach(({x:r,y:n},a)=>{let s=t[a];o.moveTo(s.x,s.y),o.lineTo(r,n)}),e){let r=t[t.length-1],n=t[0];if(!r||!n)return;o.moveTo(r.x,r.y),o.lineTo(n.x,n.y)}o.stroke()}var Mr={};Ge(Mr,{computeReshapedDimensions:()=>Ir,getCenterPoint:()=>Ot,isDimensions:()=>Ve,isEven:()=>ze,isFloat:()=>Nr,isTensor:()=>Bt,isTensor1D:()=>Dn,isTensor2D:()=>Cr,isTensor3D:()=>ht,isTensor4D:()=>z,isValidNumber:()=>rt,isValidProbablitiy:()=>te,range:()=>ct,round:()=>Rt});var go=b(g());var A=class{constructor(t,e){if(!rt(t)||!rt(e))throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({width:t,height:e})}`);this._width=t,this._height=e}get width(){return this._width}get height(){return this._height}reverse(){return new A(1/this.width,1/this.height)}};function Bt(o,t){return o instanceof go.Tensor&&o.shape.length===t}function Dn(o){return Bt(o,1)}function Cr(o){return Bt(o,2)}function ht(o){return Bt(o,3)}function z(o){return Bt(o,4)}function Nr(o){return o%1!=0}function ze(o){return o%2==0}function Rt(o,t=2){let e=10**t;return Math.floor(o*e)/e}function Ve(o){return o&&o.width&&o.height}function Ir({width:o,height:t},e){let r=e/Math.max(t,o);return new A(Math.round(o*r),Math.round(t*r))}function Ot(o){return o.reduce((t,e)=>t.add(e),new x(0,0)).div(new x(o.length,o.length))}function ct(o,t,e){return Array(o).fill(0).map((r,n)=>t+n*e)}function rt(o){return!!o&&o!==Infinity&&o!==-Infinity&&!Number.isNaN(o)||o===0}function te(o){return rt(o)&&o>=0&&o<=1}var x=class{constructor(t,e){this._x=t,this._y=e}get x(){return this._x}get y(){return this._y}add(t){return new x(this.x+t.x,this.y+t.y)}sub(t){return new x(this.x-t.x,this.y-t.y)}mul(t){return new x(this.x*t.x,this.y*t.y)}div(t){return new x(this.x/t.x,this.y/t.y)}abs(){return new x(Math.abs(this.x),Math.abs(this.y))}magnitude(){return Math.sqrt(this.x**2+this.y**2)}floor(){return new x(Math.floor(this.x),Math.floor(this.y))}};var D=class{static isRect(t){return!!t&&[t.x,t.y,t.width,t.height].every(rt)}static assertIsValidBox(t,e,r=!1){if(!D.isRect(t))throw new Error(`${e} - invalid box: ${JSON.stringify(t)}, expected object with properties x, y, width, height`);if(!r&&(t.width<0||t.height<0))throw new Error(`${e} - width (${t.width}) and height (${t.height}) must be positive numbers`)}constructor(t,e=!0){let r=t||{},n=[r.left,r.top,r.right,r.bottom].every(rt),a=[r.x,r.y,r.width,r.height].every(rt);if(!a&&!n)throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(r)}`);let[s,i,c,m]=a?[r.x,r.y,r.width,r.height]:[r.left,r.top,r.right-r.left,r.bottom-r.top];D.assertIsValidBox({x:s,y:i,width:c,height:m},"Box.constructor",e),this._x=s,this._y=i,this._width=c,this._height=m}get x(){return this._x}get y(){return this._y}get width(){return this._width}get height(){return this._height}get left(){return this.x}get top(){return this.y}get right(){return this.x+this.width}get bottom(){return this.y+this.height}get area(){return this.width*this.height}get topLeft(){return new x(this.left,this.top)}get topRight(){return new x(this.right,this.top)}get bottomLeft(){return new x(this.left,this.bottom)}get bottomRight(){return new x(this.right,this.bottom)}round(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.round(a));return new D({x:t,y:e,width:r,height:n})}floor(){let[t,e,r,n]=[this.x,this.y,this.width,this.height].map(a=>Math.floor(a));return new D({x:t,y:e,width:r,height:n})}toSquare(){let{x:t,y:e,width:r,height:n}=this,a=Math.abs(r-n);return re&&(i=-d+e+r,d=e),u>t&&(c=-u+t+n,u=t),m<1&&(c=2-m,m=1),p<1&&(c=2-p,p=1),{dy:s,edy:c,dx:a,edx:i,y:p,ey:u,x:m,ex:d,w:r,h:n}}calibrate(t){return new D({left:this.left+t.left*this.width,top:this.top+t.top*this.height,right:this.right+t.right*this.width,bottom:this.bottom+t.bottom*this.height}).toSquare().round()}};var ee=class extends D{constructor(t,e,r,n,a=!1){super({left:t,top:e,right:r,bottom:n},a)}};var Dt=class{constructor(t,e,r,n,a){this._imageDims=new A(a.width,a.height),this._score=t,this._classScore=e,this._className=r,this._box=new D(n).rescale(this._imageDims)}get score(){return this._score}get classScore(){return this._classScore}get className(){return this._className}get box(){return this._box}get imageDims(){return this._imageDims}get imageWidth(){return this.imageDims.width}get imageHeight(){return this.imageDims.height}get relativeBox(){return new D(this._box).rescale(this.imageDims.reverse())}forSize(t,e){return new Dt(this.score,this.classScore,this.className,this.relativeBox,{width:t,height:e})}};var M=class extends Dt{constructor(t,e,r){super(t,t,"",e,r)}forSize(t,e){let{score:r,relativeBox:n,imageDims:a}=super.forSize(t,e);return new M(r,n,a)}};function Lr(o,t,e=!0){let r=Math.max(0,Math.min(o.right,t.right)-Math.max(o.left,t.left)),n=Math.max(0,Math.min(o.bottom,t.bottom)-Math.max(o.top,t.top)),a=r*n;return e?a/(o.area+t.area-a):a/Math.min(o.area,t.area)}function kr(o){let t=o.map(i=>i.x),e=o.map(i=>i.y),r=t.reduce((i,c)=>ccii({score:s,boxIndex:i})).sort((s,i)=>s.score-i.score).map(s=>s.boxIndex),a=[];for(;n.length>0;){let s=n.pop();a.push(s);let i=n,c=[];for(let m=0;mc[p]<=e)}return a}var mt=b(g());function ot(o,t){return mt.tidy(()=>{let[e,r,n]=t,a=mt.fill([...o.shape.slice(0,3),1],e,"float32"),s=mt.fill([...o.shape.slice(0,3),1],r,"float32"),i=mt.fill([...o.shape.slice(0,3),1],n,"float32"),c=mt.concat([a,s,i],3);return mt.sub(o,c)})}var Et=b(g());function Ar(o,t=!1){return Et.tidy(()=>{let[e,r]=o.shape.slice(1);if(e===r)return o;let n=Math.abs(e-r),a=Math.round(n*(t?.5:1)),s=e>r?2:1,i=u=>{let l=o.shape.slice();return l[s]=u,Et.fill(l,0,"float32")},c=i(a),m=n-c.shape[s],d=[t&&m?i(m):null,o,c].filter(u=>!!u).map(u=>Et.cast(u,"float32"));return Et.concat(d,s)})}function En(o){let t=o.slice();for(let e=t.length-1;e>0;e--){let r=Math.floor(Math.random()*(e+1)),n=t[e];t[e]=t[r],t[r]=n}return t}function De(o){return 1/(1+Math.exp(-o))}function Mn(o){return Math.log(o/(1-o))}var re=class extends D{constructor(t,e,r,n,a=!1){super({x:t,y:e,width:r,height:n},a)}};var Cn=.5,Nn=.43,In=.45,V=class{constructor(t,e,r=new x(0,0)){let{width:n,height:a}=e;this._imgDims=new A(n,a),this._shift=r,this._positions=t.map(s=>s.mul(new x(n,a)).add(r))}get shift(){return new x(this._shift.x,this._shift.y)}get imageWidth(){return this._imgDims.width}get imageHeight(){return this._imgDims.height}get positions(){return this._positions}get relativePositions(){return this._positions.map(t=>t.sub(this._shift).div(new x(this.imageWidth,this.imageHeight)))}forSize(t,e){return new this.constructor(this.relativePositions,{width:t,height:e})}shiftBy(t,e){return new this.constructor(this.relativePositions,this._imgDims,new x(t,e))}shiftByPoint(t){return this.shiftBy(t.x,t.y)}align(t,e={}){if(t){let a=t instanceof M?t.box.floor():new D(t);return this.shiftBy(a.x,a.y).align(null,e)}let{useDlibAlignment:r,minBoxPadding:n}={useDlibAlignment:!1,minBoxPadding:.2,...e};return r?this.alignDlib():this.alignMinBbox(n)}alignDlib(){let t=this.getRefPointsForAlignment(),[e,r,n]=t,a=d=>n.sub(d).magnitude(),s=(a(e)+a(r))/2,i=Math.floor(s/In),c=Ot(t),m=Math.floor(Math.max(0,c.x-Cn*i)),p=Math.floor(Math.max(0,c.y-Nn*i));return new re(m,p,Math.min(i,this.imageWidth+m),Math.min(i,this.imageHeight+p))}alignMinBbox(t){let e=kr(this.positions);return e.pad(e.width*t,e.height*t)}getRefPointsForAlignment(){throw new Error("getRefPointsForAlignment not implemented by base class")}};var vo=class extends V{getRefPointsForAlignment(){let t=this.positions;return[t[0],t[1],Ot([t[3],t[4]])]}};var oe=class extends V{getJawOutline(){return this.positions.slice(0,17)}getLeftEyeBrow(){return this.positions.slice(17,22)}getRightEyeBrow(){return this.positions.slice(22,27)}getNose(){return this.positions.slice(27,36)}getLeftEye(){return this.positions.slice(36,42)}getRightEye(){return this.positions.slice(42,48)}getMouth(){return this.positions.slice(48,68)}getRefPointsForAlignment(){return[this.getLeftEye(),this.getRightEye(),this.getMouth()].map(Ot)}};var Ee=class{constructor(t,e){this._label=t,this._distance=e}get label(){return this._label}get distance(){return this._distance}toString(t=!0){return`${this.label}${t?` (${Rt(this.distance)})`:""}`}};var Me=class extends D{static assertIsValidLabeledBox(t,e){if(D.assertIsValidBox(t,e),!rt(t.label))throw new Error(`${e} - expected property label (${t.label}) to be a number`)}constructor(t,e){super(t);this._label=e}get label(){return this._label}};var xt=class{constructor(t,e){if(typeof t!="string")throw new Error("LabeledFaceDescriptors - constructor expected label to be a string");if(!Array.isArray(e)||e.some(r=>!(r instanceof Float32Array)))throw new Error("LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array");this._label=t,this._descriptors=e}get label(){return this._label}get descriptors(){return this._descriptors}toJSON(){return{label:this.label,descriptors:this.descriptors.map(t=>Array.from(t))}}static fromJSON(t){let e=t.descriptors.map(r=>new Float32Array(r));return new xt(t.label,e)}};var yo=class extends Me{static assertIsValidPredictedBox(t,e){if(Me.assertIsValidLabeledBox(t,e),!te(t.score)||!te(t.classScore))throw new Error(`${e} - expected properties score (${t.score}) and (${t.classScore}) to be a number between [0, 1]`)}constructor(t,e,r,n){super(t,e);this._score=r,this._classScore=n}get score(){return this._score}get classScore(){return this._classScore}};function pt(o){return o.detection instanceof M}function $t(o,t){return{...o,...{detection:t}}}function Wr(){let o=window.fetch;if(!o)throw new Error("fetch - missing fetch implementation for browser environment");let t=()=>{throw new Error("readFile - filesystem not available for browser environment")};return{Canvas:HTMLCanvasElement,CanvasRenderingContext2D,Image:HTMLImageElement,ImageData,Video:HTMLVideoElement,createCanvasElement:()=>document.createElement("canvas"),createImageElement:()=>document.createElement("img"),fetch:o,readFile:t}}function Ue(o){let t="";if(!o)try{o=require("fs")}catch(r){t=r.toString()}return{readFile:o?r=>new Promise((n,a)=>{o.readFile(r,(s,i)=>s?a(s):n(i))}):()=>{throw new Error(`readFile - failed to require fs in nodejs environment with error: ${t}`)}}}function Br(){let o=global.Canvas||global.HTMLCanvasElement,t=global.Image||global.HTMLImageElement,e=()=>{if(o)return new o;throw new Error("createCanvasElement - missing Canvas implementation for nodejs environment")},r=()=>{if(t)return new t;throw new Error("createImageElement - missing Image implementation for nodejs environment")},n=global.fetch,a=Ue();return{Canvas:o||class{},CanvasRenderingContext2D:global.CanvasRenderingContext2D||class{},Image:t||class{},ImageData:global.ImageData||class{},Video:global.HTMLVideoElement||class{},createCanvasElement:e,createImageElement:r,fetch:n,...a}}function Rr(){return typeof window=="object"&&typeof document!="undefined"&&typeof HTMLImageElement!="undefined"&&typeof HTMLCanvasElement!="undefined"&&typeof HTMLVideoElement!="undefined"&&typeof ImageData!="undefined"&&typeof CanvasRenderingContext2D!="undefined"}var Or=b(To()),k;function Sn(){if(!k)throw new Error("getEnv - environment is not defined, check isNodejs() and isBrowser()");return k}function $r(o){k=o}function jr(){return Rr()?$r(Wr()):Or.isNodejs()?$r(Br()):null}function An(o){if(k||jr(),!k)throw new Error("monkeyPatch - environment is not defined, check isNodejs() and isBrowser()");let{Canvas:t=k.Canvas,Image:e=k.Image}=o;k.Canvas=t,k.Image=e,k.createCanvasElement=o.createCanvasElement||(()=>new t),k.createImageElement=o.createImageElement||(()=>new e),k.ImageData=o.ImageData||k.ImageData,k.Video=o.Video||k.Video,k.fetch=o.fetch||k.fetch,k.readFile=o.readFile||k.readFile}var w={getEnv:Sn,setEnv:$r,initialize:jr,createBrowserEnv:Wr,createFileSystem:Ue,createNodejsEnv:Br,monkeyPatch:An,isBrowser:Rr,isNodejs:Or.isNodejs};jr();function jt(o){return!w.isNodejs()&&typeof o=="string"?document.getElementById(o):o}function O(o){let{Canvas:t,CanvasRenderingContext2D:e}=w.getEnv();if(o instanceof e)return o;let r=jt(o);if(!(r instanceof t))throw new Error("resolveContext2d - expected canvas to be of instance of Canvas");let n=r.getContext("2d");if(!n)throw new Error("resolveContext2d - canvas 2d context is null");return n}var dt;(function(o){o.TOP_LEFT="TOP_LEFT",o.TOP_RIGHT="TOP_RIGHT",o.BOTTOM_LEFT="BOTTOM_LEFT",o.BOTTOM_RIGHT="BOTTOM_RIGHT"})(dt||(dt={}));var Ce=class{constructor(t={}){let{anchorPosition:e,backgroundColor:r,fontColor:n,fontSize:a,fontStyle:s,padding:i}=t;this.anchorPosition=e||dt.TOP_LEFT,this.backgroundColor=r||"rgba(0, 0, 0, 0.5)",this.fontColor=n||"rgba(255, 255, 255, 1)",this.fontSize=a||14,this.fontStyle=s||"Georgia",this.padding=i||4}},Mt=class{constructor(t,e,r={}){this.text=typeof t=="string"?[t]:t instanceof Mt?t.text:t,this.anchor=e,this.options=new Ce(r)}measureWidth(t){let{padding:e}=this.options;return this.text.map(r=>t.measureText(r).width).reduce((r,n)=>r{let v=c+d.x,_=c+d.y+(l+1)*s;r.fillText(u,v,_)})}};var Hr=class{constructor(t={}){let{boxColor:e,lineWidth:r,label:n,drawLabelOptions:a}=t;this.boxColor=e||"rgba(0, 0, 255, 1)",this.lineWidth=r||2,this.label=n;let s={anchorPosition:dt.BOTTOM_LEFT,backgroundColor:this.boxColor};this.drawLabelOptions=new Ce({...s,...a})}},Xe=class{constructor(t,e={}){this.box=new D(t),this.options=new Hr(e)}draw(t){let e=O(t),{boxColor:r,lineWidth:n}=this.options,{x:a,y:s,width:i,height:c}=this.box;e.strokeStyle=r,e.lineWidth=n,e.strokeRect(a,s,i,c);let{label:m}=this.options;m&&new Mt([m],{x:a-n/2,y:s},this.options.drawLabelOptions).draw(t)}};function Wn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof M?r.score:pt(r)?r.detection.score:void 0,a=r instanceof M?r.box:pt(r)?r.detection.box:new D(r),s=n?`${Rt(n)}`:void 0;new Xe(a,{label:s}).draw(o)})}var ue=b(g());function Ne(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t&&o.complete||o instanceof e&&o.readyState>=3}function Yr(o){return new Promise((t,e)=>{if(o instanceof w.getEnv().Canvas||Ne(o))return t(null);function r(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),e(a))}function n(a){!a.currentTarget||(a.currentTarget.removeEventListener("load",n),a.currentTarget.removeEventListener("error",r),t(a))}o.addEventListener("load",n),o.addEventListener("error",r)})}function Gr(o){return new Promise((t,e)=>{o instanceof Blob||e(new Error("bufferToImage - expected buf to be of type: Blob"));let r=new FileReader;r.onload=()=>{typeof r.result!="string"&&e(new Error("bufferToImage - expected reader.result to be a string, in onload"));let n=w.getEnv().createImageElement();n.onload=()=>t(n),n.onerror=e,n.src=r.result},r.onerror=e,r.readAsDataURL(o)})}function Ht(o){let{Image:t,Video:e}=w.getEnv();return o instanceof t?new A(o.naturalWidth,o.naturalHeight):o instanceof e?new A(o.videoWidth,o.videoHeight):new A(o.width,o.height)}function ne({width:o,height:t}){let{createCanvasElement:e}=w.getEnv(),r=e();return r.width=o,r.height=t,r}function Ie(o,t){let{ImageData:e}=w.getEnv();if(!(o instanceof e)&&!Ne(o))throw new Error("createCanvasFromMedia - media has not finished loading yet");let{width:r,height:n}=t||Ht(o),a=ne({width:r,height:n});return o instanceof e?O(a).putImageData(o,0,0):O(a).drawImage(o,0,0,r,n),a}var Je=b(g());async function zr(o,t){let e=t||w.getEnv().createCanvasElement(),[r,n,a]=o.shape.slice(z(o)?1:0),s=Je.tidy(()=>o.as3D(r,n,a).toInt());return await Je.browser.toPixels(s,e),s.dispose(),e}function qe(o){let{Image:t,Canvas:e,Video:r}=w.getEnv();return o instanceof t||o instanceof e||o instanceof r}var J=b(g());function Vr(o,t,e=!1){let{Image:r,Canvas:n}=w.getEnv();if(!(o instanceof r||o instanceof n))throw new Error("imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement");let a=Ht(o),s=t/Math.max(a.height,a.width),i=s*a.width,c=s*a.height,m=ne({width:t,height:t}),p=o instanceof n?o:Ie(o),d=Math.abs(i-c)/2,u=e&&i{if(ht(r)){this._imageTensors[n]=r,this._inputDimensions[n]=r.shape;return}if(z(r)){let s=r.shape[0];if(s!==1)throw new Error(`NetInput - tf.Tensor4D with batchSize ${s} passed, but not supported in input array`);this._imageTensors[n]=r,this._inputDimensions[n]=r.shape.slice(1);return}let a=r instanceof w.getEnv().Canvas?r:Ie(r);this._canvases[n]=a,this._inputDimensions[n]=[a.height,a.width,3]})}get imageTensors(){return this._imageTensors}get canvases(){return this._canvases}get isBatchInput(){return this.batchSize>1||this._treatAsBatchInput}get batchSize(){return this._batchSize}get inputDimensions(){return this._inputDimensions}get inputSize(){return this._inputSize}get reshapedInputDimensions(){return ct(this.batchSize,0,1).map((t,e)=>this.getReshapedInputDimensions(e))}getInput(t){return this.canvases[t]||this.imageTensors[t]}getInputDimensions(t){return this._inputDimensions[t]}getInputHeight(t){return this._inputDimensions[t][0]}getInputWidth(t){return this._inputDimensions[t][1]}getReshapedInputDimensions(t){if(typeof this.inputSize!="number")throw new Error("getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet");let e=this.getInputWidth(t),r=this.getInputHeight(t);return Ir({width:e,height:r},this.inputSize)}toBatchTensor(t,e=!0){return this._inputSize=t,J.tidy(()=>{let r=ct(this.batchSize,0,1).map(a=>{let s=this.getInput(a);if(s instanceof J.Tensor){let i=z(s)?s:s.expandDims();return i=Ar(i,e),(i.shape[1]!==t||i.shape[2]!==t)&&(i=J.image.resizeBilinear(i,[t,t])),i.as3D(t,t,3)}if(s instanceof w.getEnv().Canvas)return J.browser.fromPixels(Vr(s,t,e));throw new Error(`toBatchTensor - at batchIdx ${a}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${s}`)});return J.stack(r.map(a=>J.cast(a,"float32"))).as4D(this.batchSize,t,t,3)})}};async function E(o){if(o instanceof bt)return o;let t=Array.isArray(o)?o:[o];if(!t.length)throw new Error("toNetInput - empty array passed as input");let e=n=>Array.isArray(o)?` at input index ${n}:`:"",r=t.map(jt);return r.forEach((n,a)=>{if(!qe(n)&&!ht(n)&&!z(n))throw typeof t[a]=="string"?new Error(`toNetInput -${e(a)} string passed, but could not resolve HTMLElement for element id ${t[a]}`):new Error(`toNetInput -${e(a)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);if(z(n)){let s=n.shape[0];if(s!==1)throw new Error(`toNetInput -${e(a)} tf.Tensor4D with batchSize ${s} passed, but not supported in input array`)}}),await Promise.all(r.map(n=>qe(n)&&Yr(n))),new bt(r,Array.isArray(o))}async function ae(o,t){let{Canvas:e}=w.getEnv(),r=o;if(!(o instanceof e)){let s=await E(o);if(s.batchSize>1)throw new Error("extractFaces - batchSize > 1 not supported");let i=s.getInput(0);r=i instanceof e?i:await zr(i)}let n=O(r);return t.map(s=>s instanceof M?s.forSize(r.width,r.height).box.floor():s).map(s=>s.clipAtImageBorders(r.width,r.height)).map(({x:s,y:i,width:c,height:m})=>{let p=ne({width:c,height:m});return O(p).putImageData(n.getImageData(s,i,c,m),0,0),p})}var Ze=b(g());async function se(o,t){if(!ht(o)&&!z(o))throw new Error("extractFaceTensors - expected image tensor to be 3D or 4D");if(z(o)&&o.shape[0]>1)throw new Error("extractFaceTensors - batchSize > 1 not supported");return Ze.tidy(()=>{let[e,r,n]=o.shape.slice(z(o)?1:0);return t.map(i=>i instanceof M?i.forSize(r,e).box:i).map(i=>i.clipAtImageBorders(r,e)).map(({x:i,y:c,width:m,height:p})=>Ze.slice3d(o.as3D(e,r,n),[c,i,0],[p,m,n]))})}async function Yt(o,t){let{fetch:e}=w.getEnv(),r=await e(o,t);if(!(r.status<400))throw new Error(`failed to fetch: (${r.status}) ${r.statusText}, from url: ${r.url}`);return r}async function Bn(o){let t=await Yt(o),e=await t.blob();if(!e.type.startsWith("image/"))throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${e.type}, for url: ${t.url}`);return Gr(e)}async function Ur(o){return(await Yt(o)).json()}async function Rn(o){return new Float32Array(await(await Yt(o)).arrayBuffer())}var Po=b(g());function Ke(o,t){let e=`${t}-weights_manifest.json`;if(!o)return{modelBaseUri:"",manifestUri:e};if(o==="/")return{modelBaseUri:"/",manifestUri:`/${e}`};let r=o.startsWith("http://")?"http://":o.startsWith("https://")?"https://":"";o=o.replace(r,"");let n=o.split("/").filter(i=>i),a=o.endsWith(".json")?n[n.length-1]:e,s=r+(o.endsWith(".json")?n.slice(0,n.length-1):n).join("/");return s=o.startsWith("/")?`/${s}`:s,{modelBaseUri:s,manifestUri:s==="/"?`/${a}`:`${s}/${a}`}}async function Xr(o,t){let{manifestUri:e,modelBaseUri:r}=Ke(o,t),n=await Ur(e);return Po.io.loadWeights(n,r)}function On(o,t,e=!1){let{width:r,height:n}=e?Ht(t):t;return o.width=r,o.height=n,{width:r,height:n}}var Nt=b(g());var gt=b(g());var S=class{constructor(t){this._params=void 0;this._paramMappings=[];this._name=t}get params(){return this._params}get paramMappings(){return this._paramMappings}get isLoaded(){return!!this.params}getParamFromPath(t){let{obj:e,objProp:r}=this.traversePropertyPath(t);return e[r]}reassignParamFromPath(t,e){let{obj:r,objProp:n}=this.traversePropertyPath(t);r[n].dispose(),r[n]=e}getParamList(){return this._paramMappings.map(({paramPath:t})=>({path:t,tensor:this.getParamFromPath(t)}))}getTrainableParams(){return this.getParamList().filter(t=>t.tensor instanceof gt.Variable)}getFrozenParams(){return this.getParamList().filter(t=>!(t.tensor instanceof gt.Variable))}variable(){this.getFrozenParams().forEach(({path:t,tensor:e})=>{this.reassignParamFromPath(t,e.variable())})}freeze(){this.getTrainableParams().forEach(({path:t,tensor:e})=>{let r=gt.tensor(e.dataSync());e.dispose(),this.reassignParamFromPath(t,r)})}dispose(t=!0){this.getParamList().forEach(e=>{if(t&&e.tensor.isDisposed)throw new Error(`param tensor has already been disposed for path ${e.path}`);e.tensor.dispose()}),this._params=void 0}serializeParams(){return new Float32Array(this.getParamList().map(({tensor:t})=>Array.from(t.dataSync())).reduce((t,e)=>t.concat(e)))}async load(t){if(t instanceof Float32Array){this.extractWeights(t);return}await this.loadFromUri(t)}async loadFromUri(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromUri - expected model uri`);let e=await Xr(t,this.getDefaultModelName());this.loadFromWeightMap(e)}async loadFromDisk(t){if(t&&typeof t!="string")throw new Error(`${this._name}.loadFromDisk - expected model file path`);let{readFile:e}=w.getEnv(),{manifestUri:r,modelBaseUri:n}=Ke(t,this.getDefaultModelName()),a=m=>Promise.all(m.map(p=>e(p).then(d=>d.buffer))),s=gt.io.weightsLoaderFactory(a),i=JSON.parse((await e(r)).toString()),c=await s(i,n);this.loadFromWeightMap(c)}loadFromWeightMap(t){let{paramMappings:e,params:r}=this.extractParamsFromWeightMap(t);this._paramMappings=e,this._params=r}extractWeights(t){let{paramMappings:e,params:r}=this.extractParams(t);this._paramMappings=e,this._params=r}traversePropertyPath(t){if(!this.params)throw new Error("traversePropertyPath - model has no loaded params");let e=t.split("/").reduce((a,s)=>{if(!a.nextObj.hasOwnProperty(s))throw new Error(`traversePropertyPath - object does not have property ${s}, for path ${t}`);return{obj:a.nextObj,objProp:s,nextObj:a.nextObj[s]}},{nextObj:this.params}),{obj:r,objProp:n}=e;if(!r||!n||!(r[n]instanceof gt.Tensor))throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${t}`);return{obj:r,objProp:n}}};var C=b(g());var ie=b(g());function $(o,t,e){return ie.tidy(()=>{let r=ie.separableConv2d(o,t.depthwise_filter,t.pointwise_filter,e,"same");return r=ie.add(r,t.bias),r})}function Qe(o,t,e=!1){return C.tidy(()=>{let r=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,[2,2],"same"),t.conv0.bias):$(o,t.conv0,[2,2])),n=$(r,t.conv1,[1,1]),a=C.relu(C.add(r,n)),s=$(a,t.conv2,[1,1]);return C.relu(C.add(r,C.add(n,s)))})}function Le(o,t,e=!1,r=!0){return C.tidy(()=>{let n=C.relu(e?C.add(C.conv2d(o,t.conv0.filters,r?[2,2]:[1,1],"same"),t.conv0.bias):$(o,t.conv0,r?[2,2]:[1,1])),a=$(n,t.conv1,[1,1]),s=C.relu(C.add(n,a)),i=$(s,t.conv2,[1,1]),c=C.relu(C.add(n,C.add(a,i))),m=$(c,t.conv3,[1,1]);return C.relu(C.add(n,C.add(a,C.add(i,m))))})}var Ct=b(g());function Gt(o,t,e="same",r=!1){return Ct.tidy(()=>{let n=Ct.add(Ct.conv2d(o,t.filters,[1,1],e),t.bias);return r?Ct.relu(n):n})}function W(o,t){Object.keys(o).forEach(e=>{t.some(r=>r.originalPath===e)||o[e].dispose()})}var tr=b(g());function ce(o,t){return(e,r,n,a)=>{let s=tr.tensor4d(o(e*r*n*n),[n,n,e,r]),i=tr.tensor1d(o(r));return t.push({paramPath:`${a}/filters`},{paramPath:`${a}/bias`}),{filters:s,bias:i}}}var er=b(g());function rr(o,t){return(e,r,n)=>{let a=er.tensor2d(o(e*r),[e,r]),s=er.tensor1d(o(r));return t.push({paramPath:`${n}/weights`},{paramPath:`${n}/bias`}),{weights:a,bias:s}}}var ke=b(g());var or=class{constructor(t,e,r){this.depthwise_filter=t;this.pointwise_filter=e;this.bias=r}};function me(o,t){return(e,r,n)=>{let a=ke.tensor4d(o(3*3*e),[3,3,e,1]),s=ke.tensor4d(o(e*r),[1,1,e,r]),i=ke.tensor1d(o(r));return t.push({paramPath:`${n}/depthwise_filter`},{paramPath:`${n}/pointwise_filter`},{paramPath:`${n}/bias`}),new or(a,s,i)}}function pe(o){return t=>{let e=o(`${t}/depthwise_filter`,4),r=o(`${t}/pointwise_filter`,4),n=o(`${t}/bias`,1);return new or(e,r,n)}}function j(o,t){return(e,r,n)=>{let a=o[e];if(!Bt(a,r))throw new Error(`expected weightMap[${e}] to be a Tensor${r}D, instead have ${a}`);return t.push({originalPath:e,paramPath:n||e}),a}}function B(o){let t=o;function e(n){let a=t.slice(0,n);return t=t.slice(n),a}function r(){return t}return{extractWeights:e,getRemainingWeights:r}}function nr(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c,m=!1){let p=m?e(s,i,3,`${c}/conv0`):r(s,i,`${c}/conv0`),d=r(i,i,`${c}/conv1`),u=r(i,i,`${c}/conv2`);return{conv0:p,conv1:d,conv2:u}}function a(s,i,c,m=!1){let{conv0:p,conv1:d,conv2:u}=n(s,i,c,m),l=r(i,i,`${c}/conv3`);return{conv0:p,conv1:d,conv2:u,conv3:l}}return{extractDenseBlock3Params:n,extractDenseBlock4Params:a}}function _o(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock4Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2"),c=n(128,256,"dense3");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i,dense3:c}}}function ar(o){return t=>{let e=o(`${t}/filters`,4),r=o(`${t}/bias`,1);return{filters:e,bias:r}}}function sr(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`);return{conv0:m,conv1:p,conv2:d}}function s(i,c=!1){let m=c?r(`${i}/conv0`):n(`${i}/conv0`),p=n(`${i}/conv1`),d=n(`${i}/conv2`),u=n(`${i}/conv3`);return{conv0:m,conv1:p,conv2:d,conv3:u}}return{extractDenseBlock3Params:a,extractDenseBlock4Params:s}}function wo(o){let t=[],{extractDenseBlock4Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2"),dense3:e("dense3")};return W(o,t),{params:r,paramMappings:t}}var Se=class extends S{constructor(){super("FaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceFeatureExtractor - load model before inference");return Nt.tidy(()=>{let r=Nt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Nt.scalar(255)),s=Le(a,e.dense0,!0);return s=Le(s,e.dense1),s=Le(s,e.dense2),s=Le(s,e.dense3),s=Nt.avgPool(s,[7,7],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_model"}extractParamsFromWeightMap(t){return wo(t)}extractParams(t){return _o(t)}};var Mo=b(g());var de=b(g());function Ae(o,t){return de.tidy(()=>de.add(de.matMul(o,t.weights),t.bias))}function Do(o,t,e){let r=[],{extractWeights:n,getRemainingWeights:a}=B(o),i=rr(n,r)(t,e,"fc");if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{paramMappings:r,params:{fc:i}}}function Eo(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:r("fc")};return W(o,t),{params:n,paramMappings:t}}function ir(o){let t={},e={};return Object.keys(o).forEach(r=>{let n=r.startsWith("fc")?e:t;n[r]=o[r]}),{featureExtractorMap:t,classifierMap:e}}var We=class extends S{constructor(t,e){super(t);this._faceFeatureExtractor=e}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return Mo.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t;return Ae(r.as2D(r.shape[0],-1),e.fc)})}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return Do(t,this.getClassifierChannelsIn(),this.getClassifierChannelsOut())}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),Eo(r)}extractParams(t){let e=this.getClassifierChannelsIn(),r=this.getClassifierChannelsOut(),n=r*e+r,a=t.slice(0,t.length-n),s=t.slice(t.length-n);return this.faceFeatureExtractor.extractWeights(a),this.extractClassifierParams(s)}};var Jr=["neutral","happy","sad","angry","fearful","disgusted","surprised"],It=class{constructor(t){if(t.length!==7)throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${t.length}`);Jr.forEach((e,r)=>{this[e]=t[r]})}asSortedArray(){return Jr.map(t=>({expression:t,probability:this[t]})).sort((t,e)=>e.probability-t.probability)}};var cr=class extends We{constructor(t=new Se){super("FaceExpressionNet",t)}forwardInput(t){return ue.tidy(()=>ue.softmax(this.runNet(t)))}async forward(t){return this.forwardInput(await E(t))}async predictExpressions(t){let e=await E(t),r=await this.forwardInput(e),n=await Promise.all(ue.unstack(r).map(async s=>{let i=await s.data();return s.dispose(),i}));r.dispose();let a=n.map(s=>new It(s));return e.isBatchInput?a:a[0]}getDefaultModelName(){return"face_expression_model"}getClassifierChannelsIn(){return 256}getClassifierChannelsOut(){return 7}};function qr(o){return o.expressions instanceof It}function mr(o,t){return{...o,...{expressions:t}}}function $n(o,t,e=.1,r){(Array.isArray(t)?t:[t]).forEach(a=>{let s=a instanceof It?a:qr(a)?a.expressions:void 0;if(!s)throw new Error("drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof");let c=s.asSortedArray().filter(d=>d.probability>e),m=pt(a)?a.detection.box.bottomLeft:r||new x(0,0);new Mt(c.map(d=>`${d.expression} (${Rt(d.probability)})`),m).draw(o)})}function zt(o){return pt(o)&&o.landmarks instanceof V&&o.unshiftedLandmarks instanceof V&&o.alignedRect instanceof M}function le(o,t){let{box:e}=o.detection,r=t.shiftBy(e.x,e.y),n=r.align(),{imageDims:a}=o.detection,s=new M(o.detection.score,n.rescale(a.reverse()),a);return{...o,...{landmarks:r,unshiftedLandmarks:t,alignedRect:s}}}var Zr=class{constructor(t={}){let{drawLines:e=!0,drawPoints:r=!0,lineWidth:n,lineColor:a,pointSize:s,pointColor:i}=t;this.drawLines=e,this.drawPoints=r,this.lineWidth=n||1,this.pointSize=s||2,this.lineColor=a||"rgba(0, 255, 255, 1)",this.pointColor=i||"rgba(255, 0, 255, 1)"}},Kr=class{constructor(t,e={}){this.faceLandmarks=t,this.options=new Zr(e)}draw(t){let e=O(t),{drawLines:r,drawPoints:n,lineWidth:a,lineColor:s,pointSize:i,pointColor:c}=this.options;if(r&&this.faceLandmarks instanceof oe&&(e.strokeStyle=s,e.lineWidth=a,ft(e,this.faceLandmarks.getJawOutline()),ft(e,this.faceLandmarks.getLeftEyeBrow()),ft(e,this.faceLandmarks.getRightEyeBrow()),ft(e,this.faceLandmarks.getNose()),ft(e,this.faceLandmarks.getLeftEye(),!0),ft(e,this.faceLandmarks.getRightEye(),!0),ft(e,this.faceLandmarks.getMouth(),!0)),n){e.strokeStyle=c,e.fillStyle=c;let m=p=>{e.beginPath(),e.arc(p.x,p.y,i,0,2*Math.PI),e.fill()};this.faceLandmarks.positions.forEach(m)}}};function jn(o,t){(Array.isArray(t)?t:[t]).forEach(r=>{let n=r instanceof V?r:zt(r)?r.landmarks:void 0;if(!n)throw new Error("drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof");new Kr(n).draw(o)})}var Co="0.11.6";var ut=b(g());var I=b(g());function Hn(o,t){let e=ce(o,t),r=me(o,t);function n(s,i,c){let m=r(s,i,`${c}/separable_conv0`),p=r(i,i,`${c}/separable_conv1`),d=e(s,i,1,`${c}/expansion_conv`);return{separable_conv0:m,separable_conv1:p,expansion_conv:d}}function a(s,i){let c=r(s,s,`${i}/separable_conv0`),m=r(s,s,`${i}/separable_conv1`),p=r(s,s,`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:e,extractSeparableConvParams:r,extractReductionBlockParams:n,extractMainBlockParams:a}}function No(o,t){let e=[],{extractWeights:r,getRemainingWeights:n}=B(o),{extractConvParams:a,extractSeparableConvParams:s,extractReductionBlockParams:i,extractMainBlockParams:c}=Hn(r,e),m=a(3,32,3,"entry_flow/conv_in"),p=i(32,64,"entry_flow/reduction_block_0"),d=i(64,128,"entry_flow/reduction_block_1"),u={conv_in:m,reduction_block_0:p,reduction_block_1:d},l={};ct(t,0,1).forEach(y=>{l[`main_block_${y}`]=c(128,`middle_flow/main_block_${y}`)});let v=i(128,256,"exit_flow/reduction_block"),_=s(256,512,"exit_flow/separable_conv"),h={reduction_block:v,separable_conv:_};if(n().length!==0)throw new Error(`weights remaing after extract: ${n().length}`);return{paramMappings:e,params:{entry_flow:u,middle_flow:l,exit_flow:h}}}function Yn(o,t){let e=j(o,t),r=ar(e),n=pe(e);function a(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=r(`${i}/expansion_conv`);return{separable_conv0:c,separable_conv1:m,expansion_conv:p}}function s(i){let c=n(`${i}/separable_conv0`),m=n(`${i}/separable_conv1`),p=n(`${i}/separable_conv2`);return{separable_conv0:c,separable_conv1:m,separable_conv2:p}}return{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}}function Io(o,t){let e=[],{extractConvParams:r,extractSeparableConvParams:n,extractReductionBlockParams:a,extractMainBlockParams:s}=Yn(o,e),i=r("entry_flow/conv_in"),c=a("entry_flow/reduction_block_0"),m=a("entry_flow/reduction_block_1"),p={conv_in:i,reduction_block_0:c,reduction_block_1:m},d={};ct(t,0,1).forEach(_=>{d[`main_block_${_}`]=s(`middle_flow/main_block_${_}`)});let u=a("exit_flow/reduction_block"),l=n("exit_flow/separable_conv"),v={reduction_block:u,separable_conv:l};return W(o,e),{params:{entry_flow:p,middle_flow:d,exit_flow:v},paramMappings:e}}function Lo(o,t,e){return I.add(I.conv2d(o,t.filters,e,"same"),t.bias)}function to(o,t,e=!0){let r=e?I.relu(o):o;return r=$(r,t.separable_conv0,[1,1]),r=$(I.relu(r),t.separable_conv1,[1,1]),r=I.maxPool(r,[3,3],[2,2],"same"),r=I.add(r,Lo(o,t.expansion_conv,[2,2])),r}function Gn(o,t){let e=$(I.relu(o),t.separable_conv0,[1,1]);return e=$(I.relu(e),t.separable_conv1,[1,1]),e=$(I.relu(e),t.separable_conv2,[1,1]),e=I.add(e,o),e}var eo=class extends S{constructor(t){super("TinyXception");this._numMainBlocks=t}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyXception - load model before inference");return I.tidy(()=>{let r=I.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(I.scalar(256)),s=I.relu(Lo(a,e.entry_flow.conv_in,[2,2]));return s=to(s,e.entry_flow.reduction_block_0,!1),s=to(s,e.entry_flow.reduction_block_1),ct(this._numMainBlocks,0,1).forEach(i=>{s=Gn(s,e.middle_flow[`main_block_${i}`])}),s=to(s,e.exit_flow.reduction_block),s=I.relu($(s,e.exit_flow.separable_conv,[1,1])),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"tiny_xception_model"}extractParamsFromWeightMap(t){return Io(t,this._numMainBlocks)}extractParams(t){return No(t,this._numMainBlocks)}};function ko(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),n=rr(e,t),a=n(512,1,"fc/age"),s=n(512,2,"fc/gender");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{fc:{age:a,gender:s}}}}function So(o){let t=[],e=j(o,t);function r(a){let s=e(`${a}/weights`,2),i=e(`${a}/bias`,1);return{weights:s,bias:i}}let n={fc:{age:r("fc/age"),gender:r("fc/gender")}};return W(o,t),{params:n,paramMappings:t}}var vt;(function(o){o.FEMALE="female",o.MALE="male"})(vt||(vt={}));var pr=class extends S{constructor(t=new eo(2)){super("AgeGenderNet");this._faceFeatureExtractor=t}get faceFeatureExtractor(){return this._faceFeatureExtractor}runNet(t){let{params:e}=this;if(!e)throw new Error(`${this._name} - load model before inference`);return ut.tidy(()=>{let r=t instanceof bt?this.faceFeatureExtractor.forwardInput(t):t,n=ut.avgPool(r,[7,7],[2,2],"valid").as2D(r.shape[0],-1),a=Ae(n,e.fc.age).as1D(),s=Ae(n,e.fc.gender);return{age:a,gender:s}})}forwardInput(t){return ut.tidy(()=>{let{age:e,gender:r}=this.runNet(t);return{age:e,gender:ut.softmax(r)}})}async forward(t){return this.forwardInput(await E(t))}async predictAgeAndGender(t){let e=await E(t),r=await this.forwardInput(e),n=ut.unstack(r.age),a=ut.unstack(r.gender),s=n.map((c,m)=>({ageTensor:c,genderTensor:a[m]})),i=await Promise.all(s.map(async({ageTensor:c,genderTensor:m})=>{let p=(await c.data())[0],d=(await m.data())[0],u=d>.5,l=u?vt.MALE:vt.FEMALE,v=u?d:1-d;return c.dispose(),m.dispose(),{age:p,gender:l,genderProbability:v}}));return r.age.dispose(),r.gender.dispose(),e.isBatchInput?i:i[0]}getDefaultModelName(){return"age_gender_model"}dispose(t=!0){this.faceFeatureExtractor.dispose(t),super.dispose(t)}loadClassifierParams(t){let{params:e,paramMappings:r}=this.extractClassifierParams(t);this._params=e,this._paramMappings=r}extractClassifierParams(t){return ko(t)}extractParamsFromWeightMap(t){let{featureExtractorMap:e,classifierMap:r}=ir(t);return this.faceFeatureExtractor.loadFromWeightMap(e),So(r)}extractParams(t){let e=512*1+1+(512*2+2),r=t.slice(0,t.length-e),n=t.slice(t.length-e);return this.faceFeatureExtractor.extractWeights(r),this.extractClassifierParams(n)}};var H=b(g());var Be=class extends We{postProcess(t,e,r){let n=r.map(({width:s,height:i})=>{let c=e/Math.max(i,s);return{width:s*c,height:i*c}}),a=n.length;return H.tidy(()=>{let s=(d,u)=>H.stack([H.fill([68],d,"float32"),H.fill([68],u,"float32")],1).as2D(1,136).as1D(),i=(d,u)=>{let{width:l,height:v}=n[d];return u(l,v)?Math.abs(l-v)/2:0},c=d=>i(d,(u,l)=>ui(d,(u,l)=>ls(c(u),m(u))))).div(H.stack(Array.from(Array(a),(d,u)=>s(n[u].width,n[u].height))))})}forwardInput(t){return H.tidy(()=>{let e=this.runNet(t);return this.postProcess(e,t.inputSize,t.inputDimensions.map(([r,n])=>({height:r,width:n})))})}async forward(t){return this.forwardInput(await E(t))}async detectLandmarks(t){let e=await E(t),r=H.tidy(()=>H.unstack(this.forwardInput(e))),n=await Promise.all(r.map(async(a,s)=>{let i=Array.from(await a.data()),c=i.filter((p,d)=>ze(d)),m=i.filter((p,d)=>!ze(d));return new oe(Array(68).fill(0).map((p,d)=>new x(c[d],m[d])),{height:e.getInputHeight(s),width:e.getInputWidth(s)})}));return r.forEach(a=>a.dispose()),e.isBatchInput?n:n[0]}getClassifierChannelsOut(){return 136}};var fe=class extends Be{constructor(t=new Se){super("FaceLandmark68Net",t)}getDefaultModelName(){return"face_landmark_68_model"}getClassifierChannelsIn(){return 256}};var Lt=b(g());function Ao(o){let t=[],{extractDenseBlock3Params:e}=sr(o,t),r={dense0:e("dense0",!0),dense1:e("dense1"),dense2:e("dense2")};return W(o,t),{params:r,paramMappings:t}}function Wo(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractDenseBlock3Params:n}=nr(e,t),a=n(3,32,"dense0",!0),s=n(32,64,"dense1"),i=n(64,128,"dense2");if(r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{paramMappings:t,params:{dense0:a,dense1:s,dense2:i}}}var ro=class extends S{constructor(){super("TinyFaceFeatureExtractor")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("TinyFaceFeatureExtractor - load model before inference");return Lt.tidy(()=>{let r=Lt.cast(t.toBatchTensor(112,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(Lt.scalar(255)),s=Qe(a,e.dense0,!0);return s=Qe(s,e.dense1),s=Qe(s,e.dense2),s=Lt.avgPool(s,[14,14],[2,2],"valid"),s})}async forward(t){return this.forwardInput(await E(t))}getDefaultModelName(){return"face_feature_extractor_tiny_model"}extractParamsFromWeightMap(t){return Ao(t)}extractParams(t){return Wo(t)}};var dr=class extends Be{constructor(t=new ro){super("FaceLandmark68TinyNet",t)}getDefaultModelName(){return"face_landmark_68_tiny_model"}getClassifierChannelsIn(){return 128}};var Bo=class extends fe{};var U=b(g());var he=b(g());var ur=b(g());function Ro(o,t){return ur.add(ur.mul(o,t.weights),t.biases)}function oo(o,t,e,r,n="same"){let{filters:a,bias:s}=t.conv,i=he.conv2d(o,a,e,n);return i=he.add(i,s),i=Ro(i,t.scale),r?he.relu(i):i}function Oo(o,t){return oo(o,t,[1,1],!0)}function no(o,t){return oo(o,t,[1,1],!1)}function lr(o,t){return oo(o,t,[2,2],!0,"valid")}var Y=b(g());function zn(o,t){function e(i,c,m){let p=o(i),d=p.length/(c*m*m);if(Nr(d))throw new Error(`depth has to be an integer: ${d}, weights.length: ${p.length}, numFilters: ${c}, filterSize: ${m}`);return Y.tidy(()=>Y.transpose(Y.tensor4d(p,[c,d,m,m]),[2,3,1,0]))}function r(i,c,m,p){let d=e(i,c,m),u=Y.tensor1d(o(c));return t.push({paramPath:`${p}/filters`},{paramPath:`${p}/bias`}),{filters:d,bias:u}}function n(i,c){let m=Y.tensor1d(o(i)),p=Y.tensor1d(o(i));return t.push({paramPath:`${c}/weights`},{paramPath:`${c}/biases`}),{weights:m,biases:p}}function a(i,c,m,p){let d=r(i,c,m,`${p}/conv`),u=n(c,`${p}/scale`);return{conv:d,scale:u}}function s(i,c,m,p,d=!1){let u=a((d?.5:1)*i,c,m,`${p}/conv1`),l=a(i,c,m,`${p}/conv2`);return{conv1:u,conv2:l}}return{extractConvLayerParams:a,extractResidualLayerParams:s}}function $o(o){let{extractWeights:t,getRemainingWeights:e}=B(o),r=[],{extractConvLayerParams:n,extractResidualLayerParams:a}=zn(t,r),s=n(4704,32,7,"conv32_down"),i=a(9216,32,3,"conv32_1"),c=a(9216,32,3,"conv32_2"),m=a(9216,32,3,"conv32_3"),p=a(36864,64,3,"conv64_down",!0),d=a(36864,64,3,"conv64_1"),u=a(36864,64,3,"conv64_2"),l=a(36864,64,3,"conv64_3"),v=a(147456,128,3,"conv128_down",!0),_=a(147456,128,3,"conv128_1"),h=a(147456,128,3,"conv128_2"),y=a(589824,256,3,"conv256_down",!0),T=a(589824,256,3,"conv256_1"),F=a(589824,256,3,"conv256_2"),L=a(589824,256,3,"conv256_down_out"),G=Y.tidy(()=>Y.transpose(Y.tensor2d(t(256*128),[128,256]),[1,0]));if(r.push({paramPath:"fc"}),e().length!==0)throw new Error(`weights remaing after extract: ${e().length}`);return{params:{conv32_down:s,conv32_1:i,conv32_2:c,conv32_3:m,conv64_down:p,conv64_1:d,conv64_2:u,conv64_3:l,conv128_down:v,conv128_1:_,conv128_2:h,conv256_down:y,conv256_1:T,conv256_2:F,conv256_down_out:L,fc:G},paramMappings:r}}function Vn(o,t){let e=j(o,t);function r(s){let i=e(`${s}/scale/weights`,1),c=e(`${s}/scale/biases`,1);return{weights:i,biases:c}}function n(s){let i=e(`${s}/conv/filters`,4),c=e(`${s}/conv/bias`,1),m=r(s);return{conv:{filters:i,bias:c},scale:m}}function a(s){return{conv1:n(`${s}/conv1`),conv2:n(`${s}/conv2`)}}return{extractConvLayerParams:n,extractResidualLayerParams:a}}function jo(o){let t=[],{extractConvLayerParams:e,extractResidualLayerParams:r}=Vn(o,t),n=e("conv32_down"),a=r("conv32_1"),s=r("conv32_2"),i=r("conv32_3"),c=r("conv64_down"),m=r("conv64_1"),p=r("conv64_2"),d=r("conv64_3"),u=r("conv128_down"),l=r("conv128_1"),v=r("conv128_2"),_=r("conv256_down"),h=r("conv256_1"),y=r("conv256_2"),T=r("conv256_down_out"),{fc:F}=o;if(t.push({originalPath:"fc",paramPath:"fc"}),!Cr(F))throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${F}`);let L={conv32_down:n,conv32_1:a,conv32_2:s,conv32_3:i,conv64_down:c,conv64_1:m,conv64_2:p,conv64_3:d,conv128_down:u,conv128_1:l,conv128_2:v,conv256_down:_,conv256_1:h,conv256_2:y,conv256_down_out:T,fc:F};return W(o,t),{params:L,paramMappings:t}}var R=b(g());function nt(o,t){let e=Oo(o,t.conv1);return e=no(e,t.conv2),e=R.add(e,o),e=R.relu(e),e}function Re(o,t){let e=lr(o,t.conv1);e=no(e,t.conv2);let r=R.avgPool(o,2,2,"valid"),n=R.zeros(r.shape),a=r.shape[3]!==e.shape[3];if(r.shape[1]!==e.shape[1]||r.shape[2]!==e.shape[2]){let i=[...e.shape];i[1]=1;let c=R.zeros(i);e=R.concat([e,c],1);let m=[...e.shape];m[2]=1;let p=R.zeros(m);e=R.concat([e,p],2)}return r=a?R.concat([r,n],3):r,e=R.add(r,e),e=R.relu(e),e}var xe=class extends S{constructor(){super("FaceRecognitionNet")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("FaceRecognitionNet - load model before inference");return U.tidy(()=>{let r=U.cast(t.toBatchTensor(150,!0),"float32"),a=ot(r,[122.782,117.001,104.298]).div(U.scalar(256)),s=lr(a,e.conv32_down);s=U.maxPool(s,3,2,"valid"),s=nt(s,e.conv32_1),s=nt(s,e.conv32_2),s=nt(s,e.conv32_3),s=Re(s,e.conv64_down),s=nt(s,e.conv64_1),s=nt(s,e.conv64_2),s=nt(s,e.conv64_3),s=Re(s,e.conv128_down),s=nt(s,e.conv128_1),s=nt(s,e.conv128_2),s=Re(s,e.conv256_down),s=nt(s,e.conv256_1),s=nt(s,e.conv256_2),s=Re(s,e.conv256_down_out);let i=s.mean([1,2]);return U.matMul(i,e.fc)})}async forward(t){return this.forwardInput(await E(t))}async computeFaceDescriptor(t){var a;if((a=t==null?void 0:t.shape)==null?void 0:a.some(s=>s<=0))return new Float32Array(128);let e=await E(t),r=U.tidy(()=>U.unstack(this.forwardInput(e))),n=await Promise.all(r.map(s=>s.data()));return r.forEach(s=>s.dispose()),e.isBatchInput?n:n[0]}getDefaultModelName(){return"face_recognition_model"}extractParamsFromWeightMap(t){return jo(t)}extractParams(t){return $o(t)}};function Un(o){let t=new xe;return t.extractWeights(o),t}function fr(o,t){return{...o,...{descriptor:t}}}function Xn(o){return typeof o.age=="number"}function hr(o,t){return{...o,...{age:t}}}function Jn(o){return(o.gender===vt.MALE||o.gender===vt.FEMALE)&&te(o.genderProbability)}function xr(o,t,e){return{...o,...{gender:t,genderProbability:e}}}var st=b(g());var at=b(g());function qn(o,t){function e(c,m){let p=at.tensor4d(o(3*3*c),[3,3,c,1]),d=at.tensor1d(o(c)),u=at.tensor1d(o(c)),l=at.tensor1d(o(c)),v=at.tensor1d(o(c));return t.push({paramPath:`${m}/filters`},{paramPath:`${m}/batch_norm_scale`},{paramPath:`${m}/batch_norm_offset`},{paramPath:`${m}/batch_norm_mean`},{paramPath:`${m}/batch_norm_variance`}),{filters:p,batch_norm_scale:d,batch_norm_offset:u,batch_norm_mean:l,batch_norm_variance:v}}function r(c,m,p,d,u){let l=at.tensor4d(o(c*m*p*p),[p,p,c,m]),v=at.tensor1d(o(m));return t.push({paramPath:`${d}/filters`},{paramPath:`${d}/${u?"batch_norm_offset":"bias"}`}),{filters:l,bias:v}}function n(c,m,p,d){let{filters:u,bias:l}=r(c,m,p,d,!0);return{filters:u,batch_norm_offset:l}}function a(c,m,p){let d=e(c,`${p}/depthwise_conv`),u=n(c,m,1,`${p}/pointwise_conv`);return{depthwise_conv:d,pointwise_conv:u}}function s(){let c=n(3,32,3,"mobilenetv1/conv_0"),m=a(32,64,"mobilenetv1/conv_1"),p=a(64,128,"mobilenetv1/conv_2"),d=a(128,128,"mobilenetv1/conv_3"),u=a(128,256,"mobilenetv1/conv_4"),l=a(256,256,"mobilenetv1/conv_5"),v=a(256,512,"mobilenetv1/conv_6"),_=a(512,512,"mobilenetv1/conv_7"),h=a(512,512,"mobilenetv1/conv_8"),y=a(512,512,"mobilenetv1/conv_9"),T=a(512,512,"mobilenetv1/conv_10"),F=a(512,512,"mobilenetv1/conv_11"),L=a(512,1024,"mobilenetv1/conv_12"),G=a(1024,1024,"mobilenetv1/conv_13");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,conv_8:h,conv_9:y,conv_10:T,conv_11:F,conv_12:L,conv_13:G}}function i(){let c=n(1024,256,1,"prediction_layer/conv_0"),m=n(256,512,3,"prediction_layer/conv_1"),p=n(512,128,1,"prediction_layer/conv_2"),d=n(128,256,3,"prediction_layer/conv_3"),u=n(256,128,1,"prediction_layer/conv_4"),l=n(128,256,3,"prediction_layer/conv_5"),v=n(256,64,1,"prediction_layer/conv_6"),_=n(64,128,3,"prediction_layer/conv_7"),h=r(512,12,1,"prediction_layer/box_predictor_0/box_encoding_predictor"),y=r(512,9,1,"prediction_layer/box_predictor_0/class_predictor"),T=r(1024,24,1,"prediction_layer/box_predictor_1/box_encoding_predictor"),F=r(1024,18,1,"prediction_layer/box_predictor_1/class_predictor"),L=r(512,24,1,"prediction_layer/box_predictor_2/box_encoding_predictor"),G=r(512,18,1,"prediction_layer/box_predictor_2/class_predictor"),et=r(256,24,1,"prediction_layer/box_predictor_3/box_encoding_predictor"),it=r(256,18,1,"prediction_layer/box_predictor_3/class_predictor"),X=r(256,24,1,"prediction_layer/box_predictor_4/box_encoding_predictor"),Pt=r(256,18,1,"prediction_layer/box_predictor_4/class_predictor"),_t=r(128,24,1,"prediction_layer/box_predictor_5/box_encoding_predictor"),wt=r(128,18,1,"prediction_layer/box_predictor_5/class_predictor");return{conv_0:c,conv_1:m,conv_2:p,conv_3:d,conv_4:u,conv_5:l,conv_6:v,conv_7:_,box_predictor_0:{box_encoding_predictor:h,class_predictor:y},box_predictor_1:{box_encoding_predictor:T,class_predictor:F},box_predictor_2:{box_encoding_predictor:L,class_predictor:G},box_predictor_3:{box_encoding_predictor:et,class_predictor:it},box_predictor_4:{box_encoding_predictor:X,class_predictor:Pt},box_predictor_5:{box_encoding_predictor:_t,class_predictor:wt}}}return{extractMobilenetV1Params:s,extractPredictionLayerParams:i}}function Ho(o){let t=[],{extractWeights:e,getRemainingWeights:r}=B(o),{extractMobilenetV1Params:n,extractPredictionLayerParams:a}=qn(e,t),s=n(),i=a(),m={extra_dim:at.tensor3d(e(5118*4),[1,5118,4])};if(t.push({paramPath:"output_layer/extra_dim"}),r().length!==0)throw new Error(`weights remaing after extract: ${r().length}`);return{params:{mobilenetv1:s,prediction_layer:i,output_layer:m},paramMappings:t}}function Zn(o,t){let e=j(o,t);function r(m,p,d){let u=e(`${m}/Conv2d_${p}_pointwise/weights`,4,`${d}/filters`),l=e(`${m}/Conv2d_${p}_pointwise/convolution_bn_offset`,1,`${d}/batch_norm_offset`);return{filters:u,batch_norm_offset:l}}function n(m){let p=`mobilenetv1/conv_${m}`,d=`MobilenetV1/Conv2d_${m}_depthwise`,u=`${p}/depthwise_conv`,l=`${p}/pointwise_conv`,v=e(`${d}/depthwise_weights`,4,`${u}/filters`),_=e(`${d}/BatchNorm/gamma`,1,`${u}/batch_norm_scale`),h=e(`${d}/BatchNorm/beta`,1,`${u}/batch_norm_offset`),y=e(`${d}/BatchNorm/moving_mean`,1,`${u}/batch_norm_mean`),T=e(`${d}/BatchNorm/moving_variance`,1,`${u}/batch_norm_variance`);return{depthwise_conv:{filters:v,batch_norm_scale:_,batch_norm_offset:h,batch_norm_mean:y,batch_norm_variance:T},pointwise_conv:r("MobilenetV1",m,l)}}function a(){return{conv_0:r("MobilenetV1",0,"mobilenetv1/conv_0"),conv_1:n(1),conv_2:n(2),conv_3:n(3),conv_4:n(4),conv_5:n(5),conv_6:n(6),conv_7:n(7),conv_8:n(8),conv_9:n(9),conv_10:n(10),conv_11:n(11),conv_12:n(12),conv_13:n(13)}}function s(m,p){let d=e(`${m}/weights`,4,`${p}/filters`),u=e(`${m}/biases`,1,`${p}/bias`);return{filters:d,bias:u}}function i(m){let p=s(`Prediction/BoxPredictor_${m}/BoxEncodingPredictor`,`prediction_layer/box_predictor_${m}/box_encoding_predictor`),d=s(`Prediction/BoxPredictor_${m}/ClassPredictor`,`prediction_layer/box_predictor_${m}/class_predictor`);return{box_encoding_predictor:p,class_predictor:d}}function c(){return{conv_0:r("Prediction",0,"prediction_layer/conv_0"),conv_1:r("Prediction",1,"prediction_layer/conv_1"),conv_2:r("Prediction",2,"prediction_layer/conv_2"),conv_3:r("Prediction",3,"prediction_layer/conv_3"),conv_4:r("Prediction",4,"prediction_layer/conv_4"),conv_5:r("Prediction",5,"prediction_layer/conv_5"),conv_6:r("Prediction",6,"prediction_layer/conv_6"),conv_7:r("Prediction",7,"prediction_layer/conv_7"),box_predictor_0:i(0),box_predictor_1:i(1),box_predictor_2:i(2),box_predictor_3:i(3),box_predictor_4:i(4),box_predictor_5:i(5)}}return{extractMobilenetV1Params:a,extractPredictionLayerParams:c}}function Yo(o){let t=[],{extractMobilenetV1Params:e,extractPredictionLayerParams:r}=Zn(o,t),n=o["Output/extra_dim"];if(t.push({originalPath:"Output/extra_dim",paramPath:"output_layer/extra_dim"}),!ht(n))throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${n}`);let a={mobilenetv1:e(),prediction_layer:r(),output_layer:{extra_dim:n}};return W(o,t),{params:a,paramMappings:t}}var yt=b(g());var kt=b(g());function q(o,t,e){return kt.tidy(()=>{let r=kt.conv2d(o,t.filters,e,"same");return r=kt.add(r,t.batch_norm_offset),kt.clipByValue(r,0,6)})}var Kn=.0010000000474974513;function Qn(o,t,e){return yt.tidy(()=>{let r=yt.depthwiseConv2d(o,t.filters,e,"same");return r=yt.batchNorm(r,t.batch_norm_mean,t.batch_norm_variance,t.batch_norm_offset,t.batch_norm_scale,Kn),yt.clipByValue(r,0,6)})}function ta(o){return[2,4,6,12].some(t=>t===o)?[2,2]:[1,1]}function Go(o,t){return yt.tidy(()=>{let e,r=q(o,t.conv_0,[2,2]);if([t.conv_1,t.conv_2,t.conv_3,t.conv_4,t.conv_5,t.conv_6,t.conv_7,t.conv_8,t.conv_9,t.conv_10,t.conv_11,t.conv_12,t.conv_13].forEach((a,s)=>{let i=s+1,c=ta(i);r=Qn(r,a.depthwise_conv,c),r=q(r,a.pointwise_conv,[1,1]),i===11&&(e=r)}),e===null)throw new Error("mobileNetV1 - output of conv layer 11 is null");return{out:r,conv11:e}})}function ea(o,t,e){let r=o.arraySync(),n=Math.min(r[t][0],r[t][2]),a=Math.min(r[t][1],r[t][3]),s=Math.max(r[t][0],r[t][2]),i=Math.max(r[t][1],r[t][3]),c=Math.min(r[e][0],r[e][2]),m=Math.min(r[e][1],r[e][3]),p=Math.max(r[e][0],r[e][2]),d=Math.max(r[e][1],r[e][3]),u=(s-n)*(i-a),l=(p-c)*(d-m);if(u<=0||l<=0)return 0;let v=Math.max(n,c),_=Math.max(a,m),h=Math.min(s,p),y=Math.min(i,d),T=Math.max(h-v,0)*Math.max(y-_,0);return T/(u+l-T)}function zo(o,t,e,r,n){let a=o.shape[0],s=Math.min(e,a),i=t.map((p,d)=>({score:p,boxIndex:d})).filter(p=>p.score>n).sort((p,d)=>d.score-p.score),c=p=>p<=r?1:0,m=[];return i.forEach(p=>{if(m.length>=s)return;let d=p.score;for(let u=m.length-1;u>=0;--u){let l=ea(o,p.boxIndex,m[u]);if(l!==0&&(p.score*=c(l),p.score<=n))break}d===p.score&&m.push(p.boxIndex)}),m}var f=b(g());function ra(o){let t=f.unstack(f.transpose(o,[1,0])),e=[f.sub(t[2],t[0]),f.sub(t[3],t[1])],r=[f.add(t[0],f.div(e[0],f.scalar(2))),f.add(t[1],f.div(e[1],f.scalar(2)))];return{sizes:e,centers:r}}function oa(o,t){let{sizes:e,centers:r}=ra(o),n=f.unstack(f.transpose(t,[1,0])),a=f.div(f.mul(f.exp(f.div(n[2],f.scalar(5))),e[0]),f.scalar(2)),s=f.add(f.mul(f.div(n[0],f.scalar(10)),e[0]),r[0]),i=f.div(f.mul(f.exp(f.div(n[3],f.scalar(5))),e[1]),f.scalar(2)),c=f.add(f.mul(f.div(n[1],f.scalar(10)),e[1]),r[1]);return f.transpose(f.stack([f.sub(s,a),f.sub(c,i),f.add(s,a),f.add(c,i)]),[1,0])}function Vo(o,t,e){return f.tidy(()=>{let r=o.shape[0],n=oa(f.reshape(f.tile(e.extra_dim,[r,1,1]),[-1,4]),f.reshape(o,[-1,4]));n=f.reshape(n,[r,n.shape[0]/r,4]);let a=f.sigmoid(f.slice(t,[0,0,1],[-1,-1,-1])),s=f.slice(a,[0,0,0],[-1,-1,1]);s=f.reshape(s,[r,s.shape[1]]);let i=f.unstack(n),c=f.unstack(s);return{boxes:i,scores:c}})}var $e=b(g());var Oe=b(g());function Vt(o,t){return Oe.tidy(()=>{let e=o.shape[0],r=Oe.reshape(Gt(o,t.box_encoding_predictor),[e,-1,1,4]),n=Oe.reshape(Gt(o,t.class_predictor),[e,-1,3]);return{boxPredictionEncoding:r,classPrediction:n}})}function Uo(o,t,e){return $e.tidy(()=>{let r=q(o,e.conv_0,[1,1]),n=q(r,e.conv_1,[2,2]),a=q(n,e.conv_2,[1,1]),s=q(a,e.conv_3,[2,2]),i=q(s,e.conv_4,[1,1]),c=q(i,e.conv_5,[2,2]),m=q(c,e.conv_6,[1,1]),p=q(m,e.conv_7,[2,2]),d=Vt(t,e.box_predictor_0),u=Vt(o,e.box_predictor_1),l=Vt(n,e.box_predictor_2),v=Vt(s,e.box_predictor_3),_=Vt(c,e.box_predictor_4),h=Vt(p,e.box_predictor_5),y=$e.concat([d.boxPredictionEncoding,u.boxPredictionEncoding,l.boxPredictionEncoding,v.boxPredictionEncoding,_.boxPredictionEncoding,h.boxPredictionEncoding],1),T=$e.concat([d.classPrediction,u.classPrediction,l.classPrediction,v.classPrediction,_.classPrediction,h.classPrediction],1);return{boxPredictions:y,classPredictions:T}})}var Z=class{constructor({minConfidence:t,maxResults:e}={}){this._name="SsdMobilenetv1Options";if(this._minConfidence=t||.5,this._maxResults=e||100,typeof this._minConfidence!="number"||this._minConfidence<=0||this._minConfidence>=1)throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);if(typeof this._maxResults!="number")throw new Error(`${this._name} - expected maxResults to be a number`)}get minConfidence(){return this._minConfidence}get maxResults(){return this._maxResults}};var Ut=class extends S{constructor(){super("SsdMobilenetv1")}forwardInput(t){let{params:e}=this;if(!e)throw new Error("SsdMobilenetv1 - load model before inference");return st.tidy(()=>{let r=st.cast(t.toBatchTensor(512,!1),"float32"),n=st.sub(st.mul(r,st.scalar(.007843137718737125)),st.scalar(1)),a=Go(n,e.mobilenetv1),{boxPredictions:s,classPredictions:i}=Uo(a.out,a.conv11,e.prediction_layer);return Vo(s,i,e.output_layer)})}async forward(t){return this.forwardInput(await E(t))}async locateFaces(t,e={}){let{maxResults:r,minConfidence:n}=new Z(e),a=await E(t),{boxes:s,scores:i}=this.forwardInput(a),c=s[0],m=i[0];for(let F=1;F{let[L,G]=[Math.max(0,y[F][0]),Math.min(1,y[F][2])].map(X=>X*h),[et,it]=[Math.max(0,y[F][1]),Math.min(1,y[F][3])].map(X=>X*_);return new M(p[F],new re(et,L,it-et,G-L),{height:a.getInputHeight(0),width:a.getInputWidth(0)})});return c.dispose(),m.dispose(),T}getDefaultModelName(){return"ssd_mobilenetv1_model"}extractParamsFromWeightMap(t){return Yo(t)}extractParams(t){return Ho(t)}};function Xo(o){let t=new Ut;return t.extractWeights(o),t}function na(o){return Xo(o)}var Jo=class extends Ut{};var qo=.4,Zo=[new x(.738768,.874946),new x(2.42204,2.65704),new x(4.30971,7.04493),new x(10.246,4.59428),new x(12.6868,11.8741)],Ko=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],Qo=[117.001,114.697,97.404],tn="tiny_yolov2_model",en="tiny_yolov2_separable_conv_model";var N=b(g());var br=o=>typeof o=="number";function ao(o){if(!o)throw new Error(`invalid config: ${o}`);if(typeof o.withSeparableConvs!="boolean")throw new Error(`config.withSeparableConvs has to be a boolean, have: ${o.withSeparableConvs}`);if(!br(o.iouThreshold)||o.iouThreshold<0||o.iouThreshold>1)throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${o.iouThreshold}`);if(!Array.isArray(o.classes)||!o.classes.length||!o.classes.every(t=>typeof t=="string"))throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(o.classes)}`);if(!Array.isArray(o.anchors)||!o.anchors.length||!o.anchors.map(t=>t||{}).every(t=>br(t.x)&&br(t.y)))throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(o.anchors)}`);if(o.meanRgb&&(!Array.isArray(o.meanRgb)||o.meanRgb.length!==3||!o.meanRgb.every(br)))throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(o.meanRgb)}`)}var Q=b(g());var K=b(g());function be(o){return K.tidy(()=>{let t=K.mul(o,K.scalar(.10000000149011612));return K.add(K.relu(K.sub(o,t)),t)})}function Ft(o,t){return Q.tidy(()=>{let e=Q.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=Q.conv2d(e,t.conv.filters,[1,1],"valid"),e=Q.sub(e,t.bn.sub),e=Q.mul(e,t.bn.truediv),e=Q.add(e,t.conv.bias),be(e)})}var St=b(g());function Tt(o,t){return St.tidy(()=>{let e=St.pad(o,[[0,0],[1,1],[1,1],[0,0]]);return e=St.separableConv2d(e,t.depthwise_filter,t.pointwise_filter,[1,1],"valid"),e=St.add(e,t.bias),be(e)})}var so=b(g());function aa(o,t){let e=ce(o,t);function r(s,i){let c=so.tensor1d(o(s)),m=so.tensor1d(o(s));return t.push({paramPath:`${i}/sub`},{paramPath:`${i}/truediv`}),{sub:c,truediv:m}}function n(s,i,c){let m=e(s,i,3,`${c}/conv`),p=r(i,`${c}/bn`);return{conv:m,bn:p}}let a=me(o,t);return{extractConvParams:e,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}}function rn(o,t,e,r){let{extractWeights:n,getRemainingWeights:a}=B(o),s=[],{extractConvParams:i,extractConvWithBatchNormParams:c,extractSeparableConvParams:m}=aa(n,s),p;if(t.withSeparableConvs){let[d,u,l,v,_,h,y,T,F]=r,L=t.isFirstLayerConv2d?i(d,u,3,"conv0"):m(d,u,"conv0"),G=m(u,l,"conv1"),et=m(l,v,"conv2"),it=m(v,_,"conv3"),X=m(_,h,"conv4"),Pt=m(h,y,"conv5"),_t=T?m(y,T,"conv6"):void 0,wt=F?m(T,F,"conv7"):void 0,Qt=i(F||T||y,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}else{let[d,u,l,v,_,h,y,T,F]=r,L=c(d,u,"conv0"),G=c(u,l,"conv1"),et=c(l,v,"conv2"),it=c(v,_,"conv3"),X=c(_,h,"conv4"),Pt=c(h,y,"conv5"),_t=c(y,T,"conv6"),wt=c(T,F,"conv7"),Qt=i(F,5*e,1,"conv8");p={conv0:L,conv1:G,conv2:et,conv3:it,conv4:X,conv5:Pt,conv6:_t,conv7:wt,conv8:Qt}}if(a().length!==0)throw new Error(`weights remaing after extract: ${a().length}`);return{params:p,paramMappings:s}}function sa(o,t){let e=j(o,t);function r(i){let c=e(`${i}/sub`,1),m=e(`${i}/truediv`,1);return{sub:c,truediv:m}}function n(i){let c=e(`${i}/filters`,4),m=e(`${i}/bias`,1);return{filters:c,bias:m}}function a(i){let c=n(`${i}/conv`),m=r(`${i}/bn`);return{conv:c,bn:m}}let s=pe(e);return{extractConvParams:n,extractConvWithBatchNormParams:a,extractSeparableConvParams:s}}function on(o,t){let e=[],{extractConvParams:r,extractConvWithBatchNormParams:n,extractSeparableConvParams:a}=sa(o,e),s;if(t.withSeparableConvs){let i=t.filterSizes&&t.filterSizes.length||9;s={conv0:t.isFirstLayerConv2d?r("conv0"):a("conv0"),conv1:a("conv1"),conv2:a("conv2"),conv3:a("conv3"),conv4:a("conv4"),conv5:a("conv5"),conv6:i>7?a("conv6"):void 0,conv7:i>8?a("conv7"):void 0,conv8:r("conv8")}}else s={conv0:n("conv0"),conv1:n("conv1"),conv2:n("conv2"),conv3:n("conv3"),conv4:n("conv4"),conv5:n("conv5"),conv6:n("conv6"),conv7:n("conv7"),conv8:r("conv8")};return W(o,e),{params:s,paramMappings:e}}var lt=class{constructor({inputSize:t,scoreThreshold:e}={}){this._name="TinyYolov2Options";if(this._inputSize=t||416,this._scoreThreshold=e||.5,typeof this._inputSize!="number"||this._inputSize%32!=0)throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);if(typeof this._scoreThreshold!="number"||this._scoreThreshold<=0||this._scoreThreshold>=1)throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`)}get inputSize(){return this._inputSize}get scoreThreshold(){return this._scoreThreshold}};var io=class extends S{constructor(t){super("TinyYolov2");ao(t),this._config=t}get config(){return this._config}get withClassScores(){return this.config.withClassScores||this.config.classes.length>1}get boxEncodingSize(){return 5+(this.withClassScores?this.config.classes.length:0)}runTinyYolov2(t,e){let r=Ft(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Ft(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=Ft(r,e.conv6),r=Ft(r,e.conv7),Gt(r,e.conv8,"valid",!1)}runMobilenet(t,e){let r=this.config.isFirstLayerConv2d?be(Gt(t,e.conv0,"valid",!1)):Tt(t,e.conv0);return r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv1),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv2),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv3),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv4),r=N.maxPool(r,[2,2],[2,2],"same"),r=Tt(r,e.conv5),r=N.maxPool(r,[2,2],[1,1],"same"),r=e.conv6?Tt(r,e.conv6):r,r=e.conv7?Tt(r,e.conv7):r,Gt(r,e.conv8,"valid",!1)}forwardInput(t,e){let{params:r}=this;if(!r)throw new Error("TinyYolov2 - load model before inference");return N.tidy(()=>{let n=N.cast(t.toBatchTensor(e,!1),"float32");return n=this.config.meanRgb?ot(n,this.config.meanRgb):n,n=n.div(N.scalar(256)),this.config.withSeparableConvs?this.runMobilenet(n,r):this.runTinyYolov2(n,r)})}async forward(t,e){return this.forwardInput(await E(t),e)}async detect(t,e={}){let{inputSize:r,scoreThreshold:n}=new lt(e),a=await E(t),s=await this.forwardInput(a,r),i=N.tidy(()=>N.unstack(s)[0].expandDims()),c={width:a.getInputWidth(0),height:a.getInputHeight(0)},m=await this.extractBoxes(i,a.getReshapedInputDimensions(0),n);s.dispose(),i.dispose();let p=m.map(h=>h.box),d=m.map(h=>h.score),u=m.map(h=>h.classScore),l=m.map(h=>this.config.classes[h.label]);return Sr(p.map(h=>h.rescale(r)),d,this.config.iouThreshold,!0).map(h=>new Dt(d[h],u[h],l[h],p[h],c))}getDefaultModelName(){return""}extractParamsFromWeightMap(t){return on(t,this.config)}extractParams(t){let e=this.config.filterSizes||io.DEFAULT_FILTER_SIZES,r=e?e.length:void 0;if(r!==7&&r!==8&&r!==9)throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${r} filterSizes in config`);return rn(t,this.config,this.boxEncodingSize,e)}async extractBoxes(t,e,r){let{width:n,height:a}=e,s=Math.max(n,a),i=s/n,c=s/a,m=t.shape[1],p=this.config.anchors.length,[d,u,l]=N.tidy(()=>{let y=t.reshape([m,m,p,this.boxEncodingSize]),T=y.slice([0,0,0,0],[m,m,p,4]),F=y.slice([0,0,0,4],[m,m,p,1]),L=this.withClassScores?N.softmax(y.slice([0,0,0,5],[m,m,p,this.config.classes.length]),3):N.scalar(0);return[T,F,L]}),v=[],_=await u.array(),h=await d.array();for(let y=0;yr){let G=(T+De(h[y][T][F][0]))/m*i,et=(y+De(h[y][T][F][1]))/m*c,it=Math.exp(h[y][T][F][2])*this.config.anchors[F].x/m*i,X=Math.exp(h[y][T][F][3])*this.config.anchors[F].y/m*c,Pt=G-it/2,_t=et-X/2,wt={row:y,col:T,anchor:F},{classScore:Qt,label:lo}=this.withClassScores?await this.extractPredictedClass(l,wt):{classScore:1,label:0};v.push({box:new ee(Pt,_t,Pt+it,_t+X),score:L,classScore:L*Qt,label:lo,...wt})}}return d.dispose(),u.dispose(),l.dispose(),v}async extractPredictedClass(t,e){let{row:r,col:n,anchor:a}=e,s=await t.array();return Array(this.config.classes.length).fill(0).map((i,c)=>s[r][n][a][c]).map((i,c)=>({classScore:i,label:c})).reduce((i,c)=>i.classScore>c.classScore?i:c)}},ge=io;ge.DEFAULT_FILTER_SIZES=[3,16,32,64,128,256,512,1024,1024];var ve=class extends ge{constructor(t=!0){let e={withSeparableConvs:t,iouThreshold:qo,classes:["face"],...t?{anchors:Ko,meanRgb:Qo}:{anchors:Zo,withClassScores:!0}};super(e)}get withSeparableConvs(){return this.config.withSeparableConvs}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return this.withSeparableConvs?en:tn}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};function ia(o,t=!0){let e=new ve(t);return e.extractWeights(o),e}var gr=class extends lt{constructor(){super(...arguments);this._name="TinyFaceDetectorOptions"}};var tt=class{async then(t){return t(await this.run())}async run(){throw new Error("ComposableTask - run is not implemented")}};var je=b(g());var co=b(g());async function Xt(o,t,e,r,n=({alignedRect:a})=>a){let a=o.map(c=>zt(c)?n(c):c.detection),s=r||(t instanceof co.Tensor?await se(t,a):await ae(t,a)),i=await e(s);return s.forEach(c=>c instanceof co.Tensor&&c.dispose()),i}async function ye(o,t,e,r,n){return Xt([o],t,async a=>e(a[0]),r,n)}var nn=.4,an=[new x(1.603231,2.094468),new x(6.041143,7.080126),new x(2.882459,3.518061),new x(4.266906,5.178857),new x(9.041765,10.66308)],sn=[117.001,114.697,97.404];var Fe=class extends ge{constructor(){let t={withSeparableConvs:!0,iouThreshold:nn,classes:["face"],anchors:an,meanRgb:sn,isFirstLayerConv2d:!0,filterSizes:[3,16,32,64,128,256,512]};super(t)}get anchors(){return this.config.anchors}async locateFaces(t,e){return(await this.detect(t,e)).map(n=>new M(n.score,n.relativeBox,{width:n.imageWidth,height:n.imageHeight}))}getDefaultModelName(){return"tiny_face_detector_model"}extractParamsFromWeightMap(t){return super.extractParamsFromWeightMap(t)}};var P={ssdMobilenetv1:new Ut,tinyFaceDetector:new Fe,tinyYolov2:new ve,faceLandmark68Net:new fe,faceLandmark68TinyNet:new dr,faceRecognitionNet:new xe,faceExpressionNet:new cr,ageGenderNet:new pr},cn=(o,t)=>P.ssdMobilenetv1.locateFaces(o,t),ca=(o,t)=>P.tinyFaceDetector.locateFaces(o,t),ma=(o,t)=>P.tinyYolov2.locateFaces(o,t),mn=o=>P.faceLandmark68Net.detectLandmarks(o),pa=o=>P.faceLandmark68TinyNet.detectLandmarks(o),da=o=>P.faceRecognitionNet.computeFaceDescriptor(o),ua=o=>P.faceExpressionNet.predictExpressions(o),la=o=>P.ageGenderNet.predictAgeAndGender(o),pn=o=>P.ssdMobilenetv1.load(o),fa=o=>P.tinyFaceDetector.load(o),ha=o=>P.tinyYolov2.load(o),xa=o=>P.faceLandmark68Net.load(o),ba=o=>P.faceLandmark68TinyNet.load(o),ga=o=>P.faceRecognitionNet.load(o),va=o=>P.faceExpressionNet.load(o),ya=o=>P.ageGenderNet.load(o),Fa=pn,Ta=cn,Pa=mn;var mo=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},_e=class extends mo{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.faceExpressionNet.predictExpressions(n))),this.extractedFaces);return t.map((r,n)=>mr(r,e[n]))}withAgeAndGender(){return new Te(this,this.input)}},we=class extends mo{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceExpressionNet.predictExpressions(r),this.extractedFaces);return mr(t,e)}withAgeAndGender(){return new Pe(this,this.input)}},Zt=class extends _e{withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Kt=class extends we{withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var po=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.extractedFaces=r}},Te=class extends po{async run(){let t=await this.parentTask,e=await Xt(t,this.input,async r=>Promise.all(r.map(n=>P.ageGenderNet.predictAgeAndGender(n))),this.extractedFaces);return t.map((r,n)=>{let{age:a,gender:s,genderProbability:i}=e[n];return hr(xr(r,s,i),a)})}withFaceExpressions(){return new _e(this,this.input)}},Pe=class extends po{async run(){let t=await this.parentTask;if(!t)return;let{age:e,gender:r,genderProbability:n}=await ye(t,this.input,a=>P.ageGenderNet.predictAgeAndGender(a),this.extractedFaces);return hr(xr(t,r,n),e)}withFaceExpressions(){return new we(this,this.input)}},Jt=class extends Te{withFaceExpressions(){return new Zt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},qt=class extends Pe{withFaceExpressions(){return new Kt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var vr=class extends tt{constructor(t,e){super();this.parentTask=t;this.input=e}},At=class extends vr{async run(){let t=await this.parentTask;return(await Xt(t,this.input,r=>Promise.all(r.map(n=>P.faceRecognitionNet.computeFaceDescriptor(n))),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}))).map((r,n)=>fr(t[n],r))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}},Wt=class extends vr{async run(){let t=await this.parentTask;if(!t)return;let e=await ye(t,this.input,r=>P.faceRecognitionNet.computeFaceDescriptor(r),null,r=>r.landmarks.align(null,{useDlibAlignment:!0}));return fr(t,e)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}};var yr=class extends tt{constructor(t,e,r){super();this.parentTask=t;this.input=e;this.useTinyLandmarkNet=r}get landmarkNet(){return this.useTinyLandmarkNet?P.faceLandmark68TinyNet:P.faceLandmark68Net}},Fr=class extends yr{async run(){let t=await this.parentTask,e=t.map(a=>a.detection),r=this.input instanceof je.Tensor?await se(this.input,e):await ae(this.input,e),n=await Promise.all(r.map(a=>this.landmarkNet.detectLandmarks(a)));return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),t.map((a,s)=>le(a,n[s]))}withFaceExpressions(){return new Zt(this,this.input)}withAgeAndGender(){return new Jt(this,this.input)}withFaceDescriptors(){return new At(this,this.input)}},Tr=class extends yr{async run(){let t=await this.parentTask;if(!t)return;let{detection:e}=t,r=this.input instanceof je.Tensor?await se(this.input,[e]):await ae(this.input,[e]),n=await this.landmarkNet.detectLandmarks(r[0]);return r.forEach(a=>a instanceof je.Tensor&&a.dispose()),le(t,n)}withFaceExpressions(){return new Kt(this,this.input)}withAgeAndGender(){return new qt(this,this.input)}withFaceDescriptor(){return new Wt(this,this.input)}};var Pr=class extends tt{constructor(t,e=new Z){super();this.input=t;this.options=e}},He=class extends Pr{async run(){let{input:t,options:e}=this,r=e instanceof gr?n=>P.tinyFaceDetector.locateFaces(n,e):e instanceof Z?n=>P.ssdMobilenetv1.locateFaces(n,e):e instanceof lt?n=>P.tinyYolov2.locateFaces(n,e):null;if(!r)throw new Error("detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options");return r(t)}runAndExtendWithFaceDetections(){return new Promise(async t=>{let e=await this.run();t(e.map(r=>$t({},r)))})}withFaceLandmarks(t=!1){return new Fr(this.runAndExtendWithFaceDetections(),this.input,t)}withFaceExpressions(){return new _e(this.runAndExtendWithFaceDetections(),this.input)}withAgeAndGender(){return new Te(this.runAndExtendWithFaceDetections(),this.input)}},_r=class extends Pr{async run(){let t=await new He(this.input,this.options),e=t[0];return t.forEach(r=>{r.score>e.score&&(e=r)}),e}runAndExtendWithFaceDetection(){return new Promise(async t=>{let e=await this.run();t(e?$t({},e):void 0)})}withFaceLandmarks(t=!1){return new Tr(this.runAndExtendWithFaceDetection(),this.input,t)}withFaceExpressions(){return new we(this.runAndExtendWithFaceDetection(),this.input)}withAgeAndGender(){return new Pe(this.runAndExtendWithFaceDetection(),this.input)}};function _a(o,t=new Z){return new _r(o,t)}function wr(o,t=new Z){return new He(o,t)}async function dn(o,t){return wr(o,new Z(t?{minConfidence:t}:{})).withFaceLandmarks().withFaceDescriptors()}async function wa(o,t={}){return wr(o,new lt(t)).withFaceLandmarks().withFaceDescriptors()}var Da=dn;function uo(o,t){if(o.length!==t.length)throw new Error("euclideanDistance: arr1.length !== arr2.length");let e=Array.from(o),r=Array.from(t);return Math.sqrt(e.map((n,a)=>n-r[a]).reduce((n,a)=>n+a**2,0))}var Dr=class{constructor(t,e=.6){this._distanceThreshold=e;let r=Array.isArray(t)?t:[t];if(!r.length)throw new Error("FaceRecognizer.constructor - expected atleast one input");let n=1,a=()=>`person ${n++}`;this._labeledDescriptors=r.map(s=>{if(s instanceof xt)return s;if(s instanceof Float32Array)return new xt(a(),[s]);if(s.descriptor&&s.descriptor instanceof Float32Array)return new xt(a(),[s.descriptor]);throw new Error("FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>")})}get labeledDescriptors(){return this._labeledDescriptors}get distanceThreshold(){return this._distanceThreshold}computeMeanDistance(t,e){return e.map(r=>uo(r,t)).reduce((r,n)=>r+n,0)/(e.length||1)}matchDescriptor(t){return this.labeledDescriptors.map(({descriptors:e,label:r})=>new Ee(r,this.computeMeanDistance(t,e))).reduce((e,r)=>e.distancet.toJSON())}}static fromJSON(t){let e=t.labeledDescriptors.map(r=>xt.fromJSON(r));return new Dr(e,t.distanceThreshold)}};function Ea(o){let t=new Fe;return t.extractWeights(o),t}function un(o,t){let{width:e,height:r}=new A(t.width,t.height);if(e<=0||r<=0)throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({width:e,height:r})}`);if(Array.isArray(o))return o.map(n=>un(n,{width:e,height:r}));if(zt(o)){let n=o.detection.forSize(e,r),a=o.unshiftedLandmarks.forSize(n.box.width,n.box.height);return le($t(o,n),a)}return pt(o)?$t(o,o.detection.forSize(e,r)):o instanceof V||o instanceof M?o.forSize(e,r):o}var Ca=typeof process!="undefined",Na=typeof navigator!="undefined"&&typeof navigator.userAgent!="undefined",Ia={faceapi:Co,node:Ca,browser:Na}; //# sourceMappingURL=face-api.node.js.map diff --git a/dist/face-api.node.js.map b/dist/face-api.node.js.map index 9e93573..5347aa4 100644 --- a/dist/face-api.node.js.map +++ b/dist/face-api.node.js.map @@ -1,7 +1,7 @@ { "version": 3, "sources": ["../src/tfjs/tf-node.ts", "../src/env/isNodejs.ts", "../src/index.ts", "../src/draw/index.ts", "../src/draw/drawContour.ts", "../src/utils/index.ts", "../src/classes/Dimensions.ts", "../src/classes/Point.ts", "../src/classes/Box.ts", "../src/classes/BoundingBox.ts", "../src/classes/ObjectDetection.ts", "../src/classes/FaceDetection.ts", "../src/ops/iou.ts", "../src/ops/minBbox.ts", "../src/ops/nonMaxSuppression.ts", "../src/ops/normalize.ts", "../src/ops/padToSquare.ts", "../src/ops/shuffleArray.ts", "../src/ops/index.ts", "../src/classes/Rect.ts", "../src/classes/FaceLandmarks.ts", "../src/classes/FaceLandmarks5.ts", "../src/classes/FaceLandmarks68.ts", "../src/classes/FaceMatch.ts", "../src/classes/LabeledBox.ts", "../src/classes/LabeledFaceDescriptors.ts", "../src/classes/PredictedBox.ts", "../src/factories/WithFaceDetection.ts", "../src/env/createBrowserEnv.ts", "../src/env/createFileSystem.ts", "../src/env/createNodejsEnv.ts", "../src/env/isBrowser.ts", "../src/env/index.ts", "../src/dom/resolveInput.ts", "../src/dom/getContext2dOrThrow.ts", "../src/draw/DrawTextField.ts", "../src/draw/DrawBox.ts", "../src/draw/drawDetections.ts", "../src/faceExpressionNet/FaceExpressionNet.ts", "../src/dom/isMediaLoaded.ts", "../src/dom/awaitMediaLoaded.ts", "../src/dom/bufferToImage.ts", "../src/dom/getMediaDimensions.ts", "../src/dom/createCanvas.ts", "../src/dom/imageTensorToCanvas.ts", "../src/dom/isMediaElement.ts", "../src/dom/NetInput.ts", "../src/dom/imageToSquare.ts", "../src/dom/toNetInput.ts", "../src/dom/extractFaces.ts", "../src/dom/extractFaceTensors.ts", "../src/dom/fetchOrThrow.ts", "../src/dom/fetchImage.ts", "../src/dom/fetchJson.ts", "../src/dom/fetchNetWeights.ts", "../src/dom/loadWeightMap.ts", "../src/common/getModelUris.ts", "../src/dom/matchDimensions.ts", "../src/faceFeatureExtractor/FaceFeatureExtractor.ts", "../src/NeuralNetwork.ts", "../src/faceFeatureExtractor/denseBlock.ts", "../src/common/depthwiseSeparableConv.ts", "../src/common/convLayer.ts", "../src/common/disposeUnusedWeightTensors.ts", "../src/common/extractConvParamsFactory.ts", "../src/common/extractFCParamsFactory.ts", "../src/common/extractSeparableConvParamsFactory.ts", "../src/common/types.ts", "../src/common/extractWeightEntryFactory.ts", "../src/common/extractWeightsFactory.ts", "../src/faceFeatureExtractor/extractorsFactory.ts", "../src/faceFeatureExtractor/extractParams.ts", "../src/common/loadConvParamsFactory.ts", "../src/faceFeatureExtractor/loadParamsFactory.ts", "../src/faceFeatureExtractor/extractParamsFromWeightMap.ts", "../src/faceProcessor/FaceProcessor.ts", "../src/common/fullyConnectedLayer.ts", "../src/faceProcessor/extractParams.ts", "../src/faceProcessor/extractParamsFromWeightMap.ts", "../src/faceProcessor/util.ts", "../src/faceExpressionNet/FaceExpressions.ts", "../src/factories/WithFaceExpressions.ts", "../src/draw/drawFaceExpressions.ts", "../src/factories/WithFaceLandmarks.ts", "../src/draw/DrawFaceLandmarks.ts", "../src/ageGenderNet/AgeGenderNet.ts", "../src/xception/TinyXception.ts", "../src/xception/extractParams.ts", "../src/xception/extractParamsFromWeightMap.ts", "../src/ageGenderNet/extractParams.ts", "../src/ageGenderNet/extractParamsFromWeightMap.ts", "../src/ageGenderNet/types.ts", "../src/faceLandmarkNet/FaceLandmark68NetBase.ts", "../src/faceLandmarkNet/FaceLandmark68Net.ts", "../src/faceFeatureExtractor/TinyFaceFeatureExtractor.ts", "../src/faceFeatureExtractor/extractParamsFromWeightMapTiny.ts", "../src/faceFeatureExtractor/extractParamsTiny.ts", "../src/faceLandmarkNet/FaceLandmark68TinyNet.ts", "../src/faceLandmarkNet/index.ts", "../src/faceRecognitionNet/FaceRecognitionNet.ts", "../src/faceRecognitionNet/convLayer.ts", "../src/faceRecognitionNet/scaleLayer.ts", "../src/faceRecognitionNet/extractParams.ts", "../src/faceRecognitionNet/extractParamsFromWeightMap.ts", "../src/faceRecognitionNet/residualLayer.ts", "../src/faceRecognitionNet/index.ts", "../src/factories/WithFaceDescriptor.ts", "../src/factories/WithAge.ts", "../src/factories/WithGender.ts", "../src/ssdMobilenetv1/SsdMobilenetv1.ts", "../src/ssdMobilenetv1/extractParams.ts", "../src/ssdMobilenetv1/extractParamsFromWeightMap.ts", "../src/ssdMobilenetv1/mobileNetV1.ts", "../src/ssdMobilenetv1/pointwiseConvLayer.ts", "../src/ssdMobilenetv1/nonMaxSuppression.ts", "../src/ssdMobilenetv1/outputLayer.ts", "../src/ssdMobilenetv1/predictionLayer.ts", "../src/ssdMobilenetv1/boxPredictionLayer.ts", "../src/ssdMobilenetv1/SsdMobilenetv1Options.ts", "../src/ssdMobilenetv1/index.ts", "../src/tinyYolov2/const.ts", "../src/tinyYolov2/TinyYolov2Base.ts", "../src/tinyYolov2/config.ts", "../src/tinyYolov2/convWithBatchNorm.ts", "../src/tinyYolov2/leaky.ts", "../src/tinyYolov2/depthwiseSeparableConv.ts", "../src/tinyYolov2/extractParams.ts", "../src/tinyYolov2/extractParamsFromWeightMap.ts", "../src/tinyYolov2/TinyYolov2Options.ts", "../src/tinyYolov2/TinyYolov2.ts", "../src/tinyYolov2/index.ts", "../src/tinyFaceDetector/TinyFaceDetectorOptions.ts", "../src/globalApi/ComposableTask.ts", "../src/globalApi/DetectFaceLandmarksTasks.ts", "../src/globalApi/extractFacesAndComputeResults.ts", "../src/tinyFaceDetector/const.ts", "../src/tinyFaceDetector/TinyFaceDetector.ts", "../src/globalApi/nets.ts", "../src/globalApi/PredictFaceExpressionsTask.ts", "../src/globalApi/PredictAgeAndGenderTask.ts", "../src/globalApi/ComputeFaceDescriptorsTasks.ts", "../src/globalApi/DetectFacesTasks.ts", "../src/globalApi/detectFaces.ts", "../src/globalApi/allFaces.ts", "../src/euclideanDistance.ts", "../src/globalApi/FaceMatcher.ts", "../src/tinyFaceDetector/index.ts", "../src/resizeResults.ts"], - "sourcesContent": ["/* eslint-disable import/no-extraneous-dependencies */\n/* eslint-disable node/no-unpublished-import */\n\nexport * from '@tensorflow/tfjs-node';\n", "export function isNodejs(): boolean {\n return typeof global === 'object'\n && typeof require === 'function'\n && typeof module !== 'undefined'\n // issues with gatsby.js: module.exports is undefined\n // && !!module.exports\n && typeof process !== 'undefined' && !!process.version;\n}\n", "import * as tf from '../dist/tfjs.esm';\nimport * as draw from './draw/index';\nimport * as utils from './utils/index';\nimport * as pkg from '../package.json';\n\nexport { tf, draw, utils };\n\nexport * from './ageGenderNet/index';\nexport * from './classes/index';\nexport * from './dom/index';\nexport * from './env/index';\nexport * from './faceExpressionNet/index';\nexport * from './faceLandmarkNet/index';\nexport * from './faceRecognitionNet/index';\nexport * from './factories/index';\nexport * from './globalApi/index';\nexport * from './ops/index';\nexport * from './ssdMobilenetv1/index';\nexport * from './tinyFaceDetector/index';\nexport * from './tinyYolov2/index';\nexport * from './euclideanDistance';\nexport * from './NeuralNetwork';\nexport * from './resizeResults';\n\nconst node = (typeof process !== 'undefined');\n// eslint-disable-next-line no-undef\nconst browser = (typeof navigator !== 'undefined') && (typeof navigator.userAgent !== 'undefined');\nexport const version = { faceapi: pkg.version as string, node, browser };\n", "export * from './drawContour';\nexport * from './drawDetections';\nexport * from './drawFaceExpressions';\nexport * from './DrawBox';\nexport * from './DrawFaceLandmarks';\nexport * from './DrawTextField';\n", "import { Point } from '../classes/index';\n\nexport function drawContour(\n ctx: CanvasRenderingContext2D,\n points: Point[],\n isClosed: boolean = false,\n) {\n ctx.beginPath();\n\n points.slice(1).forEach(({ x, y }, prevIdx) => {\n const from = points[prevIdx];\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(x, y);\n });\n\n if (isClosed) {\n const from = points[points.length - 1];\n const to = points[0];\n if (!from || !to) {\n return;\n }\n\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(to.x, to.y);\n }\n\n ctx.stroke();\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Point } from '../classes/index';\nimport { Dimensions, IDimensions } from '../classes/Dimensions';\n\nexport function isTensor(tensor: any, dim: number) {\n return tensor instanceof tf.Tensor && tensor.shape.length === dim;\n}\n\nexport function isTensor1D(tensor: any): tensor is tf.Tensor1D {\n return isTensor(tensor, 1);\n}\n\nexport function isTensor2D(tensor: any): tensor is tf.Tensor2D {\n return isTensor(tensor, 2);\n}\n\nexport function isTensor3D(tensor: any): tensor is tf.Tensor3D {\n return isTensor(tensor, 3);\n}\n\nexport function isTensor4D(tensor: any): tensor is tf.Tensor4D {\n return isTensor(tensor, 4);\n}\n\nexport function isFloat(num: number) {\n return num % 1 !== 0;\n}\n\nexport function isEven(num: number) {\n return num % 2 === 0;\n}\n\nexport function round(num: number, prec: number = 2) {\n const f = 10 ** prec;\n return Math.floor(num * f) / f;\n}\n\nexport function isDimensions(obj: any): boolean {\n return obj && obj.width && obj.height;\n}\n\nexport function computeReshapedDimensions({ width, height }: IDimensions, inputSize: number) {\n const scale = inputSize / Math.max(height, width);\n return new Dimensions(Math.round(width * scale), Math.round(height * scale));\n}\n\nexport function getCenterPoint(pts: Point[]): Point {\n return pts.reduce((sum, pt) => sum.add(pt), new Point(0, 0))\n .div(new Point(pts.length, pts.length));\n}\n\nexport function range(num: number, start: number, step: number): number[] {\n return Array(num).fill(0).map((_, i) => start + (i * step));\n}\n\nexport function isValidNumber(num: any) {\n // eslint-disable-next-line no-mixed-operators\n return !!num && (num !== Infinity) && (num !== -Infinity) && !Number.isNaN(num) || num === 0;\n}\n\nexport function isValidProbablitiy(num: any) {\n return isValidNumber(num) && num >= 0 && num <= 1.0;\n}\n", "import { isValidNumber } from '../utils/index';\n\nexport interface IDimensions {\n width: number\n height: number\n}\n\nexport class Dimensions implements IDimensions {\n private _width: number\n\n private _height: number\n\n constructor(width: number, height: number) {\n if (!isValidNumber(width) || !isValidNumber(height)) {\n throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({ width, height })}`);\n }\n\n this._width = width;\n this._height = height;\n }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public reverse(): Dimensions {\n return new Dimensions(1 / this.width, 1 / this.height);\n }\n}\n", "export interface IPoint {\n x: number\n y: number\n}\n\nexport class Point implements IPoint {\n private _x: number\n\n private _y: number\n\n constructor(x: number, y: number) {\n this._x = x;\n this._y = y;\n }\n\n get x(): number { return this._x; }\n\n get y(): number { return this._y; }\n\n public add(pt: IPoint): Point {\n return new Point(this.x + pt.x, this.y + pt.y);\n }\n\n public sub(pt: IPoint): Point {\n return new Point(this.x - pt.x, this.y - pt.y);\n }\n\n public mul(pt: IPoint): Point {\n return new Point(this.x * pt.x, this.y * pt.y);\n }\n\n public div(pt: IPoint): Point {\n return new Point(this.x / pt.x, this.y / pt.y);\n }\n\n public abs(): Point {\n return new Point(Math.abs(this.x), Math.abs(this.y));\n }\n\n public magnitude(): number {\n return Math.sqrt((this.x ** 2) + (this.y ** 2));\n }\n\n public floor(): Point {\n return new Point(Math.floor(this.x), Math.floor(this.y));\n }\n}\n", "import { isDimensions, isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { IDimensions } from './Dimensions';\nimport { Point } from './Point';\nimport { IRect } from './Rect';\n\nexport class Box implements IBoundingBox, IRect {\n public static isRect(rect: any): boolean {\n return !!rect && [rect.x, rect.y, rect.width, rect.height].every(isValidNumber);\n }\n\n public static assertIsValidBox(box: any, callee: string, allowNegativeDimensions: boolean = false) {\n if (!Box.isRect(box)) {\n throw new Error(`${callee} - invalid box: ${JSON.stringify(box)}, expected object with properties x, y, width, height`);\n }\n\n if (!allowNegativeDimensions && (box.width < 0 || box.height < 0)) {\n throw new Error(`${callee} - width (${box.width}) and height (${box.height}) must be positive numbers`);\n }\n }\n\n private _x: number\n\n private _y: number\n\n private _width: number\n\n private _height: number\n\n constructor(_box: IBoundingBox | IRect, allowNegativeDimensions: boolean = true) {\n const box = (_box || {}) as any;\n\n const isBbox = [box.left, box.top, box.right, box.bottom].every(isValidNumber);\n const isRect = [box.x, box.y, box.width, box.height].every(isValidNumber);\n\n if (!isRect && !isBbox) {\n throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(box)}`);\n }\n\n const [x, y, width, height] = isRect\n ? [box.x, box.y, box.width, box.height]\n : [box.left, box.top, box.right - box.left, box.bottom - box.top];\n\n Box.assertIsValidBox({\n x, y, width, height,\n }, 'Box.constructor', allowNegativeDimensions);\n\n this._x = x;\n this._y = y;\n this._width = width;\n this._height = height;\n }\n\n public get x(): number { return this._x; }\n\n public get y(): number { return this._y; }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public get left(): number { return this.x; }\n\n public get top(): number { return this.y; }\n\n public get right(): number { return this.x + this.width; }\n\n public get bottom(): number { return this.y + this.height; }\n\n public get area(): number { return this.width * this.height; }\n\n public get topLeft(): Point { return new Point(this.left, this.top); }\n\n public get topRight(): Point { return new Point(this.right, this.top); }\n\n public get bottomLeft(): Point { return new Point(this.left, this.bottom); }\n\n public get bottomRight(): Point { return new Point(this.right, this.bottom); }\n\n public round(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.round(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public floor(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.floor(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public toSquare(): Box {\n let {\n x, y, width, height,\n } = this;\n const diff = Math.abs(width - height);\n if (width < height) {\n x -= (diff / 2);\n width += diff;\n }\n if (height < width) {\n y -= (diff / 2);\n height += diff;\n }\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public rescale(s: IDimensions | number): Box {\n const scaleX = isDimensions(s) ? (s as IDimensions).width : s as number;\n const scaleY = isDimensions(s) ? (s as IDimensions).height : s as number;\n return new Box({\n x: this.x * scaleX,\n y: this.y * scaleY,\n width: this.width * scaleX,\n height: this.height * scaleY,\n });\n }\n\n public pad(padX: number, padY: number): Box {\n const [x, y, width, height] = [\n this.x - (padX / 2),\n this.y - (padY / 2),\n this.width + padX,\n this.height + padY,\n ];\n return new Box({\n x, y, width, height,\n });\n }\n\n public clipAtImageBorders(imgWidth: number, imgHeight: number): Box {\n const {\n x, y, right, bottom,\n } = this;\n const clippedX = Math.max(x, 0);\n const clippedY = Math.max(y, 0);\n\n const newWidth = right - clippedX;\n const newHeight = bottom - clippedY;\n const clippedWidth = Math.min(newWidth, imgWidth - clippedX);\n const clippedHeight = Math.min(newHeight, imgHeight - clippedY);\n\n return (new Box({\n x: clippedX, y: clippedY, width: clippedWidth, height: clippedHeight,\n })).floor();\n }\n\n public shift(sx: number, sy: number): Box {\n const { width, height } = this;\n const x = this.x + sx;\n const y = this.y + sy;\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public padAtBorders(imageHeight: number, imageWidth: number) {\n const w = this.width + 1;\n const h = this.height + 1;\n\n const dx = 1;\n const dy = 1;\n let edx = w;\n let edy = h;\n\n let x = this.left;\n let y = this.top;\n let ex = this.right;\n let ey = this.bottom;\n\n if (ex > imageWidth) {\n edx = -ex + imageWidth + w;\n ex = imageWidth;\n }\n if (ey > imageHeight) {\n edy = -ey + imageHeight + h;\n ey = imageHeight;\n }\n if (x < 1) {\n edy = 2 - x;\n x = 1;\n }\n if (y < 1) {\n edy = 2 - y;\n y = 1;\n }\n\n return {\n dy, edy, dx, edx, y, ey, x, ex, w, h,\n };\n }\n\n public calibrate(region: Box) {\n return new Box({\n left: this.left + (region.left * this.width),\n top: this.top + (region.top * this.height),\n right: this.right + (region.right * this.width),\n bottom: this.bottom + (region.bottom * this.height),\n }).toSquare().round();\n }\n}\n", "import { Box } from './Box';\n\nexport interface IBoundingBox {\n left: number\n top: number\n right: number\n bottom: number\n}\n\nexport class BoundingBox extends Box implements IBoundingBox {\n constructor(left: number, top: number, right: number, bottom: number, allowNegativeDimensions: boolean = false) {\n super({\n left, top, right, bottom,\n }, allowNegativeDimensions);\n }\n}\n", "import { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { IRect, Rect } from './Rect';\n\nexport class ObjectDetection {\n private _score: number\n\n private _classScore: number\n\n private _className: string\n\n private _box: Rect\n\n private _imageDims: Dimensions\n\n constructor(\n score: number,\n classScore: number,\n className: string,\n relativeBox: IRect,\n imageDims: IDimensions,\n ) {\n this._imageDims = new Dimensions(imageDims.width, imageDims.height);\n this._score = score;\n this._classScore = classScore;\n this._className = className;\n this._box = new Box(relativeBox).rescale(this._imageDims);\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n\n public get className(): string { return this._className; }\n\n public get box(): Box { return this._box; }\n\n public get imageDims(): Dimensions { return this._imageDims; }\n\n public get imageWidth(): number { return this.imageDims.width; }\n\n public get imageHeight(): number { return this.imageDims.height; }\n\n public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()); }\n\n public forSize(width: number, height: number): ObjectDetection {\n return new ObjectDetection(\n this.score,\n this.classScore,\n this.className,\n this.relativeBox,\n { width, height },\n );\n }\n}\n", "import { Box } from './Box';\nimport { IDimensions } from './Dimensions';\nimport { ObjectDetection } from './ObjectDetection';\nimport { Rect } from './Rect';\n\nexport interface IFaceDetecion {\n score: number\n box: Box\n}\n\nexport class FaceDetection extends ObjectDetection implements IFaceDetecion {\n constructor(\n score: number,\n relativeBox: Rect,\n imageDims: IDimensions,\n ) {\n super(score, score, '', relativeBox, imageDims);\n }\n\n public forSize(width: number, height: number): FaceDetection {\n const { score, relativeBox, imageDims } = super.forSize(width, height);\n return new FaceDetection(score, relativeBox, imageDims);\n }\n}\n", "import { Box } from '../classes/Box';\n\nexport function iou(box1: Box, box2: Box, isIOU: boolean = true) {\n const width = Math.max(0.0, Math.min(box1.right, box2.right) - Math.max(box1.left, box2.left));\n const height = Math.max(0.0, Math.min(box1.bottom, box2.bottom) - Math.max(box1.top, box2.top));\n const interSection = width * height;\n\n return isIOU\n ? interSection / (box1.area + box2.area - interSection)\n : interSection / Math.min(box1.area, box2.area);\n}\n", "import { BoundingBox, IPoint } from '../classes/index';\n\nexport function minBbox(pts: IPoint[]): BoundingBox {\n const xs = pts.map((pt) => pt.x);\n const ys = pts.map((pt) => pt.y);\n const minX = xs.reduce((min, x) => (x < min ? x : min), Infinity);\n const minY = ys.reduce((min, y) => (y < min ? y : min), Infinity);\n const maxX = xs.reduce((max, x) => (max < x ? x : max), 0);\n const maxY = ys.reduce((max, y) => (max < y ? y : max), 0);\n\n return new BoundingBox(minX, minY, maxX, maxY);\n}\n", "import { Box } from '../classes/Box';\nimport { iou } from './iou';\n\nexport function nonMaxSuppression(\n boxes: Box[],\n scores: number[],\n iouThreshold: number,\n isIOU: boolean = true,\n): number[] {\n let indicesSortedByScore = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .sort((c1, c2) => c1.score - c2.score)\n .map((c) => c.boxIndex);\n\n const pick: number[] = [];\n\n while (indicesSortedByScore.length > 0) {\n const curr = indicesSortedByScore.pop() as number;\n pick.push(curr);\n\n const indices = indicesSortedByScore;\n\n const outputs: number[] = [];\n for (let i = 0; i < indices.length; i++) {\n const idx = indices[i];\n\n const currBox = boxes[curr];\n const idxBox = boxes[idx];\n\n outputs.push(iou(currBox, idxBox, isIOU));\n }\n\n indicesSortedByScore = indicesSortedByScore.filter(\n (_, j) => outputs[j] <= iouThreshold,\n );\n }\n\n return pick;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function normalize(x: tf.Tensor4D, meanRgb: number[]): tf.Tensor4D {\n return tf.tidy(() => {\n const [r, g, b] = meanRgb;\n const avg_r = tf.fill([...x.shape.slice(0, 3), 1], r, 'float32');\n const avg_g = tf.fill([...x.shape.slice(0, 3), 1], g, 'float32');\n const avg_b = tf.fill([...x.shape.slice(0, 3), 1], b, 'float32');\n const avg_rgb = tf.concat([avg_r, avg_g, avg_b], 3);\n\n return tf.sub(x, avg_rgb);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n/**\n * Pads the smaller dimension of an image tensor with zeros, such that width === height.\n *\n * @param imgTensor The image tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The padded tensor with width === height.\n */\nexport function padToSquare(\n imgTensor: tf.Tensor4D,\n isCenterImage: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const [height, width] = imgTensor.shape.slice(1);\n if (height === width) {\n return imgTensor;\n }\n\n const dimDiff = Math.abs(height - width);\n const paddingAmount = Math.round(dimDiff * (isCenterImage ? 0.5 : 1));\n const paddingAxis = height > width ? 2 : 1;\n\n const createPaddingTensor = (paddingAmountLocal: number): tf.Tensor => {\n const paddingTensorShape = imgTensor.shape.slice();\n paddingTensorShape[paddingAxis] = paddingAmountLocal;\n return tf.fill(paddingTensorShape, 0, 'float32');\n };\n\n const paddingTensorAppend = createPaddingTensor(paddingAmount);\n const remainingPaddingAmount = dimDiff - (paddingTensorAppend.shape[paddingAxis] as number);\n\n const paddingTensorPrepend = isCenterImage && remainingPaddingAmount\n ? createPaddingTensor(remainingPaddingAmount)\n : null;\n\n const tensorsToStack = [\n paddingTensorPrepend,\n imgTensor,\n paddingTensorAppend,\n ]\n .filter((t) => !!t)\n // .map((t: tf.Tensor) => t.toFloat()) as tf.Tensor4D[]\n .map((t: tf.Tensor) => tf.cast(t, 'float32')) as tf.Tensor4D[];\n return tf.concat(tensorsToStack, paddingAxis);\n });\n}\n", "export function shuffleArray(inputArray: any[]) {\n const array = inputArray.slice();\n for (let i = array.length - 1; i > 0; i--) {\n const j = Math.floor(Math.random() * (i + 1));\n const x = array[i];\n array[i] = array[j];\n array[j] = x;\n }\n return array;\n}\n", "export * from './iou';\nexport * from './minBbox';\nexport * from './nonMaxSuppression';\nexport * from './normalize';\nexport * from './padToSquare';\nexport * from './shuffleArray';\n\nexport function sigmoid(x: number) {\n return 1 / (1 + Math.exp(-x));\n}\n\nexport function inverseSigmoid(x: number) {\n return Math.log(x / (1 - x));\n}\n", "import { Box } from './Box';\n\nexport interface IRect {\n x: number\n y: number\n width: number\n height: number\n}\n\nexport class Rect extends Box implements IRect {\n constructor(x: number, y: number, width: number, height: number, allowNegativeDimensions: boolean = false) {\n super({\n x, y, width, height,\n }, allowNegativeDimensions);\n }\n}\n", "import { minBbox } from '../ops/index';\nimport { getCenterPoint } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { FaceDetection } from './FaceDetection';\nimport { Point } from './Point';\nimport { IRect, Rect } from './Rect';\n\n// face alignment constants\nconst relX = 0.5;\nconst relY = 0.43;\nconst relScale = 0.45;\n\nexport interface IFaceLandmarks {\n positions: Point[]\n shift: Point\n}\n\nexport class FaceLandmarks implements IFaceLandmarks {\n protected _shift: Point\n\n protected _positions: Point[]\n\n protected _imgDims: Dimensions\n\n constructor(\n relativeFaceLandmarkPositions: Point[],\n imgDims: IDimensions,\n shift: Point = new Point(0, 0),\n ) {\n const { width, height } = imgDims;\n this._imgDims = new Dimensions(width, height);\n this._shift = shift;\n this._positions = relativeFaceLandmarkPositions.map(\n (pt) => pt.mul(new Point(width, height)).add(shift),\n );\n }\n\n public get shift(): Point { return new Point(this._shift.x, this._shift.y); }\n\n public get imageWidth(): number { return this._imgDims.width; }\n\n public get imageHeight(): number { return this._imgDims.height; }\n\n public get positions(): Point[] { return this._positions; }\n\n public get relativePositions(): Point[] {\n return this._positions.map(\n (pt) => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight)),\n );\n }\n\n public forSize(width: number, height: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n { width, height },\n );\n }\n\n public shiftBy(x: number, y: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n this._imgDims,\n new Point(x, y),\n );\n }\n\n public shiftByPoint(pt: Point): T {\n return this.shiftBy(pt.x, pt.y);\n }\n\n /**\n * Aligns the face landmarks after face detection from the relative positions of the faces\n * bounding box, or it's current shift. This function should be used to align the face images\n * after face detection has been performed, before they are passed to the face recognition net.\n * This will make the computed face descriptor more accurate.\n *\n * @param detection (optional) The bounding box of the face or the face detection result. If\n * no argument was passed the position of the face landmarks are assumed to be relative to\n * it's current shift.\n * @returns The bounding box of the aligned face.\n */\n public align(\n detection?: FaceDetection | IRect | IBoundingBox | null,\n options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { },\n ): Box {\n if (detection) {\n const box = detection instanceof FaceDetection\n ? detection.box.floor()\n : new Box(detection);\n\n return this.shiftBy(box.x, box.y).align(null, options);\n }\n\n const { useDlibAlignment, minBoxPadding } = { useDlibAlignment: false, minBoxPadding: 0.2, ...options };\n\n if (useDlibAlignment) {\n return this.alignDlib();\n }\n\n return this.alignMinBbox(minBoxPadding);\n }\n\n private alignDlib(): Box {\n const centers = this.getRefPointsForAlignment();\n\n const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers;\n const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude();\n const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;\n\n const size = Math.floor(eyeToMouthDist / relScale);\n\n const refPoint = getCenterPoint(centers);\n // TODO: pad in case rectangle is out of image bounds\n const x = Math.floor(Math.max(0, refPoint.x - (relX * size)));\n const y = Math.floor(Math.max(0, refPoint.y - (relY * size)));\n\n return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y));\n }\n\n private alignMinBbox(padding: number): Box {\n const box = minBbox(this.positions);\n return box.pad(box.width * padding, box.height * padding);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n throw new Error('getRefPointsForAlignment not implemented by base class');\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks5 extends FaceLandmarks {\n protected getRefPointsForAlignment(): Point[] {\n const pts = this.positions;\n return [\n pts[0],\n pts[1],\n getCenterPoint([pts[3], pts[4]]),\n ];\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks68 extends FaceLandmarks {\n public getJawOutline(): Point[] {\n return this.positions.slice(0, 17);\n }\n\n public getLeftEyeBrow(): Point[] {\n return this.positions.slice(17, 22);\n }\n\n public getRightEyeBrow(): Point[] {\n return this.positions.slice(22, 27);\n }\n\n public getNose(): Point[] {\n return this.positions.slice(27, 36);\n }\n\n public getLeftEye(): Point[] {\n return this.positions.slice(36, 42);\n }\n\n public getRightEye(): Point[] {\n return this.positions.slice(42, 48);\n }\n\n public getMouth(): Point[] {\n return this.positions.slice(48, 68);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n return [\n this.getLeftEye(),\n this.getRightEye(),\n this.getMouth(),\n ].map(getCenterPoint);\n }\n}\n", "import { round } from '../utils/index';\n\nexport interface IFaceMatch {\n label: string\n distance: number\n}\n\nexport class FaceMatch implements IFaceMatch {\n private _label: string\n\n private _distance: number\n\n constructor(label: string, distance: number) {\n this._label = label;\n this._distance = distance;\n }\n\n public get label(): string { return this._label; }\n\n public get distance(): number { return this._distance; }\n\n public toString(withDistance: boolean = true): string {\n return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`;\n }\n}\n", "import { isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { IRect } from './Rect';\n\nexport class LabeledBox extends Box {\n public static assertIsValidLabeledBox(box: any, callee: string) {\n Box.assertIsValidBox(box, callee);\n\n if (!isValidNumber(box.label)) {\n throw new Error(`${callee} - expected property label (${box.label}) to be a number`);\n }\n }\n\n private _label: number\n\n constructor(box: IBoundingBox | IRect | any, label: number) {\n super(box);\n this._label = label;\n }\n\n public get label(): number { return this._label; }\n}\n", "export class LabeledFaceDescriptors {\n private _label: string\n\n private _descriptors: Float32Array[]\n\n constructor(label: string, descriptors: Float32Array[]) {\n if (!(typeof label === 'string')) {\n throw new Error('LabeledFaceDescriptors - constructor expected label to be a string');\n }\n\n if (!Array.isArray(descriptors) || descriptors.some((desc) => !(desc instanceof Float32Array))) {\n throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array');\n }\n\n this._label = label;\n this._descriptors = descriptors;\n }\n\n public get label(): string { return this._label; }\n\n public get descriptors(): Float32Array[] { return this._descriptors; }\n\n public toJSON(): any {\n return {\n label: this.label,\n descriptors: this.descriptors.map((d) => Array.from(d)),\n };\n }\n\n public static fromJSON(json: any): LabeledFaceDescriptors {\n const descriptors = json.descriptors.map((d: any) => new Float32Array(d));\n return new LabeledFaceDescriptors(json.label, descriptors);\n }\n}\n", "import { isValidProbablitiy } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { LabeledBox } from './LabeledBox';\nimport { IRect } from './Rect';\n\nexport class PredictedBox extends LabeledBox {\n public static assertIsValidPredictedBox(box: any, callee: string) {\n LabeledBox.assertIsValidLabeledBox(box, callee);\n\n if (\n !isValidProbablitiy(box.score)\n || !isValidProbablitiy(box.classScore)\n ) {\n throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`);\n }\n }\n\n private _score: number\n\n private _classScore: number\n\n constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {\n super(box, label);\n this._score = score;\n this._classScore = classScore;\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\n\nexport type WithFaceDetection = TSource & {\n detection: FaceDetection\n}\n\nexport function isWithFaceDetection(obj: any): obj is WithFaceDetection<{}> {\n return obj.detection instanceof FaceDetection;\n}\n\nexport function extendWithFaceDetection<\n TSource\n>(\n sourceObj: TSource,\n detection: FaceDetection,\n): WithFaceDetection {\n const extension = { detection };\n return { ...sourceObj, ...extension };\n}\n", "import { Environment } from './types';\n\nexport function createBrowserEnv(): Environment {\n const fetch = window.fetch;\n if (!fetch) throw new Error('fetch - missing fetch implementation for browser environment');\n\n const readFile = () => {\n throw new Error('readFile - filesystem not available for browser environment');\n };\n\n return {\n Canvas: HTMLCanvasElement,\n CanvasRenderingContext2D,\n Image: HTMLImageElement,\n ImageData,\n Video: HTMLVideoElement,\n createCanvasElement: () => document.createElement('canvas'),\n createImageElement: () => document.createElement('img'),\n fetch,\n readFile,\n };\n}\n", "import { FileSystem } from './types';\n\nexport function createFileSystem(fs?: any): FileSystem {\n let requireFsError = '';\n\n if (!fs) {\n try {\n // eslint-disable-next-line global-require\n fs = require('fs');\n } catch (err) {\n requireFsError = err.toString();\n }\n }\n\n const readFile = fs\n ? (filePath: string) => new Promise((resolve, reject) => {\n fs.readFile(filePath, (err: any, buffer: Buffer) => (err ? reject(err) : resolve(buffer)));\n })\n : () => {\n throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`);\n };\n\n return {\n readFile,\n };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { createFileSystem } from './createFileSystem';\nimport { Environment } from './types';\n\nexport function createNodejsEnv(): Environment {\n // eslint-disable-next-line dot-notation\n const Canvas = global['Canvas'] || global.HTMLCanvasElement;\n const Image = global.Image || global.HTMLImageElement;\n\n const createCanvasElement = () => {\n if (Canvas) return new Canvas();\n throw new Error('createCanvasElement - missing Canvas implementation for nodejs environment');\n };\n\n const createImageElement = () => {\n if (Image) return new Image();\n throw new Error('createImageElement - missing Image implementation for nodejs environment');\n };\n\n const fetch = global.fetch;\n // if (!fetch) throw new Error('fetch - missing fetch implementation for nodejs environment');\n\n const fileSystem = createFileSystem();\n\n return {\n Canvas: Canvas || class {},\n CanvasRenderingContext2D: global.CanvasRenderingContext2D || class {},\n Image: Image || class {},\n ImageData: global.ImageData || class {},\n Video: global.HTMLVideoElement || class {},\n createCanvasElement,\n createImageElement,\n fetch,\n ...fileSystem,\n };\n}\n", "export function isBrowser(): boolean {\n return typeof window === 'object'\n && typeof document !== 'undefined'\n && typeof HTMLImageElement !== 'undefined'\n && typeof HTMLCanvasElement !== 'undefined'\n && typeof HTMLVideoElement !== 'undefined'\n && typeof ImageData !== 'undefined'\n && typeof CanvasRenderingContext2D !== 'undefined';\n}\n", "import { createBrowserEnv } from './createBrowserEnv';\nimport { createFileSystem } from './createFileSystem';\nimport { createNodejsEnv } from './createNodejsEnv';\nimport { isBrowser } from './isBrowser';\nimport { isNodejs } from './isNodejs';\nimport { Environment } from './types';\n\nlet environment: Environment | null;\n\nfunction getEnv(): Environment {\n if (!environment) {\n throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()');\n }\n return environment;\n}\n\nfunction setEnv(env: Environment) {\n environment = env;\n}\n\nfunction initialize() {\n // check for isBrowser() first to prevent electron renderer process\n // to be initialized with wrong environment due to isNodejs() returning true\n if (isBrowser()) return setEnv(createBrowserEnv());\n if (isNodejs()) return setEnv(createNodejsEnv());\n return null;\n}\n\nfunction monkeyPatch(env: Partial) {\n if (!environment) {\n initialize();\n }\n\n if (!environment) {\n throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()');\n }\n\n const { Canvas = environment.Canvas, Image = environment.Image } = env;\n environment.Canvas = Canvas;\n environment.Image = Image;\n environment.createCanvasElement = env.createCanvasElement || (() => new Canvas());\n environment.createImageElement = env.createImageElement || (() => new Image());\n\n environment.ImageData = env.ImageData || environment.ImageData;\n environment.Video = env.Video || environment.Video;\n environment.fetch = env.fetch || environment.fetch;\n environment.readFile = env.readFile || environment.readFile;\n}\n\nexport const env = {\n getEnv,\n setEnv,\n initialize,\n createBrowserEnv,\n createFileSystem,\n createNodejsEnv,\n monkeyPatch,\n isBrowser,\n isNodejs,\n};\n\ninitialize();\n\nexport * from './types';\n", "import { env } from '../env/index';\n\nexport function resolveInput(arg: string | any) {\n if (!env.isNodejs() && typeof arg === 'string') {\n return document.getElementById(arg);\n }\n return arg;\n}\n", "import { env } from '../env/index';\nimport { resolveInput } from './resolveInput';\n\nexport function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {\n const { Canvas, CanvasRenderingContext2D } = env.getEnv();\n\n if (canvasArg instanceof CanvasRenderingContext2D) {\n return canvasArg;\n }\n\n const canvas = resolveInput(canvasArg);\n\n if (!(canvas instanceof Canvas)) {\n throw new Error('resolveContext2d - expected canvas to be of instance of Canvas');\n }\n\n const ctx = canvas.getContext('2d');\n if (!ctx) {\n throw new Error('resolveContext2d - canvas 2d context is null');\n }\n\n return ctx;\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IDimensions, IPoint } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { resolveInput } from '../dom/resolveInput';\n\n// eslint-disable-next-line no-shadow\nexport enum AnchorPosition {\n // eslint-disable-next-line no-unused-vars\n TOP_LEFT = 'TOP_LEFT',\n // eslint-disable-next-line no-unused-vars\n TOP_RIGHT = 'TOP_RIGHT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_LEFT = 'BOTTOM_LEFT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_RIGHT = 'BOTTOM_RIGHT'\n}\n\nexport interface IDrawTextFieldOptions {\n anchorPosition?: AnchorPosition\n backgroundColor?: string\n fontColor?: string\n fontSize?: number\n fontStyle?: string\n padding?: number\n}\n\nexport class DrawTextFieldOptions implements IDrawTextFieldOptions {\n public anchorPosition: AnchorPosition\n\n public backgroundColor: string\n\n public fontColor: string\n\n public fontSize: number\n\n public fontStyle: string\n\n public padding: number\n\n constructor(options: IDrawTextFieldOptions = {}) {\n const {\n anchorPosition, backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = options;\n this.anchorPosition = anchorPosition || AnchorPosition.TOP_LEFT;\n this.backgroundColor = backgroundColor || 'rgba(0, 0, 0, 0.5)';\n this.fontColor = fontColor || 'rgba(255, 255, 255, 1)';\n this.fontSize = fontSize || 14;\n this.fontStyle = fontStyle || 'Georgia';\n this.padding = padding || 4;\n }\n}\n\nexport class DrawTextField {\n public text: string[]\n\n public anchor : IPoint\n\n public options: DrawTextFieldOptions\n\n constructor(\n text: string | string[] | DrawTextField,\n anchor: IPoint,\n options: IDrawTextFieldOptions = {},\n ) {\n // eslint-disable-next-line no-nested-ternary\n this.text = typeof text === 'string'\n ? [text]\n : (text instanceof DrawTextField ? text.text : text);\n this.anchor = anchor;\n this.options = new DrawTextFieldOptions(options);\n }\n\n measureWidth(ctx: CanvasRenderingContext2D): number {\n const { padding } = this.options;\n return this.text.map((l) => ctx.measureText(l).width).reduce((w0, w1) => (w0 < w1 ? w1 : w0), 0) + (2 * padding);\n }\n\n measureHeight(): number {\n const { fontSize, padding } = this.options;\n return this.text.length * fontSize + (2 * padding);\n }\n\n getUpperLeft(ctx: CanvasRenderingContext2D, canvasDims?: IDimensions): IPoint {\n const { anchorPosition } = this.options;\n const isShiftLeft = anchorPosition === AnchorPosition.BOTTOM_RIGHT || anchorPosition === AnchorPosition.TOP_RIGHT;\n const isShiftTop = anchorPosition === AnchorPosition.BOTTOM_LEFT || anchorPosition === AnchorPosition.BOTTOM_RIGHT;\n\n const textFieldWidth = this.measureWidth(ctx);\n const textFieldHeight = this.measureHeight();\n const x = (isShiftLeft ? this.anchor.x - textFieldWidth : this.anchor.x);\n const y = isShiftTop ? this.anchor.y - textFieldHeight : this.anchor.y;\n\n // adjust anchor if text box exceeds canvas borders\n if (canvasDims) {\n const { width, height } = canvasDims;\n const newX = Math.max(Math.min(x, width - textFieldWidth), 0);\n const newY = Math.max(Math.min(y, height - textFieldHeight), 0);\n return { x: newX, y: newY };\n }\n return { x, y };\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const canvas = resolveInput(canvasArg);\n const ctx = getContext2dOrThrow(canvas);\n\n const {\n backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = this.options;\n\n ctx.font = `${fontSize}px ${fontStyle}`;\n const maxTextWidth = this.measureWidth(ctx);\n const textHeight = this.measureHeight();\n\n ctx.fillStyle = backgroundColor;\n const upperLeft = this.getUpperLeft(ctx, canvas);\n ctx.fillRect(upperLeft.x, upperLeft.y, maxTextWidth, textHeight);\n\n ctx.fillStyle = fontColor;\n this.text.forEach((textLine, i) => {\n const x = padding + upperLeft.x;\n const y = padding + upperLeft.y + ((i + 1) * fontSize);\n ctx.fillText(textLine, x, y);\n });\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { Box, IBoundingBox, IRect } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport {\n AnchorPosition, DrawTextField, DrawTextFieldOptions, IDrawTextFieldOptions,\n} from './DrawTextField';\n\nexport interface IDrawBoxOptions {\n boxColor?: string\n lineWidth?: number\n drawLabelOptions?: IDrawTextFieldOptions\n label?: string\n}\n\nexport class DrawBoxOptions {\n public boxColor: string\n\n public lineWidth: number\n\n public drawLabelOptions: DrawTextFieldOptions\n\n public label?: string\n\n constructor(options: IDrawBoxOptions = {}) {\n const {\n boxColor, lineWidth, label, drawLabelOptions,\n } = options;\n this.boxColor = boxColor || 'rgba(0, 0, 255, 1)';\n this.lineWidth = lineWidth || 2;\n this.label = label;\n\n const defaultDrawLabelOptions = {\n anchorPosition: AnchorPosition.BOTTOM_LEFT,\n backgroundColor: this.boxColor,\n };\n this.drawLabelOptions = new DrawTextFieldOptions({ ...defaultDrawLabelOptions, ...drawLabelOptions });\n }\n}\n\nexport class DrawBox {\n public box: Box\n\n public options: DrawBoxOptions\n\n constructor(\n box: IBoundingBox | IRect,\n options: IDrawBoxOptions = {},\n ) {\n this.box = new Box(box);\n this.options = new DrawBoxOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const { boxColor, lineWidth } = this.options;\n\n const {\n x, y, width, height,\n } = this.box;\n ctx.strokeStyle = boxColor;\n ctx.lineWidth = lineWidth;\n ctx.strokeRect(x, y, width, height);\n\n const { label } = this.options;\n if (label) {\n new DrawTextField([label], { x: x - (lineWidth / 2), y }, this.options.drawLabelOptions).draw(canvasArg);\n }\n }\n}\n", "import { Box, IBoundingBox, IRect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { round } from '../utils/index';\nimport { DrawBox } from './DrawBox';\n\nexport type TDrawDetectionsInput = IRect | IBoundingBox | FaceDetection | WithFaceDetection<{}>\n\nexport function drawDetections(\n canvasArg: string | HTMLCanvasElement,\n detections: TDrawDetectionsInput | Array,\n) {\n const detectionsArray = Array.isArray(detections) ? detections : [detections];\n\n detectionsArray.forEach((det) => {\n // eslint-disable-next-line no-nested-ternary\n const score = det instanceof FaceDetection\n ? det.score\n : (isWithFaceDetection(det) ? det.detection.score : undefined);\n\n // eslint-disable-next-line no-nested-ternary\n const box = det instanceof FaceDetection\n ? det.box\n : (isWithFaceDetection(det) ? det.detection.box : new Box(det));\n\n const label = score ? `${round(score)}` : undefined;\n new DrawBox(box, { label }).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { FaceExpressions } from './FaceExpressions';\n\nexport class FaceExpressionNet extends FaceProcessor {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceExpressionNet', faceFeatureExtractor);\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n return tf.tidy(() => tf.softmax(this.runNet(input)));\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictExpressions(input: TNetInput) {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n const probabilitesByBatch = await Promise.all(tf.unstack(out).map(async (t) => {\n const data = await t.data();\n t.dispose();\n return data;\n }));\n out.dispose();\n\n const predictionsByBatch = probabilitesByBatch\n .map((probabilites) => new FaceExpressions(probabilites as Float32Array));\n\n return netInput.isBatchInput\n ? predictionsByBatch\n : predictionsByBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_expression_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n\n protected getClassifierChannelsOut(): number {\n return 7;\n }\n}\n", "import { env } from '../env/index';\n\nexport function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {\n const { Image, Video } = env.getEnv();\n\n return (media instanceof Image && media.complete)\n || (media instanceof Video && media.readyState >= 3);\n}\n", "import { env } from '../env/index';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {\n // eslint-disable-next-line consistent-return\n return new Promise((resolve, reject) => {\n if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {\n return resolve(null);\n }\n\n function onError(e: Event) {\n if (!e.currentTarget) return;\n // eslint-disable-next-line no-use-before-define\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n reject(e);\n }\n\n function onLoad(e: Event) {\n if (!e.currentTarget) return;\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n resolve(e);\n }\n\n media.addEventListener('load', onLoad);\n media.addEventListener('error', onError);\n });\n}\n", "import { env } from '../env/index';\n\nexport function bufferToImage(buf: Blob): Promise {\n return new Promise((resolve, reject) => {\n if (!(buf instanceof Blob)) reject(new Error('bufferToImage - expected buf to be of type: Blob'));\n const reader = new FileReader();\n reader.onload = () => {\n if (typeof reader.result !== 'string') reject(new Error('bufferToImage - expected reader.result to be a string, in onload'));\n const img = env.getEnv().createImageElement();\n img.onload = () => resolve(img);\n img.onerror = reject;\n img.src = reader.result as string;\n };\n reader.onerror = reject;\n reader.readAsDataURL(buf);\n });\n}\n", "import { Dimensions, IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\n\nexport function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {\n const { Image, Video } = env.getEnv();\n\n if (input instanceof Image) {\n return new Dimensions(input.naturalWidth, input.naturalHeight);\n }\n if (input instanceof Video) {\n return new Dimensions(input.videoWidth, input.videoHeight);\n }\n return new Dimensions(input.width, input.height);\n}\n", "import { IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {\n const { createCanvasElement } = env.getEnv();\n const canvas = createCanvasElement();\n canvas.width = width;\n canvas.height = height;\n return canvas;\n}\n\nexport function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {\n const { ImageData } = env.getEnv();\n\n if (!(media instanceof ImageData) && !isMediaLoaded(media)) {\n throw new Error('createCanvasFromMedia - media has not finished loading yet');\n }\n\n const { width, height } = dims || getMediaDimensions(media);\n const canvas = createCanvas({ width, height });\n\n if (media instanceof ImageData) {\n getContext2dOrThrow(canvas).putImageData(media, 0, 0);\n } else {\n getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height);\n }\n return canvas;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { env } from '../env/index';\nimport { isTensor4D } from '../utils/index';\n\nexport async function imageTensorToCanvas(\n imgTensor: tf.Tensor,\n canvas?: HTMLCanvasElement,\n): Promise {\n const targetCanvas = canvas || env.getEnv().createCanvasElement();\n\n const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0);\n const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt());\n await tf.browser.toPixels(imgTensor3D, targetCanvas);\n\n imgTensor3D.dispose();\n\n return targetCanvas;\n}\n", "import { env } from '../env/index';\n\nexport function isMediaElement(input: any) {\n const { Image, Canvas, Video } = env.getEnv();\n\n return input instanceof Image\n || input instanceof Canvas\n || input instanceof Video;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Dimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { padToSquare } from '../ops/padToSquare';\nimport {\n computeReshapedDimensions, isTensor3D, isTensor4D, range,\n} from '../utils/index';\nimport { createCanvasFromMedia } from './createCanvas';\nimport { imageToSquare } from './imageToSquare';\nimport { TResolvedNetInput } from './types';\n\nexport class NetInput {\n private _imageTensors: Array = []\n\n private _canvases: HTMLCanvasElement[] = []\n\n private _batchSize: number\n\n private _treatAsBatchInput: boolean = false\n\n private _inputDimensions: number[][] = []\n\n private _inputSize: number\n\n constructor(\n inputs: Array,\n treatAsBatchInput: boolean = false,\n ) {\n if (!Array.isArray(inputs)) {\n throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`);\n }\n\n this._treatAsBatchInput = treatAsBatchInput;\n this._batchSize = inputs.length;\n\n inputs.forEach((input, idx) => {\n if (isTensor3D(input)) {\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = input.shape;\n return;\n }\n\n if (isTensor4D(input)) {\n const batchSize = (input as any).shape[0];\n if (batchSize !== 1) {\n throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = (input as any).shape.slice(1);\n return;\n }\n\n const canvas = (input as any) instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input);\n this._canvases[idx] = canvas;\n this._inputDimensions[idx] = [canvas.height, canvas.width, 3];\n });\n }\n\n public get imageTensors(): Array {\n return this._imageTensors;\n }\n\n public get canvases(): HTMLCanvasElement[] {\n return this._canvases;\n }\n\n public get isBatchInput(): boolean {\n return this.batchSize > 1 || this._treatAsBatchInput;\n }\n\n public get batchSize(): number {\n return this._batchSize;\n }\n\n public get inputDimensions(): number[][] {\n return this._inputDimensions;\n }\n\n public get inputSize(): number | undefined {\n return this._inputSize;\n }\n\n public get reshapedInputDimensions(): Dimensions[] {\n return range(this.batchSize, 0, 1).map(\n (_, batchIdx) => this.getReshapedInputDimensions(batchIdx),\n );\n }\n\n public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {\n return this.canvases[batchIdx] || this.imageTensors[batchIdx];\n }\n\n public getInputDimensions(batchIdx: number): number[] {\n return this._inputDimensions[batchIdx];\n }\n\n public getInputHeight(batchIdx: number): number {\n return this._inputDimensions[batchIdx][0];\n }\n\n public getInputWidth(batchIdx: number): number {\n return this._inputDimensions[batchIdx][1];\n }\n\n public getReshapedInputDimensions(batchIdx: number): Dimensions {\n if (typeof this.inputSize !== 'number') {\n throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet');\n }\n\n const width = this.getInputWidth(batchIdx);\n const height = this.getInputHeight(batchIdx);\n return computeReshapedDimensions({ width, height }, this.inputSize);\n }\n\n /**\n * Create a batch tensor from all input canvases and tensors\n * with size [batchSize, inputSize, inputSize, 3].\n *\n * @param inputSize Height and width of the tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The batch tensor.\n */\n public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {\n this._inputSize = inputSize;\n\n return tf.tidy(() => {\n const inputTensors = range(this.batchSize, 0, 1).map((batchIdx) => {\n const input = this.getInput(batchIdx);\n\n if (input instanceof tf.Tensor) {\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n let imgTensor = isTensor4D(input) ? input : input.expandDims();\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n imgTensor = padToSquare(imgTensor, isCenterInputs);\n\n if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {\n imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize]);\n }\n\n return imgTensor.as3D(inputSize, inputSize, 3);\n }\n\n if (input instanceof env.getEnv().Canvas) {\n return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs));\n }\n\n throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`);\n });\n\n // const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)\n const batchTensor = tf.stack(inputTensors.map((t) => tf.cast(t, 'float32'))).as4D(this.batchSize, inputSize, inputSize, 3);\n // const batchTensor = tf.stack(inputTensors.map(t => tf.Tensor.as4D(tf.cast(t, 'float32'))), this.batchSize, inputSize, inputSize, 3);\n\n return batchTensor;\n });\n }\n}\n", "import { env } from '../env/index';\nimport { createCanvas, createCanvasFromMedia } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {\n const { Image, Canvas } = env.getEnv();\n\n if (!(input instanceof Image || input instanceof Canvas)) {\n throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement');\n }\n\n const dims = getMediaDimensions(input);\n const scale = inputSize / Math.max(dims.height, dims.width);\n const width = scale * dims.width;\n const height = scale * dims.height;\n\n const targetCanvas = createCanvas({ width: inputSize, height: inputSize });\n const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input);\n\n const offset = Math.abs(width - height) / 2;\n const dx = centerImage && width < height ? offset : 0;\n const dy = centerImage && height < width ? offset : 0;\n getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height);\n\n return targetCanvas;\n}\n", "import { isTensor3D, isTensor4D } from '../utils/index';\nimport { awaitMediaLoaded } from './awaitMediaLoaded';\nimport { isMediaElement } from './isMediaElement';\nimport { NetInput } from './NetInput';\nimport { resolveInput } from './resolveInput';\nimport { TNetInput } from './types';\n\n/**\n * Validates the input to make sure, they are valid net inputs and awaits all media elements\n * to be finished loading.\n *\n * @param input The input, which can be a media element or an array of different media elements.\n * @returns A NetInput instance, which can be passed into one of the neural networks.\n */\nexport async function toNetInput(inputs: TNetInput): Promise {\n if (inputs instanceof NetInput) {\n return inputs;\n }\n\n const inputArgArray = Array.isArray(inputs)\n ? inputs\n : [inputs];\n\n if (!inputArgArray.length) {\n throw new Error('toNetInput - empty array passed as input');\n }\n\n const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');\n\n const inputArray = inputArgArray.map(resolveInput);\n\n inputArray.forEach((input, i) => {\n if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {\n if (typeof inputArgArray[i] === 'string') {\n throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);\n }\n\n throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);\n }\n\n if (isTensor4D(input)) {\n // if tf.Tensor4D is passed in the input array, the batch size has to be 1\n const batchSize = input.shape[0];\n if (batchSize !== 1) {\n throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n }\n });\n\n // wait for all media elements being loaded\n await Promise.all(\n inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),\n );\n\n return new NetInput(inputArray, Array.isArray(inputs));\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { Rect } from '../classes/Rect';\nimport { env } from '../env/index';\nimport { createCanvas } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { imageTensorToCanvas } from './imageTensorToCanvas';\nimport { toNetInput } from './toNetInput';\nimport { TNetInput } from './types';\n\n/**\n * Extracts the image regions containing the detected faces.\n *\n * @param input The image that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns The Canvases of the corresponding image region for each detected face.\n */\nexport async function extractFaces(\n input: TNetInput,\n detections: Array,\n): Promise {\n const { Canvas } = env.getEnv();\n\n let canvas = input as HTMLCanvasElement;\n\n if (!(input instanceof Canvas)) {\n const netInput = await toNetInput(input);\n\n if (netInput.batchSize > 1) {\n throw new Error('extractFaces - batchSize > 1 not supported');\n }\n\n const tensorOrCanvas = netInput.getInput(0);\n canvas = tensorOrCanvas instanceof Canvas\n ? tensorOrCanvas\n : await imageTensorToCanvas(tensorOrCanvas);\n }\n\n const ctx = getContext2dOrThrow(canvas);\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(canvas.width, canvas.height).box.floor()\n : det),\n )\n .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));\n\n return boxes.map(({\n x, y, width, height,\n }) => {\n const faceImg = createCanvas({ width, height });\n getContext2dOrThrow(faceImg)\n .putImageData(ctx.getImageData(x, y, width, height), 0, 0);\n return faceImg;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isTensor3D, isTensor4D } from '../utils/index';\n\n/**\n * Extracts the tensors of the image regions containing the detected faces.\n * Useful if you want to compute the face descriptors for the face images.\n * Using this method is faster then extracting a canvas for each face and\n * converting them to tensors individually.\n *\n * @param imageTensor The image tensor that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns Tensors of the corresponding image region for each detected face.\n */\nexport async function extractFaceTensors(\n imageTensor: tf.Tensor3D | tf.Tensor4D,\n detections: Array,\n): Promise {\n if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {\n throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D');\n }\n\n if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {\n throw new Error('extractFaceTensors - batchSize > 1 not supported');\n }\n\n return tf.tidy(() => {\n const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0);\n\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(imgWidth, imgHeight).box\n : det),\n )\n .map((box) => box.clipAtImageBorders(imgWidth, imgHeight));\n\n const faceTensors = boxes.map(({\n x, y, width, height,\n }) => tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels]));\n\n return faceTensors;\n });\n}\n", "import { env } from '../env/index';\n\nexport async function fetchOrThrow(\n url: string,\n // eslint-disable-next-line no-undef\n init?: RequestInit,\n): Promise {\n const { fetch } = env.getEnv();\n const res = await fetch(url, init);\n if (!(res.status < 400)) {\n throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`);\n }\n return res;\n}\n", "import { bufferToImage } from './bufferToImage';\nimport { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchImage(uri: string): Promise {\n const res = await fetchOrThrow(uri);\n const blob = await (res).blob();\n\n if (!blob.type.startsWith('image/')) {\n throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`);\n }\n return bufferToImage(blob);\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchJson(uri: string): Promise {\n return (await fetchOrThrow(uri)).json();\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchNetWeights(uri: string): Promise {\n return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer());\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { getModelUris } from '../common/getModelUris';\nimport { fetchJson } from './fetchJson';\n\nexport async function loadWeightMap(\n uri: string | undefined,\n defaultModelName: string,\n): Promise {\n const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName);\n const manifest = await fetchJson(manifestUri);\n // if (manifest['weightsManifest']) manifest = manifest['weightsManifest'];\n return tf.io.loadWeights(manifest, modelBaseUri);\n}\n", "export function getModelUris(uri: string | undefined, defaultModelName: string) {\n const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`;\n\n if (!uri) {\n return {\n modelBaseUri: '',\n manifestUri: defaultManifestFilename,\n };\n }\n\n if (uri === '/') {\n return {\n modelBaseUri: '/',\n manifestUri: `/${defaultManifestFilename}`,\n };\n }\n // eslint-disable-next-line no-nested-ternary\n const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';\n uri = uri.replace(protocol, '');\n\n const parts = uri.split('/').filter((s) => s);\n\n const manifestFile = uri.endsWith('.json')\n ? parts[parts.length - 1]\n : defaultManifestFilename;\n\n let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/');\n modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri;\n\n return {\n modelBaseUri,\n manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`,\n };\n}\n", "import { IDimensions } from '../classes/index';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {\n const { width, height } = useMediaDimensions\n ? getMediaDimensions(reference)\n : reference;\n input.width = width;\n input.height = height;\n return { width, height };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock4 } from './denseBlock';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';\n\nexport class FaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('FaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock4(normalized, params.dense0, true);\n out = denseBlock4(out, params.dense1);\n out = denseBlock4(out, params.dense2);\n out = denseBlock4(out, params.dense3);\n out = tf.avgPool(out, [7, 7], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../dist/tfjs.esm';\n\nimport { ParamMapping } from './common/index';\nimport { getModelUris } from './common/getModelUris';\nimport { loadWeightMap } from './dom/index';\nimport { env } from './env/index';\n\nexport abstract class NeuralNetwork {\n protected _params: TNetParams | undefined = undefined\n\n protected _paramMappings: ParamMapping[] = []\n\n public _name: any;\n\n public get params(): TNetParams | undefined { return this._params; }\n\n public get paramMappings(): ParamMapping[] { return this._paramMappings; }\n\n public get isLoaded(): boolean { return !!this.params; }\n\n public getParamFromPath(paramPath: string): tf.Tensor {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n return obj[objProp];\n }\n\n public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n obj[objProp].dispose();\n obj[objProp] = tensor;\n }\n\n public getParamList() {\n return this._paramMappings.map(({ paramPath }) => ({\n path: paramPath,\n tensor: this.getParamFromPath(paramPath),\n }));\n }\n\n public getTrainableParams() {\n return this.getParamList().filter((param) => param.tensor instanceof tf.Variable);\n }\n\n public getFrozenParams() {\n return this.getParamList().filter((param) => !(param.tensor instanceof tf.Variable));\n }\n\n public variable() {\n this.getFrozenParams().forEach(({ path, tensor }) => {\n this.reassignParamFromPath(path, tensor.variable());\n });\n }\n\n public freeze() {\n this.getTrainableParams().forEach(({ path, tensor: variable }) => {\n const tensor = tf.tensor(variable.dataSync());\n variable.dispose();\n this.reassignParamFromPath(path, tensor);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.getParamList().forEach((param) => {\n if (throwOnRedispose && param.tensor.isDisposed) {\n throw new Error(`param tensor has already been disposed for path ${param.path}`);\n }\n param.tensor.dispose();\n });\n this._params = undefined;\n }\n\n public serializeParams(): Float32Array {\n return new Float32Array(\n this.getParamList()\n .map(({ tensor }) => Array.from(tensor.dataSync()) as number[])\n .reduce((flat, arr) => flat.concat(arr)),\n );\n }\n\n public async load(weightsOrUrl: Float32Array | string | undefined): Promise {\n if (weightsOrUrl instanceof Float32Array) {\n this.extractWeights(weightsOrUrl);\n return;\n }\n\n await this.loadFromUri(weightsOrUrl);\n }\n\n public async loadFromUri(uri: string | undefined) {\n if (uri && typeof uri !== 'string') {\n throw new Error(`${this._name}.loadFromUri - expected model uri`);\n }\n\n const weightMap = await loadWeightMap(uri, this.getDefaultModelName());\n this.loadFromWeightMap(weightMap);\n }\n\n public async loadFromDisk(filePath: string | undefined) {\n if (filePath && typeof filePath !== 'string') {\n throw new Error(`${this._name}.loadFromDisk - expected model file path`);\n }\n\n const { readFile } = env.getEnv();\n\n const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName());\n\n const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(\n filePaths.map((fp) => readFile(fp).then((buf) => buf.buffer)),\n );\n const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk);\n const manifest = JSON.parse((await readFile(manifestUri)).toString());\n const weightMap = await loadWeights(manifest, modelBaseUri);\n\n this.loadFromWeightMap(weightMap);\n }\n\n public loadFromWeightMap(weightMap: tf.NamedTensorMap) {\n const {\n paramMappings,\n params,\n } = this.extractParamsFromWeightMap(weightMap);\n\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n public extractWeights(weights: Float32Array) {\n const {\n paramMappings,\n params,\n } = this.extractParams(weights);\n\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n private traversePropertyPath(paramPath: string) {\n if (!this.params) {\n throw new Error('traversePropertyPath - model has no loaded params');\n }\n\n const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {\n // eslint-disable-next-line no-prototype-builtins\n if (!res.nextObj.hasOwnProperty(objProp)) {\n throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`);\n }\n\n return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] };\n }, { nextObj: this.params });\n\n const { obj, objProp } = result;\n if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {\n throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`);\n }\n\n return { obj, objProp };\n }\n\n protected abstract getDefaultModelName(): string\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, SeparableConvParams } from '../common/index';\nimport { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function denseBlock3(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock3Params,\n isFirstLayer: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n });\n}\n\nexport function denseBlock4(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock4Params,\n isFirstLayer: boolean = false,\n isScaleDown: boolean = true,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from './types';\n\nexport function depthwiseSeparableConv(\n x: tf.Tensor4D,\n params: SeparableConvParams,\n stride: [number, number],\n): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same');\n out = tf.add(out, params.bias);\n return out;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\nexport function convLayer(\n x: tf.Tensor4D,\n params: ConvParams,\n padding: 'valid' | 'same' = 'same',\n withRelu: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out = tf.add(\n tf.conv2d(x, params.filters, [1, 1], padding),\n params.bias,\n ) as tf.Tensor4D;\n\n return withRelu ? tf.relu(out) : out;\n });\n}\n", "import { ParamMapping } from './types';\n\nexport function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {\n Object.keys(weightMap).forEach((path) => {\n if (!paramMappings.some((pm) => pm.originalPath === path)) {\n weightMap[path].dispose();\n }\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';\n\nexport function extractConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams => {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, FCParams, ParamMapping } from './types';\n\nexport function extractFCParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): FCParams => {\n const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);\n const fc_bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return {\n weights: fc_weights,\n bias: fc_bias,\n };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';\n\nexport function extractSeparableConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams => {\n const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1]);\n const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut]);\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/depthwise_filter` },\n { paramPath: `${mappedPrefix}/pointwise_filter` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n\nexport function loadSeparableConvParamsFactory(\n // eslint-disable-next-line no-unused-vars\n extractWeightEntry: (originalPath: string, paramRank: number) => T,\n) {\n return (prefix: string): SeparableConvParams => {\n const depthwise_filter = extractWeightEntry(`${prefix}/depthwise_filter`, 4);\n const pointwise_filter = extractWeightEntry(`${prefix}/pointwise_filter`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n// eslint-disable-next-line no-unused-vars\nexport type ExtractWeightsFunction = (numWeights: number) => Float32Array\n\nexport type ParamMapping = {\n originalPath?: string\n paramPath: string\n}\n\nexport type ConvParams = {\n filters: tf.Tensor4D\n bias: tf.Tensor1D\n}\n\nexport type FCParams = {\n weights: tf.Tensor2D\n bias: tf.Tensor1D\n}\n\nexport class SeparableConvParams {\n // eslint-disable-next-line no-useless-constructor\n constructor(\n // eslint-disable-next-line no-unused-vars\n public depthwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public pointwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public bias: tf.Tensor1D,\n // eslint-disable-next-line no-empty-function\n ) {}\n}\n", "import { isTensor } from '../utils/index';\nimport { ParamMapping } from './types';\n\nexport function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {\n return (originalPath: string, paramRank: number, mappedPath?: string) => {\n const tensor = weightMap[originalPath];\n\n if (!isTensor(tensor, paramRank)) {\n throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`);\n }\n\n paramMappings.push(\n { originalPath, paramPath: mappedPath || originalPath },\n );\n\n return tensor;\n };\n}\n", "export function extractWeightsFactory(weights: Float32Array) {\n let remainingWeights = weights;\n\n function extractWeights(numWeights: number): Float32Array {\n const ret = remainingWeights.slice(0, numWeights);\n remainingWeights = remainingWeights.slice(numWeights);\n return ret;\n }\n\n function getRemainingWeights(): Float32Array {\n return remainingWeights;\n }\n\n return {\n extractWeights,\n getRemainingWeights,\n };\n}\n", "import {\n extractConvParamsFactory,\n extractSeparableConvParamsFactory,\n ExtractWeightsFunction,\n ParamMapping,\n} from '../common/index';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)\n : extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`);\n const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`);\n const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer);\n const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock4Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock4Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock4Params(64, 128, 'dense2');\n const dense3 = extractDenseBlock4Params(128, 256, 'dense3');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: {\n dense0, dense1, dense2, dense3,\n },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\n// eslint-disable-next-line no-unused-vars\nexport function loadConvParamsFactory(extractWeightEntry: (originalPath: string, paramRank: number) => T) {\n return (prefix: string): ConvParams => {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return { filters, bias };\n };\n}\n", "import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n const conv3 = extractSeparableConvParams(`${prefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock4Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock4Params('dense0', true),\n dense1: extractDenseBlock4Params('dense1'),\n dense2: extractDenseBlock4Params('dense2'),\n dense3: extractDenseBlock4Params('dense3'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { NetInput } from '../dom/index';\nimport {\n FaceFeatureExtractorParams,\n IFaceFeatureExtractor,\n TinyFaceFeatureExtractorParams,\n} from '../faceFeatureExtractor/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { NetParams } from './types';\nimport { seperateWeightMaps } from './util';\n\nexport abstract class FaceProcessor<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends NeuralNetwork {\n protected _faceFeatureExtractor: IFaceFeatureExtractor\n\n constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor) {\n super(_name);\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): IFaceFeatureExtractor {\n return this._faceFeatureExtractor;\n }\n\n protected abstract getDefaultModelName(): string\n\n protected abstract getClassifierChannelsIn(): number\n\n protected abstract getClassifierChannelsOut(): number\n\n public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut());\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const cIn = this.getClassifierChannelsIn();\n const cOut = this.getClassifierChannelsOut();\n const classifierWeightSize = (cOut * cIn) + cOut;\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from './types';\n\nexport function fullyConnectedLayer(\n x: tf.Tensor2D,\n params: FCParams,\n): tf.Tensor2D {\n return tf.tidy(() => tf.add(\n tf.matMul(x, params.weights),\n params.bias,\n ));\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const fc = extractFCParams(channelsIn, channelsOut, 'fc');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: extractFcParams('fc'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function seperateWeightMaps(weightMap: tf.NamedTensorMap) {\n const featureExtractorMap: tf.NamedTensorMap = {};\n const classifierMap: tf.NamedTensorMap = {};\n\n Object.keys(weightMap).forEach((key) => {\n const map = key.startsWith('fc') ? classifierMap : featureExtractorMap;\n map[key] = weightMap[key];\n });\n\n return { featureExtractorMap, classifierMap };\n}\n", "export const FACE_EXPRESSION_LABELS = ['neutral', 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised'];\n\nexport class FaceExpressions {\n public neutral: number\n\n public happy: number\n\n public sad: number\n\n public angry: number\n\n public fearful: number\n\n public disgusted: number\n\n public surprised: number\n\n constructor(probabilities: number[] | Float32Array) {\n if (probabilities.length !== 7) {\n throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${probabilities.length}`);\n }\n\n FACE_EXPRESSION_LABELS.forEach((expression, idx) => {\n this[expression] = probabilities[idx];\n });\n }\n\n asSortedArray() {\n return FACE_EXPRESSION_LABELS\n .map((expression) => ({ expression, probability: this[expression] as number }))\n .sort((e0, e1) => e1.probability - e0.probability);\n }\n}\n", "import { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\n\nexport type WithFaceExpressions = TSource & {\n expressions: FaceExpressions\n}\n\nexport function isWithFaceExpressions(obj: any): obj is WithFaceExpressions<{}> {\n return obj.expressions instanceof FaceExpressions;\n}\n\nexport function extendWithFaceExpressions<\n TSource\n>(\n sourceObj: TSource,\n expressions: FaceExpressions,\n): WithFaceExpressions {\n const extension = { expressions };\n return { ...sourceObj, ...extension };\n}\n", "import { IPoint, Point } from '../classes/index';\nimport { FaceExpressions } from '../faceExpressionNet/index';\nimport { isWithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { round } from '../utils/index';\nimport { DrawTextField } from './DrawTextField';\n\nexport type DrawFaceExpressionsInput = FaceExpressions | WithFaceExpressions<{}>\n\nexport function drawFaceExpressions(\n canvasArg: string | HTMLCanvasElement,\n faceExpressions: DrawFaceExpressionsInput | Array,\n minConfidence = 0.1,\n textFieldAnchor?: IPoint,\n) {\n const faceExpressionsArray = Array.isArray(faceExpressions) ? faceExpressions : [faceExpressions];\n\n faceExpressionsArray.forEach((e) => {\n // eslint-disable-next-line no-nested-ternary\n const expr = e instanceof FaceExpressions\n ? e\n : (isWithFaceExpressions(e) ? e.expressions : undefined);\n if (!expr) {\n throw new Error('drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof');\n }\n\n const sorted = expr.asSortedArray();\n const resultsToDisplay = sorted.filter((exprLocal) => exprLocal.probability > minConfidence);\n\n const anchor = isWithFaceDetection(e)\n ? e.detection.box.bottomLeft\n : (textFieldAnchor || new Point(0, 0));\n\n const drawTextField = new DrawTextField(\n resultsToDisplay.map((exprLocal) => `${exprLocal.expression} (${round(exprLocal.probability)})`),\n anchor,\n );\n drawTextField.draw(canvasArg);\n });\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { isWithFaceDetection, WithFaceDetection } from './WithFaceDetection';\n\nexport type WithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 > = TSource & {\n landmarks: TFaceLandmarks\n unshiftedLandmarks: TFaceLandmarks\n alignedRect: FaceDetection\n }\n\nexport function isWithFaceLandmarks(obj: any): obj is WithFaceLandmarks, FaceLandmarks> {\n return isWithFaceDetection(obj)\n // eslint-disable-next-line dot-notation\n && obj['landmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['unshiftedLandmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['alignedRect'] instanceof FaceDetection;\n}\n\nexport function extendWithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 >(sourceObj: TSource, unshiftedLandmarks: TFaceLandmarks): WithFaceLandmarks {\n const { box: shift } = sourceObj.detection;\n const landmarks = unshiftedLandmarks.shiftBy(shift.x, shift.y);\n\n const rect = landmarks.align();\n const { imageDims } = sourceObj.detection;\n const alignedRect = new FaceDetection(sourceObj.detection.score, rect.rescale(imageDims.reverse()), imageDims);\n\n const extension = {\n landmarks,\n unshiftedLandmarks,\n alignedRect,\n };\n\n return { ...sourceObj, ...extension };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IPoint } from '../classes/index';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { drawContour } from './drawContour';\n\nexport interface IDrawFaceLandmarksOptions {\n drawLines?: boolean\n drawPoints?: boolean\n lineWidth?: number\n pointSize?: number\n lineColor?: string\n pointColor?: string\n}\n\nexport class DrawFaceLandmarksOptions {\n public drawLines: boolean\n\n public drawPoints: boolean\n\n public lineWidth: number\n\n public pointSize: number\n\n public lineColor: string\n\n public pointColor: string\n\n constructor(options: IDrawFaceLandmarksOptions = {}) {\n const {\n drawLines = true, drawPoints = true, lineWidth, lineColor, pointSize, pointColor,\n } = options;\n this.drawLines = drawLines;\n this.drawPoints = drawPoints;\n this.lineWidth = lineWidth || 1;\n this.pointSize = pointSize || 2;\n this.lineColor = lineColor || 'rgba(0, 255, 255, 1)';\n this.pointColor = pointColor || 'rgba(255, 0, 255, 1)';\n }\n}\n\nexport class DrawFaceLandmarks {\n public faceLandmarks: FaceLandmarks\n\n public options: DrawFaceLandmarksOptions\n\n constructor(\n faceLandmarks: FaceLandmarks,\n options: IDrawFaceLandmarksOptions = {},\n ) {\n this.faceLandmarks = faceLandmarks;\n this.options = new DrawFaceLandmarksOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const {\n drawLines, drawPoints, lineWidth, lineColor, pointSize, pointColor,\n } = this.options;\n\n if (drawLines && this.faceLandmarks instanceof FaceLandmarks68) {\n ctx.strokeStyle = lineColor;\n ctx.lineWidth = lineWidth;\n drawContour(ctx, this.faceLandmarks.getJawOutline());\n drawContour(ctx, this.faceLandmarks.getLeftEyeBrow());\n drawContour(ctx, this.faceLandmarks.getRightEyeBrow());\n drawContour(ctx, this.faceLandmarks.getNose());\n drawContour(ctx, this.faceLandmarks.getLeftEye(), true);\n drawContour(ctx, this.faceLandmarks.getRightEye(), true);\n drawContour(ctx, this.faceLandmarks.getMouth(), true);\n }\n\n if (drawPoints) {\n ctx.strokeStyle = pointColor;\n ctx.fillStyle = pointColor;\n\n const drawPoint = (pt: IPoint) => {\n ctx.beginPath();\n ctx.arc(pt.x, pt.y, pointSize, 0, 2 * Math.PI);\n ctx.fill();\n };\n this.faceLandmarks.positions.forEach(drawPoint);\n }\n }\n}\n\nexport type DrawFaceLandmarksInput = FaceLandmarks | WithFaceLandmarks>\n\nexport function drawFaceLandmarks(\n canvasArg: string | HTMLCanvasElement,\n faceLandmarks: DrawFaceLandmarksInput | Array,\n) {\n const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];\n faceLandmarksArray.forEach((f) => {\n // eslint-disable-next-line no-nested-ternary\n const landmarks = f instanceof FaceLandmarks\n ? f\n : (isWithFaceLandmarks(f) ? f.landmarks : undefined);\n if (!landmarks) {\n throw new Error('drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof');\n }\n\n new DrawFaceLandmarks(landmarks).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { seperateWeightMaps } from '../faceProcessor/util';\nimport { TinyXception } from '../xception/TinyXception';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport {\n AgeAndGenderPrediction, Gender, NetOutput, NetParams,\n} from './types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\n\nexport class AgeGenderNet extends NeuralNetwork {\n private _faceFeatureExtractor: TinyXception\n\n constructor(faceFeatureExtractor: TinyXception = new TinyXception(2)) {\n super('AgeGenderNet');\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): TinyXception {\n return this._faceFeatureExtractor;\n }\n\n public runNet(input: NetInput | tf.Tensor4D): NetOutput {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n\n const pooled = tf.avgPool(bottleneckFeatures, [7, 7], [2, 2], 'valid').as2D(bottleneckFeatures.shape[0], -1);\n const age = fullyConnectedLayer(pooled, params.fc.age).as1D();\n const gender = fullyConnectedLayer(pooled, params.fc.gender);\n return { age, gender };\n });\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): NetOutput {\n return tf.tidy(() => {\n const { age, gender } = this.runNet(input);\n return { age, gender: tf.softmax(gender) };\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictAgeAndGender(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n\n const ages = tf.unstack(out.age);\n const genders = tf.unstack(out.gender);\n const ageAndGenderTensors = ages.map((ageTensor, i) => ({\n ageTensor,\n genderTensor: genders[i],\n }));\n\n const predictionsByBatch = await Promise.all(\n ageAndGenderTensors.map(async ({ ageTensor, genderTensor }) => {\n const age = (await ageTensor.data())[0];\n const probMale = (await genderTensor.data())[0];\n const isMale = probMale > 0.5;\n const gender = isMale ? Gender.MALE : Gender.FEMALE;\n const genderProbability = isMale ? probMale : (1 - probMale);\n\n ageTensor.dispose();\n genderTensor.dispose();\n return { age, gender, genderProbability };\n }),\n );\n out.age.dispose();\n out.gender.dispose();\n\n return netInput.isBatchInput ? predictionsByBatch as AgeAndGenderPrediction[] : predictionsByBatch[0] as AgeAndGenderPrediction;\n }\n\n protected getDefaultModelName(): string {\n return 'age_gender_model';\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights);\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const classifierWeightSize = (512 * 1 + 1) + (512 * 2 + 2);\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, depthwiseSeparableConv } from '../common/index';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { range } from '../utils/index';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction conv(x: tf.Tensor4D, params: ConvParams, stride: [number, number]): tf.Tensor4D {\n return tf.add(tf.conv2d(x, params.filters, stride, 'same'), params.bias);\n}\n\nfunction reductionBlock(x: tf.Tensor4D, params: ReductionBlockParams, isActivateInput: boolean = true): tf.Tensor4D {\n let out = isActivateInput ? tf.relu(x) : x;\n out = depthwiseSeparableConv(out, params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = tf.maxPool(out, [3, 3], [2, 2], 'same');\n out = tf.add(out, conv(x, params.expansion_conv, [2, 2]));\n return out;\n}\n\nfunction mainBlock(x: tf.Tensor4D, params: MainBlockParams): tf.Tensor4D {\n let out = depthwiseSeparableConv(tf.relu(x), params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv2, [1, 1]);\n out = tf.add(out, x);\n return out;\n}\n\nexport class TinyXception extends NeuralNetwork {\n private _numMainBlocks: number\n\n constructor(numMainBlocks: number) {\n super('TinyXception');\n this._numMainBlocks = numMainBlocks;\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyXception - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = tf.relu(conv(normalized, params.entry_flow.conv_in, [2, 2]));\n out = reductionBlock(out, params.entry_flow.reduction_block_0, false);\n out = reductionBlock(out, params.entry_flow.reduction_block_1);\n\n range(this._numMainBlocks, 0, 1).forEach((idx) => {\n out = mainBlock(out, params.middle_flow[`main_block_${idx}`]);\n });\n\n out = reductionBlock(out, params.exit_flow.reduction_block);\n out = tf.relu(depthwiseSeparableConv(out, params.exit_flow.separable_conv, [1, 1]));\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_xception_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this._numMainBlocks);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights, this._numMainBlocks);\n }\n}\n", "import { extractConvParamsFactory, extractSeparableConvParamsFactory, extractWeightsFactory } from '../common/index';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractReductionBlockParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(channels: number, mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParams(weights: Float32Array, numMainBlocks: number): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const entry_flow_conv_in = extractConvParams(3, 32, 3, 'entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams(32, 64, 'entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams(64, 128, 'entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(128, `middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams(128, 256, 'exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams(256, 512, 'exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { entry_flow, middle_flow, exit_flow },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors,\n extractWeightEntryFactory,\n loadSeparableConvParamsFactory,\n ParamMapping,\n} from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractReductionBlockParams(mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(`${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(`${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n numMainBlocks: number,\n): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const entry_flow_conv_in = extractConvParams('entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams('entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams('entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(`middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams('exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams('exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params: { entry_flow, middle_flow, exit_flow }, paramMappings };\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const age = extractFCParams(512, 1, 'fc/age');\n const gender = extractFCParams(512, 2, 'fc/gender');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc: { age, gender } },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: {\n age: extractFcParams('fc/age'),\n gender: extractFcParams('fc/gender'),\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from '../common/index';\n\n// eslint-disable-next-line no-shadow\nexport enum Gender {\n // eslint-disable-next-line no-unused-vars\n FEMALE = 'female',\n // eslint-disable-next-line no-unused-vars\n MALE = 'male'\n}\n\nexport type AgeAndGenderPrediction = {\n age: number\n gender: Gender\n genderProbability: number\n}\n\nexport type NetOutput = { age: tf.Tensor1D, gender: tf.Tensor2D }\n\nexport type NetParams = {\n fc: {\n age: FCParams\n gender: FCParams\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { IDimensions, Point } from '../classes/index';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { isEven } from '../utils/index';\n\nexport abstract class FaceLandmark68NetBase<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends FaceProcessor {\n public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {\n const inputDimensions = originalDimensions.map(({ width, height }) => {\n const scale = inputSize / Math.max(height, width);\n return {\n width: width * scale,\n height: height * scale,\n };\n });\n\n const batchSize = inputDimensions.length;\n\n return tf.tidy(() => {\n const createInterleavedTensor = (fillX: number, fillY: number) => tf.stack([tf.fill([68], fillX, 'float32'), tf.fill([68], fillY, 'float32')], 1).as2D(1, 136).as1D();\n\n // eslint-disable-next-line no-unused-vars\n const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {\n const { width, height } = inputDimensions[batchIdx];\n return cond(width, height) ? Math.abs(width - height) / 2 : 0;\n };\n\n const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h);\n const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w);\n\n const landmarkTensors = output\n .mul(tf.fill([batchSize, 136], inputSize, 'float32'))\n .sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n getPaddingX(batchIdx),\n getPaddingY(batchIdx),\n ))))\n .div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n inputDimensions[batchIdx].width,\n inputDimensions[batchIdx].height,\n ))));\n\n return landmarkTensors as tf.Tensor2D;\n });\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n return tf.tidy(() => {\n const out = this.runNet(input);\n return this.postProcess(\n out,\n input.inputSize as number,\n input.inputDimensions.map(([height, width]) => ({ height, width })),\n );\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async detectLandmarks(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const landmarkTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const landmarksForBatch = await Promise.all(landmarkTensors.map(\n async (landmarkTensor, batchIdx) => {\n const landmarksArray = Array.from(await landmarkTensor.data());\n const xCoords = landmarksArray.filter((_, i) => isEven(i));\n const yCoords = landmarksArray.filter((_, i) => !isEven(i));\n\n return new FaceLandmarks68(\n Array(68).fill(0).map((_, i) => new Point(xCoords[i] as number, yCoords[i] as number)),\n {\n height: netInput.getInputHeight(batchIdx),\n width: netInput.getInputWidth(batchIdx),\n },\n );\n },\n ));\n\n landmarkTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput ? landmarksForBatch as FaceLandmarks68[] : landmarksForBatch[0] as FaceLandmarks68;\n }\n\n protected getClassifierChannelsOut(): number {\n return 136;\n }\n}\n", "import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68Net extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceLandmark68Net', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock3 } from './denseBlock';\nimport { extractParamsFromWeightMapTiny } from './extractParamsFromWeightMapTiny';\nimport { extractParamsTiny } from './extractParamsTiny';\nimport { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';\n\nexport class TinyFaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('TinyFaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyFaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock3(normalized, params.dense0, true);\n out = denseBlock3(out, params.dense1);\n out = denseBlock3(out, params.dense2);\n out = tf.avgPool(out, [14, 14], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_tiny_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMapTiny(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParamsTiny(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMapTiny(\n weightMap: tf.NamedTensorMap,\n): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock3Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock3Params('dense0', true),\n dense1: extractDenseBlock3Params('dense1'),\n dense2: extractDenseBlock3Params('dense2'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock3Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock3Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock3Params(64, 128, 'dense2');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { dense0, dense1, dense2 },\n };\n}\n", "import { TinyFaceFeatureExtractor } from '../faceFeatureExtractor/TinyFaceFeatureExtractor';\nimport { TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68TinyNet extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: TinyFaceFeatureExtractor = new TinyFaceFeatureExtractor()) {\n super('FaceLandmark68TinyNet', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_tiny_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 128;\n }\n}\n", "import { FaceLandmark68Net } from './FaceLandmark68Net';\n\nexport * from './FaceLandmark68Net';\nexport * from './FaceLandmark68TinyNet';\n\nexport class FaceLandmarkNet extends FaceLandmark68Net {}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { convDown } from './convLayer';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { residual, residualDown } from './residualLayer';\nimport { NetParams } from './types';\n\nexport class FaceRecognitionNet extends NeuralNetwork {\n constructor() {\n super('FaceRecognitionNet');\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceRecognitionNet - load model before inference');\n }\n\n return tf.tidy(() => {\n // const batchTensor = input.toBatchTensor(150, true).toFloat()\n const batchTensor = tf.cast(input.toBatchTensor(150, true), 'float32');\n\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = convDown(normalized, params.conv32_down);\n out = tf.maxPool(out, 3, 2, 'valid');\n\n out = residual(out, params.conv32_1);\n out = residual(out, params.conv32_2);\n out = residual(out, params.conv32_3);\n\n out = residualDown(out, params.conv64_down);\n out = residual(out, params.conv64_1);\n out = residual(out, params.conv64_2);\n out = residual(out, params.conv64_3);\n\n out = residualDown(out, params.conv128_down);\n out = residual(out, params.conv128_1);\n out = residual(out, params.conv128_2);\n\n out = residualDown(out, params.conv256_down);\n out = residual(out, params.conv256_1);\n out = residual(out, params.conv256_2);\n out = residualDown(out, params.conv256_down_out);\n\n const globalAvg = out.mean([1, 2]) as tf.Tensor2D;\n const fullyConnected = tf.matMul(globalAvg, params.fc);\n\n return fullyConnected;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async computeFaceDescriptor(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n\n const faceDescriptorTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map(\n (t) => t.data(),\n )) as Float32Array[];\n\n faceDescriptorTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput\n ? faceDescriptorsForBatch\n : faceDescriptorsForBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_recognition_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { scale } from './scaleLayer';\nimport { ConvLayerParams } from './types';\n\nfunction convLayer(\n x: tf.Tensor4D,\n params: ConvLayerParams,\n strides: [number, number],\n withRelu: boolean,\n padding: 'valid' | 'same' = 'same',\n): tf.Tensor4D {\n const { filters, bias } = params.conv;\n\n let out = tf.conv2d(x, filters, strides, padding);\n out = tf.add(out, bias);\n out = scale(out, params.scale);\n return withRelu ? tf.relu(out) : out;\n}\n\nexport function conv(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], true);\n}\n\nexport function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], false);\n}\n\nexport function convDown(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [2, 2], true, 'valid');\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ScaleLayerParams } from './types';\n\nexport function scale(x: tf.Tensor4D, params: ScaleLayerParams): tf.Tensor4D {\n return tf.add(tf.mul(x, params.weights), params.biases);\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping,\n} from '../common/index';\nimport { isFloat } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {\n const weights = extractWeights(numFilterValues);\n const depth = weights.length / (numFilters * filterSize * filterSize);\n\n if (isFloat(depth)) {\n throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`);\n }\n\n return tf.tidy(\n () => tf.transpose(\n tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),\n [2, 3, 1, 0],\n ),\n );\n }\n\n function extractConvParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams {\n const filters = extractFilterValues(numFilterValues, numFilters, filterSize);\n const bias = tf.tensor1d(extractWeights(numFilters));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n }\n\n function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {\n const weights = tf.tensor1d(extractWeights(numWeights));\n const biases = tf.tensor1d(extractWeights(numWeights));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/biases` },\n );\n\n return {\n weights,\n biases,\n };\n }\n\n function extractConvLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvLayerParams {\n const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`);\n const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`);\n\n return { conv, scale };\n }\n\n function extractResidualLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n isDown: boolean = false,\n ): ResidualLayerParams {\n const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`);\n const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`);\n\n return { conv1, conv2 };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down');\n const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1');\n const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2');\n const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3');\n\n const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true);\n const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1');\n const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2');\n const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3');\n\n const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true);\n const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1');\n const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2');\n\n const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true);\n const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1');\n const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2');\n const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out');\n\n const fc = tf.tidy(\n () => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0]),\n );\n paramMappings.push({ paramPath: 'fc' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common/index';\nimport { isTensor2D } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractScaleLayerParams(prefix: string): ScaleLayerParams {\n const weights = extractWeightEntry(`${prefix}/scale/weights`, 1);\n const biases = extractWeightEntry(`${prefix}/scale/biases`, 1);\n\n return { weights, biases };\n }\n\n function extractConvLayerParams(prefix: string): ConvLayerParams {\n const filters = extractWeightEntry(`${prefix}/conv/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/conv/bias`, 1);\n const scale = extractScaleLayerParams(prefix);\n\n return { conv: { filters, bias }, scale };\n }\n\n function extractResidualLayerParams(prefix: string): ResidualLayerParams {\n return {\n conv1: extractConvLayerParams(`${prefix}/conv1`),\n conv2: extractConvLayerParams(`${prefix}/conv2`),\n };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const conv32_down = extractConvLayerParams('conv32_down');\n const conv32_1 = extractResidualLayerParams('conv32_1');\n const conv32_2 = extractResidualLayerParams('conv32_2');\n const conv32_3 = extractResidualLayerParams('conv32_3');\n\n const conv64_down = extractResidualLayerParams('conv64_down');\n const conv64_1 = extractResidualLayerParams('conv64_1');\n const conv64_2 = extractResidualLayerParams('conv64_2');\n const conv64_3 = extractResidualLayerParams('conv64_3');\n\n const conv128_down = extractResidualLayerParams('conv128_down');\n const conv128_1 = extractResidualLayerParams('conv128_1');\n const conv128_2 = extractResidualLayerParams('conv128_2');\n\n const conv256_down = extractResidualLayerParams('conv256_down');\n const conv256_1 = extractResidualLayerParams('conv256_1');\n const conv256_2 = extractResidualLayerParams('conv256_2');\n const conv256_down_out = extractResidualLayerParams('conv256_down_out');\n\n const { fc } = weightMap;\n paramMappings.push({ originalPath: 'fc', paramPath: 'fc' });\n\n if (!isTensor2D(fc)) {\n throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { conv, convDown, convNoRelu } from './convLayer';\nimport { ResidualLayerParams } from './types';\n\nexport function residual(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = conv(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n out = tf.add(out, x);\n out = tf.relu(out);\n return out;\n}\n\nexport function residualDown(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = convDown(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n\n let pooled = tf.avgPool(x, 2, 2, 'valid') as tf.Tensor4D;\n const zeros = tf.zeros(pooled.shape);\n const isPad = pooled.shape[3] !== out.shape[3];\n const isAdjustShape = pooled.shape[1] !== out.shape[1] || pooled.shape[2] !== out.shape[2];\n\n if (isAdjustShape) {\n const padShapeX = [...out.shape] as [number, number, number, number];\n padShapeX[1] = 1;\n const zerosW = tf.zeros(padShapeX);\n out = tf.concat([out, zerosW], 1);\n\n const padShapeY = [...out.shape] as [number, number, number, number];\n padShapeY[2] = 1;\n const zerosH = tf.zeros(padShapeY);\n out = tf.concat([out, zerosH], 2);\n }\n\n pooled = isPad ? tf.concat([pooled, zeros], 3) : pooled;\n out = tf.add(pooled, out) as tf.Tensor4D;\n\n out = tf.relu(out);\n return out;\n}\n", "import { FaceRecognitionNet } from './FaceRecognitionNet';\n\nexport * from './FaceRecognitionNet';\n\nexport function createFaceRecognitionNet(weights: Float32Array) {\n const net = new FaceRecognitionNet();\n net.extractWeights(weights);\n return net;\n}\n", "export type WithFaceDescriptor = TSource & {\n descriptor: Float32Array\n}\n\nexport function extendWithFaceDescriptor<\n TSource\n>(\n sourceObj: TSource,\n descriptor: Float32Array,\n): WithFaceDescriptor {\n const extension = { descriptor };\n return { ...sourceObj, ...extension };\n}\n", "export type WithAge = TSource & {\n age: number\n}\n\nexport function isWithAge(obj: any): obj is WithAge<{}> {\n return typeof obj.age === 'number';\n}\n\nexport function extendWithAge<\n TSource\n>(\n sourceObj: TSource,\n age: number,\n): WithAge {\n const extension = { age };\n return { ...sourceObj, ...extension };\n}\n", "import { Gender } from '../ageGenderNet/types';\nimport { isValidProbablitiy } from '../utils/index';\n\nexport type WithGender = TSource & {\n gender: Gender\n genderProbability: number\n}\n\nexport function isWithGender(obj: any): obj is WithGender<{}> {\n return (obj.gender === Gender.MALE || obj.gender === Gender.FEMALE)\n && isValidProbablitiy(obj.genderProbability);\n}\n\nexport function extendWithGender<\n TSource\n>(\n sourceObj: TSource,\n gender: Gender,\n genderProbability: number,\n): WithGender {\n const extension = { gender, genderProbability };\n return { ...sourceObj, ...extension };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { mobileNetV1 } from './mobileNetV1';\nimport { nonMaxSuppression } from './nonMaxSuppression';\nimport { outputLayer } from './outputLayer';\nimport { predictionLayer } from './predictionLayer';\nimport { ISsdMobilenetv1Options, SsdMobilenetv1Options } from './SsdMobilenetv1Options';\nimport { NetParams } from './types';\n\nexport class SsdMobilenetv1 extends NeuralNetwork {\n constructor() {\n super('SsdMobilenetv1');\n }\n\n public forwardInput(input: NetInput) {\n const { params } = this;\n\n if (!params) {\n throw new Error('SsdMobilenetv1 - load model before inference');\n }\n\n return tf.tidy(() => {\n // const batchTensor = input.toBatchTensor(512, false).toFloat()\n const batchTensor = tf.cast(input.toBatchTensor(512, false), 'float32');\n\n const x = tf.sub(tf.mul(batchTensor, tf.scalar(0.007843137718737125)), tf.scalar(1)) as tf.Tensor4D;\n const features = mobileNetV1(x, params.mobilenetv1);\n\n const {\n boxPredictions,\n classPredictions,\n } = predictionLayer(features.out, features.conv11, params.prediction_layer);\n\n return outputLayer(boxPredictions, classPredictions, params.output_layer);\n });\n }\n\n public async forward(input: TNetInput) {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async locateFaces(\n input: TNetInput,\n options: ISsdMobilenetv1Options = {},\n ): Promise {\n const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);\n\n const netInput = await toNetInput(input);\n\n const {\n boxes: _boxes,\n scores: _scores,\n } = this.forwardInput(netInput);\n\n // TODO batches\n const boxes = _boxes[0];\n const scores = _scores[0];\n for (let i = 1; i < _boxes.length; i++) {\n _boxes[i].dispose();\n _scores[i].dispose();\n }\n\n // TODO find a better way to filter by minConfidence\n const scoresData = Array.from(await scores.data());\n\n const iouThreshold = 0.5;\n const indices = nonMaxSuppression(\n boxes,\n scoresData as number[],\n maxResults,\n iouThreshold,\n minConfidence,\n );\n\n const reshapedDims = netInput.getReshapedInputDimensions(0);\n const inputSize = netInput.inputSize as number;\n const padX = inputSize / reshapedDims.width;\n const padY = inputSize / reshapedDims.height;\n\n const boxesData = boxes.arraySync();\n const results = indices\n .map((idx) => {\n const [top, bottom] = [\n Math.max(0, boxesData[idx][0]),\n Math.min(1.0, boxesData[idx][2]),\n ].map((val) => val * padY);\n const [left, right] = [\n Math.max(0, boxesData[idx][1]),\n Math.min(1.0, boxesData[idx][3]),\n ].map((val) => val * padX);\n return new FaceDetection(\n scoresData[idx] as number,\n new Rect(\n left,\n top,\n right - left,\n bottom - top,\n ),\n {\n height: netInput.getInputHeight(0),\n width: netInput.getInputWidth(0),\n },\n );\n });\n\n boxes.dispose();\n scores.dispose();\n\n return results;\n }\n\n protected getDefaultModelName(): string {\n return 'ssd_mobilenetv1_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ExtractWeightsFunction, ParamMapping, ConvParams, extractWeightsFactory,\n} from '../common/index';\nimport {\n MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractDepthwiseConvParams(numChannels: number, mappedPrefix: string): MobileNetV1.DepthwiseConvParams {\n const filters = tf.tensor4d(extractWeights(3 * 3 * numChannels), [3, 3, numChannels, 1]);\n const batch_norm_scale = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_offset = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_mean = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_variance = tf.tensor1d(extractWeights(numChannels));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/batch_norm_scale` },\n { paramPath: `${mappedPrefix}/batch_norm_offset` },\n { paramPath: `${mappedPrefix}/batch_norm_mean` },\n { paramPath: `${mappedPrefix}/batch_norm_variance` },\n );\n\n return {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n };\n }\n\n function extractConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n isPointwiseConv?: boolean,\n ): ConvParams {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/${isPointwiseConv ? 'batch_norm_offset' : 'bias'}` },\n );\n\n return { filters, bias };\n }\n\n function extractPointwiseConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): PointwiseConvParams {\n const {\n filters,\n bias,\n } = extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix, true);\n\n return {\n filters,\n batch_norm_offset: bias,\n };\n }\n\n function extractConvPairParams(\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): MobileNetV1.ConvPairParams {\n const depthwise_conv = extractDepthwiseConvParams(channelsIn, `${mappedPrefix}/depthwise_conv`);\n const pointwise_conv = extractPointwiseConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/pointwise_conv`);\n\n return { depthwise_conv, pointwise_conv };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n const conv_0 = extractPointwiseConvParams(3, 32, 3, 'mobilenetv1/conv_0');\n\n const conv_1 = extractConvPairParams(32, 64, 'mobilenetv1/conv_1');\n const conv_2 = extractConvPairParams(64, 128, 'mobilenetv1/conv_2');\n const conv_3 = extractConvPairParams(128, 128, 'mobilenetv1/conv_3');\n const conv_4 = extractConvPairParams(128, 256, 'mobilenetv1/conv_4');\n const conv_5 = extractConvPairParams(256, 256, 'mobilenetv1/conv_5');\n const conv_6 = extractConvPairParams(256, 512, 'mobilenetv1/conv_6');\n const conv_7 = extractConvPairParams(512, 512, 'mobilenetv1/conv_7');\n const conv_8 = extractConvPairParams(512, 512, 'mobilenetv1/conv_8');\n const conv_9 = extractConvPairParams(512, 512, 'mobilenetv1/conv_9');\n const conv_10 = extractConvPairParams(512, 512, 'mobilenetv1/conv_10');\n const conv_11 = extractConvPairParams(512, 512, 'mobilenetv1/conv_11');\n const conv_12 = extractConvPairParams(512, 1024, 'mobilenetv1/conv_12');\n const conv_13 = extractConvPairParams(1024, 1024, 'mobilenetv1/conv_13');\n\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n conv_8,\n conv_9,\n conv_10,\n conv_11,\n conv_12,\n conv_13,\n };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n const conv_0 = extractPointwiseConvParams(1024, 256, 1, 'prediction_layer/conv_0');\n const conv_1 = extractPointwiseConvParams(256, 512, 3, 'prediction_layer/conv_1');\n const conv_2 = extractPointwiseConvParams(512, 128, 1, 'prediction_layer/conv_2');\n const conv_3 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_3');\n const conv_4 = extractPointwiseConvParams(256, 128, 1, 'prediction_layer/conv_4');\n const conv_5 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_5');\n const conv_6 = extractPointwiseConvParams(256, 64, 1, 'prediction_layer/conv_6');\n const conv_7 = extractPointwiseConvParams(64, 128, 3, 'prediction_layer/conv_7');\n\n const box_encoding_0_predictor = extractConvParams(512, 12, 1, 'prediction_layer/box_predictor_0/box_encoding_predictor');\n const class_predictor_0 = extractConvParams(512, 9, 1, 'prediction_layer/box_predictor_0/class_predictor');\n const box_encoding_1_predictor = extractConvParams(1024, 24, 1, 'prediction_layer/box_predictor_1/box_encoding_predictor');\n const class_predictor_1 = extractConvParams(1024, 18, 1, 'prediction_layer/box_predictor_1/class_predictor');\n const box_encoding_2_predictor = extractConvParams(512, 24, 1, 'prediction_layer/box_predictor_2/box_encoding_predictor');\n const class_predictor_2 = extractConvParams(512, 18, 1, 'prediction_layer/box_predictor_2/class_predictor');\n const box_encoding_3_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_3/box_encoding_predictor');\n const class_predictor_3 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_3/class_predictor');\n const box_encoding_4_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_4/box_encoding_predictor');\n const class_predictor_4 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_4/class_predictor');\n const box_encoding_5_predictor = extractConvParams(128, 24, 1, 'prediction_layer/box_predictor_5/box_encoding_predictor');\n const class_predictor_5 = extractConvParams(128, 18, 1, 'prediction_layer/box_predictor_5/class_predictor');\n\n const box_predictor_0 = {\n box_encoding_predictor: box_encoding_0_predictor,\n class_predictor: class_predictor_0,\n };\n const box_predictor_1 = {\n box_encoding_predictor: box_encoding_1_predictor,\n class_predictor: class_predictor_1,\n };\n const box_predictor_2 = {\n box_encoding_predictor: box_encoding_2_predictor,\n class_predictor: class_predictor_2,\n };\n const box_predictor_3 = {\n box_encoding_predictor: box_encoding_3_predictor,\n class_predictor: class_predictor_3,\n };\n const box_predictor_4 = {\n box_encoding_predictor: box_encoding_4_predictor,\n class_predictor: class_predictor_4,\n };\n const box_predictor_5 = {\n box_encoding_predictor: box_encoding_5_predictor,\n class_predictor: class_predictor_5,\n };\n\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n box_predictor_0,\n box_predictor_1,\n box_predictor_2,\n box_predictor_3,\n box_predictor_4,\n box_predictor_5,\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const mobilenetv1 = extractMobilenetV1Params();\n const prediction_layer = extractPredictionLayerParams();\n const extra_dim = tf.tensor3d(\n extractWeights(5118 * 4),\n [1, 5118, 4],\n );\n const output_layer = {\n extra_dim,\n };\n\n paramMappings.push({ paramPath: 'output_layer/extra_dim' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n params: {\n mobilenetv1,\n prediction_layer,\n output_layer,\n },\n paramMappings,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping,\n} from '../common/index';\nimport { isTensor3D } from '../utils/index';\nimport {\n BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractPointwiseConvParams(prefix: string, idx: number, mappedPrefix: string): PointwiseConvParams {\n const filters = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/weights`, 4, `${mappedPrefix}/filters`);\n const batch_norm_offset = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/convolution_bn_offset`, 1, `${mappedPrefix}/batch_norm_offset`);\n\n return { filters, batch_norm_offset };\n }\n\n function extractConvPairParams(idx: number): MobileNetV1.ConvPairParams {\n const mappedPrefix = `mobilenetv1/conv_${idx}`;\n const prefixDepthwiseConv = `MobilenetV1/Conv2d_${idx}_depthwise`;\n const mappedPrefixDepthwiseConv = `${mappedPrefix}/depthwise_conv`;\n const mappedPrefixPointwiseConv = `${mappedPrefix}/pointwise_conv`;\n\n const filters = extractWeightEntry(`${prefixDepthwiseConv}/depthwise_weights`, 4, `${mappedPrefixDepthwiseConv}/filters`);\n const batch_norm_scale = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/gamma`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_scale`);\n const batch_norm_offset = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/beta`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_offset`);\n const batch_norm_mean = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_mean`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_mean`);\n const batch_norm_variance = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_variance`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_variance`);\n\n return {\n depthwise_conv: {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n },\n pointwise_conv: extractPointwiseConvParams('MobilenetV1', idx, mappedPrefixPointwiseConv),\n };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n return {\n conv_0: extractPointwiseConvParams('MobilenetV1', 0, 'mobilenetv1/conv_0'),\n conv_1: extractConvPairParams(1),\n conv_2: extractConvPairParams(2),\n conv_3: extractConvPairParams(3),\n conv_4: extractConvPairParams(4),\n conv_5: extractConvPairParams(5),\n conv_6: extractConvPairParams(6),\n conv_7: extractConvPairParams(7),\n conv_8: extractConvPairParams(8),\n conv_9: extractConvPairParams(9),\n conv_10: extractConvPairParams(10),\n conv_11: extractConvPairParams(11),\n conv_12: extractConvPairParams(12),\n conv_13: extractConvPairParams(13),\n };\n }\n\n function extractConvParams(prefix: string, mappedPrefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/weights`, 4, `${mappedPrefix}/filters`);\n const bias = extractWeightEntry(`${prefix}/biases`, 1, `${mappedPrefix}/bias`);\n\n return { filters, bias };\n }\n\n function extractBoxPredictorParams(idx: number): BoxPredictionParams {\n const box_encoding_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/BoxEncodingPredictor`,\n `prediction_layer/box_predictor_${idx}/box_encoding_predictor`,\n );\n const class_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/ClassPredictor`,\n `prediction_layer/box_predictor_${idx}/class_predictor`,\n );\n\n return { box_encoding_predictor, class_predictor };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n return {\n conv_0: extractPointwiseConvParams('Prediction', 0, 'prediction_layer/conv_0'),\n conv_1: extractPointwiseConvParams('Prediction', 1, 'prediction_layer/conv_1'),\n conv_2: extractPointwiseConvParams('Prediction', 2, 'prediction_layer/conv_2'),\n conv_3: extractPointwiseConvParams('Prediction', 3, 'prediction_layer/conv_3'),\n conv_4: extractPointwiseConvParams('Prediction', 4, 'prediction_layer/conv_4'),\n conv_5: extractPointwiseConvParams('Prediction', 5, 'prediction_layer/conv_5'),\n conv_6: extractPointwiseConvParams('Prediction', 6, 'prediction_layer/conv_6'),\n conv_7: extractPointwiseConvParams('Prediction', 7, 'prediction_layer/conv_7'),\n box_predictor_0: extractBoxPredictorParams(0),\n box_predictor_1: extractBoxPredictorParams(1),\n box_predictor_2: extractBoxPredictorParams(2),\n box_predictor_3: extractBoxPredictorParams(3),\n box_predictor_4: extractBoxPredictorParams(4),\n box_predictor_5: extractBoxPredictorParams(5),\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const extra_dim = weightMap['Output/extra_dim'];\n paramMappings.push({ originalPath: 'Output/extra_dim', paramPath: 'output_layer/extra_dim' });\n\n if (!isTensor3D(extra_dim)) {\n throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${extra_dim}`);\n }\n\n const params = {\n mobilenetv1: extractMobilenetV1Params(),\n prediction_layer: extractPredictionLayerParams(),\n output_layer: {\n extra_dim,\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { MobileNetV1 } from './types';\n\nconst epsilon = 0.0010000000474974513;\n\nfunction depthwiseConvLayer(\n x: tf.Tensor4D,\n params: MobileNetV1.DepthwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.depthwiseConv2d(x, params.filters, strides, 'same');\n out = tf.batchNorm(\n out,\n params.batch_norm_mean,\n params.batch_norm_variance,\n params.batch_norm_offset,\n params.batch_norm_scale,\n epsilon,\n );\n return tf.clipByValue(out, 0, 6);\n });\n}\n\nfunction getStridesForLayerIdx(layerIdx: number): [number, number] {\n return [2, 4, 6, 12].some((idx) => idx === layerIdx) ? [2, 2] : [1, 1];\n}\n\nexport function mobileNetV1(x: tf.Tensor4D, params: MobileNetV1.Params) {\n return tf.tidy(() => {\n let conv11;\n let out = pointwiseConvLayer(x, params.conv_0, [2, 2]);\n\n const convPairParams = [\n params.conv_1,\n params.conv_2,\n params.conv_3,\n params.conv_4,\n params.conv_5,\n params.conv_6,\n params.conv_7,\n params.conv_8,\n params.conv_9,\n params.conv_10,\n params.conv_11,\n params.conv_12,\n params.conv_13,\n ];\n\n convPairParams.forEach((param, i) => {\n const layerIdx = i + 1;\n const depthwiseConvStrides = getStridesForLayerIdx(layerIdx);\n out = depthwiseConvLayer(out, param.depthwise_conv, depthwiseConvStrides);\n out = pointwiseConvLayer(out, param.pointwise_conv, [1, 1]);\n if (layerIdx === 11) {\n conv11 = out;\n }\n });\n\n if (conv11 === null) {\n throw new Error('mobileNetV1 - output of conv layer 11 is null');\n }\n\n return {\n out,\n conv11: conv11 as any,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { PointwiseConvParams } from './types';\n\nexport function pointwiseConvLayer(\n x: tf.Tensor4D,\n params: PointwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.conv2d(x, params.filters, strides, 'same');\n out = tf.add(out, params.batch_norm_offset);\n return tf.clipByValue(out, 0, 6);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nfunction IOU(boxes: tf.Tensor2D, i: number, j: number) {\n const boxesData = boxes.arraySync();\n const yminI = Math.min(boxesData[i][0], boxesData[i][2]);\n const xminI = Math.min(boxesData[i][1], boxesData[i][3]);\n const ymaxI = Math.max(boxesData[i][0], boxesData[i][2]);\n const xmaxI = Math.max(boxesData[i][1], boxesData[i][3]);\n const yminJ = Math.min(boxesData[j][0], boxesData[j][2]);\n const xminJ = Math.min(boxesData[j][1], boxesData[j][3]);\n const ymaxJ = Math.max(boxesData[j][0], boxesData[j][2]);\n const xmaxJ = Math.max(boxesData[j][1], boxesData[j][3]);\n const areaI = (ymaxI - yminI) * (xmaxI - xminI);\n const areaJ = (ymaxJ - yminJ) * (xmaxJ - xminJ);\n if (areaI <= 0 || areaJ <= 0) {\n return 0.0;\n }\n const intersectionYmin = Math.max(yminI, yminJ);\n const intersectionXmin = Math.max(xminI, xminJ);\n const intersectionYmax = Math.min(ymaxI, ymaxJ);\n const intersectionXmax = Math.min(xmaxI, xmaxJ);\n const intersectionArea = Math.max(intersectionYmax - intersectionYmin, 0.0)\n * Math.max(intersectionXmax - intersectionXmin, 0.0);\n return intersectionArea / (areaI + areaJ - intersectionArea);\n}\n\nexport function nonMaxSuppression(\n boxes: tf.Tensor2D,\n scores: number[],\n maxOutputSize: number,\n iouThreshold: number,\n scoreThreshold: number,\n): number[] {\n const numBoxes = boxes.shape[0];\n const outputSize = Math.min(\n maxOutputSize,\n numBoxes,\n );\n\n const candidates = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .filter((c) => c.score > scoreThreshold)\n .sort((c1, c2) => c2.score - c1.score);\n\n const suppressFunc = (x: number) => (x <= iouThreshold ? 1 : 0);\n\n const selected: number[] = [];\n\n candidates.forEach((c) => {\n if (selected.length >= outputSize) {\n return;\n }\n const originalScore = c.score;\n\n for (let j = selected.length - 1; j >= 0; --j) {\n const iou = IOU(boxes, c.boxIndex, selected[j]);\n if (iou === 0.0) continue;\n c.score *= suppressFunc(iou);\n if (c.score <= scoreThreshold) break;\n }\n if (originalScore === c.score) {\n selected.push(c.boxIndex);\n }\n });\n\n return selected;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { OutputLayerParams } from './types';\n\nfunction getCenterCoordinatesAndSizesLayer(x: tf.Tensor2D) {\n const vec = tf.unstack(tf.transpose(x, [1, 0]));\n\n const sizes = [\n tf.sub(vec[2], vec[0]),\n tf.sub(vec[3], vec[1]),\n ];\n\n const centers = [\n tf.add(vec[0], tf.div(sizes[0], tf.scalar(2))),\n tf.add(vec[1], tf.div(sizes[1], tf.scalar(2))),\n ];\n\n return {\n sizes,\n centers,\n };\n}\n\nfunction decodeBoxesLayer(x0: tf.Tensor2D, x1: tf.Tensor2D) {\n const {\n sizes,\n centers,\n } = getCenterCoordinatesAndSizesLayer(x0);\n\n const vec = tf.unstack(tf.transpose(x1, [1, 0]));\n\n const div0_out = tf.div(tf.mul(tf.exp(tf.div(vec[2], tf.scalar(5))), sizes[0]), tf.scalar(2));\n const add0_out = tf.add(tf.mul(tf.div(vec[0], tf.scalar(10)), sizes[0]), centers[0]);\n\n const div1_out = tf.div(tf.mul(tf.exp(tf.div(vec[3], tf.scalar(5))), sizes[1]), tf.scalar(2));\n const add1_out = tf.add(tf.mul(tf.div(vec[1], tf.scalar(10)), sizes[1]), centers[1]);\n\n return tf.transpose(\n tf.stack([\n tf.sub(add0_out, div0_out),\n tf.sub(add1_out, div1_out),\n tf.add(add0_out, div0_out),\n tf.add(add1_out, div1_out),\n ]),\n [1, 0],\n );\n}\n\nexport function outputLayer(\n boxPredictions: tf.Tensor4D,\n classPredictions: tf.Tensor4D,\n params: OutputLayerParams,\n) {\n return tf.tidy(() => {\n const batchSize = boxPredictions.shape[0];\n\n let boxes = decodeBoxesLayer(\n tf.reshape(tf.tile(params.extra_dim, [batchSize, 1, 1]), [-1, 4]) as tf.Tensor2D,\n tf.reshape(boxPredictions, [-1, 4]) as tf.Tensor2D,\n );\n boxes = tf.reshape(\n boxes,\n [batchSize, (boxes.shape[0] / batchSize), 4],\n );\n\n const scoresAndClasses = tf.sigmoid(tf.slice(classPredictions, [0, 0, 1], [-1, -1, -1]));\n let scores = tf.slice(scoresAndClasses, [0, 0, 0], [-1, -1, 1]) as tf.Tensor;\n\n scores = tf.reshape(\n scores,\n [batchSize, scores.shape[1] as number],\n );\n\n const boxesByBatch = tf.unstack(boxes) as tf.Tensor2D[];\n const scoresByBatch = tf.unstack(scores) as tf.Tensor1D[];\n\n return {\n boxes: boxesByBatch,\n scores: scoresByBatch,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { boxPredictionLayer } from './boxPredictionLayer';\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { PredictionLayerParams } from './types';\n\nexport function predictionLayer(\n x: tf.Tensor4D,\n conv11: tf.Tensor4D,\n params: PredictionLayerParams,\n) {\n return tf.tidy(() => {\n const conv0 = pointwiseConvLayer(x, params.conv_0, [1, 1]);\n const conv1 = pointwiseConvLayer(conv0, params.conv_1, [2, 2]);\n const conv2 = pointwiseConvLayer(conv1, params.conv_2, [1, 1]);\n const conv3 = pointwiseConvLayer(conv2, params.conv_3, [2, 2]);\n const conv4 = pointwiseConvLayer(conv3, params.conv_4, [1, 1]);\n const conv5 = pointwiseConvLayer(conv4, params.conv_5, [2, 2]);\n const conv6 = pointwiseConvLayer(conv5, params.conv_6, [1, 1]);\n const conv7 = pointwiseConvLayer(conv6, params.conv_7, [2, 2]);\n\n const boxPrediction0 = boxPredictionLayer(conv11, params.box_predictor_0);\n const boxPrediction1 = boxPredictionLayer(x, params.box_predictor_1);\n const boxPrediction2 = boxPredictionLayer(conv1, params.box_predictor_2);\n const boxPrediction3 = boxPredictionLayer(conv3, params.box_predictor_3);\n const boxPrediction4 = boxPredictionLayer(conv5, params.box_predictor_4);\n const boxPrediction5 = boxPredictionLayer(conv7, params.box_predictor_5);\n\n const boxPredictions = tf.concat([\n boxPrediction0.boxPredictionEncoding,\n boxPrediction1.boxPredictionEncoding,\n boxPrediction2.boxPredictionEncoding,\n boxPrediction3.boxPredictionEncoding,\n boxPrediction4.boxPredictionEncoding,\n boxPrediction5.boxPredictionEncoding,\n ], 1) as tf.Tensor4D;\n\n const classPredictions = tf.concat([\n boxPrediction0.classPrediction,\n boxPrediction1.classPrediction,\n boxPrediction2.classPrediction,\n boxPrediction3.classPrediction,\n boxPrediction4.classPrediction,\n boxPrediction5.classPrediction,\n ], 1) as tf.Tensor4D;\n\n return {\n boxPredictions,\n classPredictions,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { convLayer } from '../common/index';\nimport { BoxPredictionParams } from './types';\n\nexport function boxPredictionLayer(\n x: tf.Tensor4D,\n params: BoxPredictionParams,\n) {\n return tf.tidy(() => {\n const batchSize = x.shape[0];\n\n const boxPredictionEncoding = tf.reshape(\n convLayer(x, params.box_encoding_predictor),\n [batchSize, -1, 1, 4],\n );\n const classPrediction = tf.reshape(\n convLayer(x, params.class_predictor),\n [batchSize, -1, 3],\n );\n\n return {\n boxPredictionEncoding,\n classPrediction,\n };\n });\n}\n", "export interface ISsdMobilenetv1Options {\n minConfidence?: number\n maxResults?: number\n}\n\nexport class SsdMobilenetv1Options {\n protected _name: string = 'SsdMobilenetv1Options'\n\n private _minConfidence: number\n\n private _maxResults: number\n\n constructor({ minConfidence, maxResults }: ISsdMobilenetv1Options = {}) {\n this._minConfidence = minConfidence || 0.5;\n this._maxResults = maxResults || 100;\n\n if (typeof this._minConfidence !== 'number' || this._minConfidence <= 0 || this._minConfidence >= 1) {\n throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);\n }\n\n if (typeof this._maxResults !== 'number') {\n throw new Error(`${this._name} - expected maxResults to be a number`);\n }\n }\n\n get minConfidence(): number { return this._minConfidence; }\n\n get maxResults(): number { return this._maxResults; }\n}\n", "import { SsdMobilenetv1 } from './SsdMobilenetv1';\n\nexport * from './SsdMobilenetv1';\nexport * from './SsdMobilenetv1Options';\n\nexport function createSsdMobilenetv1(weights: Float32Array) {\n const net = new SsdMobilenetv1();\n net.extractWeights(weights);\n return net;\n}\n\nexport function createFaceDetectionNet(weights: Float32Array) {\n return createSsdMobilenetv1(weights);\n}\n\n// alias for backward compatibily\nexport class FaceDetectionNet extends SsdMobilenetv1 {}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(0.738768, 0.874946),\n new Point(2.42204, 2.65704),\n new Point(4.30971, 7.04493),\n new Point(10.246, 4.59428),\n new Point(12.6868, 11.8741),\n];\n\nexport const BOX_ANCHORS_SEPARABLE = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB_SEPARABLE: [number, number, number] = [117.001, 114.697, 97.404];\n\nexport const DEFAULT_MODEL_NAME = 'tiny_yolov2_model';\nexport const DEFAULT_MODEL_NAME_SEPARABLE_CONV = 'tiny_yolov2_separable_conv_model';\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { BoundingBox } from '../classes/BoundingBox';\nimport { Dimensions } from '../classes/Dimensions';\nimport { ObjectDetection } from '../classes/ObjectDetection';\nimport { convLayer } from '../common/index';\nimport { ConvParams, SeparableConvParams } from '../common/types';\nimport { toNetInput } from '../dom/index';\nimport { NetInput } from '../dom/NetInput';\nimport { TNetInput } from '../dom/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { sigmoid } from '../ops/index';\nimport { nonMaxSuppression } from '../ops/nonMaxSuppression';\nimport { normalize } from '../ops/normalize';\nimport { TinyYolov2Config, validateConfig } from './config';\nimport { convWithBatchNorm } from './convWithBatchNorm';\nimport { depthwiseSeparableConv } from './depthwiseSeparableConv';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { leaky } from './leaky';\nimport { ITinyYolov2Options, TinyYolov2Options } from './TinyYolov2Options';\nimport { DefaultTinyYolov2NetParams, MobilenetParams, TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2Base extends NeuralNetwork {\n public static DEFAULT_FILTER_SIZES = [\n 3, 16, 32, 64, 128, 256, 512, 1024, 1024,\n ]\n\n private _config: TinyYolov2Config\n\n constructor(config: TinyYolov2Config) {\n super('TinyYolov2');\n validateConfig(config);\n this._config = config;\n }\n\n public get config(): TinyYolov2Config {\n return this._config;\n }\n\n public get withClassScores(): boolean {\n return this.config.withClassScores || this.config.classes.length > 1;\n }\n\n public get boxEncodingSize(): number {\n return 5 + (this.withClassScores ? this.config.classes.length : 0);\n }\n\n public runTinyYolov2(x: tf.Tensor4D, params: DefaultTinyYolov2NetParams): tf.Tensor4D {\n let out = convWithBatchNorm(x, params.conv0);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = convWithBatchNorm(out, params.conv6);\n out = convWithBatchNorm(out, params.conv7);\n\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public runMobilenet(x: tf.Tensor4D, params: MobilenetParams): tf.Tensor4D {\n let out = this.config.isFirstLayerConv2d\n ? leaky(convLayer(x, params.conv0 as ConvParams, 'valid', false))\n : depthwiseSeparableConv(x, params.conv0 as SeparableConvParams);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = params.conv6 ? depthwiseSeparableConv(out, params.conv6) : out;\n out = params.conv7 ? depthwiseSeparableConv(out, params.conv7) : out;\n\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public forwardInput(input: NetInput, inputSize: number): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyYolov2 - load model before inference');\n }\n\n return tf.tidy(() => {\n // let batchTensor = input.toBatchTensor(inputSize, false).toFloat()\n let batchTensor = tf.cast(input.toBatchTensor(inputSize, false), 'float32');\n batchTensor = this.config.meanRgb\n ? normalize(batchTensor, this.config.meanRgb)\n : batchTensor;\n batchTensor = batchTensor.div(tf.scalar(256)) as tf.Tensor4D;\n\n return this.config.withSeparableConvs\n ? this.runMobilenet(batchTensor, params as MobilenetParams)\n : this.runTinyYolov2(batchTensor, params as DefaultTinyYolov2NetParams);\n });\n }\n\n public async forward(input: TNetInput, inputSize: number): Promise {\n return this.forwardInput(await toNetInput(input), inputSize);\n }\n\n public async detect(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise {\n const { inputSize, scoreThreshold } = new TinyYolov2Options(forwardParams);\n\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput, inputSize);\n const out0 = tf.tidy(() => tf.unstack(out)[0].expandDims()) as tf.Tensor4D;\n\n const inputDimensions = {\n width: netInput.getInputWidth(0),\n height: netInput.getInputHeight(0),\n };\n\n const results = await this.extractBoxes(out0, netInput.getReshapedInputDimensions(0), scoreThreshold);\n out.dispose();\n out0.dispose();\n\n const boxes = results.map((res) => res.box);\n const scores = results.map((res) => res.score);\n const classScores = results.map((res) => res.classScore);\n const classNames = results.map((res) => this.config.classes[res.label]);\n\n const indices = nonMaxSuppression(\n boxes.map((box) => box.rescale(inputSize)),\n scores,\n this.config.iouThreshold,\n true,\n );\n\n const detections = indices.map((idx) => new ObjectDetection(\n scores[idx],\n classScores[idx],\n classNames[idx],\n boxes[idx],\n inputDimensions,\n ));\n\n return detections;\n }\n\n protected getDefaultModelName(): string {\n return '';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this.config);\n }\n\n protected extractParams(weights: Float32Array) {\n const filterSizes = this.config.filterSizes || TinyYolov2Base.DEFAULT_FILTER_SIZES;\n\n const numFilters = filterSizes ? filterSizes.length : undefined;\n if (numFilters !== 7 && numFilters !== 8 && numFilters !== 9) {\n throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${numFilters} filterSizes in config`);\n }\n return extractParams(weights, this.config, this.boxEncodingSize, filterSizes);\n }\n\n protected async extractBoxes(\n outputTensor: tf.Tensor4D,\n inputBlobDimensions: Dimensions,\n scoreThreshold?: number,\n ) {\n const { width, height } = inputBlobDimensions;\n const inputSize = Math.max(width, height);\n const correctionFactorX = inputSize / width;\n const correctionFactorY = inputSize / height;\n\n const numCells = outputTensor.shape[1];\n const numBoxes = this.config.anchors.length;\n\n const [boxesTensor, scoresTensor, classScoresTensor] = tf.tidy(() => {\n const reshaped = outputTensor.reshape([numCells, numCells, numBoxes, this.boxEncodingSize]);\n\n const boxes = reshaped.slice([0, 0, 0, 0], [numCells, numCells, numBoxes, 4]);\n const scores = reshaped.slice([0, 0, 0, 4], [numCells, numCells, numBoxes, 1]);\n const classScores = this.withClassScores\n ? tf.softmax(reshaped.slice([0, 0, 0, 5], [numCells, numCells, numBoxes, this.config.classes.length]), 3)\n : tf.scalar(0);\n return [boxes, scores, classScores];\n });\n\n const results = [] as any;\n\n const scoresData = await scoresTensor.array();\n const boxesData = await boxesTensor.array();\n for (let row = 0; row < numCells; row++) {\n for (let col = 0; col < numCells; col++) {\n for (let anchor = 0; anchor < numBoxes; anchor++) {\n const score = sigmoid(scoresData[row][col][anchor][0]);\n if (!scoreThreshold || score > scoreThreshold) {\n const ctX = ((col + sigmoid(boxesData[row][col][anchor][0])) / numCells) * correctionFactorX;\n const ctY = ((row + sigmoid(boxesData[row][col][anchor][1])) / numCells) * correctionFactorY;\n const widthLocal = ((Math.exp(boxesData[row][col][anchor][2]) * this.config.anchors[anchor].x) / numCells) * correctionFactorX;\n const heightLocal = ((Math.exp(boxesData[row][col][anchor][3]) * this.config.anchors[anchor].y) / numCells) * correctionFactorY;\n\n const x = (ctX - (widthLocal / 2));\n const y = (ctY - (heightLocal / 2));\n\n const pos = { row, col, anchor };\n const { classScore, label } = this.withClassScores\n ? await this.extractPredictedClass(classScoresTensor as tf.Tensor4D, pos)\n : { classScore: 1, label: 0 };\n\n results.push({\n box: new BoundingBox(x, y, x + widthLocal, y + heightLocal),\n score,\n classScore: score * classScore,\n label,\n ...pos,\n });\n }\n }\n }\n }\n\n boxesTensor.dispose();\n scoresTensor.dispose();\n classScoresTensor.dispose();\n\n return results;\n }\n\n private async extractPredictedClass(classesTensor: tf.Tensor4D, pos: { row: number, col: number, anchor: number }) {\n const { row, col, anchor } = pos;\n const classesData = await classesTensor.array();\n return Array(this.config.classes.length).fill(0)\n .map((_, i) => classesData[row][col][anchor][i])\n .map((classScore, label) => ({\n classScore,\n label,\n }))\n .reduce((max, curr) => (max.classScore > curr.classScore ? max : curr));\n }\n}\n", "import { Point } from '../classes/Point';\n\nexport type TinyYolov2Config = {\n withSeparableConvs: boolean\n iouThreshold: number\n anchors: Point[]\n classes: string[]\n meanRgb?: [number, number, number]\n withClassScores?: boolean,\n filterSizes?: number[]\n isFirstLayerConv2d?: boolean\n}\n\nconst isNumber = (arg: any) => typeof arg === 'number';\n\nexport function validateConfig(config: any) {\n if (!config) {\n throw new Error(`invalid config: ${config}`);\n }\n\n if (typeof config.withSeparableConvs !== 'boolean') {\n throw new Error(`config.withSeparableConvs has to be a boolean, have: ${config.withSeparableConvs}`);\n }\n\n if (!isNumber(config.iouThreshold) || config.iouThreshold < 0 || config.iouThreshold > 1.0) {\n throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${config.iouThreshold}`);\n }\n\n if (\n !Array.isArray(config.classes)\n || !config.classes.length\n || !config.classes.every((c: any) => typeof c === 'string')\n ) {\n throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(config.classes)}`);\n }\n\n if (\n !Array.isArray(config.anchors)\n || !config.anchors.length\n || !config.anchors.map((a: any) => a || {}).every((a: any) => isNumber(a.x) && isNumber(a.y))\n ) {\n throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(config.anchors)}`);\n }\n\n if (config.meanRgb && (\n !Array.isArray(config.meanRgb)\n || config.meanRgb.length !== 3\n || !config.meanRgb.every(isNumber)\n )) {\n throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(config.meanRgb)}`);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { leaky } from './leaky';\nimport { ConvWithBatchNorm } from './types';\n\nexport function convWithBatchNorm(x: tf.Tensor4D, params: ConvWithBatchNorm): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n\n out = tf.conv2d(out, params.conv.filters, [1, 1], 'valid');\n out = tf.sub(out, params.bn.sub);\n out = tf.mul(out, params.bn.truediv);\n out = tf.add(out, params.conv.bias);\n\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function leaky(x: tf.Tensor4D): tf.Tensor4D {\n return tf.tidy(() => {\n const min = tf.mul(x, tf.scalar(0.10000000149011612));\n return tf.add(tf.relu(tf.sub(x, min)), min);\n // return tf.maximum(x, min)\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from '../common/types';\nimport { leaky } from './leaky';\n\nexport function depthwiseSeparableConv(x: tf.Tensor4D, params: SeparableConvParams): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n\n out = tf.separableConv2d(out, params.depthwise_filter, params.pointwise_filter, [1, 1], 'valid');\n out = tf.add(out, params.bias);\n\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { extractConvParamsFactory } from '../common/index';\nimport { extractSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightsFactory } from '../common/extractWeightsFactory';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n\n function extractBatchNormParams(size: number, mappedPrefix: string): BatchNorm {\n const sub = tf.tensor1d(extractWeights(size));\n const truediv = tf.tensor1d(extractWeights(size));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/sub` },\n { paramPath: `${mappedPrefix}/truediv` },\n );\n\n return { sub, truediv };\n }\n\n function extractConvWithBatchNormParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv`);\n const bn = extractBatchNormParams(channelsOut, `${mappedPrefix}/bn`);\n\n return { conv, bn };\n }\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParams(\n weights: Float32Array,\n config: TinyYolov2Config,\n boxEncodingSize: number,\n filterSizes: number[],\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n\n const conv0 = config.isFirstLayerConv2d\n ? extractConvParams(s0, s1, 3, 'conv0')\n : extractSeparableConvParams(s0, s1, 'conv0');\n const conv1 = extractSeparableConvParams(s1, s2, 'conv1');\n const conv2 = extractSeparableConvParams(s2, s3, 'conv2');\n const conv3 = extractSeparableConvParams(s3, s4, 'conv3');\n const conv4 = extractSeparableConvParams(s4, s5, 'conv4');\n const conv5 = extractSeparableConvParams(s5, s6, 'conv5');\n const conv6 = s7 ? extractSeparableConvParams(s6, s7, 'conv6') : undefined;\n const conv7 = s8 ? extractSeparableConvParams(s7, s8, 'conv7') : undefined;\n const conv8 = extractConvParams(s8 || s7 || s6, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n } else {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = extractConvWithBatchNormParams(s0, s1, 'conv0');\n const conv1 = extractConvWithBatchNormParams(s1, s2, 'conv1');\n const conv2 = extractConvWithBatchNormParams(s2, s3, 'conv2');\n const conv3 = extractConvWithBatchNormParams(s3, s4, 'conv3');\n const conv4 = extractConvWithBatchNormParams(s4, s5, 'conv4');\n const conv5 = extractConvWithBatchNormParams(s5, s6, 'conv5');\n const conv6 = extractConvWithBatchNormParams(s6, s7, 'conv6');\n const conv7 = extractConvWithBatchNormParams(s7, s8, 'conv7');\n const conv8 = extractConvParams(s8, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n }\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from '../common/index';\nimport { disposeUnusedWeightTensors } from '../common/disposeUnusedWeightTensors';\nimport { loadSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightEntryFactory } from '../common/extractWeightEntryFactory';\nimport { ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractBatchNormParams(prefix: string): BatchNorm {\n const sub = extractWeightEntry(`${prefix}/sub`, 1);\n const truediv = extractWeightEntry(`${prefix}/truediv`, 1);\n return { sub, truediv };\n }\n\n function extractConvParams(prefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { filters, bias };\n }\n\n function extractConvWithBatchNormParams(prefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(`${prefix}/conv`);\n const bn = extractBatchNormParams(`${prefix}/bn`);\n return { conv, bn };\n }\n\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n config: TinyYolov2Config,\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n // eslint-disable-next-line no-mixed-operators\n const numFilters = (config.filterSizes && config.filterSizes.length || 9);\n params = {\n conv0: config.isFirstLayerConv2d ? extractConvParams('conv0') : extractSeparableConvParams('conv0'),\n conv1: extractSeparableConvParams('conv1'),\n conv2: extractSeparableConvParams('conv2'),\n conv3: extractSeparableConvParams('conv3'),\n conv4: extractSeparableConvParams('conv4'),\n conv5: extractSeparableConvParams('conv5'),\n conv6: numFilters > 7 ? extractSeparableConvParams('conv6') : undefined,\n conv7: numFilters > 8 ? extractSeparableConvParams('conv7') : undefined,\n conv8: extractConvParams('conv8'),\n };\n } else {\n params = {\n conv0: extractConvWithBatchNormParams('conv0'),\n conv1: extractConvWithBatchNormParams('conv1'),\n conv2: extractConvWithBatchNormParams('conv2'),\n conv3: extractConvWithBatchNormParams('conv3'),\n conv4: extractConvWithBatchNormParams('conv4'),\n conv5: extractConvWithBatchNormParams('conv5'),\n conv6: extractConvWithBatchNormParams('conv6'),\n conv7: extractConvWithBatchNormParams('conv7'),\n conv8: extractConvParams('conv8'),\n };\n }\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "export interface ITinyYolov2Options {\n inputSize?: number\n scoreThreshold?: number\n}\n\nexport class TinyYolov2Options {\n protected _name: string = 'TinyYolov2Options'\n\n private _inputSize: number\n\n private _scoreThreshold: number\n\n constructor({ inputSize, scoreThreshold }: ITinyYolov2Options = {}) {\n this._inputSize = inputSize || 416;\n this._scoreThreshold = scoreThreshold || 0.5;\n\n if (typeof this._inputSize !== 'number' || this._inputSize % 32 !== 0) {\n throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);\n }\n\n if (typeof this._scoreThreshold !== 'number' || this._scoreThreshold <= 0 || this._scoreThreshold >= 1) {\n throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`);\n }\n }\n\n get inputSize(): number { return this._inputSize; }\n\n get scoreThreshold(): number { return this._scoreThreshold; }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/types';\nimport { TNetInput } from '../dom/types';\nimport {\n BOX_ANCHORS,\n BOX_ANCHORS_SEPARABLE,\n DEFAULT_MODEL_NAME,\n DEFAULT_MODEL_NAME_SEPARABLE_CONV,\n IOU_THRESHOLD,\n MEAN_RGB_SEPARABLE,\n} from './const';\nimport { TinyYolov2Base } from './TinyYolov2Base';\nimport { ITinyYolov2Options } from './TinyYolov2Options';\nimport { TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2 extends TinyYolov2Base {\n constructor(withSeparableConvs: boolean = true) {\n const config = {\n withSeparableConvs,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n ...(withSeparableConvs\n ? {\n anchors: BOX_ANCHORS_SEPARABLE,\n meanRgb: MEAN_RGB_SEPARABLE,\n }\n : {\n anchors: BOX_ANCHORS,\n withClassScores: true,\n }),\n };\n\n super(config);\n }\n\n public get withSeparableConvs(): boolean {\n return this.config.withSeparableConvs;\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return this.withSeparableConvs ? DEFAULT_MODEL_NAME_SEPARABLE_CONV : DEFAULT_MODEL_NAME;\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { TinyYolov2 } from './TinyYolov2';\n\nexport * from './TinyYolov2Options';\n\nexport * from './config';\nexport * from './types';\n\nexport { TinyYolov2 };\n\nexport function createTinyYolov2(weights: Float32Array, withSeparableConvs: boolean = true) {\n const net = new TinyYolov2(withSeparableConvs);\n net.extractWeights(weights);\n return net;\n}\n", "import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\n\nexport interface ITinyFaceDetectorOptions extends ITinyYolov2Options {}\n\nexport class TinyFaceDetectorOptions extends TinyYolov2Options {\n protected _name: string = 'TinyFaceDetectorOptions'\n}\n", "export class ComposableTask {\n public async then(\n // eslint-disable-next-line no-unused-vars\n onfulfilled: (value: T) => T | PromiseLike,\n ): Promise {\n return onfulfilled(await this.run());\n }\n\n public async run(): Promise {\n throw new Error('ComposableTask - run is not implemented');\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class DetectFaceLandmarksTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected useTinyLandmarkNet: boolean,\n ) {\n super();\n }\n\n protected get landmarkNet(): FaceLandmark68Net | FaceLandmark68TinyNet {\n return this.useTinyLandmarkNet\n ? nets.faceLandmark68TinyNet\n : nets.faceLandmark68Net;\n }\n}\n\nexport class DetectAllFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n const detections = parentResults.map((res) => res.detection);\n\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, detections)\n : await extractFaces(this.input, detections);\n\n const faceLandmarksByFace = await Promise.all(faces.map(\n (face) => this.landmarkNet.detectLandmarks(face),\n )) as FaceLandmarks68[];\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return parentResults.map((parentResult, i) => extendWithFaceLandmarks(parentResult, faceLandmarksByFace[i]));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class DetectSingleFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { detection } = parentResult;\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, [detection])\n : await extractFaces(this.input, [detection]);\n\n const landmarks = await this.landmarkNet.detectLandmarks(faces[0]) as FaceLandmarks68;\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return extendWithFaceLandmarks(parentResult, landmarks);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\n\nexport async function extractAllFacesAndComputeResults, TResult>(\n parentResults: TSource[],\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResults: (faces: Array) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment: (parentResult: WithFaceLandmarks) => FaceDetection = ({ alignedRect }) => alignedRect,\n) {\n const faceBoxes = parentResults.map((parentResult) => (isWithFaceLandmarks(parentResult)\n ? getRectForAlignment(parentResult)\n : parentResult.detection));\n const faces: Array = extractedFaces || (\n input instanceof tf.Tensor\n ? await extractFaceTensors(input, faceBoxes)\n : await extractFaces(input, faceBoxes)\n );\n\n const results = await computeResults(faces);\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return results;\n}\n\nexport async function extractSingleFaceAndComputeResult, TResult>(\n parentResult: TSource,\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResult: (face: HTMLCanvasElement | tf.Tensor3D) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment?: (parentResultLocal: WithFaceLandmarks) => FaceDetection,\n) {\n return extractAllFacesAndComputeResults(\n [parentResult],\n input,\n async (faces) => computeResult(faces[0]),\n extractedFaces,\n getRectForAlignment,\n );\n}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB: [number, number, number] = [117.001, 114.697, 97.404];\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/index';\nimport { TNetInput } from '../dom/index';\nimport { ITinyYolov2Options } from '../tinyYolov2/index';\nimport { TinyYolov2Base } from '../tinyYolov2/TinyYolov2Base';\nimport { TinyYolov2NetParams } from '../tinyYolov2/types';\nimport { BOX_ANCHORS, IOU_THRESHOLD, MEAN_RGB } from './const';\n\nexport class TinyFaceDetector extends TinyYolov2Base {\n constructor() {\n const config = {\n withSeparableConvs: true,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n anchors: BOX_ANCHORS,\n meanRgb: MEAN_RGB,\n isFirstLayerConv2d: true,\n filterSizes: [3, 16, 32, 64, 128, 256, 512],\n };\n\n super(config);\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_face_detector_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { AgeGenderNet } from '../ageGenderNet/AgeGenderNet';\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressionNet } from '../faceExpressionNet/FaceExpressionNet';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { FaceRecognitionNet } from '../faceRecognitionNet/FaceRecognitionNet';\nimport { SsdMobilenetv1 } from '../ssdMobilenetv1/SsdMobilenetv1';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetector } from '../tinyFaceDetector/TinyFaceDetector';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { ITinyYolov2Options, TinyYolov2 } from '../tinyYolov2/index';\n\nexport const nets = {\n ssdMobilenetv1: new SsdMobilenetv1(),\n tinyFaceDetector: new TinyFaceDetector(),\n tinyYolov2: new TinyYolov2(),\n faceLandmark68Net: new FaceLandmark68Net(),\n faceLandmark68TinyNet: new FaceLandmark68TinyNet(),\n faceRecognitionNet: new FaceRecognitionNet(),\n faceExpressionNet: new FaceExpressionNet(),\n ageGenderNet: new AgeGenderNet(),\n};\n\n/**\n * Attempts to detect all faces in an image using SSD Mobilenetv1 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see SsdMobilenetv1Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const ssdMobilenetv1 = (input: TNetInput, options: SsdMobilenetv1Options): Promise => nets.ssdMobilenetv1.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Face Detector.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyFaceDetectorOptions constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyFaceDetector = (input: TNetInput, options: TinyFaceDetectorOptions): Promise => nets.tinyFaceDetector.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Yolov2 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyYolov2Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyYolov2 = (input: TNetInput, options: ITinyYolov2Options): Promise => nets.tinyYolov2.locateFaces(input, options);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarks = (input: TNetInput): Promise => nets.faceLandmark68Net.detectLandmarks(input);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image\n * using a tinier version of the 68 point face landmark model, which is slightly\n * faster at inference, but also slightly less accurate.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarksTiny = (input: TNetInput): Promise => nets.faceLandmark68TinyNet.detectLandmarks(input);\n\n/**\n * Computes a 128 entry vector (face descriptor / face embeddings) from the face shown in an image,\n * which uniquely represents the features of that persons face. The computed face descriptor can\n * be used to measure the similarity between faces, by computing the euclidean distance of two\n * face descriptors.\n *\n * @param inputs The face image extracted from the aligned bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Face descriptor with 128 entries or array thereof in case of batch input.\n */\nexport const computeFaceDescriptor = (input: TNetInput): Promise => nets.faceRecognitionNet.computeFaceDescriptor(input);\n\n/**\n * Recognizes the facial expressions from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Facial expressions with corresponding probabilities or array thereof in case of batch input.\n */\nexport const recognizeFaceExpressions = (input: TNetInput): Promise => nets.faceExpressionNet.predictExpressions(input);\n\n/**\n * Predicts age and gender from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Predictions with age, gender and gender probability or array thereof in case of batch input.\n */\nexport const predictAgeAndGender = (input: TNetInput): Promise => nets.ageGenderNet.predictAgeAndGender(input);\n\nexport const loadSsdMobilenetv1Model = (url: string) => nets.ssdMobilenetv1.load(url);\nexport const loadTinyFaceDetectorModel = (url: string) => nets.tinyFaceDetector.load(url);\nexport const loadTinyYolov2Model = (url: string) => nets.tinyYolov2.load(url);\nexport const loadFaceLandmarkModel = (url: string) => nets.faceLandmark68Net.load(url);\nexport const loadFaceLandmarkTinyModel = (url: string) => nets.faceLandmark68TinyNet.load(url);\nexport const loadFaceRecognitionModel = (url: string) => nets.faceRecognitionNet.load(url);\nexport const loadFaceExpressionModel = (url: string) => nets.faceExpressionNet.load(url);\nexport const loadAgeGenderModel = (url: string) => nets.ageGenderNet.load(url);\n\n// backward compatibility\nexport const loadFaceDetectionModel = loadSsdMobilenetv1Model;\nexport const locateFaces = ssdMobilenetv1;\nexport const detectLandmarks = detectFaceLandmarks;\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderTask,\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\n\nexport class PredictFaceExpressionsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const faceExpressionsByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map(\n (parentResult, i) => extendWithFaceExpressions(parentResult, faceExpressionsByFace[i]),\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const faceExpressions = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithFaceExpressions(parentResult, faceExpressions);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictAllFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { TNetInput } from '../dom/index';\nimport { extendWithAge, WithAge } from '../factories/WithAge';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { extendWithGender, WithGender } from '../factories/WithGender';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllFaceExpressionsTask,\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class PredictAgeAndGenderTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase>[], TSource[]> {\n public async run(): Promise>[]> {\n const parentResults = await this.parentTask;\n\n const ageAndGenderByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map((parentResult, i) => {\n const { age, gender, genderProbability } = ageAndGenderByFace[i];\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n });\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase> | undefined, TSource | undefined> {\n public async run(): Promise> | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { age, gender, genderProbability } = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictAllAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDescriptor, WithFaceDescriptor } from '../factories/WithFaceDescriptor';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class ComputeFaceDescriptorsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n ) {\n super();\n }\n}\n\nexport class ComputeAllFaceDescriptorsTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const descriptors = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n (faces) => Promise.all(faces.map((face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise)),\n null,\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return descriptors.map((descriptor, i) => extendWithFaceDescriptor(parentResults[i], descriptor));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n\nexport class ComputeSingleFaceDescriptorTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n const descriptor = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise,\n null,\n // eslint-disable-next-line no-shadow\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return extendWithFaceDescriptor(parentResult, descriptor);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { TinyYolov2Options } from '../tinyYolov2/index';\nimport { ComposableTask } from './ComposableTask';\nimport { DetectAllFaceLandmarksTask, DetectSingleFaceLandmarksTask } from './DetectFaceLandmarksTasks';\nimport { nets } from './nets';\nimport { PredictAllAgeAndGenderTask, PredictSingleAgeAndGenderTask } from './PredictAgeAndGenderTask';\nimport { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from './PredictFaceExpressionsTask';\nimport { FaceDetectionOptions } from './types';\n\nexport class DetectFacesTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n ) {\n super();\n }\n}\n\nexport class DetectAllFacesTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const { input, options } = this;\n\n // eslint-disable-next-line no-nested-ternary\n const faceDetectionFunction = options instanceof TinyFaceDetectorOptions\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyFaceDetector.locateFaces(input, options)\n : (\n // eslint-disable-next-line no-nested-ternary\n options instanceof SsdMobilenetv1Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.ssdMobilenetv1.locateFaces(input, options)\n : (\n options instanceof TinyYolov2Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyYolov2.locateFaces(input, options)\n : null\n )\n );\n\n if (!faceDetectionFunction) {\n throw new Error('detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options');\n }\n\n return faceDetectionFunction(input);\n }\n\n private runAndExtendWithFaceDetections(): Promise[]> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise[]>(async (resolve) => {\n const detections = await this.run();\n resolve(detections.map((detection) => extendWithFaceDetection({}, detection)));\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectAllFaceLandmarksTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n}\n\nexport class DetectSingleFaceTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const faceDetections = await new DetectAllFacesTask(this.input, this.options);\n let faceDetectionWithHighestScore = faceDetections[0];\n faceDetections.forEach((faceDetection) => {\n if (faceDetection.score > faceDetectionWithHighestScore.score) {\n faceDetectionWithHighestScore = faceDetection;\n }\n });\n return faceDetectionWithHighestScore;\n }\n\n private runAndExtendWithFaceDetection(): Promise | undefined> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise | undefined>(async (resolve) => {\n const detection = await this.run();\n resolve(detection ? extendWithFaceDetection<{}>({}, detection) : undefined);\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectSingleFaceLandmarksTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n}\n", "import { TNetInput } from '../dom/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { DetectAllFacesTask, DetectSingleFaceTask } from './DetectFacesTasks';\nimport { FaceDetectionOptions } from './types';\n\nexport function detectSingleFace(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectSingleFaceTask {\n return new DetectSingleFaceTask(input, options);\n}\n\nexport function detectAllFaces(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectAllFacesTask {\n return new DetectAllFacesTask(input, options);\n}\n", "import { TNetInput } from '../dom/index';\nimport { WithFaceDescriptor, WithFaceDetection, WithFaceLandmarks } from '../factories/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';\nimport { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\nimport { detectAllFaces } from './detectFaces';\n\n// export allFaces API for backward compatibility\n\nexport async function allFacesSsdMobilenetv1(\n input: TNetInput,\n minConfidence?: number,\n): Promise>>[]> {\n return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport async function allFacesTinyYolov2(\n input: TNetInput,\n forwardParams: ITinyYolov2Options = {},\n): Promise>>[]> {\n return detectAllFaces(input, new TinyYolov2Options(forwardParams))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport const allFaces = allFacesSsdMobilenetv1;\n", "export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {\n if (arr1.length !== arr2.length) throw new Error('euclideanDistance: arr1.length !== arr2.length');\n\n const desc1 = Array.from(arr1);\n const desc2 = Array.from(arr2);\n\n return Math.sqrt(\n desc1\n .map((val, i) => val - desc2[i])\n .reduce((res, diff) => res + (diff ** 2), 0),\n );\n}\n", "import { FaceMatch } from '../classes/FaceMatch';\nimport { LabeledFaceDescriptors } from '../classes/LabeledFaceDescriptors';\nimport { euclideanDistance } from '../euclideanDistance';\nimport { WithFaceDescriptor } from '../factories/index';\n\nexport class FaceMatcher {\n private _labeledDescriptors: LabeledFaceDescriptors[]\n\n private _distanceThreshold: number\n\n constructor(\n inputs: LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>,\n distanceThreshold: number = 0.6,\n ) {\n this._distanceThreshold = distanceThreshold;\n\n const inputArray = Array.isArray(inputs) ? inputs : [inputs];\n\n if (!inputArray.length) {\n throw new Error('FaceRecognizer.constructor - expected atleast one input');\n }\n\n let count = 1;\n const createUniqueLabel = () => `person ${count++}`;\n\n this._labeledDescriptors = inputArray.map((desc) => {\n if (desc instanceof LabeledFaceDescriptors) {\n return desc;\n }\n\n if (desc instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc]);\n }\n\n if (desc.descriptor && desc.descriptor instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc.descriptor]);\n }\n\n throw new Error('FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>');\n });\n }\n\n public get labeledDescriptors(): LabeledFaceDescriptors[] { return this._labeledDescriptors; }\n\n public get distanceThreshold(): number { return this._distanceThreshold; }\n\n public computeMeanDistance(queryDescriptor: Float32Array, descriptors: Float32Array[]): number {\n return descriptors\n .map((d) => euclideanDistance(d, queryDescriptor))\n .reduce((d1, d2) => d1 + d2, 0)\n / (descriptors.length || 1);\n }\n\n public matchDescriptor(queryDescriptor: Float32Array): FaceMatch {\n return this.labeledDescriptors\n .map(({ descriptors, label }) => new FaceMatch(\n label,\n this.computeMeanDistance(queryDescriptor, descriptors),\n ))\n .reduce((best, curr) => (best.distance < curr.distance ? best : curr));\n }\n\n public findBestMatch(queryDescriptor: Float32Array): FaceMatch {\n const bestMatch = this.matchDescriptor(queryDescriptor);\n return bestMatch.distance < this.distanceThreshold\n ? bestMatch\n : new FaceMatch('unknown', bestMatch.distance);\n }\n\n public toJSON(): any {\n return {\n distanceThreshold: this.distanceThreshold,\n labeledDescriptors: this.labeledDescriptors.map((ld) => ld.toJSON()),\n };\n }\n\n public static fromJSON(json: any): FaceMatcher {\n const labeledDescriptors = json.labeledDescriptors\n .map((ld: any) => LabeledFaceDescriptors.fromJSON(ld));\n return new FaceMatcher(labeledDescriptors, json.distanceThreshold);\n }\n}\n", "import { TinyFaceDetector } from './TinyFaceDetector';\n\nexport * from './TinyFaceDetector';\nexport * from './TinyFaceDetectorOptions';\n\nexport function createTinyFaceDetector(weights: Float32Array) {\n const net = new TinyFaceDetector();\n net.extractWeights(weights);\n return net;\n}\n", "import { Dimensions, IDimensions } from './classes/index';\nimport { FaceDetection } from './classes/FaceDetection';\nimport { FaceLandmarks } from './classes/FaceLandmarks';\nimport { extendWithFaceDetection, isWithFaceDetection } from './factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, isWithFaceLandmarks } from './factories/WithFaceLandmarks';\n\nexport function resizeResults(results: T, dimensions: IDimensions): T {\n const { width, height } = new Dimensions(dimensions.width, dimensions.height);\n\n if (width <= 0 || height <= 0) {\n throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({ width, height })}`);\n }\n\n if (Array.isArray(results)) {\n // return results.map(obj => resizeResults(obj, { width, height })) as any as T\n return (results as Array).map((obj) => resizeResults(obj, { width, height } as IDimensions)) as any as T;\n }\n\n if (isWithFaceLandmarks(results)) {\n const resizedDetection = results.detection.forSize(width, height);\n const resizedLandmarks = results.unshiftedLandmarks.forSize(resizedDetection.box.width, resizedDetection.box.height);\n return extendWithFaceLandmarks(extendWithFaceDetection(results, resizedDetection), resizedLandmarks);\n }\n\n if (isWithFaceDetection(results)) {\n return extendWithFaceDetection(results, results.detection.forSize(width, height));\n }\n\n if (results instanceof FaceLandmarks || results instanceof FaceDetection) {\n return (results as any).forSize(width, height);\n }\n\n return results;\n}\n"], - "mappings": ";;;;;;;wlCAGA,GAAA,GAAc,GAAA,qCCHd,6CAAO,cACL,MAAO,OAAO,SAAW,UACpB,IACA,MAAO,KAAW,aAGlB,MAAO,UAAY,aAAe,CAAC,CAAC,QAAQ,WCNnD,6xFAAA,OAAoB,OCApB,qRCEO,YACL,EACA,EACA,EAAoB,IAUpB,GARA,EAAI,YAEJ,EAAO,MAAM,GAAG,QAAQ,CAAC,CAAE,IAAG,KAAK,KACjC,GAAM,GAAO,EAAO,GACpB,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,KAGZ,GACF,GAAM,GAAO,EAAO,EAAO,OAAS,GAC9B,EAAK,EAAO,GAClB,GAAI,CAAC,GAAQ,CAAC,EACZ,OAGF,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,EAAG,EAAG,GAGtB,EAAI,SC1BN,2RAAA,OAAoB,OCApB,YAYE,YAAY,EAAe,GACzB,GAAI,CAAC,GAAc,IAAU,CAAC,GAAc,GAC1C,KAAM,IAAI,OAAM,wFAAwF,KAAK,UAAU,CAAE,QAAO,cAGlI,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,QAEnC,UACL,MAAO,IAAI,GAAW,EAAI,KAAK,MAAO,EAAI,KAAK,UDrB5C,YAAkB,EAAa,GACpC,MAAO,aAAqB,YAAU,EAAO,MAAM,SAAW,EAGzD,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,WAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAiB,GACtB,MAAO,GAAM,GAAM,EAGd,YAAgB,GACrB,MAAO,GAAM,GAAM,EAGd,YAAe,EAAa,EAAe,GAChD,GAAM,GAAI,IAAM,EAChB,MAAO,MAAK,MAAM,EAAM,GAAK,EAGxB,YAAsB,GAC3B,MAAO,IAAO,EAAI,OAAS,EAAI,OAG1B,YAAmC,CAAE,QAAO,UAAuB,GACxE,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,IAAI,GAAW,KAAK,MAAM,EAAQ,GAAQ,KAAK,MAAM,EAAS,IAGhE,YAAwB,GAC7B,MAAO,GAAI,OAAO,CAAC,EAAK,IAAO,EAAI,IAAI,GAAK,GAAI,GAAM,EAAG,IACtD,IAAI,GAAI,GAAM,EAAI,OAAQ,EAAI,SAG5B,YAAe,EAAa,EAAe,GAChD,MAAO,OAAM,GAAK,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,EAAS,EAAI,GAGhD,YAAuB,GAE5B,MAAO,CAAC,CAAC,GAAQ,IAAQ,UAAc,IAAQ,WAAc,CAAC,OAAO,MAAM,IAAQ,IAAQ,EAGtF,YAA4B,GACjC,MAAO,IAAc,IAAQ,GAAO,GAAK,GAAO,EE9DlD,YAUE,YAAY,EAAW,GACrB,KAAK,GAAK,EACV,KAAK,GAAK,KAGR,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,GAEvB,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,MACL,MAAO,IAAI,GAAM,KAAK,IAAI,KAAK,GAAI,KAAK,IAAI,KAAK,IAG5C,YACL,MAAO,MAAK,KAAM,KAAK,GAAK,EAAM,KAAK,GAAK,GAGvC,QACL,MAAO,IAAI,GAAM,KAAK,MAAM,KAAK,GAAI,KAAK,MAAM,KAAK,MC5CzD,kBAOgB,QAAO,GACnB,MAAO,CAAC,CAAC,GAAQ,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,MAAO,EAAK,QAAQ,MAAM,UAGrD,kBAAiB,EAAU,EAAgB,EAAmC,IAC1F,GAAI,CAAC,EAAI,OAAO,GACd,KAAM,IAAI,OAAM,GAAG,oBAAyB,KAAK,UAAU,2DAG7D,GAAI,CAAC,GAA4B,GAAI,MAAQ,GAAK,EAAI,OAAS,GAC7D,KAAM,IAAI,OAAM,GAAG,cAAmB,EAAI,sBAAsB,EAAI,oCAYxE,YAAY,EAA4B,EAAmC,IACzE,GAAM,GAAO,GAAQ,GAEf,EAAS,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAO,EAAI,QAAQ,MAAM,IAC1D,EAAS,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAAQ,MAAM,IAE3D,GAAI,CAAC,GAAU,CAAC,EACd,KAAM,IAAI,OAAM,2EAA2E,KAAK,UAAU,MAG5G,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,EAC1B,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAC9B,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAQ,EAAI,KAAM,EAAI,OAAS,EAAI,KAE/D,EAAI,iBAAiB,CACnB,IAAG,IAAG,QAAO,UACZ,kBAAmB,GAEtB,KAAK,GAAK,EACV,KAAK,GAAK,EACV,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,MAE1B,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,WAE/B,QAAiB,MAAO,MAAK,KAE7B,OAAgB,MAAO,MAAK,KAE5B,SAAkB,MAAO,MAAK,EAAI,KAAK,SAEvC,UAAmB,MAAO,MAAK,EAAI,KAAK,UAExC,QAAiB,MAAO,MAAK,MAAQ,KAAK,UAE1C,WAAmB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,QAEpD,YAAoB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAEtD,cAAsB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,WAEvD,eAAuB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAE7D,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,WACL,GAAI,CACF,IAAG,IAAG,QAAO,UACX,KACE,EAAO,KAAK,IAAI,EAAQ,GAC9B,MAAI,GAAQ,GACV,IAAM,EAAO,EACb,GAAS,GAEP,EAAS,GACX,IAAM,EAAO,EACb,GAAU,GAGL,GAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QAAQ,GACb,GAAM,GAAS,GAAa,GAAM,EAAkB,MAAQ,EACtD,EAAS,GAAa,GAAM,EAAkB,OAAS,EAC7D,MAAO,IAAI,GAAI,CACb,EAAG,KAAK,EAAI,EACZ,EAAG,KAAK,EAAI,EACZ,MAAO,KAAK,MAAQ,EACpB,OAAQ,KAAK,OAAS,IAInB,IAAI,EAAc,GACvB,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAC5B,KAAK,EAAK,EAAO,EACjB,KAAK,EAAK,EAAO,EACjB,KAAK,MAAQ,EACb,KAAK,OAAS,GAEhB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,mBAAmB,EAAkB,GAC1C,GAAM,CACJ,IAAG,IAAG,QAAO,UACX,KACE,EAAW,KAAK,IAAI,EAAG,GACvB,EAAW,KAAK,IAAI,EAAG,GAEvB,EAAW,EAAQ,EACnB,EAAY,EAAS,EACrB,EAAe,KAAK,IAAI,EAAU,EAAW,GAC7C,EAAgB,KAAK,IAAI,EAAW,EAAY,GAEtD,MAAQ,IAAI,GAAI,CACd,EAAG,EAAU,EAAG,EAAU,MAAO,EAAc,OAAQ,IACrD,QAGC,MAAM,EAAY,GACvB,GAAM,CAAE,QAAO,UAAW,KACpB,EAAI,KAAK,EAAI,EACb,EAAI,KAAK,EAAI,EAEnB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,aAAa,EAAqB,GACvC,GAAM,GAAI,KAAK,MAAQ,EACjB,EAAI,KAAK,OAAS,EAElB,EAAK,EACL,EAAK,EACP,EAAM,EACN,EAAM,EAEN,EAAI,KAAK,KACT,EAAI,KAAK,IACT,EAAK,KAAK,MACV,EAAK,KAAK,OAEd,MAAI,GAAK,GACP,GAAM,CAAC,EAAK,EAAa,EACzB,EAAK,GAEH,EAAK,GACP,GAAM,CAAC,EAAK,EAAc,EAC1B,EAAK,GAEH,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAEF,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAGC,CACL,KAAI,MAAK,KAAI,MAAK,IAAG,KAAI,IAAG,KAAI,IAAG,KAIhC,UAAU,GACf,MAAO,IAAI,GAAI,CACb,KAAM,KAAK,KAAQ,EAAO,KAAO,KAAK,MACtC,IAAK,KAAK,IAAO,EAAO,IAAM,KAAK,OACnC,MAAO,KAAK,MAAS,EAAO,MAAQ,KAAK,MACzC,OAAQ,KAAK,OAAU,EAAO,OAAS,KAAK,SAC3C,WAAW,UC9MlB,oBASiC,GAC/B,YAAY,EAAc,EAAa,EAAe,EAAgB,EAAmC,IACvG,MAAM,CACJ,OAAM,MAAK,QAAO,UACjB,KCbP,aAeE,YACE,EACA,EACA,EACA,EACA,GAEA,KAAK,WAAa,GAAI,GAAW,EAAU,MAAO,EAAU,QAC5D,KAAK,OAAS,EACd,KAAK,YAAc,EACnB,KAAK,WAAa,EAClB,KAAK,KAAO,GAAI,GAAI,GAAa,QAAQ,KAAK,eAGrC,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,eAEnC,aAAsB,MAAO,MAAK,cAElC,OAAa,MAAO,MAAK,QAEzB,aAA0B,MAAO,MAAK,cAEtC,cAAuB,MAAO,MAAK,UAAU,SAE7C,eAAwB,MAAO,MAAK,UAAU,UAE9C,eAAqB,MAAO,IAAI,GAAI,KAAK,MAAM,QAAQ,KAAK,UAAU,WAE1E,QAAQ,EAAe,GAC5B,MAAO,IAAI,IACT,KAAK,MACL,KAAK,WACL,KAAK,UACL,KAAK,YACL,CAAE,QAAO,aCnDf,mBAUmC,IACjC,YACE,EACA,EACA,GAEA,MAAM,EAAO,EAAO,GAAI,EAAa,GAGhC,QAAQ,EAAe,GAC5B,GAAM,CAAE,QAAO,cAAa,aAAc,MAAM,QAAQ,EAAO,GAC/D,MAAO,IAAI,GAAc,EAAO,EAAa,KCnB1C,YAAa,EAAW,EAAW,EAAiB,IACzD,GAAM,GAAQ,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,MAAO,EAAK,OAAS,KAAK,IAAI,EAAK,KAAM,EAAK,OAClF,EAAS,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,OAAQ,EAAK,QAAU,KAAK,IAAI,EAAK,IAAK,EAAK,MACpF,EAAe,EAAQ,EAE7B,MAAO,GACH,EAAgB,GAAK,KAAO,EAAK,KAAO,GACxC,EAAe,KAAK,IAAI,EAAK,KAAM,EAAK,MCPvC,YAAiB,GACtB,GAAM,GAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAExD,MAAO,IAAI,IAAY,EAAM,EAAM,EAAM,GCPpC,YACL,EACA,EACA,EACA,EAAiB,IAEjB,GAAI,GAAuB,EACxB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAC/B,IAAI,AAAC,GAAM,EAAE,UAEV,EAAiB,GAEvB,KAAO,EAAqB,OAAS,IACnC,GAAM,GAAO,EAAqB,MAClC,EAAK,KAAK,GAEV,GAAM,GAAU,EAEV,EAAoB,GAC1B,OAAS,GAAI,EAAG,EAAI,EAAQ,OAAQ,KAClC,GAAM,GAAM,EAAQ,GAEd,EAAU,EAAM,GAChB,EAAS,EAAM,GAErB,EAAQ,KAAK,GAAI,EAAS,EAAQ,IAGpC,EAAuB,EAAqB,OAC1C,CAAC,EAAG,IAAM,EAAQ,IAAM,GAI5B,MAAO,GCrCT,OAAoB,OAEb,YAAmB,EAAgB,GACxC,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAG,EAAG,GAAK,EACZ,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAU,AAAG,UAAO,CAAC,EAAO,EAAO,GAAQ,GAEjD,MAAO,AAAG,QAAI,EAAG,KCVrB,OAAoB,OAUb,YACL,EACA,EAAyB,IAEzB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAQ,GAAS,EAAU,MAAM,MAAM,GAC9C,GAAI,IAAW,EACb,MAAO,GAGT,GAAM,GAAU,KAAK,IAAI,EAAS,GAC5B,EAAgB,KAAK,MAAM,EAAW,GAAgB,GAAM,IAC5D,EAAc,EAAS,EAAQ,EAAI,EAEnC,EAAsB,AAAC,IAC3B,GAAM,GAAqB,EAAU,MAAM,QAC3C,SAAmB,GAAe,EAC3B,AAAG,QAAK,EAAoB,EAAG,YAGlC,EAAsB,EAAoB,GAC1C,EAAyB,EAAW,EAAoB,MAAM,GAM9D,EAAiB,CAJM,GAAiB,EAC1C,EAAoB,GACpB,KAIF,EACA,GAEC,OAAO,AAAC,GAAM,CAAC,CAAC,GAEhB,IAAI,AAAC,GAAiB,AAAG,QAAK,EAAG,YACpC,MAAO,AAAG,WAAO,EAAgB,KC7C9B,YAAsB,GAC3B,GAAM,GAAQ,EAAW,QACzB,OAAS,GAAI,EAAM,OAAS,EAAG,EAAI,EAAG,KACpC,GAAM,GAAI,KAAK,MAAM,KAAK,SAAY,GAAI,IACpC,EAAI,EAAM,GAChB,EAAM,GAAK,EAAM,GACjB,EAAM,GAAK,EAEb,MAAO,GCDF,YAAiB,GACtB,MAAO,GAAK,GAAI,KAAK,IAAI,CAAC,IAGrB,YAAwB,GAC7B,MAAO,MAAK,IAAI,EAAK,GAAI,ICZ3B,oBAS0B,GACxB,YAAY,EAAW,EAAW,EAAe,EAAgB,EAAmC,IAClG,MAAM,CACJ,IAAG,IAAG,QAAO,UACZ,KCHP,GAAM,IAAO,GACP,GAAO,IACP,GAAW,IAZjB,QA0BE,YACE,EACA,EACA,EAAe,GAAI,GAAM,EAAG,IAE5B,GAAM,CAAE,QAAO,UAAW,EAC1B,KAAK,SAAW,GAAI,GAAW,EAAO,GACtC,KAAK,OAAS,EACd,KAAK,WAAa,EAA8B,IAC9C,AAAC,GAAO,EAAG,IAAI,GAAI,GAAM,EAAO,IAAS,IAAI,OAItC,SAAiB,MAAO,IAAI,GAAM,KAAK,OAAO,EAAG,KAAK,OAAO,MAE7D,cAAuB,MAAO,MAAK,SAAS,SAE5C,eAAwB,MAAO,MAAK,SAAS,UAE7C,aAAuB,MAAO,MAAK,cAEnC,qBACT,MAAO,MAAK,WAAW,IACrB,AAAC,GAAO,EAAG,IAAI,KAAK,QAAQ,IAAI,GAAI,GAAM,KAAK,WAAY,KAAK,eAI7D,QAAiC,EAAe,GACrD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,CAAE,QAAO,WAIN,QAAiC,EAAW,GACjD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,KAAK,SACL,GAAI,GAAM,EAAG,IAIV,aAAsC,GAC3C,MAAO,MAAK,QAAQ,EAAG,EAAG,EAAG,GAcxB,MACL,EACA,EAAkE,IAElE,GAAI,GACF,GAAM,GAAM,YAAqB,GAC7B,EAAU,IAAI,QACd,GAAI,GAAI,GAEZ,MAAO,MAAK,QAAQ,EAAI,EAAG,EAAI,GAAG,MAAM,KAAM,GAGhD,GAAM,CAAE,mBAAkB,iBAAkB,CAAE,iBAAkB,GAAO,cAAe,MAAQ,GAE9F,MAAI,GACK,KAAK,YAGP,KAAK,aAAa,GAGnB,YACN,GAAM,GAAU,KAAK,2BAEf,CAAC,EAAe,EAAgB,GAAe,EAC/C,EAAc,AAAC,GAAc,EAAY,IAAI,GAAI,YACjD,EAAkB,GAAY,GAAiB,EAAY,IAAmB,EAE9E,EAAO,KAAK,MAAM,EAAiB,IAEnC,EAAW,GAAe,GAE1B,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAChD,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAEtD,MAAO,IAAI,IAAK,EAAG,EAAG,KAAK,IAAI,EAAM,KAAK,WAAa,GAAI,KAAK,IAAI,EAAM,KAAK,YAAc,IAGvF,aAAa,GACnB,GAAM,GAAM,GAAQ,KAAK,WACzB,MAAO,GAAI,IAAI,EAAI,MAAQ,EAAS,EAAI,OAAS,GAGzC,2BACR,KAAM,IAAI,OAAM,4DC/HpB,oBAIoC,GACxB,2BACR,GAAM,GAAM,KAAK,UACjB,MAAO,CACL,EAAI,GACJ,EAAI,GACJ,GAAe,CAAC,EAAI,GAAI,EAAI,QCVlC,oBAIqC,GAC5B,gBACL,MAAO,MAAK,UAAU,MAAM,EAAG,IAG1B,iBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,kBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,UACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,aACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,cACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,WACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAGxB,2BACR,MAAO,CACL,KAAK,aACL,KAAK,cACL,KAAK,YACL,IAAI,MCtCV,aAYE,YAAY,EAAe,GACzB,KAAK,OAAS,EACd,KAAK,UAAY,KAGR,SAAkB,MAAO,MAAK,UAE9B,YAAqB,MAAO,MAAK,UAErC,SAAS,EAAwB,IACtC,MAAO,GAAG,KAAK,QAAQ,EAAe,KAAK,GAAM,KAAK,aAAe,OCtBzE,oBAKgC,SAChB,yBAAwB,EAAU,GAG9C,GAFA,EAAI,iBAAiB,EAAK,GAEtB,CAAC,GAAc,EAAI,OACrB,KAAM,IAAI,OAAM,GAAG,gCAAqC,EAAI,yBAMhE,YAAY,EAAiC,GAC3C,MAAM,GACN,KAAK,OAAS,KAGL,SAAkB,MAAO,MAAK,SCrB3C,aAKE,YAAY,EAAe,GACzB,GAAM,MAAO,IAAU,SACrB,KAAM,IAAI,OAAM,sEAGlB,GAAI,CAAC,MAAM,QAAQ,IAAgB,EAAY,KAAK,AAAC,GAAS,CAAE,aAAgB,gBAC9E,KAAM,IAAI,OAAM,4FAGlB,KAAK,OAAS,EACd,KAAK,aAAe,KAGX,SAAkB,MAAO,MAAK,UAE9B,eAAgC,MAAO,MAAK,aAEhD,SACL,MAAO,CACL,MAAO,KAAK,MACZ,YAAa,KAAK,YAAY,IAAI,AAAC,GAAM,MAAM,KAAK,WAI1C,UAAS,GACrB,GAAM,GAAc,EAAK,YAAY,IAAI,AAAC,GAAW,GAAI,cAAa,IACtE,MAAO,IAAI,IAAuB,EAAK,MAAO,KC/BlD,oBAKkC,UAClB,2BAA0B,EAAU,GAGhD,GAFA,GAAW,wBAAwB,EAAK,GAGtC,CAAC,GAAmB,EAAI,QACrB,CAAC,GAAmB,EAAI,YAE3B,KAAM,IAAI,OAAM,GAAG,kCAAuC,EAAI,eAAe,EAAI,6CAQrF,YAAY,EAAiC,EAAe,EAAe,GACzE,MAAM,EAAK,GACX,KAAK,OAAS,EACd,KAAK,YAAc,KAGV,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,cCvBzC,YAA6B,GAClC,MAAO,GAAI,oBAAqB,GAG3B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,cCdf,cACL,GAAM,GAAQ,OAAO,MACrB,GAAI,CAAC,EAAO,KAAM,IAAI,OAAM,gEAE5B,GAAM,GAAW,KACf,KAAM,IAAI,OAAM,gEAGlB,MAAO,CACL,OAAQ,kBACR,yBACA,MAAO,iBACP,UACA,MAAO,iBACP,oBAAqB,IAAM,SAAS,cAAc,UAClD,mBAAoB,IAAM,SAAS,cAAc,OACjD,QACA,YCjBG,YAA0B,GAC/B,GAAI,GAAiB,GAErB,GAAI,CAAC,EACH,IAEE,EAAa,oBACN,GACP,EAAiB,EAAI,WAYzB,MAAO,CACL,SATe,EACb,AAAC,GAAqB,GAAI,SAAgB,CAAC,EAAS,KACpD,EAAG,SAAS,EAAU,CAAC,EAAU,IAAoB,EAAM,EAAO,GAAO,EAAQ,MAEjF,KACA,KAAM,IAAI,OAAM,qEAAqE,OCfpF,cAEL,GAAM,GAAS,OAAO,QAAa,OAAO,kBACpC,EAAQ,OAAO,OAAS,OAAO,iBAE/B,EAAsB,KAC1B,GAAI,EAAQ,MAAO,IAAI,GACvB,KAAM,IAAI,OAAM,+EAGZ,EAAqB,KACzB,GAAI,EAAO,MAAO,IAAI,GACtB,KAAM,IAAI,OAAM,6EAGZ,EAAQ,OAAO,MAGf,EAAa,KAEnB,MAAO,CACL,OAAQ,GAAU,QAClB,yBAA0B,OAAO,0BAA4B,QAC7D,MAAO,GAAS,QAChB,UAAW,OAAO,WAAa,QAC/B,MAAO,OAAO,kBAAoB,QAClC,sBACA,qBACA,WACG,GCjCA,cACL,MAAO,OAAO,SAAW,UACpB,MAAO,WAAa,aACpB,MAAO,mBAAqB,aAC5B,MAAO,oBAAsB,aAC7B,MAAO,mBAAqB,aAC5B,MAAO,YAAc,aACrB,MAAO,2BAA6B,YCH3C,OAAyB,QAGrB,EAEJ,cACE,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,yEAElB,MAAO,GAGT,YAAgB,GACd,EAAc,EAGhB,cAGE,MAAI,MAAoB,GAAO,MAC3B,cAAmB,GAAO,MACvB,KAGT,YAAqB,GAKnB,GAJK,GACH,KAGE,CAAC,EACH,KAAM,IAAI,OAAM,8EAGlB,GAAM,CAAE,SAAS,EAAY,OAAQ,QAAQ,EAAY,OAAU,EACnE,EAAY,OAAS,EACrB,EAAY,MAAQ,EACpB,EAAY,oBAAsB,EAAI,qBAAwB,KAAM,GAAI,IACxE,EAAY,mBAAqB,EAAI,oBAAuB,KAAM,GAAI,IAEtE,EAAY,UAAY,EAAI,WAAa,EAAY,UACrD,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,SAAW,EAAI,UAAY,EAAY,SAG9C,GAAM,GAAM,CACjB,UACA,UACA,cACA,oBACA,oBACA,mBACA,eACA,aACA,sBAGF,KC3DO,YAAsB,GAC3B,MAAI,CAAC,EAAI,YAAc,MAAO,IAAQ,SAC7B,SAAS,eAAe,GAE1B,ECHF,WAA6B,GAClC,GAAM,CAAE,SAAQ,4BAA6B,EAAI,SAEjD,GAAI,YAAqB,GACvB,MAAO,GAGT,GAAM,GAAS,GAAa,GAE5B,GAAI,CAAE,aAAkB,IACtB,KAAM,IAAI,OAAM,kEAGlB,GAAM,GAAM,EAAO,WAAW,MAC9B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,GCfF,GAAK,IAAL,UAAK,GAEV,WAAW,WAEX,YAAY,YAEZ,cAAc,cAEd,eAAe,iBARL,aANZ,aAuCE,YAAY,EAAiC,IAC3C,GAAM,CACJ,iBAAgB,kBAAiB,YAAW,WAAU,YAAW,WAC/D,EACJ,KAAK,eAAiB,GAAkB,GAAe,SACvD,KAAK,gBAAkB,GAAmB,qBAC1C,KAAK,UAAY,GAAa,yBAC9B,KAAK,SAAW,GAAY,GAC5B,KAAK,UAAY,GAAa,UAC9B,KAAK,QAAU,GAAW,IAhD9B,SA2DE,YACE,EACA,EACA,EAAiC,IAGjC,KAAK,KAAO,MAAO,IAAS,SACxB,CAAC,GACA,YAAgB,IAAgB,EAAK,KAAO,EACjD,KAAK,OAAS,EACd,KAAK,QAAU,GAAI,IAAqB,GAG1C,aAAa,GACX,GAAM,CAAE,WAAY,KAAK,QACzB,MAAO,MAAK,KAAK,IAAI,AAAC,GAAM,EAAI,YAAY,GAAG,OAAO,OAAO,CAAC,EAAI,IAAQ,EAAK,EAAK,EAAK,EAAK,GAAM,EAAI,EAG1G,gBACE,GAAM,CAAE,WAAU,WAAY,KAAK,QACnC,MAAO,MAAK,KAAK,OAAS,EAAY,EAAI,EAG5C,aAAa,EAA+B,GAC1C,GAAM,CAAE,kBAAmB,KAAK,QAC1B,EAAc,IAAmB,GAAe,cAAgB,IAAmB,GAAe,UAClG,EAAa,IAAmB,GAAe,aAAe,IAAmB,GAAe,aAEhG,EAAiB,KAAK,aAAa,GACnC,EAAkB,KAAK,gBACvB,EAAK,EAAc,KAAK,OAAO,EAAI,EAAiB,KAAK,OAAO,EAChE,EAAI,EAAa,KAAK,OAAO,EAAI,EAAkB,KAAK,OAAO,EAGrE,GAAI,GACF,GAAM,CAAE,QAAO,UAAW,EACpB,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAQ,GAAiB,GACrD,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAS,GAAkB,GAC7D,MAAO,CAAE,EAAG,EAAM,EAAG,GAEvB,MAAO,CAAE,IAAG,KAGd,KAAK,GACH,GAAM,GAAS,GAAa,GACtB,EAAM,EAAoB,GAE1B,CACJ,kBAAiB,YAAW,WAAU,YAAW,WAC/C,KAAK,QAET,EAAI,KAAO,GAAG,OAAc,IAC5B,GAAM,GAAe,KAAK,aAAa,GACjC,EAAa,KAAK,gBAExB,EAAI,UAAY,EAChB,GAAM,GAAY,KAAK,aAAa,EAAK,GACzC,EAAI,SAAS,EAAU,EAAG,EAAU,EAAG,EAAc,GAErD,EAAI,UAAY,EAChB,KAAK,KAAK,QAAQ,CAAC,EAAU,KAC3B,GAAM,GAAI,EAAU,EAAU,EACxB,EAAI,EAAU,EAAU,EAAM,GAAI,GAAK,EAC7C,EAAI,SAAS,EAAU,EAAG,OC1HhC,aAuBE,YAAY,EAA2B,IACrC,GAAM,CACJ,WAAU,YAAW,QAAO,oBAC1B,EACJ,KAAK,SAAW,GAAY,qBAC5B,KAAK,UAAY,GAAa,EAC9B,KAAK,MAAQ,EAEb,GAAM,GAA0B,CAC9B,eAAgB,GAAe,YAC/B,gBAAiB,KAAK,UAExB,KAAK,iBAAmB,GAAI,IAAqB,IAAK,KAA4B,MAnCtF,SA4CE,YACE,EACA,EAA2B,IAE3B,KAAK,IAAM,GAAI,GAAI,GACnB,KAAK,QAAU,GAAI,IAAe,GAGpC,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CAAE,WAAU,aAAc,KAAK,QAE/B,CACJ,IAAG,IAAG,QAAO,UACX,KAAK,IACT,EAAI,YAAc,EAClB,EAAI,UAAY,EAChB,EAAI,WAAW,EAAG,EAAG,EAAO,GAE5B,GAAM,CAAE,SAAU,KAAK,QACvB,AAAI,GACF,GAAI,IAAc,CAAC,GAAQ,CAAE,EAAG,EAAK,EAAY,EAAI,KAAK,KAAK,QAAQ,kBAAkB,KAAK,KC1D7F,YACL,EACA,GAIA,AAFwB,OAAM,QAAQ,GAAc,EAAa,CAAC,IAElD,QAAQ,AAAC,IAEvB,GAAM,GAAQ,YAAe,GACzB,EAAI,MACH,GAAoB,GAAO,EAAI,UAAU,MAAQ,OAGhD,EAAM,YAAe,GACvB,EAAI,IACH,GAAoB,GAAO,EAAI,UAAU,IAAM,GAAI,GAAI,GAEtD,EAAQ,EAAQ,GAAG,GAAM,KAAW,OAC1C,GAAI,IAAQ,EAAK,CAAE,UAAS,KAAK,KC1BrC,OAAoB,OCEb,YAAuB,GAC5B,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAQ,aAAiB,IAAS,EAAM,UAClC,YAAiB,IAAS,EAAM,YAAc,ECH/C,YAA0B,GAE/B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,GAAI,YAAiB,GAAI,SAAS,QAAU,GAAc,GACxD,MAAO,GAAQ,MAGjB,WAAiB,GACf,AAAI,CAAC,EAAE,eAEP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAO,IAGT,WAAgB,GACd,AAAI,CAAC,EAAE,eACP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAQ,IAGV,EAAM,iBAAiB,OAAQ,GAC/B,EAAM,iBAAiB,QAAS,KCxB7B,YAAuB,GAC5B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,AAAM,YAAe,OAAO,EAAO,GAAI,OAAM,qDAC7C,GAAM,GAAS,GAAI,YACnB,EAAO,OAAS,KACd,AAAI,MAAO,GAAO,QAAW,UAAU,EAAO,GAAI,OAAM,qEACxD,GAAM,GAAM,EAAI,SAAS,qBACzB,EAAI,OAAS,IAAM,EAAQ,GAC3B,EAAI,QAAU,EACd,EAAI,IAAM,EAAO,QAEnB,EAAO,QAAU,EACjB,EAAO,cAAc,KCXlB,YAA4B,GACjC,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAI,aAAiB,GACZ,GAAI,GAAW,EAAM,aAAc,EAAM,eAE9C,YAAiB,GACZ,GAAI,GAAW,EAAM,WAAY,EAAM,aAEzC,GAAI,GAAW,EAAM,MAAO,EAAM,QCNpC,YAAsB,CAAE,QAAO,WACpC,GAAM,CAAE,uBAAwB,EAAI,SAC9B,EAAS,IACf,SAAO,MAAQ,EACf,EAAO,OAAS,EACT,EAGF,YAA+B,EAAwD,GAC5F,GAAM,CAAE,aAAc,EAAI,SAE1B,GAAI,CAAE,aAAiB,KAAc,CAAC,GAAc,GAClD,KAAM,IAAI,OAAM,8DAGlB,GAAM,CAAE,QAAO,UAAW,GAAQ,GAAmB,GAC/C,EAAS,GAAa,CAAE,QAAO,WAErC,MAAI,aAAiB,GACnB,EAAoB,GAAQ,aAAa,EAAO,EAAG,GAEnD,EAAoB,GAAQ,UAAU,EAAO,EAAG,EAAG,EAAO,GAErD,EC7BT,OAAoB,OAKpB,kBACE,EACA,GAEA,GAAM,GAAe,GAAU,EAAI,SAAS,sBAEtC,CAAC,EAAQ,EAAO,GAAe,EAAU,MAAM,MAAM,EAAW,GAAa,EAAI,GACjF,EAAc,AAAG,QAAK,IAAM,EAAU,KAAK,EAAQ,EAAO,GAAa,SAC7E,YAAM,AAAG,YAAQ,SAAS,EAAa,GAEvC,EAAY,UAEL,ECfF,YAAwB,GAC7B,GAAM,CAAE,QAAO,SAAQ,SAAU,EAAI,SAErC,MAAO,aAAiB,IACnB,YAAiB,IACjB,YAAiB,GCPxB,MAAoB,OCKb,YAAuB,EAA6C,EAAmB,EAAuB,IACnH,GAAM,CAAE,QAAO,UAAW,EAAI,SAE9B,GAAI,CAAE,aAAiB,IAAS,YAAiB,IAC/C,KAAM,IAAI,OAAM,4EAGlB,GAAM,GAAO,GAAmB,GAC1B,EAAQ,EAAY,KAAK,IAAI,EAAK,OAAQ,EAAK,OAC/C,EAAQ,EAAQ,EAAK,MACrB,EAAS,EAAQ,EAAK,OAEtB,EAAe,GAAa,CAAE,MAAO,EAAW,OAAQ,IACxD,EAAc,YAAiB,GAAS,EAAQ,GAAsB,GAEtE,EAAS,KAAK,IAAI,EAAQ,GAAU,EACpC,EAAK,GAAe,EAAQ,EAAS,EAAS,EAC9C,EAAK,GAAe,EAAS,EAAQ,EAAS,EACpD,SAAoB,GAAc,UAAU,EAAa,EAAI,EAAI,EAAO,GAEjE,EDzBT,aAyBE,YACE,EACA,EAA6B,IAdvB,mBAAkD,GAElD,eAAiC,GAIjC,wBAA8B,GAE9B,sBAA+B,GAQrC,GAAI,CAAC,MAAM,QAAQ,GACjB,KAAM,IAAI,OAAM,4HAA4H,KAG9I,KAAK,mBAAqB,EAC1B,KAAK,WAAa,EAAO,OAEzB,EAAO,QAAQ,CAAC,EAAO,KACrB,GAAI,GAAW,IACb,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAO,EAAM,MACnC,OAGF,GAAI,EAAW,IACb,GAAM,GAAa,EAAc,MAAM,GACvC,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,yCAAyC,8CAG3D,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAQ,EAAc,MAAM,MAAM,GACxD,OAGF,GAAM,GAAU,YAAyB,GAAI,SAAS,OAAS,EAAQ,GAAsB,GAC7F,KAAK,UAAU,GAAO,EACtB,KAAK,iBAAiB,GAAO,CAAC,EAAO,OAAQ,EAAO,MAAO,QAIpD,gBACT,MAAO,MAAK,iBAGH,YACT,MAAO,MAAK,aAGH,gBACT,MAAO,MAAK,UAAY,GAAK,KAAK,sBAGzB,aACT,MAAO,MAAK,cAGH,mBACT,MAAO,MAAK,oBAGH,aACT,MAAO,MAAK,cAGH,2BACT,MAAO,IAAM,KAAK,UAAW,EAAG,GAAG,IACjC,CAAC,EAAG,IAAa,KAAK,2BAA2B,IAI9C,SAAS,GACd,MAAO,MAAK,SAAS,IAAa,KAAK,aAAa,GAG/C,mBAAmB,GACxB,MAAO,MAAK,iBAAiB,GAGxB,eAAe,GACpB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,cAAc,GACnB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,2BAA2B,GAChC,GAAI,MAAO,MAAK,WAAc,SAC5B,KAAM,IAAI,OAAM,yFAGlB,GAAM,GAAQ,KAAK,cAAc,GAC3B,EAAS,KAAK,eAAe,GACnC,MAAO,IAA0B,CAAE,QAAO,UAAU,KAAK,WAYpD,cAAc,EAAmB,EAA0B,IAChE,YAAK,WAAa,EAEX,AAAG,OAAK,KACb,GAAM,GAAe,GAAM,KAAK,UAAW,EAAG,GAAG,IAAI,AAAC,IACpD,GAAM,GAAQ,KAAK,SAAS,GAE5B,GAAI,YAAoB,WAEtB,GAAI,GAAY,EAAW,GAAS,EAAQ,EAAM,aAElD,SAAY,GAAY,EAAW,GAE/B,GAAU,MAAM,KAAO,GAAa,EAAU,MAAM,KAAO,IAC7D,GAAY,AAAG,QAAM,eAAe,EAAW,CAAC,EAAW,KAGtD,EAAU,KAAK,EAAW,EAAW,GAG9C,GAAI,YAAiB,GAAI,SAAS,OAChC,MAAO,AAAG,WAAQ,WAAW,GAAc,EAAO,EAAW,IAG/D,KAAM,IAAI,OAAM,+BAA+B,8FAAqG,OAOtJ,MAHoB,AAAG,SAAM,EAAa,IAAI,AAAC,GAAM,AAAG,OAAK,EAAG,aAAa,KAAK,KAAK,UAAW,EAAW,EAAW,OE3I9H,iBAAiC,GAC/B,GAAI,YAAkB,IACpB,MAAO,GAGT,GAAM,GAAgB,MAAM,QAAQ,GAChC,EACA,CAAC,GAEL,GAAI,CAAC,EAAc,OACjB,KAAM,IAAI,OAAM,4CAGlB,GAAM,GAAa,AAAC,GAAiB,MAAM,QAAQ,GAAU,mBAAmB,KAAS,GAEnF,EAAa,EAAc,IAAI,IAErC,SAAW,QAAQ,CAAC,EAAO,KACzB,GAAI,CAAC,GAAe,IAAU,CAAC,GAAW,IAAU,CAAC,EAAW,GAC9D,KAAI,OAAO,GAAc,IAAO,SACxB,GAAI,OAAM,eAAe,EAAW,sEAAsE,EAAc,MAG1H,GAAI,OAAM,eAAe,EAAW,iIAG5C,GAAI,EAAW,IAEb,GAAM,GAAY,EAAM,MAAM,GAC9B,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,eAAe,EAAW,iCAAiC,iDAMjF,KAAM,SAAQ,IACZ,EAAW,IAAI,AAAC,GAAU,GAAe,IAAU,GAAiB,KAG/D,GAAI,IAAS,EAAY,MAAM,QAAQ,ICtChD,kBACE,EACA,GAEA,GAAM,CAAE,UAAW,EAAI,SAEnB,EAAS,EAEb,GAAI,CAAE,aAAiB,KACrB,GAAM,GAAW,KAAM,GAAW,GAElC,GAAI,EAAS,UAAY,EACvB,KAAM,IAAI,OAAM,8CAGlB,GAAM,GAAiB,EAAS,SAAS,GACzC,EAAS,YAA0B,GAC/B,EACA,KAAM,IAAoB,GAGhC,GAAM,GAAM,EAAoB,GAQhC,MAAO,AAPO,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAO,MAAO,EAAO,QAAQ,IAAI,QAC7C,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAO,MAAO,EAAO,SAE/C,IAAI,CAAC,CAChB,IAAG,IAAG,QAAO,aAEb,GAAM,GAAU,GAAa,CAAE,QAAO,WACtC,SAAoB,GACjB,aAAa,EAAI,aAAa,EAAG,EAAG,EAAO,GAAS,EAAG,GACnD,ICnDX,OAAoB,OAgBpB,kBACE,EACA,GAEA,GAAI,CAAC,GAAW,IAAgB,CAAC,EAAW,GAC1C,KAAM,IAAI,OAAM,6DAGlB,GAAI,EAAW,IAAgB,EAAY,MAAM,GAAK,EACpD,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAW,EAAU,GAAe,EAAY,MAAM,MAAM,EAAW,GAAe,EAAI,GAajG,MAJoB,AAPN,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAU,GAAW,IACjC,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAU,IAEvB,IAAI,CAAC,CAC7B,IAAG,IAAG,QAAO,YACT,AAAG,WAAQ,EAAY,KAAK,EAAW,EAAU,GAAc,CAAC,EAAG,EAAG,GAAI,CAAC,EAAQ,EAAO,OCtCpG,kBACE,EAEA,GAEA,GAAM,CAAE,SAAU,EAAI,SAChB,EAAM,KAAM,GAAM,EAAK,GAC7B,GAAI,CAAE,GAAI,OAAS,KACjB,KAAM,IAAI,OAAM,qBAAqB,EAAI,WAAW,EAAI,yBAAyB,EAAI,OAEvF,MAAO,GCTT,kBAAiC,GAC/B,GAAM,GAAM,KAAM,IAAa,GACzB,EAAO,KAAO,GAAK,OAEzB,GAAI,CAAC,EAAK,KAAK,WAAW,UACxB,KAAM,IAAI,OAAM,wEAAwE,EAAK,kBAAkB,EAAI,OAErH,MAAO,IAAc,GCRvB,kBAAmC,GACjC,MAAQ,MAAM,IAAa,IAAM,OCDnC,kBAAsC,GACpC,MAAO,IAAI,cAAa,KAAO,MAAM,IAAa,IAAM,eCH1D,OAAoB,OCAb,YAAsB,EAAyB,GACpD,GAAM,GAA0B,GAAG,0BAEnC,GAAI,CAAC,EACH,MAAO,CACL,aAAc,GACd,YAAa,GAIjB,GAAI,IAAQ,IACV,MAAO,CACL,aAAc,IACd,YAAa,IAAI,KAIrB,GAAM,GAAW,EAAI,WAAW,WAAa,UAAY,EAAI,WAAW,YAAc,WAAa,GACnG,EAAM,EAAI,QAAQ,EAAU,IAE5B,GAAM,GAAQ,EAAI,MAAM,KAAK,OAAO,AAAC,GAAM,GAErC,EAAe,EAAI,SAAS,SAC9B,EAAM,EAAM,OAAS,GACrB,EAEA,EAAe,EAAY,GAAI,SAAS,SAAW,EAAM,MAAM,EAAG,EAAM,OAAS,GAAK,GAAO,KAAK,KACtG,SAAe,EAAI,WAAW,KAAO,IAAI,IAAiB,EAEnD,CACL,eACA,YAAa,IAAiB,IAAM,IAAI,IAAiB,GAAG,KAAgB,KD1BhF,kBACE,EACA,GAEA,GAAM,CAAE,cAAa,gBAAiB,GAAa,EAAK,GAClD,EAAW,KAAM,IAAuC,GAE9D,MAAO,AAAG,OAAG,YAAY,EAAU,GET9B,YAAyB,EAAoB,EAAwB,EAA8B,IACxG,GAAM,CAAE,QAAO,UAAW,EACtB,GAAmB,GACnB,EACJ,SAAM,MAAQ,EACd,EAAM,OAAS,EACR,CAAE,QAAO,UCTlB,OAAoB,OCApB,OAAoB,OAApB,0BAQY,aAAkC,OAElC,oBAAiC,MAIhC,UAAmC,MAAO,MAAK,WAE/C,iBAAkC,MAAO,MAAK,kBAE9C,YAAsB,MAAO,CAAC,CAAC,KAAK,OAExC,iBAAiB,GACtB,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,MAAO,GAAI,GAGN,sBAAsB,EAAmB,GAC9C,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,EAAI,GAAS,UACb,EAAI,GAAW,EAGV,eACL,MAAO,MAAK,eAAe,IAAI,CAAC,CAAE,eAAiB,EACjD,KAAM,EACN,OAAQ,KAAK,iBAAiB,MAI3B,qBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,EAAM,iBAAqB,cAGnE,kBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,CAAE,GAAM,iBAAqB,eAGrE,WACL,KAAK,kBAAkB,QAAQ,CAAC,CAAE,OAAM,aACtC,KAAK,sBAAsB,EAAM,EAAO,cAIrC,SACL,KAAK,qBAAqB,QAAQ,CAAC,CAAE,OAAM,OAAQ,MACjD,GAAM,GAAS,AAAG,UAAO,EAAS,YAClC,EAAS,UACT,KAAK,sBAAsB,EAAM,KAI9B,QAAQ,EAA4B,IACzC,KAAK,eAAe,QAAQ,AAAC,IAC3B,GAAI,GAAoB,EAAM,OAAO,WACnC,KAAM,IAAI,OAAM,mDAAmD,EAAM,QAE3E,EAAM,OAAO,YAEf,KAAK,QAAU,OAGV,kBACL,MAAO,IAAI,cACT,KAAK,eACF,IAAI,CAAC,CAAE,YAAa,MAAM,KAAK,EAAO,aACtC,OAAO,CAAC,EAAM,IAAQ,EAAK,OAAO,UAI5B,MAAK,GAChB,GAAI,YAAwB,eAC1B,KAAK,eAAe,GACpB,OAGF,KAAM,MAAK,YAAY,QAGZ,aAAY,GACvB,GAAI,GAAO,MAAO,IAAQ,SACxB,KAAM,IAAI,OAAM,GAAG,KAAK,0CAG1B,GAAM,GAAY,KAAM,IAAc,EAAK,KAAK,uBAChD,KAAK,kBAAkB,QAGZ,cAAa,GACxB,GAAI,GAAY,MAAO,IAAa,SAClC,KAAM,IAAI,OAAM,GAAG,KAAK,iDAG1B,GAAM,CAAE,YAAa,EAAI,SAEnB,CAAE,cAAa,gBAAiB,GAAa,EAAU,KAAK,uBAE5D,EAAuB,AAAC,GAAwB,QAAQ,IAC5D,EAAU,IAAI,AAAC,GAAO,EAAS,GAAI,KAAK,AAAC,GAAQ,EAAI,UAEjD,EAAc,AAAG,MAAG,qBAAqB,GACzC,EAAW,KAAK,MAAO,MAAM,GAAS,IAAc,YACpD,EAAY,KAAM,GAAY,EAAU,GAE9C,KAAK,kBAAkB,GAGlB,kBAAkB,GACvB,GAAM,CACJ,gBACA,UACE,KAAK,2BAA2B,GAEpC,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGV,eAAe,GACpB,GAAM,CACJ,gBACA,UACE,KAAK,cAAc,GAEvB,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGT,qBAAqB,GAC3B,GAAI,CAAC,KAAK,OACR,KAAM,IAAI,OAAM,qDAGlB,GAAM,GAAS,EAAU,MAAM,KAAK,OAAO,CAAC,EAAoD,KAE9F,GAAI,CAAC,EAAI,QAAQ,eAAe,GAC9B,KAAM,IAAI,OAAM,wDAAwD,eAAqB,KAG/F,MAAO,CAAE,IAAK,EAAI,QAAS,UAAS,QAAS,EAAI,QAAQ,KACxD,CAAE,QAAS,KAAK,SAEb,CAAE,MAAK,WAAY,EACzB,GAAI,CAAC,GAAO,CAAC,GAAW,CAAE,GAAI,YAAuB,YACnD,KAAM,IAAI,OAAM,8DAA8D,KAGhF,MAAO,CAAE,MAAK,aC1JlB,MAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,iBAAkB,EAAO,iBAAkB,EAAQ,QAC1F,SAAM,AAAG,OAAI,EAAK,EAAO,MAClB,IDNJ,YACL,EACA,EACA,EAAwB,IAExB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,CAAC,EAAG,GAAI,QACrE,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,CAAC,EAAG,KAE7E,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,OAItC,YACL,EACA,EACA,EAAwB,GACxB,EAAuB,IAEvB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,GAAI,QAC5F,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,KAEpG,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAE/D,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,KACxC,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,QEpD1D,OAAoB,OAIb,YACL,EACA,EACA,EAA4B,OAC5B,EAAoB,IAEpB,MAAO,AAAG,SAAK,KACb,GAAM,GAAM,AAAG,OACb,AAAG,UAAO,EAAG,EAAO,QAAS,CAAC,EAAG,GAAI,GACrC,EAAO,MAGT,MAAO,GAAW,AAAG,QAAK,GAAO,ICd9B,WAAoC,EAAgB,GACzD,OAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,AAAK,EAAc,KAAK,AAAC,GAAO,EAAG,eAAiB,IAClD,EAAU,GAAM,YCLtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,EACA,KAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,SCzBtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,KAEA,GAAM,GAAa,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAY,IAChF,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CACL,QAAS,EACT,KAAM,ICvBZ,OAAoB,OCApB,aAsBE,YAES,EAEA,EAEA,GAJA,wBAEA,wBAEA,cDxBJ,YACL,EACA,GAEA,MAAO,CAAC,EAAoB,EAAqB,KAC/C,GAAM,GAAmB,AAAG,YAAS,EAAe,EAAI,EAAI,GAAa,CAAC,EAAG,EAAG,EAAY,IACtF,EAAmB,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAG,EAAG,EAAY,IAC5F,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,WAGX,GAAI,IACT,EACA,EACA,IAKC,YAEL,GAEA,MAAO,AAAC,KACN,GAAM,GAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,IAAI,IACT,EACA,EACA,IEpCC,WAAmC,EAAgB,GACxD,MAAO,CAAC,EAAsB,EAAmB,KAC/C,GAAM,GAAS,EAAU,GAEzB,GAAI,CAAC,GAAS,EAAQ,GACpB,KAAM,IAAI,OAAM,sBAAsB,oBAA+B,oBAA4B,KAGnG,SAAc,KACZ,CAAE,eAAc,UAAW,GAAc,IAGpC,GCfJ,WAA+B,GACpC,GAAI,GAAmB,EAEvB,WAAwB,GACtB,GAAM,GAAM,EAAiB,MAAM,EAAG,GACtC,SAAmB,EAAiB,MAAM,GACnC,EAGT,aACE,MAAO,GAGT,MAAO,CACL,iBACA,uBCPG,YAA2B,EAAwC,GACxE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,GAAQ,EACV,EAAkB,EAAY,EAAa,EAAG,GAAG,WACjD,EAA2B,EAAY,EAAa,GAAG,WACrD,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAChE,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,CAAE,QAAO,QAAO,SAAU,EAAyB,EAAY,EAAa,EAAc,GAC1F,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAC3C,EAAS,EAAyB,IAAK,IAAK,UAElD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CACN,SAAQ,SAAQ,SAAQ,WCvBvB,YAA+B,GACpC,MAAO,AAAC,KACN,GAAM,GAAU,EAAgC,GAAG,YAAkB,GAC/D,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,CAAE,UAAS,SCNf,YAA2B,EAAgB,GAChD,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBhBxBnB,oBAU0C,GACxC,cACE,MAAM,wBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,sDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAE/B,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,+BAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KiBlDzB,OAAoB,OCApB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,IAAM,AAAG,OACtB,AAAG,UAAO,EAAG,EAAO,SACpB,EAAO,OCPJ,YAAuB,EAAuB,EAAoB,GACvE,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAIpB,EAAK,AAFa,GAAuB,EAAgB,GAEpC,EAAY,EAAa,MAEpD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,OCdP,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,EAAgB,OAGtB,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,YAA4B,GACjC,GAAM,GAAyC,GACzC,EAAmC,GAEzC,cAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,GAAM,GAAM,EAAI,WAAW,MAAQ,EAAgB,EACnD,EAAI,GAAO,EAAU,KAGhB,CAAE,sBAAqB,iBJXhC,oBAkBU,GAGR,YAAY,EAAe,GACzB,MAAM,GACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBASP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EACJ,MAAO,IAAoB,EAAmB,KAAK,EAAmB,MAAM,GAAI,IAAK,EAAO,MAIzF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,EAAS,KAAK,0BAA2B,KAAK,4BAG3D,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAM,KAAK,0BACX,EAAO,KAAK,2BACZ,EAAwB,EAAO,EAAO,EAEtC,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KKnFjC,GAAM,IAAyB,CAAC,UAAW,QAAS,MAAO,QAAS,UAAW,YAAa,aAAnG,SAiBE,YAAY,GACV,GAAI,EAAc,SAAW,EAC3B,KAAM,IAAI,OAAM,8EAA8E,EAAc,UAG9G,GAAuB,QAAQ,CAAC,EAAY,KAC1C,KAAK,GAAc,EAAc,KAIrC,gBACE,MAAO,IACJ,IAAI,AAAC,GAAgB,EAAE,aAAY,YAAa,KAAK,MACrD,KAAK,CAAC,EAAI,IAAO,EAAG,YAAc,EAAG,e1C9B5C,oBAQuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGtB,aAAa,GAClB,MAAO,AAAG,SAAK,IAAM,AAAG,WAAQ,KAAK,OAAO,UAGjC,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,oBAAmB,GAC9B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAC9B,EAAsB,KAAM,SAAQ,IAAI,AAAG,WAAQ,GAAK,IAAI,KAAO,KACvE,GAAM,GAAO,KAAM,GAAE,OACrB,SAAE,UACK,KAET,EAAI,UAEJ,GAAM,GAAqB,EACxB,IAAI,AAAC,GAAiB,GAAI,IAAgB,IAE7C,MAAO,GAAS,aACZ,EACA,EAAmB,GAGf,sBACR,MAAO,wBAGC,0BACR,MAAO,KAGC,2BACR,MAAO,K2C1CJ,YAA+B,GACpC,MAAO,GAAI,sBAAuB,IAG7B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,gBCPf,YACL,EACA,EACA,EAAgB,GAChB,GAIA,AAF6B,OAAM,QAAQ,GAAmB,EAAkB,CAAC,IAE5D,QAAQ,AAAC,IAE5B,GAAM,GAAO,YAAa,IACtB,EACC,GAAsB,GAAK,EAAE,YAAc,OAChD,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mHAIlB,GAAM,GAAmB,AADV,EAAK,gBACY,OAAO,AAAC,GAAc,EAAU,YAAc,GAExE,EAAS,GAAoB,GAC/B,EAAE,UAAU,IAAI,WACf,GAAmB,GAAI,GAAM,EAAG,GAMrC,AAJsB,GAAI,IACxB,EAAiB,IAAI,AAAC,GAAc,GAAG,EAAU,eAAe,GAAM,EAAU,iBAChF,GAEY,KAAK,KCxBhB,YAA6B,GAClC,MAAO,IAAoB,IAEtB,EAAI,oBAAwB,IAE5B,EAAI,6BAAiC,IAErC,EAAI,sBAA0B,GAG9B,YAEoD,EAAoB,GAC7E,GAAM,CAAE,IAAK,GAAU,EAAU,UAC3B,EAAY,EAAmB,QAAwB,EAAM,EAAG,EAAM,GAEtE,EAAO,EAAU,QACjB,CAAE,aAAc,EAAU,UAC1B,EAAc,GAAI,GAAc,EAAU,UAAU,MAAO,EAAK,QAAQ,EAAU,WAAY,GAQpG,MAAO,IAAK,KANM,CAChB,YACA,qBACA,gBCpCJ,aA+BE,YAAY,EAAqC,IAC/C,GAAM,CACJ,YAAY,GAAM,aAAa,GAAM,YAAW,YAAW,YAAW,cACpE,EACJ,KAAK,UAAY,EACjB,KAAK,WAAa,EAClB,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,uBAC9B,KAAK,WAAa,GAAc,yBAxCpC,SAiDE,YACE,EACA,EAAqC,IAErC,KAAK,cAAgB,EACrB,KAAK,QAAU,GAAI,IAAyB,GAG9C,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CACJ,YAAW,aAAY,YAAW,YAAW,YAAW,cACtD,KAAK,QAcT,GAZI,GAAa,KAAK,wBAAyB,KAC7C,GAAI,YAAc,EAClB,EAAI,UAAY,EAChB,GAAY,EAAK,KAAK,cAAc,iBACpC,GAAY,EAAK,KAAK,cAAc,kBACpC,GAAY,EAAK,KAAK,cAAc,mBACpC,GAAY,EAAK,KAAK,cAAc,WACpC,GAAY,EAAK,KAAK,cAAc,aAAc,IAClD,GAAY,EAAK,KAAK,cAAc,cAAe,IACnD,GAAY,EAAK,KAAK,cAAc,WAAY,KAG9C,GACF,EAAI,YAAc,EAClB,EAAI,UAAY,EAEhB,GAAM,GAAY,AAAC,IACjB,EAAI,YACJ,EAAI,IAAI,EAAG,EAAG,EAAG,EAAG,EAAW,EAAG,EAAI,KAAK,IAC3C,EAAI,QAEN,KAAK,cAAc,UAAU,QAAQ,MAOpC,YACL,EACA,GAGA,AAD2B,OAAM,QAAQ,GAAiB,EAAgB,CAAC,IACxD,QAAQ,AAAC,IAE1B,GAAM,GAAY,YAAa,GAC3B,EACC,GAAoB,GAAK,EAAE,UAAY,OAC5C,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gIAGlB,GAAI,IAAkB,GAAW,KAAK,qBC1G1C,OAAoB,OCApB,MAAoB,OCKpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAqC,EAAoB,EAAqB,GAC5E,GAAM,GAAkB,EAA2B,EAAY,EAAa,GAAG,qBACzE,EAAkB,EAA2B,EAAa,EAAa,GAAG,qBAC1E,EAAiB,EAAkB,EAAY,EAAa,EAAG,GAAG,oBAExE,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,EAAkB,GAChD,GAAM,GAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBAE1E,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YAAuB,EAAuB,GACnD,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAgB,GAEhC,EAAqB,EAAkB,EAAG,GAAI,EAAG,sBACjD,EAA+B,EAA4B,GAAI,GAAI,gCACnE,EAA+B,EAA4B,GAAI,IAAK,gCAEpE,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,IAAK,0BAA0B,OAG3F,GAAM,GAA4B,EAA4B,IAAK,IAAK,6BAClE,EAA2B,EAA2B,IAAK,IAAK,4BAEhE,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,aAAY,cAAa,cCjEvC,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAqC,GACnC,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAiB,EAAkB,GAAG,oBAE5C,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,GAC9B,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAEtD,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAW,GAE3B,EAAqB,EAAkB,sBACvC,EAA+B,EAA4B,gCAC3D,EAA+B,EAA4B,gCAE3D,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,0BAA0B,OAGtF,GAAM,GAA4B,EAA4B,6BACxD,EAA2B,EAA2B,4BAEtD,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,SAA2B,EAAW,GAE/B,CAAE,OAAQ,CAAE,aAAY,cAAa,aAAa,iBFrE3D,YAAc,EAAgB,EAAoB,GAChD,MAAO,AAAG,OAAI,AAAG,SAAO,EAAG,EAAO,QAAS,EAAQ,QAAS,EAAO,MAGrE,YAAwB,EAAgB,EAA8B,EAA2B,IAC/F,GAAI,GAAM,EAAkB,AAAG,OAAK,GAAK,EACzC,SAAM,EAAuB,EAAK,EAAO,gBAAiB,CAAC,EAAG,IAC9D,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,AAAG,MAAI,EAAK,GAAK,EAAG,EAAO,eAAgB,CAAC,EAAG,KAC9C,EAGT,YAAmB,EAAgB,GACjC,GAAI,GAAM,EAAuB,AAAG,OAAK,GAAI,EAAO,gBAAiB,CAAC,EAAG,IACzE,SAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,MAAI,EAAK,GACX,EA7BT,oBAgCkC,GAGhC,YAAY,GACV,MAAM,gBACN,KAAK,eAAiB,EAGjB,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,8CAGlB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,AAAG,OAAK,GAAK,EAAY,EAAO,WAAW,QAAS,CAAC,EAAG,KAClE,SAAM,GAAe,EAAK,EAAO,WAAW,kBAAmB,IAC/D,EAAM,GAAe,EAAK,EAAO,WAAW,mBAE5C,GAAM,KAAK,eAAgB,EAAG,GAAG,QAAQ,AAAC,IACxC,EAAM,GAAU,EAAK,EAAO,YAAY,cAAc,QAGxD,EAAM,GAAe,EAAK,EAAO,UAAU,iBAC3C,EAAM,AAAG,OAAK,EAAuB,EAAK,EAAO,UAAU,eAAgB,CAAC,EAAG,KACxE,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,sBAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,gBAG1C,cAAc,GACtB,MAAO,IAAc,EAAS,KAAK,kBG5EhC,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAkB,GAAuB,EAAgB,GAEzD,EAAM,EAAgB,IAAK,EAAG,UAC9B,EAAS,EAAgB,IAAK,EAAG,aAEvC,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,GAAI,CAAE,MAAK,YCflB,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,CACF,IAAK,EAAgB,UACrB,OAAQ,EAAgB,eAI5B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,GAAK,IAAL,UAAK,GAEV,SAAS,SAET,OAAO,SAJG,aNLZ,oBAakC,GAGhC,YAAY,EAAqC,GAAI,IAAa,IAChE,MAAM,gBACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBAGP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EAEE,EAAS,AAAG,WAAQ,EAAoB,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAAS,KAAK,EAAmB,MAAM,GAAI,IACnG,EAAM,GAAoB,EAAQ,EAAO,GAAG,KAAK,OACjD,EAAS,GAAoB,EAAQ,EAAO,GAAG,QACrD,MAAO,CAAE,MAAK,YAIX,aAAa,GAClB,MAAO,AAAG,SAAK,KACb,GAAM,CAAE,MAAK,UAAW,KAAK,OAAO,GACpC,MAAO,CAAE,MAAK,OAAQ,AAAG,WAAQ,WAIxB,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,qBAAoB,GAC/B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAE9B,EAAO,AAAG,WAAQ,EAAI,KACtB,EAAU,AAAG,WAAQ,EAAI,QACzB,EAAsB,EAAK,IAAI,CAAC,EAAW,IAAO,EACtD,YACA,aAAc,EAAQ,MAGlB,EAAqB,KAAM,SAAQ,IACvC,EAAoB,IAAI,MAAO,CAAE,YAAW,mBAC1C,GAAM,GAAO,MAAM,GAAU,QAAQ,GAC/B,EAAY,MAAM,GAAa,QAAQ,GACvC,EAAS,EAAW,GACpB,EAAS,EAAS,GAAO,KAAO,GAAO,OACvC,EAAoB,EAAS,EAAY,EAAI,EAEnD,SAAU,UACV,EAAa,UACN,CAAE,MAAK,SAAQ,wBAG1B,SAAI,IAAI,UACR,EAAI,OAAO,UAEJ,EAAS,aAAe,EAAiD,EAAmB,GAG3F,sBACR,MAAO,mBAGF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,GAGb,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAwB,IAAM,EAAI,EAAM,KAAM,EAAI,GAElD,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KOvHxC,MAAoB,OAApB,oBAYU,IACD,YAAY,EAAqB,EAAmB,GACzD,GAAM,GAAkB,EAAmB,IAAI,CAAC,CAAE,QAAO,aACvD,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,CACL,MAAO,EAAQ,EACf,OAAQ,EAAS,KAIf,EAAY,EAAgB,OAElC,MAAO,AAAG,QAAK,KACb,GAAM,GAA0B,CAAC,EAAe,IAAkB,AAAG,QAAM,CAAC,AAAG,OAAK,CAAC,IAAK,EAAO,WAAY,AAAG,OAAK,CAAC,IAAK,EAAO,YAAa,GAAG,KAAK,EAAG,KAAK,OAGzJ,EAAa,CAAC,EAAkB,KACpC,GAAM,CAAE,QAAO,UAAW,EAAgB,GAC1C,MAAO,GAAK,EAAO,GAAU,KAAK,IAAI,EAAQ,GAAU,EAAI,GAGxD,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GACvE,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GAa7E,MAXwB,GACrB,IAAI,AAAG,OAAK,CAAC,EAAW,KAAM,EAAW,YACzC,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAY,GACZ,EAAY,OAEb,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAgB,GAAU,MAC1B,EAAgB,GAAU,aAO3B,aAAa,GAClB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,KAAK,OAAO,GACxB,MAAO,MAAK,YACV,EACA,EAAM,UACN,EAAM,gBAAgB,IAAI,CAAC,CAAC,EAAQ,KAAY,EAAE,SAAQ,mBAKnD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,iBAAgB,GAC3B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAkB,AAAG,OACzB,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAAoB,KAAM,SAAQ,IAAI,EAAgB,IAC1D,MAAO,EAAgB,KACrB,GAAM,GAAiB,MAAM,KAAK,KAAM,GAAe,QACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,GAAO,IACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,CAAC,GAAO,IAExD,MAAO,IAAI,IACT,MAAM,IAAI,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,GAAI,GAAM,EAAQ,GAAc,EAAQ,KACxE,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,QAMtC,SAAgB,QAAQ,AAAC,GAAM,EAAE,WAE1B,EAAS,aAAe,EAAyC,EAAkB,GAGlF,2BACR,MAAO,OC9FX,oBAIuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGnB,sBACR,MAAO,yBAGC,0BACR,MAAO,OCdX,OAAoB,OCMb,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCnBZ,YAA2B,GAChC,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAEjD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,SAAQ,SAAQ,WF1B9B,oBAU8C,GAC5C,cACE,MAAM,4BAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,0DAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,GAAI,IAAK,CAAC,EAAG,GAAI,SAEjC,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,oCAGC,2BAA2B,GACnC,MAAO,IAA+B,GAG9B,cAAc,GACtB,MAAO,IAAkB,KGjD7B,oBAI2C,IACzC,YAAY,EAAiD,GAAI,KAC/D,MAAM,wBAAyB,GAGvB,sBACR,MAAO,8BAGC,0BACR,MAAO,OCdX,oBAKqC,MCLrC,MAAoB,OCApB,OAAoB,OCApB,OAAoB,OAIb,YAAe,EAAgB,GACpC,MAAO,AAAG,QAAI,AAAG,OAAI,EAAG,EAAO,SAAU,EAAO,QDAlD,YACE,EACA,EACA,EACA,EACA,EAA4B,QAE5B,GAAM,CAAE,UAAS,QAAS,EAAO,KAE7B,EAAM,AAAG,UAAO,EAAG,EAAS,EAAS,GACzC,SAAM,AAAG,OAAI,EAAK,GAClB,EAAM,GAAM,EAAK,EAAO,OACjB,EAAW,AAAG,QAAK,GAAO,EAG5B,YAAc,EAAgB,GACnC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAoB,EAAgB,GACzC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAkB,EAAgB,GACvC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,GAAM,SE7B5C,MAAoB,OAUpB,YAA2B,EAAwC,GACjE,WAA6B,EAAyB,EAAoB,GACxE,GAAM,GAAU,EAAe,GACzB,EAAQ,EAAQ,OAAU,GAAa,EAAa,GAE1D,GAAI,GAAQ,GACV,KAAM,IAAI,OAAM,+BAA+B,sBAA0B,EAAQ,uBAAuB,kBAA2B,KAGrI,MAAO,AAAG,QACR,IAAM,AAAG,YACP,AAAG,WAAS,EAAS,CAAC,EAAY,EAAO,EAAY,IACrD,CAAC,EAAG,EAAG,EAAG,KAKhB,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAU,EAAoB,EAAiB,EAAY,GAC3D,EAAO,AAAG,WAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,QAGpB,WAAiC,EAAoB,GACnD,GAAM,GAAU,AAAG,WAAS,EAAe,IACrC,EAAS,AAAG,WAAS,EAAe,IAE1C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,aAGX,CACL,UACA,UAIJ,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAO,EAAkB,EAAiB,EAAY,EAAY,GAAG,UACrE,EAAQ,EAAwB,EAAY,GAAG,WAErD,MAAO,CAAE,OAAM,SAGjB,WACE,EACA,EACA,EACA,EACA,EAAkB,IAElB,GAAM,GAAQ,EAAwB,GAAS,GAAM,GAAK,EAAiB,EAAY,EAAY,GAAG,WAChG,EAAQ,EAAuB,EAAiB,EAAY,EAAY,GAAG,WAEjF,MAAO,CAAE,QAAO,SAGlB,MAAO,CACL,yBACA,8BAIG,YAAuB,GAC5B,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAgB,GAEhC,EAAc,EAAuB,KAAM,GAAI,EAAG,eAClD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YAEnD,EAAc,EAA2B,MAAO,GAAI,EAAG,cAAe,IACtE,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YAEpD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aAEvD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAmB,EAA2B,OAAQ,IAAK,EAAG,oBAE9D,EAAK,AAAG,OACZ,IAAM,AAAG,YAAU,AAAG,WAAS,EAAe,IAAM,KAAM,CAAC,IAAK,MAAO,CAAC,EAAG,KAI7E,GAFA,EAAc,KAAK,CAAE,UAAW,OAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAsB1E,MAAO,CAAE,OAnBM,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGe,iBC9InB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAiC,GAC/B,GAAM,GAAU,EAAmB,GAAG,kBAAwB,GACxD,EAAS,EAAmB,GAAG,iBAAuB,GAE5D,MAAO,CAAE,UAAS,UAGpB,WAAgC,GAC9B,GAAM,GAAU,EAAmB,GAAG,iBAAuB,GACvD,EAAO,EAAmB,GAAG,cAAoB,GACjD,EAAQ,EAAwB,GAEtC,MAAO,CAAE,KAAM,CAAE,UAAS,QAAQ,SAGpC,WAAoC,GAClC,MAAO,CACL,MAAO,EAAuB,GAAG,WACjC,MAAO,EAAuB,GAAG,YAIrC,MAAO,CACL,yBACA,8BAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAW,GAE3B,EAAc,EAAuB,eACrC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAc,EAA2B,eACzC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aAEvC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aACvC,EAAmB,EAA2B,oBAE9C,CAAE,MAAO,EAGf,GAFA,EAAc,KAAK,CAAE,aAAc,KAAM,UAAW,OAEhD,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yDAAyD,KAG3E,GAAM,GAAS,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGF,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBChGnB,MAAoB,OAKb,YAAkB,EAAgB,GACvC,GAAI,GAAM,GAAK,EAAG,EAAO,OACzB,SAAM,GAAW,EAAK,EAAO,OAC7B,EAAM,AAAG,MAAI,EAAK,GAClB,EAAM,AAAG,OAAK,GACP,EAGF,YAAsB,EAAgB,GAC3C,GAAI,GAAM,GAAS,EAAG,EAAO,OAC7B,EAAM,GAAW,EAAK,EAAO,OAE7B,GAAI,GAAS,AAAG,UAAQ,EAAG,EAAG,EAAG,SAC3B,EAAQ,AAAG,QAAkB,EAAO,OACpC,EAAQ,EAAO,MAAM,KAAO,EAAI,MAAM,GAG5C,GAFsB,EAAO,MAAM,KAAO,EAAI,MAAM,IAAM,EAAO,MAAM,KAAO,EAAI,MAAM,IAGtF,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAE/B,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAGjC,SAAS,EAAQ,AAAG,SAAO,CAAC,EAAQ,GAAQ,GAAK,EACjD,EAAM,AAAG,MAAI,EAAQ,GAErB,EAAM,AAAG,OAAK,GACP,ELtCT,oBAWwC,GACtC,cACE,MAAM,sBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,QAAK,KAEb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAGtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,GAAS,EAAY,EAAO,aACtC,EAAM,AAAG,UAAQ,EAAK,EAAG,EAAG,SAE5B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,aAC/B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAa,EAAK,EAAO,kBAE/B,GAAM,GAAY,EAAI,KAAK,CAAC,EAAG,IAG/B,MAFuB,AAAG,UAAO,EAAW,EAAO,WAM1C,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,uBAAsB,GACjC,GAAM,GAAW,KAAM,GAAW,GAE5B,EAAwB,AAAG,OAC/B,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAA0B,KAAM,SAAQ,IAAI,EAAsB,IACtE,AAAC,GAAM,EAAE,SAGX,SAAsB,QAAQ,AAAC,GAAM,EAAE,WAEhC,EAAS,aACZ,EACA,EAAwB,GAGpB,sBACR,MAAO,yBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KMrFlB,YAAkC,GACvC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECHF,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,eCNf,YAAmB,GACxB,MAAO,OAAO,GAAI,KAAQ,SAGrB,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,QCNf,YAAsB,GAC3B,MAAQ,GAAI,SAAW,GAAO,MAAQ,EAAI,SAAW,GAAO,SACvD,GAAmB,EAAI,mBAGvB,YAGL,EACA,EACA,GAGA,MAAO,IAAK,KADM,CAAE,SAAQ,sBCpB9B,OAAoB,OCApB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,WAAoC,EAAqB,GACvD,GAAM,GAAU,AAAG,YAAS,EAAe,EAAI,EAAI,GAAc,CAAC,EAAG,EAAG,EAAa,IAC/E,EAAmB,AAAG,YAAS,EAAe,IAC9C,EAAoB,AAAG,YAAS,EAAe,IAC/C,EAAkB,AAAG,YAAS,EAAe,IAC7C,EAAsB,AAAG,YAAS,EAAe,IAEvD,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,uBAChB,CAAE,UAAW,GAAG,qBAChB,CAAE,UAAW,GAAG,0BAGX,CACL,UACA,mBACA,oBACA,kBACA,uBAIJ,WACE,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,KAAgB,EAAkB,oBAAsB,WAGnE,CAAE,UAAS,QAGpB,WACE,EACA,EACA,EACA,GAEA,GAAM,CACJ,UACA,QACE,EAAkB,EAAY,EAAa,EAAY,EAAc,IAEzE,MAAO,CACL,UACA,kBAAmB,GAIvB,WACE,EACA,EACA,GAEA,GAAM,GAAiB,EAA2B,EAAY,GAAG,oBAC3D,EAAiB,EAA2B,EAAY,EAAa,EAAG,GAAG,oBAEjF,MAAO,CAAE,iBAAgB,kBAG3B,aACE,GAAM,GAAS,EAA2B,EAAG,GAAI,EAAG,sBAE9C,EAAS,EAAsB,GAAI,GAAI,sBACvC,EAAS,EAAsB,GAAI,IAAK,sBACxC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,KAAM,uBAC3C,EAAU,EAAsB,KAAM,KAAM,uBAElD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,UACA,UACA,UACA,WAIJ,aACE,GAAM,GAAS,EAA2B,KAAM,IAAK,EAAG,2BAClD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,GAAI,EAAG,2BAChD,EAAS,EAA2B,GAAI,IAAK,EAAG,2BAEhD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,EAAG,EAAG,oDACjD,EAA2B,EAAkB,KAAM,GAAI,EAAG,2DAC1D,EAAoB,EAAkB,KAAM,GAAI,EAAG,oDACnD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDA2BxD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,gBAlCsB,CACtB,uBAAwB,EACxB,gBAAiB,GAiCjB,gBA/BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA8BjB,gBA5BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA2BjB,gBAzBsB,CACtB,uBAAwB,GACxB,gBAAiB,IAwBjB,gBAtBsB,CACtB,uBAAwB,EACxB,gBAAiB,IAqBjB,gBAnBsB,CACtB,uBAAwB,GACxB,gBAAiB,KAqBrB,MAAO,CACL,2BACA,gCAIG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,2BACA,gCACE,GAAkB,EAAgB,GAEhC,EAAc,IACd,EAAmB,IAKnB,EAAe,CACnB,UALgB,AAAG,YACnB,EAAe,KAAO,GACtB,CAAC,EAAG,KAAM,KAQZ,GAFA,EAAc,KAAK,CAAE,UAAW,2BAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,OAAQ,CACN,cACA,mBACA,gBAEF,iBCvNJ,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAoC,EAAgB,EAAa,GAC/D,GAAM,GAAU,EAAmB,GAAG,YAAiB,sBAAyB,EAAG,GAAG,aAChF,EAAoB,EAAmB,GAAG,YAAiB,oCAAuC,EAAG,GAAG,uBAE9G,MAAO,CAAE,UAAS,qBAGpB,WAA+B,GAC7B,GAAM,GAAe,oBAAoB,IACnC,EAAsB,sBAAsB,cAC5C,EAA4B,GAAG,mBAC/B,EAA4B,GAAG,mBAE/B,EAAU,EAAmB,GAAG,sBAAyC,EAAG,GAAG,aAC/E,EAAmB,EAAmB,GAAG,oBAAuC,EAAG,GAAG,sBACtF,EAAoB,EAAmB,GAAG,mBAAsC,EAAG,GAAG,uBACtF,EAAkB,EAAmB,GAAG,0BAA6C,EAAG,GAAG,qBAC3F,EAAsB,EAAmB,GAAG,8BAAiD,EAAG,GAAG,yBAEzG,MAAO,CACL,eAAgB,CACd,UACA,mBACA,oBACA,kBACA,uBAEF,eAAgB,EAA2B,cAAe,EAAK,IAInE,aACE,MAAO,CACL,OAAQ,EAA2B,cAAe,EAAG,sBACrD,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,KAInC,WAA2B,EAAgB,GACzC,GAAM,GAAU,EAAmB,GAAG,YAAkB,EAAG,GAAG,aACxD,EAAO,EAAmB,GAAG,WAAiB,EAAG,GAAG,UAE1D,MAAO,CAAE,UAAS,QAGpB,WAAmC,GACjC,GAAM,GAAyB,EAC7B,2BAA2B,yBAC3B,kCAAkC,4BAE9B,EAAkB,EACtB,2BAA2B,mBAC3B,kCAAkC,qBAGpC,MAAO,CAAE,yBAAwB,mBAGnC,aACE,MAAO,CACL,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,IAI/C,MAAO,CACL,2BACA,gCAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,2BACA,gCACE,GAAkB,EAAW,GAE3B,EAAY,EAAU,oBAG5B,GAFA,EAAc,KAAK,CAAE,aAAc,mBAAoB,UAAW,2BAE9D,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yEAAyE,KAG3F,GAAM,GAAS,CACb,YAAa,IACb,iBAAkB,IAClB,aAAc,CACZ,cAIJ,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCvInB,OAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,UAAO,EAAG,EAAO,QAAS,EAAS,QAChD,SAAM,AAAG,OAAI,EAAK,EAAO,mBAClB,AAAG,eAAY,EAAK,EAAG,KDPlC,GAAM,IAAU,qBAEhB,YACE,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,QAAS,EAAS,QACzD,SAAM,AAAG,aACP,EACA,EAAO,gBACP,EAAO,oBACP,EAAO,kBACP,EAAO,iBACP,IAEK,AAAG,eAAY,EAAK,EAAG,KAIlC,YAA+B,GAC7B,MAAO,CAAC,EAAG,EAAG,EAAG,IAAI,KAAK,AAAC,GAAQ,IAAQ,GAAY,CAAC,EAAG,GAAK,CAAC,EAAG,GAG/D,YAAqB,EAAgB,GAC1C,MAAO,AAAG,SAAK,KACb,GAAI,GACA,EAAM,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IA4BnD,GAVA,AAhBuB,CACrB,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,QACP,EAAO,QACP,EAAO,QACP,EAAO,SAGM,QAAQ,CAAC,EAAO,KAC7B,GAAM,GAAW,EAAI,EACf,EAAuB,GAAsB,GACnD,EAAM,GAAmB,EAAK,EAAM,eAAgB,GACpD,EAAM,EAAmB,EAAK,EAAM,eAAgB,CAAC,EAAG,IACpD,IAAa,IACf,GAAS,KAIT,IAAW,KACb,KAAM,IAAI,OAAM,iDAGlB,MAAO,CACL,MACA,OAAQ,KEjEd,YAAa,EAAoB,EAAW,GAC1C,GAAM,GAAY,EAAM,YAClB,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAS,GAAQ,GAAU,GAAQ,GACnC,EAAS,GAAQ,GAAU,GAAQ,GACzC,GAAI,GAAS,GAAK,GAAS,EACzB,MAAO,GAET,GAAM,GAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAmB,EAAkB,GACjE,KAAK,IAAI,EAAmB,EAAkB,GACpD,MAAO,GAAoB,GAAQ,EAAQ,GAGtC,YACL,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAW,EAAM,MAAM,GACvB,EAAa,KAAK,IACtB,EACA,GAGI,EAAa,EAChB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,OAAO,AAAC,GAAM,EAAE,MAAQ,GACxB,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAE5B,EAAe,AAAC,GAAe,GAAK,EAAe,EAAI,EAEvD,EAAqB,GAE3B,SAAW,QAAQ,AAAC,IAClB,GAAI,EAAS,QAAU,EACrB,OAEF,GAAM,GAAgB,EAAE,MAExB,OAAS,GAAI,EAAS,OAAS,EAAG,GAAK,EAAG,EAAE,GAC1C,GAAM,GAAM,GAAI,EAAO,EAAE,SAAU,EAAS,IAC5C,GAAI,IAAQ,GACZ,GAAE,OAAS,EAAa,GACpB,EAAE,OAAS,GAAgB,MAEjC,AAAI,IAAkB,EAAE,OACtB,EAAS,KAAK,EAAE,YAIb,ECjET,MAAoB,OAIpB,YAA2C,GACzC,GAAM,GAAM,AAAG,UAAQ,AAAG,YAAU,EAAG,CAAC,EAAG,KAErC,EAAQ,CACZ,AAAG,MAAI,EAAI,GAAI,EAAI,IACnB,AAAG,MAAI,EAAI,GAAI,EAAI,KAGf,EAAU,CACd,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,KAC1C,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,MAG5C,MAAO,CACL,QACA,WAIJ,YAA0B,EAAiB,GACzC,GAAM,CACJ,QACA,WACE,GAAkC,GAEhC,EAAM,AAAG,UAAQ,AAAG,YAAU,EAAI,CAAC,EAAG,KAEtC,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAE3E,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAEjF,MAAO,AAAG,aACR,AAAG,QAAM,CACP,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,KAEnB,CAAC,EAAG,IAID,YACL,EACA,EACA,GAEA,MAAO,AAAG,QAAK,KACb,GAAM,GAAY,EAAe,MAAM,GAEnC,EAAQ,GACV,AAAG,UAAQ,AAAG,OAAK,EAAO,UAAW,CAAC,EAAW,EAAG,IAAK,CAAC,GAAI,IAC9D,AAAG,UAAQ,EAAgB,CAAC,GAAI,KAElC,EAAQ,AAAG,UACT,EACA,CAAC,EAAY,EAAM,MAAM,GAAK,EAAY,IAG5C,GAAM,GAAmB,AAAG,UAAQ,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,MAC/E,EAAS,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,IAE5D,EAAS,AAAG,UACV,EACA,CAAC,EAAW,EAAO,MAAM,KAG3B,GAAM,GAAe,AAAG,UAAQ,GAC1B,EAAgB,AAAG,UAAQ,GAEjC,MAAO,CACL,MAAO,EACP,OAAQ,KC9Ed,OAAoB,OCApB,OAAoB,OAKb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAY,EAAE,MAAM,GAEpB,EAAwB,AAAG,WAC/B,GAAU,EAAG,EAAO,wBACpB,CAAC,EAAW,GAAI,EAAG,IAEf,EAAkB,AAAG,WACzB,GAAU,EAAG,EAAO,iBACpB,CAAC,EAAW,GAAI,IAGlB,MAAO,CACL,wBACA,qBDjBC,YACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAQ,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IACjD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IAErD,EAAiB,GAAmB,EAAQ,EAAO,iBACnD,EAAiB,GAAmB,EAAG,EAAO,iBAC9C,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAElD,EAAiB,AAAG,UAAO,CAC/B,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,uBACd,GAEG,EAAmB,AAAG,UAAO,CACjC,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,iBACd,GAEH,MAAO,CACL,iBACA,sBEhDN,YAYE,YAAY,CAAE,gBAAe,cAAuC,IAN1D,WAAgB,wBAUxB,GAHA,KAAK,eAAiB,GAAiB,GACvC,KAAK,YAAc,GAAc,IAE7B,MAAO,MAAK,gBAAmB,UAAY,KAAK,gBAAkB,GAAK,KAAK,gBAAkB,EAChG,KAAM,IAAI,OAAM,GAAG,KAAK,iEAG1B,GAAI,MAAO,MAAK,aAAgB,SAC9B,KAAM,IAAI,OAAM,GAAG,KAAK,iDAIxB,iBAA0B,MAAO,MAAK,kBAEtC,cAAuB,MAAO,MAAK,cT3BzC,oBAeoC,GAClC,cACE,MAAM,kBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,AAAG,SAAK,KAEb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAQ,WAEvD,EAAI,AAAG,OAAI,AAAG,OAAI,EAAa,AAAG,UAAO,sBAAwB,AAAG,UAAO,IAC3E,EAAW,GAAY,EAAG,EAAO,aAEjC,CACJ,iBACA,oBACE,GAAgB,EAAS,IAAK,EAAS,OAAQ,EAAO,kBAE1D,MAAO,IAAY,EAAgB,EAAkB,EAAO,qBAInD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,aACX,EACA,EAAkC,IAElC,GAAM,CAAE,aAAY,iBAAkB,GAAI,GAAsB,GAE1D,EAAW,KAAM,GAAW,GAE5B,CACJ,MAAO,EACP,OAAQ,GACN,KAAK,aAAa,GAGhB,EAAQ,EAAO,GACf,EAAS,EAAQ,GACvB,OAAS,GAAI,EAAG,EAAI,EAAO,OAAQ,IACjC,EAAO,GAAG,UACV,EAAQ,GAAG,UAIb,GAAM,GAAa,MAAM,KAAK,KAAM,GAAO,QAGrC,EAAU,GACd,EACA,EACA,EAJmB,GAMnB,GAGI,EAAe,EAAS,2BAA2B,GACnD,EAAY,EAAS,UACrB,EAAO,EAAY,EAAa,MAChC,EAAO,EAAY,EAAa,OAEhC,EAAY,EAAM,YAClB,EAAU,EACb,IAAI,AAAC,IACJ,GAAM,CAAC,EAAK,GAAU,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACf,CAAC,GAAM,IAAS,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACrB,MAAO,IAAI,GACT,EAAW,GACX,GAAI,IACF,GACA,EACA,GAAQ,GACR,EAAS,GAEX,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,OAKtC,SAAM,UACN,EAAO,UAEA,EAGC,sBACR,MAAO,wBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KUzHlB,YAA8B,GACnC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,EAGF,YAAgC,GACrC,MAAO,IAAqB,GAZ9B,oBAgBsC,MCd/B,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,QAAU,SACpB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,OAAQ,SAClB,GAAI,GAAM,QAAS,UAGR,GAAwB,CACnC,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAA+C,CAAC,QAAS,QAAS,QAElE,GAAqB,oBACrB,GAAoC,mCCvBjD,MAAoB,OCapB,GAAM,IAAW,AAAC,GAAa,MAAO,IAAQ,SAEvC,YAAwB,GAC7B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mBAAmB,KAGrC,GAAI,MAAO,GAAO,oBAAuB,UACvC,KAAM,IAAI,OAAM,wDAAwD,EAAO,sBAGjF,GAAI,CAAC,GAAS,EAAO,eAAiB,EAAO,aAAe,GAAK,EAAO,aAAe,EACrF,KAAM,IAAI,OAAM,gEAAgE,EAAO,gBAGzF,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,MAAM,AAAC,GAAW,MAAO,IAAM,UAElD,KAAM,IAAI,OAAM,kEAAkE,KAAK,UAAU,EAAO,YAG1G,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,IAAI,AAAC,GAAW,GAAK,IAAI,MAAM,AAAC,GAAW,GAAS,EAAE,IAAM,GAAS,EAAE,IAE1F,KAAM,IAAI,OAAM,wEAAwE,KAAK,UAAU,EAAO,YAGhH,GAAI,EAAO,SACT,EAAC,MAAM,QAAQ,EAAO,UACnB,EAAO,QAAQ,SAAW,GAC1B,CAAC,EAAO,QAAQ,MAAM,KAEzB,KAAM,IAAI,OAAM,8EAA8E,KAAK,UAAU,EAAO,YCjDxH,MAAoB,OCApB,MAAoB,OAEb,YAAe,GACpB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,AAAG,MAAI,EAAG,AAAG,SAAO,qBAChC,MAAO,AAAG,OAAI,AAAG,OAAK,AAAG,MAAI,EAAG,IAAO,KDApC,YAA2B,EAAgB,GAChD,MAAO,AAAG,QAAK,KACb,GAAI,GAAM,AAAG,MAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KAEjD,SAAM,AAAG,SAAO,EAAK,EAAO,KAAK,QAAS,CAAC,EAAG,GAAI,SAClD,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,KAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,SAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,KAAK,MAEvB,GAAM,KEdjB,OAAoB,OAKb,YAAgC,EAAgB,GACrD,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,OAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KAEjD,SAAM,AAAG,mBAAgB,EAAK,EAAO,iBAAkB,EAAO,iBAAkB,CAAC,EAAG,GAAI,SACxF,EAAM,AAAG,OAAI,EAAK,EAAO,MAElB,GAAM,KCZjB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAEnE,WAAgC,EAAc,GAC5C,GAAM,GAAM,AAAG,YAAS,EAAe,IACjC,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,SAChB,CAAE,UAAW,GAAG,cAGX,CAAE,MAAK,WAGhB,WAAwC,EAAoB,EAAqB,GAC/E,GAAM,GAAO,EAAkB,EAAY,EAAa,EAAG,GAAG,UACxD,EAAK,EAAuB,EAAa,GAAG,QAElD,MAAO,CAAE,OAAM,MAEjB,GAAM,GAA6B,GAAkC,EAAgB,GAErF,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,EACA,EACA,GAEA,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAgB,GAElC,EAEJ,GAAI,EAAO,oBACT,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EAEvC,EAAQ,EAAO,mBACjB,EAAkB,EAAI,EAAI,EAAG,SAC7B,EAA2B,EAAI,EAAI,SACjC,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAkB,GAAM,GAAM,EAAI,EAAI,EAAiB,EAAG,SACxE,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,eAG1D,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAAkB,EAAI,EAAI,EAAiB,EAAG,SAC5D,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,UAI5D,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CAAE,SAAQ,iBCvFnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAgC,GAC9B,GAAM,GAAM,EAAmB,GAAG,QAAc,GAC1C,EAAU,EAAmB,GAAG,YAAkB,GACxD,MAAO,CAAE,MAAK,WAGhB,WAA2B,GACzB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,WAAwC,GACtC,GAAM,GAAO,EAAkB,GAAG,UAC5B,EAAK,EAAuB,GAAG,QACrC,MAAO,CAAE,OAAM,MAGjB,GAAM,GAA6B,GAA+B,GAElE,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAW,GAE7B,EAEJ,GAAI,EAAO,oBAET,GAAM,GAAc,EAAO,aAAe,EAAO,YAAY,QAAU,EACvE,EAAS,CACP,MAAO,EAAO,mBAAqB,EAAkB,SAAW,EAA2B,SAC3F,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAkB,cAG3B,GAAS,CACP,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAAkB,UAI7B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCpFnB,aAYE,YAAY,CAAE,YAAW,kBAAuC,IANtD,WAAgB,oBAUxB,GAHA,KAAK,WAAa,GAAa,IAC/B,KAAK,gBAAkB,GAAkB,GAErC,MAAO,MAAK,YAAe,UAAY,KAAK,WAAa,IAAO,EAClE,KAAM,IAAI,OAAM,GAAG,KAAK,6DAG1B,GAAI,MAAO,MAAK,iBAAoB,UAAY,KAAK,iBAAmB,GAAK,KAAK,iBAAmB,EACnG,KAAM,IAAI,OAAM,GAAG,KAAK,qEAIxB,aAAsB,MAAO,MAAK,cAElC,kBAA2B,MAAO,MAAK,kBP3B7C,oBAuBoC,GAOlC,YAAY,GACV,MAAM,cACN,GAAe,GACf,KAAK,QAAU,KAGN,UACT,MAAO,MAAK,WAGH,mBACT,MAAO,MAAK,OAAO,iBAAmB,KAAK,OAAO,QAAQ,OAAS,KAG1D,mBACT,MAAO,GAAK,MAAK,gBAAkB,KAAK,OAAO,QAAQ,OAAS,GAG3D,cAAc,EAAgB,GACnC,GAAI,GAAM,GAAkB,EAAG,EAAO,OACtC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,GAAkB,EAAK,EAAO,OAE7B,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAgB,GAClC,GAAI,GAAM,KAAK,OAAO,mBAClB,GAAM,GAAU,EAAG,EAAO,MAAqB,QAAS,KACxD,GAAuB,EAAG,EAAO,OACrC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EACjE,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EAE1D,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAiB,GACnC,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,4CAGlB,MAAO,AAAG,QAAK,KAEb,GAAI,GAAc,AAAG,OAAK,EAAM,cAAc,EAAW,IAAQ,WACjE,SAAc,KAAK,OAAO,QACtB,GAAU,EAAa,KAAK,OAAO,SACnC,EACJ,EAAc,EAAY,IAAI,AAAG,SAAO,MAEjC,KAAK,OAAO,mBACf,KAAK,aAAa,EAAa,GAC/B,KAAK,cAAc,EAAa,UAI3B,SAAQ,EAAkB,GACrC,MAAO,MAAK,aAAa,KAAM,GAAW,GAAQ,QAGvC,QAAO,EAAkB,EAAoC,IACxE,GAAM,CAAE,YAAW,kBAAmB,GAAI,IAAkB,GAEtD,EAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,EAAU,GACxC,EAAO,AAAG,OAAK,IAAM,AAAG,UAAQ,GAAK,GAAG,cAExC,EAAkB,CACtB,MAAO,EAAS,cAAc,GAC9B,OAAQ,EAAS,eAAe,IAG5B,EAAU,KAAM,MAAK,aAAa,EAAM,EAAS,2BAA2B,GAAI,GACtF,EAAI,UACJ,EAAK,UAEL,GAAM,GAAQ,EAAQ,IAAI,AAAC,GAAQ,EAAI,KACjC,EAAS,EAAQ,IAAI,AAAC,GAAQ,EAAI,OAClC,EAAc,EAAQ,IAAI,AAAC,GAAQ,EAAI,YACvC,EAAa,EAAQ,IAAI,AAAC,GAAQ,KAAK,OAAO,QAAQ,EAAI,QAiBhE,MARmB,AAPH,IACd,EAAM,IAAI,AAAC,GAAQ,EAAI,QAAQ,IAC/B,EACA,KAAK,OAAO,aACZ,IAGyB,IAAI,AAAC,GAAQ,GAAI,IAC1C,EAAO,GACP,EAAY,GACZ,EAAW,GACX,EAAM,GACN,IAMM,sBACR,MAAO,GAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,QAG1C,cAAc,GACtB,GAAM,GAAc,KAAK,OAAO,aAAe,GAAe,qBAExD,EAAa,EAAc,EAAY,OAAS,OACtD,GAAI,IAAe,GAAK,IAAe,GAAK,IAAe,EACzD,KAAM,IAAI,OAAM,oEAAoE,2BAEtF,MAAO,IAAc,EAAS,KAAK,OAAQ,KAAK,gBAAiB,QAGnD,cACd,EACA,EACA,GAEA,GAAM,CAAE,QAAO,UAAW,EACpB,EAAY,KAAK,IAAI,EAAO,GAC5B,EAAoB,EAAY,EAChC,EAAoB,EAAY,EAEhC,EAAW,EAAa,MAAM,GAC9B,EAAW,KAAK,OAAO,QAAQ,OAE/B,CAAC,EAAa,EAAc,GAAqB,AAAG,OAAK,KAC7D,GAAM,GAAW,EAAa,QAAQ,CAAC,EAAU,EAAU,EAAU,KAAK,kBAEpE,EAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACpE,EAAS,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACrE,EAAc,KAAK,gBACrB,AAAG,UAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,KAAK,OAAO,QAAQ,SAAU,GACrG,AAAG,SAAO,GACd,MAAO,CAAC,EAAO,EAAQ,KAGnB,EAAU,GAEV,EAAa,KAAM,GAAa,QAChC,EAAY,KAAM,GAAY,QACpC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAS,EAAG,EAAS,EAAU,KACtC,GAAM,GAAQ,GAAQ,EAAW,GAAK,GAAK,GAAQ,IACnD,GAAI,CAAC,GAAkB,EAAQ,GAC7B,GAAM,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAe,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACvG,EAAgB,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EAExG,GAAK,EAAO,GAAa,EACzB,GAAK,GAAO,EAAc,EAE1B,GAAM,CAAE,MAAK,MAAK,UAClB,CAAE,cAAY,UAAU,KAAK,gBAC/B,KAAM,MAAK,sBAAsB,EAAkC,IACnE,CAAE,WAAY,EAAG,MAAO,GAE5B,EAAQ,KAAK,CACX,IAAK,GAAI,IAAY,GAAG,GAAG,GAAI,GAAY,GAAI,GAC/C,QACA,WAAY,EAAQ,GACpB,YACG,MAOb,SAAY,UACZ,EAAa,UACb,EAAkB,UAEX,OAGK,uBAAsB,EAA4B,GAC9D,GAAM,CAAE,MAAK,MAAK,UAAW,EACvB,EAAc,KAAM,GAAc,QACxC,MAAO,OAAM,KAAK,OAAO,QAAQ,QAAQ,KAAK,GAC3C,IAAI,CAAC,EAAG,IAAM,EAAY,GAAK,GAAK,GAAQ,IAC5C,IAAI,CAAC,EAAY,IAAW,EAC3B,aACA,WAED,OAAO,CAAC,EAAK,IAAU,EAAI,WAAa,EAAK,WAAa,EAAM,KApPvE,MAwBgB,AAxBhB,GAwBgB,qBAAuB,CACnC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,IAAK,KAAM,MQzBxC,oBAiBgC,IAC9B,YAAY,EAA8B,IACxC,GAAM,GAAS,CACb,qBACA,aAAc,GACd,QAAS,CAAC,WACN,EACA,CACA,QAAS,GACT,QAAS,IAET,CACA,QAAS,GACT,gBAAiB,KAIvB,MAAM,MAGG,sBACT,MAAO,MAAK,OAAO,sBAGV,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,MAAK,mBAAqB,GAAoC,GAG7D,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KC9CrC,YAA0B,EAAuB,EAA8B,IACpF,GAAM,GAAM,GAAI,IAAW,GAC3B,SAAI,eAAe,GACZ,ECZT,oBAI6C,IAJ7C,kCAKY,WAAgB,4BCL5B,kBACe,MAEX,GAEA,MAAO,GAAY,KAAM,MAAK,YAGnB,OACX,KAAM,IAAI,OAAM,6CCRpB,OAAoB,OCDpB,OAAoB,OAOpB,kBACE,EACA,EAEA,EACA,EAEA,EAAwF,CAAC,CAAE,iBAAkB,GAE7G,GAAM,GAAY,EAAc,IAAI,AAAC,GAAkB,GAAoB,GACvE,EAAoB,GACpB,EAAa,WACX,EAAgD,GACpD,aAAoB,WAChB,KAAM,IAAmB,EAAO,GAChC,KAAM,IAAa,EAAO,IAG1B,EAAU,KAAM,GAAe,GAErC,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAGT,kBACE,EACA,EAEA,EACA,EAEA,GAEA,MAAO,IACL,CAAC,GACD,EACA,KAAO,IAAU,EAAc,EAAM,IACrC,EACA,GC5CG,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAAqC,CAAC,QAAS,QAAS,QCZrE,oBAUsC,IACpC,cACE,GAAM,GAAS,CACb,mBAAoB,GACpB,aAAc,GACd,QAAS,CAAC,QACV,QAAS,GACT,QAAS,GACT,mBAAoB,GACpB,YAAa,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,MAGzC,MAAM,MAGG,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,2BAGC,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KCvBrC,GAAM,GAAO,CAClB,eAAgB,GAAI,IACpB,iBAAkB,GAAI,IACtB,WAAY,GAAI,IAChB,kBAAmB,GAAI,IACvB,sBAAuB,GAAI,IAC3B,mBAAoB,GAAI,IACxB,kBAAmB,GAAI,IACvB,aAAc,GAAI,KAUP,GAAiB,CAAC,EAAkB,IAA6D,EAAK,eAAe,YAAY,EAAO,GASxI,GAAmB,CAAC,EAAkB,IAA+D,EAAK,iBAAiB,YAAY,EAAO,GAS9I,GAAa,CAAC,EAAkB,IAA0D,EAAK,WAAW,YAAY,EAAO,GAS7H,GAAsB,AAAC,GAAmE,EAAK,kBAAkB,gBAAgB,GAWjI,GAA0B,AAAC,GAAmE,EAAK,sBAAsB,gBAAgB,GAYzI,GAAwB,AAAC,GAA6D,EAAK,mBAAmB,sBAAsB,GASpI,GAA2B,AAAC,GAAmE,EAAK,kBAAkB,mBAAmB,GASzI,GAAsB,AAAC,GAAiF,EAAK,aAAa,oBAAoB,GAE9I,GAA0B,AAAC,GAAgB,EAAK,eAAe,KAAK,GACpE,GAA4B,AAAC,GAAgB,EAAK,iBAAiB,KAAK,GACxE,GAAsB,AAAC,GAAgB,EAAK,WAAW,KAAK,GAC5D,GAAwB,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACrE,GAA4B,AAAC,GAAgB,EAAK,sBAAsB,KAAK,GAC7E,GAA2B,AAAC,GAAgB,EAAK,mBAAmB,KAAK,GACzE,GAA0B,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACvE,GAAqB,AAAC,GAAgB,EAAK,aAAa,KAAK,GAG7D,GAAyB,GACzB,GAAc,GACd,GAAkB,GCpH/B,oBAmB4E,IAC1E,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA1Bd,gBAkCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAwB,KAAM,IAClC,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,KAEtD,KAAK,gBAGP,MAAO,GAAc,IACnB,CAAC,EAAc,IAAM,GAAmC,EAAc,EAAsB,KAIhG,mBACE,MAAO,IAAI,IAA2B,KAAM,KAAK,SArDrD,gBA2DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,GAAkB,KAAM,IAC5B,EACA,KAAK,MACL,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,GACpD,KAAK,gBAGP,MAAO,IAA0B,EAAc,GAGjD,mBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA7ExD,gBAmFU,IACR,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAzFxD,gBA+FU,IACR,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCrG1D,oBAoByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA3Bd,gBAmCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAqB,KAAM,IAC/B,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,aAAa,oBAAoB,KAElD,KAAK,gBAGP,MAAO,GAAc,IAAI,CAAC,EAAc,KACtC,GAAM,CAAE,MAAK,SAAQ,qBAAsB,EAAmB,GAC9D,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,KAIpF,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAvDxD,gBA6DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,MAAK,SAAQ,qBAAsB,KAAM,IAC/C,EACA,KAAK,MACL,AAAC,GAAS,EAAK,aAAa,oBAAoB,GAChD,KAAK,gBAGP,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,GAGlF,sBACE,MAAO,IAAI,IAAiC,KAAM,KAAK,SA/E3D,gBAqFU,IACR,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA3FxD,gBAiGU,IACR,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCvG1D,oBAiB4E,IAC1E,YAEY,EAEA,GAEV,QAJU,kBAEA,eAtBd,gBA8BU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAUjC,MAAO,AARa,MAAM,IACxB,EACA,KAAK,MACL,AAAC,GAAU,QAAQ,IAAI,EAAM,IAAI,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,KACzF,KACA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,OAGxD,IAAI,CAAC,EAAY,IAAM,GAAkC,EAAc,GAAI,IAGhG,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,SAlDtE,gBAwDU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAEF,GAAM,GAAa,KAAM,IACvB,EACA,KAAK,MACL,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,GACxD,KAEA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,MAG3E,MAAO,IAAyB,EAAc,GAGhD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,SP/EzE,oBAqByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,6BAKE,eACZ,MAAO,MAAK,mBACR,EAAK,sBACL,EAAK,oBApCb,gBA0CU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAC3B,EAAa,EAAc,IAAI,AAAC,GAAQ,EAAI,WAE5C,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,GACrC,KAAM,IAAa,KAAK,MAAO,GAE7B,EAAsB,KAAM,SAAQ,IAAI,EAAM,IAClD,AAAC,GAAS,KAAK,YAAY,gBAAgB,KAG7C,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAAc,IAAI,CAAC,EAAc,IAAM,GAAiC,EAAc,EAAoB,KAGnH,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SArExD,gBA2EU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,aAAc,EAChB,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,CAAC,IACtC,KAAM,IAAa,KAAK,MAAO,CAAC,IAE9B,EAAY,KAAM,MAAK,YAAY,gBAAgB,EAAM,IAE/D,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,GAAiC,EAAc,GAGxD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SQvG1D,oBAckD,IAChD,YAEY,EAEA,EAAgC,GAAI,IAE9C,QAJU,aAEA,iBAnBd,gBAyBwC,SACzB,OACX,GAAM,CAAE,QAAO,WAAY,KAGrB,EAAwB,YAAmB,IAE7C,AAAC,GAAqB,EAAK,iBAAiB,YAAY,EAAO,GAG/D,YAAmB,GAEf,AAAC,GAAqB,EAAK,eAAe,YAAY,EAAO,GAE7D,YAAmB,IAEf,AAAC,GAAqB,EAAK,WAAW,YAAY,EAAO,GACzD,KAIZ,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,uIAGlB,MAAO,GAAsB,GAGvB,iCAEN,MAAO,IAAI,SAAiC,KAAO,KACjD,GAAM,GAAa,KAAM,MAAK,MAC9B,EAAQ,EAAW,IAAI,AAAC,GAAc,GAAwB,GAAI,OAItE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,SA/EX,gBAoF0C,SAC3B,OACX,GAAM,GAAiB,KAAM,IAAI,IAAmB,KAAK,MAAO,KAAK,SACjE,EAAgC,EAAe,GACnD,SAAe,QAAQ,AAAC,IACtB,AAAI,EAAc,MAAQ,EAA8B,OACtD,GAAgC,KAG7B,EAGD,gCAEN,MAAO,IAAI,SAA2C,KAAO,KAC3D,GAAM,GAAY,KAAM,MAAK,MAC7B,EAAQ,EAAY,GAA4B,GAAI,GAAa,UAIrE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,SCrHJ,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAqB,EAAO,GAGlC,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAmB,EAAO,GCRvC,kBACE,EACA,GAEA,MAAO,IAAe,EAAO,GAAI,GAAsB,EAAgB,CAAE,iBAAkB,KACxF,oBACA,sBAGL,kBACE,EACA,EAAoC,IAEpC,MAAO,IAAe,EAAO,GAAI,IAAkB,IAChD,oBACA,sBAGE,GAAM,IAAW,GC1BjB,YAA2B,EAA+B,GAC/D,GAAI,EAAK,SAAW,EAAK,OAAQ,KAAM,IAAI,OAAM,kDAEjD,GAAM,GAAQ,MAAM,KAAK,GACnB,EAAQ,MAAM,KAAK,GAEzB,MAAO,MAAK,KACV,EACG,IAAI,CAAC,EAAK,IAAM,EAAM,EAAM,IAC5B,OAAO,CAAC,EAAK,IAAS,EAAO,GAAQ,EAAI,ICThD,aAUE,YACE,EACA,EAA4B,IAE5B,KAAK,mBAAqB,EAE1B,GAAM,GAAa,MAAM,QAAQ,GAAU,EAAS,CAAC,GAErD,GAAI,CAAC,EAAW,OACd,KAAM,IAAI,OAAM,2DAGlB,GAAI,GAAQ,EACN,EAAoB,IAAM,UAAU,MAE1C,KAAK,oBAAsB,EAAW,IAAI,AAAC,IACzC,GAAI,YAAgB,IAClB,MAAO,GAGT,GAAI,YAAgB,cAClB,MAAO,IAAI,IAAuB,IAAqB,CAAC,IAG1D,GAAI,EAAK,YAAc,EAAK,qBAAsB,cAChD,MAAO,IAAI,IAAuB,IAAqB,CAAC,EAAK,aAG/D,KAAM,IAAI,OAAM,4MAIT,sBAAiD,MAAO,MAAK,uBAE7D,qBAA8B,MAAO,MAAK,mBAE9C,oBAAoB,EAA+B,GACxD,MAAO,GACJ,IAAI,AAAC,GAAM,GAAkB,EAAG,IAChC,OAAO,CAAC,EAAI,IAAO,EAAK,EAAI,GACxB,GAAY,QAAU,GAGxB,gBAAgB,GACrB,MAAO,MAAK,mBACT,IAAI,CAAC,CAAE,cAAa,WAAY,GAAI,IACnC,EACA,KAAK,oBAAoB,EAAiB,KAE3C,OAAO,CAAC,EAAM,IAAU,EAAK,SAAW,EAAK,SAAW,EAAO,GAG7D,cAAc,GACnB,GAAM,GAAY,KAAK,gBAAgB,GACvC,MAAO,GAAU,SAAW,KAAK,kBAC7B,EACA,GAAI,IAAU,UAAW,EAAU,UAGlC,SACL,MAAO,CACL,kBAAmB,KAAK,kBACxB,mBAAoB,KAAK,mBAAmB,IAAI,AAAC,GAAO,EAAG,iBAIjD,UAAS,GACrB,GAAM,GAAqB,EAAK,mBAC7B,IAAI,AAAC,GAAY,GAAuB,SAAS,IACpD,MAAO,IAAI,IAAY,EAAoB,EAAK,qBC1E7C,YAAgC,GACrC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECFF,YAA0B,EAAY,GAC3C,GAAM,CAAE,QAAO,UAAW,GAAI,GAAW,EAAW,MAAO,EAAW,QAEtE,GAAI,GAAS,GAAK,GAAU,EAC1B,KAAM,IAAI,OAAM,uCAAuC,KAAK,UAAU,CAAE,QAAO,cAGjF,GAAI,MAAM,QAAQ,GAEhB,MAAQ,GAAuB,IAAI,AAAC,GAAQ,GAAc,EAAK,CAAE,QAAO,YAG1E,GAAI,GAAoB,IACtB,GAAM,GAAmB,EAAQ,UAAU,QAAQ,EAAO,GACpD,EAAmB,EAAQ,mBAAmB,QAAQ,EAAiB,IAAI,MAAO,EAAiB,IAAI,QAC7G,MAAO,IAAwB,GAAwB,EAAS,GAAmB,GAGrF,MAAI,IAAoB,GACf,GAAwB,EAAS,EAAQ,UAAU,QAAQ,EAAO,IAGvE,YAAmB,IAAiB,YAAmB,GACjD,EAAgB,QAAQ,EAAO,GAGlC,EjJRT,GAAM,IAAQ,MAAO,UAAY,YAE3B,GAAW,MAAO,YAAc,aAAiB,MAAO,WAAU,WAAc,YACzE,GAAU,CAAE,QAAa,GAAmB,QAAM", + "sourcesContent": ["/* eslint-disable import/no-extraneous-dependencies */\n/* eslint-disable node/no-unpublished-import */\n\nexport * from '@tensorflow/tfjs-node';\n", "export function isNodejs(): boolean {\n return typeof global === 'object'\n && typeof require === 'function'\n && typeof module !== 'undefined'\n // issues with gatsby.js: module.exports is undefined\n // && !!module.exports\n && typeof process !== 'undefined' && !!process.version;\n}\n", "import * as tf from '../dist/tfjs.esm';\nimport * as draw from './draw/index';\nimport * as utils from './utils/index';\nimport * as pkg from '../package.json';\n\nexport { tf, draw, utils };\n\nexport * from './ageGenderNet/index';\nexport * from './classes/index';\nexport * from './dom/index';\nexport * from './env/index';\nexport * from './faceExpressionNet/index';\nexport * from './faceLandmarkNet/index';\nexport * from './faceRecognitionNet/index';\nexport * from './factories/index';\nexport * from './globalApi/index';\nexport * from './ops/index';\nexport * from './ssdMobilenetv1/index';\nexport * from './tinyFaceDetector/index';\nexport * from './tinyYolov2/index';\nexport * from './euclideanDistance';\nexport * from './NeuralNetwork';\nexport * from './resizeResults';\n\nconst node = (typeof process !== 'undefined');\nconst browser = (typeof navigator !== 'undefined') && (typeof navigator.userAgent !== 'undefined');\nexport const version = { faceapi: pkg.version as string, node, browser };\n", "export * from './drawContour';\nexport * from './drawDetections';\nexport * from './drawFaceExpressions';\nexport * from './DrawBox';\nexport * from './DrawFaceLandmarks';\nexport * from './DrawTextField';\n", "import { Point } from '../classes/index';\n\nexport function drawContour(\n ctx: CanvasRenderingContext2D,\n points: Point[],\n isClosed: boolean = false,\n) {\n ctx.beginPath();\n\n points.slice(1).forEach(({ x, y }, prevIdx) => {\n const from = points[prevIdx];\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(x, y);\n });\n\n if (isClosed) {\n const from = points[points.length - 1];\n const to = points[0];\n if (!from || !to) {\n return;\n }\n\n ctx.moveTo(from.x, from.y);\n ctx.lineTo(to.x, to.y);\n }\n\n ctx.stroke();\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Point } from '../classes/index';\nimport { Dimensions, IDimensions } from '../classes/Dimensions';\n\nexport function isTensor(tensor: any, dim: number) {\n return tensor instanceof tf.Tensor && tensor.shape.length === dim;\n}\n\nexport function isTensor1D(tensor: any): tensor is tf.Tensor1D {\n return isTensor(tensor, 1);\n}\n\nexport function isTensor2D(tensor: any): tensor is tf.Tensor2D {\n return isTensor(tensor, 2);\n}\n\nexport function isTensor3D(tensor: any): tensor is tf.Tensor3D {\n return isTensor(tensor, 3);\n}\n\nexport function isTensor4D(tensor: any): tensor is tf.Tensor4D {\n return isTensor(tensor, 4);\n}\n\nexport function isFloat(num: number) {\n return num % 1 !== 0;\n}\n\nexport function isEven(num: number) {\n return num % 2 === 0;\n}\n\nexport function round(num: number, prec: number = 2) {\n const f = 10 ** prec;\n return Math.floor(num * f) / f;\n}\n\nexport function isDimensions(obj: any): boolean {\n return obj && obj.width && obj.height;\n}\n\nexport function computeReshapedDimensions({ width, height }: IDimensions, inputSize: number) {\n const scale = inputSize / Math.max(height, width);\n return new Dimensions(Math.round(width * scale), Math.round(height * scale));\n}\n\nexport function getCenterPoint(pts: Point[]): Point {\n return pts.reduce((sum, pt) => sum.add(pt), new Point(0, 0))\n .div(new Point(pts.length, pts.length));\n}\n\nexport function range(num: number, start: number, step: number): number[] {\n return Array(num).fill(0).map((_, i) => start + (i * step));\n}\n\nexport function isValidNumber(num: any) {\n return !!num && (num !== Infinity) && (num !== -Infinity) && !Number.isNaN(num) || num === 0;\n}\n\nexport function isValidProbablitiy(num: any) {\n return isValidNumber(num) && num >= 0 && num <= 1.0;\n}\n", "import { isValidNumber } from '../utils/index';\n\nexport interface IDimensions {\n width: number\n height: number\n}\n\nexport class Dimensions implements IDimensions {\n private _width: number\n\n private _height: number\n\n constructor(width: number, height: number) {\n if (!isValidNumber(width) || !isValidNumber(height)) {\n throw new Error(`Dimensions.constructor - expected width and height to be valid numbers, instead have ${JSON.stringify({ width, height })}`);\n }\n\n this._width = width;\n this._height = height;\n }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public reverse(): Dimensions {\n return new Dimensions(1 / this.width, 1 / this.height);\n }\n}\n", "export interface IPoint {\n x: number\n y: number\n}\n\nexport class Point implements IPoint {\n private _x: number\n\n private _y: number\n\n constructor(x: number, y: number) {\n this._x = x;\n this._y = y;\n }\n\n get x(): number { return this._x; }\n\n get y(): number { return this._y; }\n\n public add(pt: IPoint): Point {\n return new Point(this.x + pt.x, this.y + pt.y);\n }\n\n public sub(pt: IPoint): Point {\n return new Point(this.x - pt.x, this.y - pt.y);\n }\n\n public mul(pt: IPoint): Point {\n return new Point(this.x * pt.x, this.y * pt.y);\n }\n\n public div(pt: IPoint): Point {\n return new Point(this.x / pt.x, this.y / pt.y);\n }\n\n public abs(): Point {\n return new Point(Math.abs(this.x), Math.abs(this.y));\n }\n\n public magnitude(): number {\n return Math.sqrt((this.x ** 2) + (this.y ** 2));\n }\n\n public floor(): Point {\n return new Point(Math.floor(this.x), Math.floor(this.y));\n }\n}\n", "import { isDimensions, isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { IDimensions } from './Dimensions';\nimport { Point } from './Point';\nimport { IRect } from './Rect';\n\nexport class Box implements IBoundingBox, IRect {\n public static isRect(rect: any): boolean {\n return !!rect && [rect.x, rect.y, rect.width, rect.height].every(isValidNumber);\n }\n\n public static assertIsValidBox(box: any, callee: string, allowNegativeDimensions: boolean = false) {\n if (!Box.isRect(box)) {\n throw new Error(`${callee} - invalid box: ${JSON.stringify(box)}, expected object with properties x, y, width, height`);\n }\n\n if (!allowNegativeDimensions && (box.width < 0 || box.height < 0)) {\n throw new Error(`${callee} - width (${box.width}) and height (${box.height}) must be positive numbers`);\n }\n }\n\n private _x: number\n\n private _y: number\n\n private _width: number\n\n private _height: number\n\n constructor(_box: IBoundingBox | IRect, allowNegativeDimensions: boolean = true) {\n const box = (_box || {}) as any;\n\n const isBbox = [box.left, box.top, box.right, box.bottom].every(isValidNumber);\n const isRect = [box.x, box.y, box.width, box.height].every(isValidNumber);\n\n if (!isRect && !isBbox) {\n throw new Error(`Box.constructor - expected box to be IBoundingBox | IRect, instead have ${JSON.stringify(box)}`);\n }\n\n const [x, y, width, height] = isRect\n ? [box.x, box.y, box.width, box.height]\n : [box.left, box.top, box.right - box.left, box.bottom - box.top];\n\n Box.assertIsValidBox({\n x, y, width, height,\n }, 'Box.constructor', allowNegativeDimensions);\n\n this._x = x;\n this._y = y;\n this._width = width;\n this._height = height;\n }\n\n public get x(): number { return this._x; }\n\n public get y(): number { return this._y; }\n\n public get width(): number { return this._width; }\n\n public get height(): number { return this._height; }\n\n public get left(): number { return this.x; }\n\n public get top(): number { return this.y; }\n\n public get right(): number { return this.x + this.width; }\n\n public get bottom(): number { return this.y + this.height; }\n\n public get area(): number { return this.width * this.height; }\n\n public get topLeft(): Point { return new Point(this.left, this.top); }\n\n public get topRight(): Point { return new Point(this.right, this.top); }\n\n public get bottomLeft(): Point { return new Point(this.left, this.bottom); }\n\n public get bottomRight(): Point { return new Point(this.right, this.bottom); }\n\n public round(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.round(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public floor(): Box {\n const [x, y, width, height] = [this.x, this.y, this.width, this.height]\n .map((val) => Math.floor(val));\n return new Box({\n x, y, width, height,\n });\n }\n\n public toSquare(): Box {\n let {\n x, y, width, height,\n } = this;\n const diff = Math.abs(width - height);\n if (width < height) {\n x -= (diff / 2);\n width += diff;\n }\n if (height < width) {\n y -= (diff / 2);\n height += diff;\n }\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public rescale(s: IDimensions | number): Box {\n const scaleX = isDimensions(s) ? (s as IDimensions).width : s as number;\n const scaleY = isDimensions(s) ? (s as IDimensions).height : s as number;\n return new Box({\n x: this.x * scaleX,\n y: this.y * scaleY,\n width: this.width * scaleX,\n height: this.height * scaleY,\n });\n }\n\n public pad(padX: number, padY: number): Box {\n const [x, y, width, height] = [\n this.x - (padX / 2),\n this.y - (padY / 2),\n this.width + padX,\n this.height + padY,\n ];\n return new Box({\n x, y, width, height,\n });\n }\n\n public clipAtImageBorders(imgWidth: number, imgHeight: number): Box {\n const {\n x, y, right, bottom,\n } = this;\n const clippedX = Math.max(x, 0);\n const clippedY = Math.max(y, 0);\n\n const newWidth = right - clippedX;\n const newHeight = bottom - clippedY;\n const clippedWidth = Math.min(newWidth, imgWidth - clippedX);\n const clippedHeight = Math.min(newHeight, imgHeight - clippedY);\n\n return (new Box({\n x: clippedX, y: clippedY, width: clippedWidth, height: clippedHeight,\n })).floor();\n }\n\n public shift(sx: number, sy: number): Box {\n const { width, height } = this;\n const x = this.x + sx;\n const y = this.y + sy;\n\n return new Box({\n x, y, width, height,\n });\n }\n\n public padAtBorders(imageHeight: number, imageWidth: number) {\n const w = this.width + 1;\n const h = this.height + 1;\n\n const dx = 1;\n const dy = 1;\n let edx = w;\n let edy = h;\n\n let x = this.left;\n let y = this.top;\n let ex = this.right;\n let ey = this.bottom;\n\n if (ex > imageWidth) {\n edx = -ex + imageWidth + w;\n ex = imageWidth;\n }\n if (ey > imageHeight) {\n edy = -ey + imageHeight + h;\n ey = imageHeight;\n }\n if (x < 1) {\n edy = 2 - x;\n x = 1;\n }\n if (y < 1) {\n edy = 2 - y;\n y = 1;\n }\n\n return {\n dy, edy, dx, edx, y, ey, x, ex, w, h,\n };\n }\n\n public calibrate(region: Box) {\n return new Box({\n left: this.left + (region.left * this.width),\n top: this.top + (region.top * this.height),\n right: this.right + (region.right * this.width),\n bottom: this.bottom + (region.bottom * this.height),\n }).toSquare().round();\n }\n}\n", "import { Box } from './Box';\n\nexport interface IBoundingBox {\n left: number\n top: number\n right: number\n bottom: number\n}\n\nexport class BoundingBox extends Box implements IBoundingBox {\n constructor(left: number, top: number, right: number, bottom: number, allowNegativeDimensions: boolean = false) {\n super({\n left, top, right, bottom,\n }, allowNegativeDimensions);\n }\n}\n", "import { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { IRect, Rect } from './Rect';\n\nexport class ObjectDetection {\n private _score: number\n\n private _classScore: number\n\n private _className: string\n\n private _box: Rect\n\n private _imageDims: Dimensions\n\n constructor(\n score: number,\n classScore: number,\n className: string,\n relativeBox: IRect,\n imageDims: IDimensions,\n ) {\n this._imageDims = new Dimensions(imageDims.width, imageDims.height);\n this._score = score;\n this._classScore = classScore;\n this._className = className;\n this._box = new Box(relativeBox).rescale(this._imageDims);\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n\n public get className(): string { return this._className; }\n\n public get box(): Box { return this._box; }\n\n public get imageDims(): Dimensions { return this._imageDims; }\n\n public get imageWidth(): number { return this.imageDims.width; }\n\n public get imageHeight(): number { return this.imageDims.height; }\n\n public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()); }\n\n public forSize(width: number, height: number): ObjectDetection {\n return new ObjectDetection(\n this.score,\n this.classScore,\n this.className,\n this.relativeBox,\n { width, height },\n );\n }\n}\n", "import { Box } from './Box';\nimport { IDimensions } from './Dimensions';\nimport { ObjectDetection } from './ObjectDetection';\nimport { Rect } from './Rect';\n\nexport interface IFaceDetecion {\n score: number\n box: Box\n}\n\nexport class FaceDetection extends ObjectDetection implements IFaceDetecion {\n constructor(\n score: number,\n relativeBox: Rect,\n imageDims: IDimensions,\n ) {\n super(score, score, '', relativeBox, imageDims);\n }\n\n public forSize(width: number, height: number): FaceDetection {\n const { score, relativeBox, imageDims } = super.forSize(width, height);\n return new FaceDetection(score, relativeBox, imageDims);\n }\n}\n", "import { Box } from '../classes/Box';\n\nexport function iou(box1: Box, box2: Box, isIOU: boolean = true) {\n const width = Math.max(0.0, Math.min(box1.right, box2.right) - Math.max(box1.left, box2.left));\n const height = Math.max(0.0, Math.min(box1.bottom, box2.bottom) - Math.max(box1.top, box2.top));\n const interSection = width * height;\n\n return isIOU\n ? interSection / (box1.area + box2.area - interSection)\n : interSection / Math.min(box1.area, box2.area);\n}\n", "import { BoundingBox, IPoint } from '../classes/index';\n\nexport function minBbox(pts: IPoint[]): BoundingBox {\n const xs = pts.map((pt) => pt.x);\n const ys = pts.map((pt) => pt.y);\n const minX = xs.reduce((min, x) => (x < min ? x : min), Infinity);\n const minY = ys.reduce((min, y) => (y < min ? y : min), Infinity);\n const maxX = xs.reduce((max, x) => (max < x ? x : max), 0);\n const maxY = ys.reduce((max, y) => (max < y ? y : max), 0);\n\n return new BoundingBox(minX, minY, maxX, maxY);\n}\n", "import { Box } from '../classes/Box';\nimport { iou } from './iou';\n\nexport function nonMaxSuppression(\n boxes: Box[],\n scores: number[],\n iouThreshold: number,\n isIOU: boolean = true,\n): number[] {\n let indicesSortedByScore = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .sort((c1, c2) => c1.score - c2.score)\n .map((c) => c.boxIndex);\n\n const pick: number[] = [];\n\n while (indicesSortedByScore.length > 0) {\n const curr = indicesSortedByScore.pop() as number;\n pick.push(curr);\n\n const indices = indicesSortedByScore;\n\n const outputs: number[] = [];\n for (let i = 0; i < indices.length; i++) {\n const idx = indices[i];\n\n const currBox = boxes[curr];\n const idxBox = boxes[idx];\n\n outputs.push(iou(currBox, idxBox, isIOU));\n }\n\n indicesSortedByScore = indicesSortedByScore.filter(\n (_, j) => outputs[j] <= iouThreshold,\n );\n }\n\n return pick;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function normalize(x: tf.Tensor4D, meanRgb: number[]): tf.Tensor4D {\n return tf.tidy(() => {\n const [r, g, b] = meanRgb;\n const avg_r = tf.fill([...x.shape.slice(0, 3), 1], r, 'float32');\n const avg_g = tf.fill([...x.shape.slice(0, 3), 1], g, 'float32');\n const avg_b = tf.fill([...x.shape.slice(0, 3), 1], b, 'float32');\n const avg_rgb = tf.concat([avg_r, avg_g, avg_b], 3);\n\n return tf.sub(x, avg_rgb);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n/**\n * Pads the smaller dimension of an image tensor with zeros, such that width === height.\n *\n * @param imgTensor The image tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The padded tensor with width === height.\n */\nexport function padToSquare(\n imgTensor: tf.Tensor4D,\n isCenterImage: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const [height, width] = imgTensor.shape.slice(1);\n if (height === width) {\n return imgTensor;\n }\n\n const dimDiff = Math.abs(height - width);\n const paddingAmount = Math.round(dimDiff * (isCenterImage ? 0.5 : 1));\n const paddingAxis = height > width ? 2 : 1;\n\n const createPaddingTensor = (paddingAmountLocal: number): tf.Tensor => {\n const paddingTensorShape = imgTensor.shape.slice();\n paddingTensorShape[paddingAxis] = paddingAmountLocal;\n return tf.fill(paddingTensorShape, 0, 'float32');\n };\n\n const paddingTensorAppend = createPaddingTensor(paddingAmount);\n const remainingPaddingAmount = dimDiff - (paddingTensorAppend.shape[paddingAxis] as number);\n\n const paddingTensorPrepend = isCenterImage && remainingPaddingAmount\n ? createPaddingTensor(remainingPaddingAmount)\n : null;\n\n const tensorsToStack = [\n paddingTensorPrepend,\n imgTensor,\n paddingTensorAppend,\n ]\n .filter((t) => !!t)\n // .map((t: tf.Tensor) => t.toFloat()) as tf.Tensor4D[]\n .map((t: tf.Tensor) => tf.cast(t, 'float32')) as tf.Tensor4D[];\n return tf.concat(tensorsToStack, paddingAxis);\n });\n}\n", "export function shuffleArray(inputArray: any[]) {\n const array = inputArray.slice();\n for (let i = array.length - 1; i > 0; i--) {\n const j = Math.floor(Math.random() * (i + 1));\n const x = array[i];\n array[i] = array[j];\n array[j] = x;\n }\n return array;\n}\n", "export * from './iou';\nexport * from './minBbox';\nexport * from './nonMaxSuppression';\nexport * from './normalize';\nexport * from './padToSquare';\nexport * from './shuffleArray';\n\nexport function sigmoid(x: number) {\n return 1 / (1 + Math.exp(-x));\n}\n\nexport function inverseSigmoid(x: number) {\n return Math.log(x / (1 - x));\n}\n", "import { Box } from './Box';\n\nexport interface IRect {\n x: number\n y: number\n width: number\n height: number\n}\n\nexport class Rect extends Box implements IRect {\n constructor(x: number, y: number, width: number, height: number, allowNegativeDimensions: boolean = false) {\n super({\n x, y, width, height,\n }, allowNegativeDimensions);\n }\n}\n", "import { minBbox } from '../ops/index';\nimport { getCenterPoint } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { Dimensions, IDimensions } from './Dimensions';\nimport { FaceDetection } from './FaceDetection';\nimport { Point } from './Point';\nimport { IRect, Rect } from './Rect';\n\n// face alignment constants\nconst relX = 0.5;\nconst relY = 0.43;\nconst relScale = 0.45;\n\nexport interface IFaceLandmarks {\n positions: Point[]\n shift: Point\n}\n\nexport class FaceLandmarks implements IFaceLandmarks {\n protected _shift: Point\n\n protected _positions: Point[]\n\n protected _imgDims: Dimensions\n\n constructor(\n relativeFaceLandmarkPositions: Point[],\n imgDims: IDimensions,\n shift: Point = new Point(0, 0),\n ) {\n const { width, height } = imgDims;\n this._imgDims = new Dimensions(width, height);\n this._shift = shift;\n this._positions = relativeFaceLandmarkPositions.map(\n (pt) => pt.mul(new Point(width, height)).add(shift),\n );\n }\n\n public get shift(): Point { return new Point(this._shift.x, this._shift.y); }\n\n public get imageWidth(): number { return this._imgDims.width; }\n\n public get imageHeight(): number { return this._imgDims.height; }\n\n public get positions(): Point[] { return this._positions; }\n\n public get relativePositions(): Point[] {\n return this._positions.map(\n (pt) => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight)),\n );\n }\n\n public forSize(width: number, height: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n { width, height },\n );\n }\n\n public shiftBy(x: number, y: number): T {\n return new (this.constructor as any)(\n this.relativePositions,\n this._imgDims,\n new Point(x, y),\n );\n }\n\n public shiftByPoint(pt: Point): T {\n return this.shiftBy(pt.x, pt.y);\n }\n\n /**\n * Aligns the face landmarks after face detection from the relative positions of the faces\n * bounding box, or it's current shift. This function should be used to align the face images\n * after face detection has been performed, before they are passed to the face recognition net.\n * This will make the computed face descriptor more accurate.\n *\n * @param detection (optional) The bounding box of the face or the face detection result. If\n * no argument was passed the position of the face landmarks are assumed to be relative to\n * it's current shift.\n * @returns The bounding box of the aligned face.\n */\n public align(\n detection?: FaceDetection | IRect | IBoundingBox | null,\n options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { },\n ): Box {\n if (detection) {\n const box = detection instanceof FaceDetection\n ? detection.box.floor()\n : new Box(detection);\n\n return this.shiftBy(box.x, box.y).align(null, options);\n }\n\n const { useDlibAlignment, minBoxPadding } = { useDlibAlignment: false, minBoxPadding: 0.2, ...options };\n\n if (useDlibAlignment) {\n return this.alignDlib();\n }\n\n return this.alignMinBbox(minBoxPadding);\n }\n\n private alignDlib(): Box {\n const centers = this.getRefPointsForAlignment();\n\n const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers;\n const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude();\n const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;\n\n const size = Math.floor(eyeToMouthDist / relScale);\n\n const refPoint = getCenterPoint(centers);\n // TODO: pad in case rectangle is out of image bounds\n const x = Math.floor(Math.max(0, refPoint.x - (relX * size)));\n const y = Math.floor(Math.max(0, refPoint.y - (relY * size)));\n\n return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y));\n }\n\n private alignMinBbox(padding: number): Box {\n const box = minBbox(this.positions);\n return box.pad(box.width * padding, box.height * padding);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n throw new Error('getRefPointsForAlignment not implemented by base class');\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks5 extends FaceLandmarks {\n protected getRefPointsForAlignment(): Point[] {\n const pts = this.positions;\n return [\n pts[0],\n pts[1],\n getCenterPoint([pts[3], pts[4]]),\n ];\n }\n}\n", "import { getCenterPoint } from '../utils/index';\nimport { FaceLandmarks } from './FaceLandmarks';\nimport { Point } from './Point';\n\nexport class FaceLandmarks68 extends FaceLandmarks {\n public getJawOutline(): Point[] {\n return this.positions.slice(0, 17);\n }\n\n public getLeftEyeBrow(): Point[] {\n return this.positions.slice(17, 22);\n }\n\n public getRightEyeBrow(): Point[] {\n return this.positions.slice(22, 27);\n }\n\n public getNose(): Point[] {\n return this.positions.slice(27, 36);\n }\n\n public getLeftEye(): Point[] {\n return this.positions.slice(36, 42);\n }\n\n public getRightEye(): Point[] {\n return this.positions.slice(42, 48);\n }\n\n public getMouth(): Point[] {\n return this.positions.slice(48, 68);\n }\n\n protected getRefPointsForAlignment(): Point[] {\n return [\n this.getLeftEye(),\n this.getRightEye(),\n this.getMouth(),\n ].map(getCenterPoint);\n }\n}\n", "import { round } from '../utils/index';\n\nexport interface IFaceMatch {\n label: string\n distance: number\n}\n\nexport class FaceMatch implements IFaceMatch {\n private _label: string\n\n private _distance: number\n\n constructor(label: string, distance: number) {\n this._label = label;\n this._distance = distance;\n }\n\n public get label(): string { return this._label; }\n\n public get distance(): number { return this._distance; }\n\n public toString(withDistance: boolean = true): string {\n return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`;\n }\n}\n", "import { isValidNumber } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { Box } from './Box';\nimport { IRect } from './Rect';\n\nexport class LabeledBox extends Box {\n public static assertIsValidLabeledBox(box: any, callee: string) {\n Box.assertIsValidBox(box, callee);\n\n if (!isValidNumber(box.label)) {\n throw new Error(`${callee} - expected property label (${box.label}) to be a number`);\n }\n }\n\n private _label: number\n\n constructor(box: IBoundingBox | IRect | any, label: number) {\n super(box);\n this._label = label;\n }\n\n public get label(): number { return this._label; }\n}\n", "export class LabeledFaceDescriptors {\n private _label: string\n\n private _descriptors: Float32Array[]\n\n constructor(label: string, descriptors: Float32Array[]) {\n if (!(typeof label === 'string')) {\n throw new Error('LabeledFaceDescriptors - constructor expected label to be a string');\n }\n\n if (!Array.isArray(descriptors) || descriptors.some((desc) => !(desc instanceof Float32Array))) {\n throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array');\n }\n\n this._label = label;\n this._descriptors = descriptors;\n }\n\n public get label(): string { return this._label; }\n\n public get descriptors(): Float32Array[] { return this._descriptors; }\n\n public toJSON(): any {\n return {\n label: this.label,\n descriptors: this.descriptors.map((d) => Array.from(d)),\n };\n }\n\n public static fromJSON(json: any): LabeledFaceDescriptors {\n const descriptors = json.descriptors.map((d: any) => new Float32Array(d));\n return new LabeledFaceDescriptors(json.label, descriptors);\n }\n}\n", "import { isValidProbablitiy } from '../utils/index';\nimport { IBoundingBox } from './BoundingBox';\nimport { LabeledBox } from './LabeledBox';\nimport { IRect } from './Rect';\n\nexport class PredictedBox extends LabeledBox {\n public static assertIsValidPredictedBox(box: any, callee: string) {\n LabeledBox.assertIsValidLabeledBox(box, callee);\n\n if (\n !isValidProbablitiy(box.score)\n || !isValidProbablitiy(box.classScore)\n ) {\n throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`);\n }\n }\n\n private _score: number\n\n private _classScore: number\n\n constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {\n super(box, label);\n this._score = score;\n this._classScore = classScore;\n }\n\n public get score(): number { return this._score; }\n\n public get classScore(): number { return this._classScore; }\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\n\nexport type WithFaceDetection = TSource & {\n detection: FaceDetection\n}\n\nexport function isWithFaceDetection(obj: any): obj is WithFaceDetection<{}> {\n return obj.detection instanceof FaceDetection;\n}\n\nexport function extendWithFaceDetection<\n TSource\n>(\n sourceObj: TSource,\n detection: FaceDetection,\n): WithFaceDetection {\n const extension = { detection };\n return { ...sourceObj, ...extension };\n}\n", "import { Environment } from './types';\n\nexport function createBrowserEnv(): Environment {\n const fetch = window.fetch;\n if (!fetch) throw new Error('fetch - missing fetch implementation for browser environment');\n\n const readFile = () => {\n throw new Error('readFile - filesystem not available for browser environment');\n };\n\n return {\n Canvas: HTMLCanvasElement,\n CanvasRenderingContext2D,\n Image: HTMLImageElement,\n ImageData,\n Video: HTMLVideoElement,\n createCanvasElement: () => document.createElement('canvas'),\n createImageElement: () => document.createElement('img'),\n fetch,\n readFile,\n };\n}\n", "import { FileSystem } from './types';\n\nexport function createFileSystem(fs?: any): FileSystem {\n let requireFsError = '';\n\n if (!fs) {\n try {\n // eslint-disable-next-line global-require\n fs = require('fs');\n } catch (err) {\n requireFsError = err.toString();\n }\n }\n\n const readFile = fs\n ? (filePath: string) => new Promise((resolve, reject) => {\n fs.readFile(filePath, (err: any, buffer: Buffer) => (err ? reject(err) : resolve(buffer)));\n })\n : () => {\n throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`);\n };\n\n return {\n readFile,\n };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { createFileSystem } from './createFileSystem';\nimport { Environment } from './types';\n\nexport function createNodejsEnv(): Environment {\n // eslint-disable-next-line dot-notation\n const Canvas = global['Canvas'] || global.HTMLCanvasElement;\n const Image = global.Image || global.HTMLImageElement;\n\n const createCanvasElement = () => {\n if (Canvas) return new Canvas();\n throw new Error('createCanvasElement - missing Canvas implementation for nodejs environment');\n };\n\n const createImageElement = () => {\n if (Image) return new Image();\n throw new Error('createImageElement - missing Image implementation for nodejs environment');\n };\n\n const fetch = global.fetch;\n // if (!fetch) throw new Error('fetch - missing fetch implementation for nodejs environment');\n\n const fileSystem = createFileSystem();\n\n return {\n Canvas: Canvas || class {},\n CanvasRenderingContext2D: global.CanvasRenderingContext2D || class {},\n Image: Image || class {},\n ImageData: global.ImageData || class {},\n Video: global.HTMLVideoElement || class {},\n createCanvasElement,\n createImageElement,\n fetch,\n ...fileSystem,\n };\n}\n", "export function isBrowser(): boolean {\n return typeof window === 'object'\n && typeof document !== 'undefined'\n && typeof HTMLImageElement !== 'undefined'\n && typeof HTMLCanvasElement !== 'undefined'\n && typeof HTMLVideoElement !== 'undefined'\n && typeof ImageData !== 'undefined'\n && typeof CanvasRenderingContext2D !== 'undefined';\n}\n", "import { createBrowserEnv } from './createBrowserEnv';\nimport { createFileSystem } from './createFileSystem';\nimport { createNodejsEnv } from './createNodejsEnv';\nimport { isBrowser } from './isBrowser';\nimport { isNodejs } from './isNodejs';\nimport { Environment } from './types';\n\nlet environment: Environment | null;\n\nfunction getEnv(): Environment {\n if (!environment) {\n throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()');\n }\n return environment;\n}\n\nfunction setEnv(env: Environment) {\n environment = env;\n}\n\nfunction initialize() {\n // check for isBrowser() first to prevent electron renderer process\n // to be initialized with wrong environment due to isNodejs() returning true\n if (isBrowser()) return setEnv(createBrowserEnv());\n if (isNodejs()) return setEnv(createNodejsEnv());\n return null;\n}\n\nfunction monkeyPatch(env: Partial) {\n if (!environment) {\n initialize();\n }\n\n if (!environment) {\n throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()');\n }\n\n const { Canvas = environment.Canvas, Image = environment.Image } = env;\n environment.Canvas = Canvas;\n environment.Image = Image;\n environment.createCanvasElement = env.createCanvasElement || (() => new Canvas());\n environment.createImageElement = env.createImageElement || (() => new Image());\n\n environment.ImageData = env.ImageData || environment.ImageData;\n environment.Video = env.Video || environment.Video;\n environment.fetch = env.fetch || environment.fetch;\n environment.readFile = env.readFile || environment.readFile;\n}\n\nexport const env = {\n getEnv,\n setEnv,\n initialize,\n createBrowserEnv,\n createFileSystem,\n createNodejsEnv,\n monkeyPatch,\n isBrowser,\n isNodejs,\n};\n\ninitialize();\n\nexport * from './types';\n", "import { env } from '../env/index';\n\nexport function resolveInput(arg: string | any) {\n if (!env.isNodejs() && typeof arg === 'string') {\n return document.getElementById(arg);\n }\n return arg;\n}\n", "import { env } from '../env/index';\nimport { resolveInput } from './resolveInput';\n\nexport function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {\n const { Canvas, CanvasRenderingContext2D } = env.getEnv();\n\n if (canvasArg instanceof CanvasRenderingContext2D) {\n return canvasArg;\n }\n\n const canvas = resolveInput(canvasArg);\n\n if (!(canvas instanceof Canvas)) {\n throw new Error('resolveContext2d - expected canvas to be of instance of Canvas');\n }\n\n const ctx = canvas.getContext('2d');\n if (!ctx) {\n throw new Error('resolveContext2d - canvas 2d context is null');\n }\n\n return ctx;\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IDimensions, IPoint } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { resolveInput } from '../dom/resolveInput';\n\n// eslint-disable-next-line no-shadow\nexport enum AnchorPosition {\n // eslint-disable-next-line no-unused-vars\n TOP_LEFT = 'TOP_LEFT',\n // eslint-disable-next-line no-unused-vars\n TOP_RIGHT = 'TOP_RIGHT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_LEFT = 'BOTTOM_LEFT',\n // eslint-disable-next-line no-unused-vars\n BOTTOM_RIGHT = 'BOTTOM_RIGHT'\n}\n\nexport interface IDrawTextFieldOptions {\n anchorPosition?: AnchorPosition\n backgroundColor?: string\n fontColor?: string\n fontSize?: number\n fontStyle?: string\n padding?: number\n}\n\nexport class DrawTextFieldOptions implements IDrawTextFieldOptions {\n public anchorPosition: AnchorPosition\n\n public backgroundColor: string\n\n public fontColor: string\n\n public fontSize: number\n\n public fontStyle: string\n\n public padding: number\n\n constructor(options: IDrawTextFieldOptions = {}) {\n const {\n anchorPosition, backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = options;\n this.anchorPosition = anchorPosition || AnchorPosition.TOP_LEFT;\n this.backgroundColor = backgroundColor || 'rgba(0, 0, 0, 0.5)';\n this.fontColor = fontColor || 'rgba(255, 255, 255, 1)';\n this.fontSize = fontSize || 14;\n this.fontStyle = fontStyle || 'Georgia';\n this.padding = padding || 4;\n }\n}\n\nexport class DrawTextField {\n public text: string[]\n\n public anchor : IPoint\n\n public options: DrawTextFieldOptions\n\n constructor(\n text: string | string[] | DrawTextField,\n anchor: IPoint,\n options: IDrawTextFieldOptions = {},\n ) {\n // eslint-disable-next-line no-nested-ternary\n this.text = typeof text === 'string'\n ? [text]\n : (text instanceof DrawTextField ? text.text : text);\n this.anchor = anchor;\n this.options = new DrawTextFieldOptions(options);\n }\n\n measureWidth(ctx: CanvasRenderingContext2D): number {\n const { padding } = this.options;\n return this.text.map((l) => ctx.measureText(l).width).reduce((w0, w1) => (w0 < w1 ? w1 : w0), 0) + (2 * padding);\n }\n\n measureHeight(): number {\n const { fontSize, padding } = this.options;\n return this.text.length * fontSize + (2 * padding);\n }\n\n getUpperLeft(ctx: CanvasRenderingContext2D, canvasDims?: IDimensions): IPoint {\n const { anchorPosition } = this.options;\n const isShiftLeft = anchorPosition === AnchorPosition.BOTTOM_RIGHT || anchorPosition === AnchorPosition.TOP_RIGHT;\n const isShiftTop = anchorPosition === AnchorPosition.BOTTOM_LEFT || anchorPosition === AnchorPosition.BOTTOM_RIGHT;\n\n const textFieldWidth = this.measureWidth(ctx);\n const textFieldHeight = this.measureHeight();\n const x = (isShiftLeft ? this.anchor.x - textFieldWidth : this.anchor.x);\n const y = isShiftTop ? this.anchor.y - textFieldHeight : this.anchor.y;\n\n // adjust anchor if text box exceeds canvas borders\n if (canvasDims) {\n const { width, height } = canvasDims;\n const newX = Math.max(Math.min(x, width - textFieldWidth), 0);\n const newY = Math.max(Math.min(y, height - textFieldHeight), 0);\n return { x: newX, y: newY };\n }\n return { x, y };\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const canvas = resolveInput(canvasArg);\n const ctx = getContext2dOrThrow(canvas);\n\n const {\n backgroundColor, fontColor, fontSize, fontStyle, padding,\n } = this.options;\n\n ctx.font = `${fontSize}px ${fontStyle}`;\n const maxTextWidth = this.measureWidth(ctx);\n const textHeight = this.measureHeight();\n\n ctx.fillStyle = backgroundColor;\n const upperLeft = this.getUpperLeft(ctx, canvas);\n ctx.fillRect(upperLeft.x, upperLeft.y, maxTextWidth, textHeight);\n\n ctx.fillStyle = fontColor;\n this.text.forEach((textLine, i) => {\n const x = padding + upperLeft.x;\n const y = padding + upperLeft.y + ((i + 1) * fontSize);\n ctx.fillText(textLine, x, y);\n });\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { Box, IBoundingBox, IRect } from '../classes/index';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport {\n AnchorPosition, DrawTextField, DrawTextFieldOptions, IDrawTextFieldOptions,\n} from './DrawTextField';\n\nexport interface IDrawBoxOptions {\n boxColor?: string\n lineWidth?: number\n drawLabelOptions?: IDrawTextFieldOptions\n label?: string\n}\n\nexport class DrawBoxOptions {\n public boxColor: string\n\n public lineWidth: number\n\n public drawLabelOptions: DrawTextFieldOptions\n\n public label?: string\n\n constructor(options: IDrawBoxOptions = {}) {\n const {\n boxColor, lineWidth, label, drawLabelOptions,\n } = options;\n this.boxColor = boxColor || 'rgba(0, 0, 255, 1)';\n this.lineWidth = lineWidth || 2;\n this.label = label;\n\n const defaultDrawLabelOptions = {\n anchorPosition: AnchorPosition.BOTTOM_LEFT,\n backgroundColor: this.boxColor,\n };\n this.drawLabelOptions = new DrawTextFieldOptions({ ...defaultDrawLabelOptions, ...drawLabelOptions });\n }\n}\n\nexport class DrawBox {\n public box: Box\n\n public options: DrawBoxOptions\n\n constructor(\n box: IBoundingBox | IRect,\n options: IDrawBoxOptions = {},\n ) {\n this.box = new Box(box);\n this.options = new DrawBoxOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const { boxColor, lineWidth } = this.options;\n\n const {\n x, y, width, height,\n } = this.box;\n ctx.strokeStyle = boxColor;\n ctx.lineWidth = lineWidth;\n ctx.strokeRect(x, y, width, height);\n\n const { label } = this.options;\n if (label) {\n new DrawTextField([label], { x: x - (lineWidth / 2), y }, this.options.drawLabelOptions).draw(canvasArg);\n }\n }\n}\n", "import { Box, IBoundingBox, IRect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { round } from '../utils/index';\nimport { DrawBox } from './DrawBox';\n\nexport type TDrawDetectionsInput = IRect | IBoundingBox | FaceDetection | WithFaceDetection<{}>\n\nexport function drawDetections(\n canvasArg: string | HTMLCanvasElement,\n detections: TDrawDetectionsInput | Array,\n) {\n const detectionsArray = Array.isArray(detections) ? detections : [detections];\n\n detectionsArray.forEach((det) => {\n // eslint-disable-next-line no-nested-ternary\n const score = det instanceof FaceDetection\n ? det.score\n : (isWithFaceDetection(det) ? det.detection.score : undefined);\n\n // eslint-disable-next-line no-nested-ternary\n const box = det instanceof FaceDetection\n ? det.box\n : (isWithFaceDetection(det) ? det.detection.box : new Box(det));\n\n const label = score ? `${round(score)}` : undefined;\n new DrawBox(box, { label }).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { FaceExpressions } from './FaceExpressions';\n\nexport class FaceExpressionNet extends FaceProcessor {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceExpressionNet', faceFeatureExtractor);\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n return tf.tidy(() => tf.softmax(this.runNet(input)));\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictExpressions(input: TNetInput) {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n const probabilitesByBatch = await Promise.all(tf.unstack(out).map(async (t) => {\n const data = await t.data();\n t.dispose();\n return data;\n }));\n out.dispose();\n\n const predictionsByBatch = probabilitesByBatch\n .map((probabilites) => new FaceExpressions(probabilites as Float32Array));\n\n return netInput.isBatchInput\n ? predictionsByBatch\n : predictionsByBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_expression_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n\n protected getClassifierChannelsOut(): number {\n return 7;\n }\n}\n", "import { env } from '../env/index';\n\nexport function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {\n const { Image, Video } = env.getEnv();\n\n return (media instanceof Image && media.complete)\n || (media instanceof Video && media.readyState >= 3);\n}\n", "import { env } from '../env/index';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {\n // eslint-disable-next-line consistent-return\n return new Promise((resolve, reject) => {\n if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {\n return resolve(null);\n }\n\n function onError(e: Event) {\n if (!e.currentTarget) return;\n // eslint-disable-next-line no-use-before-define\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n reject(e);\n }\n\n function onLoad(e: Event) {\n if (!e.currentTarget) return;\n e.currentTarget.removeEventListener('load', onLoad);\n e.currentTarget.removeEventListener('error', onError);\n resolve(e);\n }\n\n media.addEventListener('load', onLoad);\n media.addEventListener('error', onError);\n });\n}\n", "import { env } from '../env/index';\n\nexport function bufferToImage(buf: Blob): Promise {\n return new Promise((resolve, reject) => {\n if (!(buf instanceof Blob)) reject(new Error('bufferToImage - expected buf to be of type: Blob'));\n const reader = new FileReader();\n reader.onload = () => {\n if (typeof reader.result !== 'string') reject(new Error('bufferToImage - expected reader.result to be a string, in onload'));\n const img = env.getEnv().createImageElement();\n img.onload = () => resolve(img);\n img.onerror = reject;\n img.src = reader.result as string;\n };\n reader.onerror = reject;\n reader.readAsDataURL(buf);\n });\n}\n", "import { Dimensions, IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\n\nexport function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {\n const { Image, Video } = env.getEnv();\n\n if (input instanceof Image) {\n return new Dimensions(input.naturalWidth, input.naturalHeight);\n }\n if (input instanceof Video) {\n return new Dimensions(input.videoWidth, input.videoHeight);\n }\n return new Dimensions(input.width, input.height);\n}\n", "import { IDimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\nimport { isMediaLoaded } from './isMediaLoaded';\n\nexport function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {\n const { createCanvasElement } = env.getEnv();\n const canvas = createCanvasElement();\n canvas.width = width;\n canvas.height = height;\n return canvas;\n}\n\nexport function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {\n const { ImageData } = env.getEnv();\n\n if (!(media instanceof ImageData) && !isMediaLoaded(media)) {\n throw new Error('createCanvasFromMedia - media has not finished loading yet');\n }\n\n const { width, height } = dims || getMediaDimensions(media);\n const canvas = createCanvas({ width, height });\n\n if (media instanceof ImageData) {\n getContext2dOrThrow(canvas).putImageData(media, 0, 0);\n } else {\n getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height);\n }\n return canvas;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { env } from '../env/index';\nimport { isTensor4D } from '../utils/index';\n\nexport async function imageTensorToCanvas(\n imgTensor: tf.Tensor,\n canvas?: HTMLCanvasElement,\n): Promise {\n const targetCanvas = canvas || env.getEnv().createCanvasElement();\n\n const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0);\n const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt());\n await tf.browser.toPixels(imgTensor3D, targetCanvas);\n\n imgTensor3D.dispose();\n\n return targetCanvas;\n}\n", "import { env } from '../env/index';\n\nexport function isMediaElement(input: any) {\n const { Image, Canvas, Video } = env.getEnv();\n\n return input instanceof Image\n || input instanceof Canvas\n || input instanceof Video;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Dimensions } from '../classes/Dimensions';\nimport { env } from '../env/index';\nimport { padToSquare } from '../ops/padToSquare';\nimport {\n computeReshapedDimensions, isTensor3D, isTensor4D, range,\n} from '../utils/index';\nimport { createCanvasFromMedia } from './createCanvas';\nimport { imageToSquare } from './imageToSquare';\nimport { TResolvedNetInput } from './types';\n\nexport class NetInput {\n private _imageTensors: Array = []\n\n private _canvases: HTMLCanvasElement[] = []\n\n private _batchSize: number\n\n private _treatAsBatchInput: boolean = false\n\n private _inputDimensions: number[][] = []\n\n private _inputSize: number\n\n constructor(\n inputs: Array,\n treatAsBatchInput: boolean = false,\n ) {\n if (!Array.isArray(inputs)) {\n throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`);\n }\n\n this._treatAsBatchInput = treatAsBatchInput;\n this._batchSize = inputs.length;\n\n inputs.forEach((input, idx) => {\n if (isTensor3D(input)) {\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = input.shape;\n return;\n }\n\n if (isTensor4D(input)) {\n const batchSize = (input as any).shape[0];\n if (batchSize !== 1) {\n throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n\n this._imageTensors[idx] = input;\n this._inputDimensions[idx] = (input as any).shape.slice(1);\n return;\n }\n\n const canvas = (input as any) instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input);\n this._canvases[idx] = canvas;\n this._inputDimensions[idx] = [canvas.height, canvas.width, 3];\n });\n }\n\n public get imageTensors(): Array {\n return this._imageTensors;\n }\n\n public get canvases(): HTMLCanvasElement[] {\n return this._canvases;\n }\n\n public get isBatchInput(): boolean {\n return this.batchSize > 1 || this._treatAsBatchInput;\n }\n\n public get batchSize(): number {\n return this._batchSize;\n }\n\n public get inputDimensions(): number[][] {\n return this._inputDimensions;\n }\n\n public get inputSize(): number | undefined {\n return this._inputSize;\n }\n\n public get reshapedInputDimensions(): Dimensions[] {\n return range(this.batchSize, 0, 1).map(\n (_, batchIdx) => this.getReshapedInputDimensions(batchIdx),\n );\n }\n\n public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {\n return this.canvases[batchIdx] || this.imageTensors[batchIdx];\n }\n\n public getInputDimensions(batchIdx: number): number[] {\n return this._inputDimensions[batchIdx];\n }\n\n public getInputHeight(batchIdx: number): number {\n return this._inputDimensions[batchIdx][0];\n }\n\n public getInputWidth(batchIdx: number): number {\n return this._inputDimensions[batchIdx][1];\n }\n\n public getReshapedInputDimensions(batchIdx: number): Dimensions {\n if (typeof this.inputSize !== 'number') {\n throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet');\n }\n\n const width = this.getInputWidth(batchIdx);\n const height = this.getInputHeight(batchIdx);\n return computeReshapedDimensions({ width, height }, this.inputSize);\n }\n\n /**\n * Create a batch tensor from all input canvases and tensors\n * with size [batchSize, inputSize, inputSize, 3].\n *\n * @param inputSize Height and width of the tensor.\n * @param isCenterImage (optional, default: false) If true, add an equal amount of padding on\n * both sides of the minor dimension oof the image.\n * @returns The batch tensor.\n */\n public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {\n this._inputSize = inputSize;\n\n return tf.tidy(() => {\n const inputTensors = range(this.batchSize, 0, 1).map((batchIdx) => {\n const input = this.getInput(batchIdx);\n\n if (input instanceof tf.Tensor) {\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n let imgTensor = isTensor4D(input) ? input : input.expandDims();\n // @ts-ignore: error TS2344: Type 'Rank.R4' does not satisfy the constraint 'Tensor'.\n imgTensor = padToSquare(imgTensor, isCenterInputs);\n\n if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {\n imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize]);\n }\n\n return imgTensor.as3D(inputSize, inputSize, 3);\n }\n\n if (input instanceof env.getEnv().Canvas) {\n return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs));\n }\n\n throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`);\n });\n\n // const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)\n const batchTensor = tf.stack(inputTensors.map((t) => tf.cast(t, 'float32'))).as4D(this.batchSize, inputSize, inputSize, 3);\n // const batchTensor = tf.stack(inputTensors.map(t => tf.Tensor.as4D(tf.cast(t, 'float32'))), this.batchSize, inputSize, inputSize, 3);\n\n return batchTensor;\n });\n }\n}\n", "import { env } from '../env/index';\nimport { createCanvas, createCanvasFromMedia } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {\n const { Image, Canvas } = env.getEnv();\n\n if (!(input instanceof Image || input instanceof Canvas)) {\n throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement');\n }\n\n const dims = getMediaDimensions(input);\n const scale = inputSize / Math.max(dims.height, dims.width);\n const width = scale * dims.width;\n const height = scale * dims.height;\n\n const targetCanvas = createCanvas({ width: inputSize, height: inputSize });\n const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input);\n\n const offset = Math.abs(width - height) / 2;\n const dx = centerImage && width < height ? offset : 0;\n const dy = centerImage && height < width ? offset : 0;\n getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height);\n\n return targetCanvas;\n}\n", "import { isTensor3D, isTensor4D } from '../utils/index';\nimport { awaitMediaLoaded } from './awaitMediaLoaded';\nimport { isMediaElement } from './isMediaElement';\nimport { NetInput } from './NetInput';\nimport { resolveInput } from './resolveInput';\nimport { TNetInput } from './types';\n\n/**\n * Validates the input to make sure, they are valid net inputs and awaits all media elements\n * to be finished loading.\n *\n * @param input The input, which can be a media element or an array of different media elements.\n * @returns A NetInput instance, which can be passed into one of the neural networks.\n */\nexport async function toNetInput(inputs: TNetInput): Promise {\n if (inputs instanceof NetInput) {\n return inputs;\n }\n\n const inputArgArray = Array.isArray(inputs)\n ? inputs\n : [inputs];\n\n if (!inputArgArray.length) {\n throw new Error('toNetInput - empty array passed as input');\n }\n\n const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');\n\n const inputArray = inputArgArray.map(resolveInput);\n\n inputArray.forEach((input, i) => {\n if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {\n if (typeof inputArgArray[i] === 'string') {\n throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);\n }\n\n throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);\n }\n\n if (isTensor4D(input)) {\n // if tf.Tensor4D is passed in the input array, the batch size has to be 1\n const batchSize = input.shape[0];\n if (batchSize !== 1) {\n throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);\n }\n }\n });\n\n // wait for all media elements being loaded\n await Promise.all(\n inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),\n );\n\n return new NetInput(inputArray, Array.isArray(inputs));\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { Rect } from '../classes/Rect';\nimport { env } from '../env/index';\nimport { createCanvas } from './createCanvas';\nimport { getContext2dOrThrow } from './getContext2dOrThrow';\nimport { imageTensorToCanvas } from './imageTensorToCanvas';\nimport { toNetInput } from './toNetInput';\nimport { TNetInput } from './types';\n\n/**\n * Extracts the image regions containing the detected faces.\n *\n * @param input The image that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns The Canvases of the corresponding image region for each detected face.\n */\nexport async function extractFaces(\n input: TNetInput,\n detections: Array,\n): Promise {\n const { Canvas } = env.getEnv();\n\n let canvas = input as HTMLCanvasElement;\n\n if (!(input instanceof Canvas)) {\n const netInput = await toNetInput(input);\n\n if (netInput.batchSize > 1) {\n throw new Error('extractFaces - batchSize > 1 not supported');\n }\n\n const tensorOrCanvas = netInput.getInput(0);\n canvas = tensorOrCanvas instanceof Canvas\n ? tensorOrCanvas\n : await imageTensorToCanvas(tensorOrCanvas);\n }\n\n const ctx = getContext2dOrThrow(canvas);\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(canvas.width, canvas.height).box.floor()\n : det),\n )\n .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));\n\n return boxes.map(({\n x, y, width, height,\n }) => {\n const faceImg = createCanvas({ width, height });\n getContext2dOrThrow(faceImg)\n .putImageData(ctx.getImageData(x, y, width, height), 0, 0);\n return faceImg;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { isTensor3D, isTensor4D } from '../utils/index';\n\n/**\n * Extracts the tensors of the image regions containing the detected faces.\n * Useful if you want to compute the face descriptors for the face images.\n * Using this method is faster then extracting a canvas for each face and\n * converting them to tensors individually.\n *\n * @param imageTensor The image tensor that face detection has been performed on.\n * @param detections The face detection results or face bounding boxes for that image.\n * @returns Tensors of the corresponding image region for each detected face.\n */\nexport async function extractFaceTensors(\n imageTensor: tf.Tensor3D | tf.Tensor4D,\n detections: Array,\n): Promise {\n if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {\n throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D');\n }\n\n if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {\n throw new Error('extractFaceTensors - batchSize > 1 not supported');\n }\n\n return tf.tidy(() => {\n const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0);\n\n const boxes = detections.map(\n (det) => (det instanceof FaceDetection\n ? det.forSize(imgWidth, imgHeight).box\n : det),\n )\n .map((box) => box.clipAtImageBorders(imgWidth, imgHeight));\n\n const faceTensors = boxes.map(({\n x, y, width, height,\n }) => tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels]));\n\n return faceTensors;\n });\n}\n", "import { env } from '../env/index';\n\nexport async function fetchOrThrow(\n url: string,\n // eslint-disable-next-line no-undef\n init?: RequestInit,\n): Promise {\n const { fetch } = env.getEnv();\n const res = await fetch(url, init);\n if (!(res.status < 400)) {\n throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`);\n }\n return res;\n}\n", "import { bufferToImage } from './bufferToImage';\nimport { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchImage(uri: string): Promise {\n const res = await fetchOrThrow(uri);\n const blob = await (res).blob();\n\n if (!blob.type.startsWith('image/')) {\n throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`);\n }\n return bufferToImage(blob);\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchJson(uri: string): Promise {\n return (await fetchOrThrow(uri)).json();\n}\n", "import { fetchOrThrow } from './fetchOrThrow';\n\nexport async function fetchNetWeights(uri: string): Promise {\n return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer());\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { getModelUris } from '../common/getModelUris';\nimport { fetchJson } from './fetchJson';\n\nexport async function loadWeightMap(\n uri: string | undefined,\n defaultModelName: string,\n): Promise {\n const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName);\n const manifest = await fetchJson(manifestUri);\n // if (manifest['weightsManifest']) manifest = manifest['weightsManifest'];\n return tf.io.loadWeights(manifest, modelBaseUri);\n}\n", "export function getModelUris(uri: string | undefined, defaultModelName: string) {\n const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`;\n\n if (!uri) {\n return {\n modelBaseUri: '',\n manifestUri: defaultManifestFilename,\n };\n }\n\n if (uri === '/') {\n return {\n modelBaseUri: '/',\n manifestUri: `/${defaultManifestFilename}`,\n };\n }\n // eslint-disable-next-line no-nested-ternary\n const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';\n uri = uri.replace(protocol, '');\n\n const parts = uri.split('/').filter((s) => s);\n\n const manifestFile = uri.endsWith('.json')\n ? parts[parts.length - 1]\n : defaultManifestFilename;\n\n let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/');\n modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri;\n\n return {\n modelBaseUri,\n manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`,\n };\n}\n", "import { IDimensions } from '../classes/index';\nimport { getMediaDimensions } from './getMediaDimensions';\n\nexport function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {\n const { width, height } = useMediaDimensions\n ? getMediaDimensions(reference)\n : reference;\n input.width = width;\n input.height = height;\n return { width, height };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock4 } from './denseBlock';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';\n\nexport class FaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('FaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock4(normalized, params.dense0, true);\n out = denseBlock4(out, params.dense1);\n out = denseBlock4(out, params.dense2);\n out = denseBlock4(out, params.dense3);\n out = tf.avgPool(out, [7, 7], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../dist/tfjs.esm';\n\nimport { ParamMapping } from './common/index';\nimport { getModelUris } from './common/getModelUris';\nimport { loadWeightMap } from './dom/index';\nimport { env } from './env/index';\n\nexport abstract class NeuralNetwork {\n constructor(name: string) {\n this._name = name;\n }\n\n protected _params: TNetParams | undefined = undefined\n\n protected _paramMappings: ParamMapping[] = []\n\n public _name: any;\n\n public get params(): TNetParams | undefined { return this._params; }\n\n public get paramMappings(): ParamMapping[] { return this._paramMappings; }\n\n public get isLoaded(): boolean { return !!this.params; }\n\n public getParamFromPath(paramPath: string): tf.Tensor {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n return obj[objProp];\n }\n\n public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {\n const { obj, objProp } = this.traversePropertyPath(paramPath);\n obj[objProp].dispose();\n obj[objProp] = tensor;\n }\n\n public getParamList() {\n return this._paramMappings.map(({ paramPath }) => ({\n path: paramPath,\n tensor: this.getParamFromPath(paramPath),\n }));\n }\n\n public getTrainableParams() {\n return this.getParamList().filter((param) => param.tensor instanceof tf.Variable);\n }\n\n public getFrozenParams() {\n return this.getParamList().filter((param) => !(param.tensor instanceof tf.Variable));\n }\n\n public variable() {\n this.getFrozenParams().forEach(({ path, tensor }) => {\n this.reassignParamFromPath(path, tensor.variable());\n });\n }\n\n public freeze() {\n this.getTrainableParams().forEach(({ path, tensor: variable }) => {\n const tensor = tf.tensor(variable.dataSync());\n variable.dispose();\n this.reassignParamFromPath(path, tensor);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.getParamList().forEach((param) => {\n if (throwOnRedispose && param.tensor.isDisposed) {\n throw new Error(`param tensor has already been disposed for path ${param.path}`);\n }\n param.tensor.dispose();\n });\n this._params = undefined;\n }\n\n public serializeParams(): Float32Array {\n return new Float32Array(\n this.getParamList()\n .map(({ tensor }) => Array.from(tensor.dataSync()) as number[])\n .reduce((flat, arr) => flat.concat(arr)),\n );\n }\n\n public async load(weightsOrUrl: Float32Array | string | undefined): Promise {\n if (weightsOrUrl instanceof Float32Array) {\n this.extractWeights(weightsOrUrl);\n return;\n }\n await this.loadFromUri(weightsOrUrl);\n }\n\n public async loadFromUri(uri: string | undefined) {\n if (uri && typeof uri !== 'string') {\n throw new Error(`${this._name}.loadFromUri - expected model uri`);\n }\n const weightMap = await loadWeightMap(uri, this.getDefaultModelName());\n this.loadFromWeightMap(weightMap);\n }\n\n public async loadFromDisk(filePath: string | undefined) {\n if (filePath && typeof filePath !== 'string') {\n throw new Error(`${this._name}.loadFromDisk - expected model file path`);\n }\n const { readFile } = env.getEnv();\n const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName());\n const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(filePaths.map((fp) => readFile(fp).then((buf) => buf.buffer)));\n const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk);\n const manifest = JSON.parse((await readFile(manifestUri)).toString());\n const weightMap = await loadWeights(manifest, modelBaseUri);\n this.loadFromWeightMap(weightMap);\n }\n\n public loadFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { paramMappings, params } = this.extractParamsFromWeightMap(weightMap);\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n public extractWeights(weights: Float32Array) {\n const { paramMappings, params } = this.extractParams(weights);\n this._paramMappings = paramMappings;\n this._params = params;\n }\n\n private traversePropertyPath(paramPath: string) {\n if (!this.params) {\n throw new Error('traversePropertyPath - model has no loaded params');\n }\n\n const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {\n // eslint-disable-next-line no-prototype-builtins\n if (!res.nextObj.hasOwnProperty(objProp)) {\n throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`);\n }\n return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] };\n }, { nextObj: this.params });\n\n const { obj, objProp } = result;\n if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {\n throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`);\n }\n\n return { obj, objProp };\n }\n\n protected abstract getDefaultModelName(): string\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }\n\n // eslint-disable-next-line no-unused-vars\n protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, SeparableConvParams } from '../common/index';\nimport { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function denseBlock3(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock3Params,\n isFirstLayer: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n });\n}\n\nexport function denseBlock4(\n x: tf.Tensor4D,\n denseBlockParams: DenseBlock4Params,\n isFirstLayer: boolean = false,\n isScaleDown: boolean = true,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out1 = tf.relu(\n isFirstLayer\n ? tf.add(\n tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),\n denseBlockParams.conv0.bias,\n )\n : depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1]),\n ) as tf.Tensor4D;\n const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1]);\n\n const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D;\n const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1]);\n\n const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D;\n const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1]);\n\n return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from './types';\n\nexport function depthwiseSeparableConv(\n x: tf.Tensor4D,\n params: SeparableConvParams,\n stride: [number, number],\n): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same');\n out = tf.add(out, params.bias);\n return out;\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\nexport function convLayer(\n x: tf.Tensor4D,\n params: ConvParams,\n padding: 'valid' | 'same' = 'same',\n withRelu: boolean = false,\n): tf.Tensor4D {\n return tf.tidy(() => {\n const out = tf.add(\n tf.conv2d(x, params.filters, [1, 1], padding),\n params.bias,\n ) as tf.Tensor4D;\n\n return withRelu ? tf.relu(out) : out;\n });\n}\n", "import { ParamMapping } from './types';\n\nexport function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {\n Object.keys(weightMap).forEach((path) => {\n if (!paramMappings.some((pm) => pm.originalPath === path)) {\n weightMap[path].dispose();\n }\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';\n\nexport function extractConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams => {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, FCParams, ParamMapping } from './types';\n\nexport function extractFCParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): FCParams => {\n const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);\n const fc_bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return {\n weights: fc_weights,\n bias: fc_bias,\n };\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';\n\nexport function extractSeparableConvParamsFactory(\n extractWeights: ExtractWeightsFunction,\n paramMappings: ParamMapping[],\n) {\n return (channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams => {\n const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1]);\n const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut]);\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/depthwise_filter` },\n { paramPath: `${mappedPrefix}/pointwise_filter` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n\nexport function loadSeparableConvParamsFactory(\n // eslint-disable-next-line no-unused-vars\n extractWeightEntry: (originalPath: string, paramRank: number) => T,\n) {\n return (prefix: string): SeparableConvParams => {\n const depthwise_filter = extractWeightEntry(`${prefix}/depthwise_filter`, 4);\n const pointwise_filter = extractWeightEntry(`${prefix}/pointwise_filter`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return new SeparableConvParams(\n depthwise_filter,\n pointwise_filter,\n bias,\n );\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\n// eslint-disable-next-line no-unused-vars\nexport type ExtractWeightsFunction = (numWeights: number) => Float32Array\n\nexport type ParamMapping = {\n originalPath?: string\n paramPath: string\n}\n\nexport type ConvParams = {\n filters: tf.Tensor4D\n bias: tf.Tensor1D\n}\n\nexport type FCParams = {\n weights: tf.Tensor2D\n bias: tf.Tensor1D\n}\n\nexport class SeparableConvParams {\n // eslint-disable-next-line no-useless-constructor\n constructor(\n // eslint-disable-next-line no-unused-vars\n public depthwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public pointwise_filter: tf.Tensor4D,\n // eslint-disable-next-line no-unused-vars\n public bias: tf.Tensor1D,\n // eslint-disable-next-line no-empty-function\n ) {}\n}\n", "import { isTensor } from '../utils/index';\nimport { ParamMapping } from './types';\n\nexport function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {\n return (originalPath: string, paramRank: number, mappedPath?: string) => {\n const tensor = weightMap[originalPath];\n\n if (!isTensor(tensor, paramRank)) {\n throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`);\n }\n\n paramMappings.push(\n { originalPath, paramPath: mappedPath || originalPath },\n );\n\n return tensor;\n };\n}\n", "export function extractWeightsFactory(weights: Float32Array) {\n let remainingWeights = weights;\n\n function extractWeights(numWeights: number): Float32Array {\n const ret = remainingWeights.slice(0, numWeights);\n remainingWeights = remainingWeights.slice(numWeights);\n return ret;\n }\n\n function getRemainingWeights(): Float32Array {\n return remainingWeights;\n }\n\n return {\n extractWeights,\n getRemainingWeights,\n };\n}\n", "import {\n extractConvParamsFactory,\n extractSeparableConvParamsFactory,\n ExtractWeightsFunction,\n ParamMapping,\n} from '../common/index';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)\n : extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`);\n const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`);\n const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer);\n const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock4Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock4Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock4Params(64, 128, 'dense2');\n const dense3 = extractDenseBlock4Params(128, 256, 'dense3');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: {\n dense0, dense1, dense2, dense3,\n },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from './types';\n\n// eslint-disable-next-line no-unused-vars\nexport function loadConvParamsFactory(extractWeightEntry: (originalPath: string, paramRank: number) => T) {\n return (prefix: string): ConvParams => {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n\n return { filters, bias };\n };\n}\n", "import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { DenseBlock3Params, DenseBlock4Params } from './types';\n\nexport function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n\n return { conv0, conv1, conv2 };\n }\n\n function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {\n const conv0 = isFirstLayer\n ? extractConvParams(`${prefix}/conv0`)\n : extractSeparableConvParams(`${prefix}/conv0`);\n const conv1 = extractSeparableConvParams(`${prefix}/conv1`);\n const conv2 = extractSeparableConvParams(`${prefix}/conv2`);\n const conv3 = extractSeparableConvParams(`${prefix}/conv3`);\n\n return {\n conv0, conv1, conv2, conv3,\n };\n }\n\n return {\n extractDenseBlock3Params,\n extractDenseBlock4Params,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { FaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock4Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock4Params('dense0', true),\n dense1: extractDenseBlock4Params('dense1'),\n dense2: extractDenseBlock4Params('dense2'),\n dense3: extractDenseBlock4Params('dense3'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { NetInput } from '../dom/index';\nimport {\n FaceFeatureExtractorParams,\n IFaceFeatureExtractor,\n TinyFaceFeatureExtractorParams,\n} from '../faceFeatureExtractor/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { NetParams } from './types';\nimport { seperateWeightMaps } from './util';\n\nexport abstract class FaceProcessor<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends NeuralNetwork {\n protected _faceFeatureExtractor: IFaceFeatureExtractor\n\n constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor) {\n super(_name);\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): IFaceFeatureExtractor {\n return this._faceFeatureExtractor;\n }\n\n protected abstract getDefaultModelName(): string\n\n protected abstract getClassifierChannelsIn(): number\n\n protected abstract getClassifierChannelsOut(): number\n\n public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc);\n });\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut());\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const cIn = this.getClassifierChannelsIn();\n const cOut = this.getClassifierChannelsOut();\n const classifierWeightSize = (cOut * cIn) + cOut;\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from './types';\n\nexport function fullyConnectedLayer(\n x: tf.Tensor2D,\n params: FCParams,\n): tf.Tensor2D {\n return tf.tidy(() => tf.add(\n tf.matMul(x, params.weights),\n params.bias,\n ));\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const fc = extractFCParams(channelsIn, channelsOut, 'fc');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: extractFcParams('fc'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function seperateWeightMaps(weightMap: tf.NamedTensorMap) {\n const featureExtractorMap: tf.NamedTensorMap = {};\n const classifierMap: tf.NamedTensorMap = {};\n\n Object.keys(weightMap).forEach((key) => {\n const map = key.startsWith('fc') ? classifierMap : featureExtractorMap;\n map[key] = weightMap[key];\n });\n\n return { featureExtractorMap, classifierMap };\n}\n", "export const FACE_EXPRESSION_LABELS = ['neutral', 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised'];\n\nexport class FaceExpressions {\n public neutral: number\n\n public happy: number\n\n public sad: number\n\n public angry: number\n\n public fearful: number\n\n public disgusted: number\n\n public surprised: number\n\n constructor(probabilities: number[] | Float32Array) {\n if (probabilities.length !== 7) {\n throw new Error(`FaceExpressions.constructor - expected probabilities.length to be 7, have: ${probabilities.length}`);\n }\n\n FACE_EXPRESSION_LABELS.forEach((expression, idx) => {\n this[expression] = probabilities[idx];\n });\n }\n\n asSortedArray() {\n return FACE_EXPRESSION_LABELS\n .map((expression) => ({ expression, probability: this[expression] as number }))\n .sort((e0, e1) => e1.probability - e0.probability);\n }\n}\n", "import { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\n\nexport type WithFaceExpressions = TSource & {\n expressions: FaceExpressions\n}\n\nexport function isWithFaceExpressions(obj: any): obj is WithFaceExpressions<{}> {\n return obj.expressions instanceof FaceExpressions;\n}\n\nexport function extendWithFaceExpressions<\n TSource\n>(\n sourceObj: TSource,\n expressions: FaceExpressions,\n): WithFaceExpressions {\n const extension = { expressions };\n return { ...sourceObj, ...extension };\n}\n", "import { IPoint, Point } from '../classes/index';\nimport { FaceExpressions } from '../faceExpressionNet/index';\nimport { isWithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { round } from '../utils/index';\nimport { DrawTextField } from './DrawTextField';\n\nexport type DrawFaceExpressionsInput = FaceExpressions | WithFaceExpressions<{}>\n\nexport function drawFaceExpressions(\n canvasArg: string | HTMLCanvasElement,\n faceExpressions: DrawFaceExpressionsInput | Array,\n minConfidence = 0.1,\n textFieldAnchor?: IPoint,\n) {\n const faceExpressionsArray = Array.isArray(faceExpressions) ? faceExpressions : [faceExpressions];\n\n faceExpressionsArray.forEach((e) => {\n // eslint-disable-next-line no-nested-ternary\n const expr = e instanceof FaceExpressions\n ? e\n : (isWithFaceExpressions(e) ? e.expressions : undefined);\n if (!expr) {\n throw new Error('drawFaceExpressions - expected faceExpressions to be FaceExpressions | WithFaceExpressions<{}> or array thereof');\n }\n\n const sorted = expr.asSortedArray();\n const resultsToDisplay = sorted.filter((exprLocal) => exprLocal.probability > minConfidence);\n\n const anchor = isWithFaceDetection(e)\n ? e.detection.box.bottomLeft\n : (textFieldAnchor || new Point(0, 0));\n\n const drawTextField = new DrawTextField(\n resultsToDisplay.map((exprLocal) => `${exprLocal.expression} (${round(exprLocal.probability)})`),\n anchor,\n );\n drawTextField.draw(canvasArg);\n });\n}\n", "import { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { isWithFaceDetection, WithFaceDetection } from './WithFaceDetection';\n\nexport type WithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 > = TSource & {\n landmarks: TFaceLandmarks\n unshiftedLandmarks: TFaceLandmarks\n alignedRect: FaceDetection\n }\n\nexport function isWithFaceLandmarks(obj: any): obj is WithFaceLandmarks, FaceLandmarks> {\n return isWithFaceDetection(obj)\n // eslint-disable-next-line dot-notation\n && obj['landmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['unshiftedLandmarks'] instanceof FaceLandmarks\n // eslint-disable-next-line dot-notation\n && obj['alignedRect'] instanceof FaceDetection;\n}\n\nexport function extendWithFaceLandmarks<\n TSource extends WithFaceDetection<{}>,\n TFaceLandmarks extends FaceLandmarks = FaceLandmarks68 >(sourceObj: TSource, unshiftedLandmarks: TFaceLandmarks): WithFaceLandmarks {\n const { box: shift } = sourceObj.detection;\n const landmarks = unshiftedLandmarks.shiftBy(shift.x, shift.y);\n\n const rect = landmarks.align();\n const { imageDims } = sourceObj.detection;\n const alignedRect = new FaceDetection(sourceObj.detection.score, rect.rescale(imageDims.reverse()), imageDims);\n\n const extension = {\n landmarks,\n unshiftedLandmarks,\n alignedRect,\n };\n\n return { ...sourceObj, ...extension };\n}\n", "/* eslint-disable max-classes-per-file */\nimport { IPoint } from '../classes/index';\nimport { FaceLandmarks } from '../classes/FaceLandmarks';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { getContext2dOrThrow } from '../dom/getContext2dOrThrow';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { drawContour } from './drawContour';\n\nexport interface IDrawFaceLandmarksOptions {\n drawLines?: boolean\n drawPoints?: boolean\n lineWidth?: number\n pointSize?: number\n lineColor?: string\n pointColor?: string\n}\n\nexport class DrawFaceLandmarksOptions {\n public drawLines: boolean\n\n public drawPoints: boolean\n\n public lineWidth: number\n\n public pointSize: number\n\n public lineColor: string\n\n public pointColor: string\n\n constructor(options: IDrawFaceLandmarksOptions = {}) {\n const {\n drawLines = true, drawPoints = true, lineWidth, lineColor, pointSize, pointColor,\n } = options;\n this.drawLines = drawLines;\n this.drawPoints = drawPoints;\n this.lineWidth = lineWidth || 1;\n this.pointSize = pointSize || 2;\n this.lineColor = lineColor || 'rgba(0, 255, 255, 1)';\n this.pointColor = pointColor || 'rgba(255, 0, 255, 1)';\n }\n}\n\nexport class DrawFaceLandmarks {\n public faceLandmarks: FaceLandmarks\n\n public options: DrawFaceLandmarksOptions\n\n constructor(\n faceLandmarks: FaceLandmarks,\n options: IDrawFaceLandmarksOptions = {},\n ) {\n this.faceLandmarks = faceLandmarks;\n this.options = new DrawFaceLandmarksOptions(options);\n }\n\n draw(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D) {\n const ctx = getContext2dOrThrow(canvasArg);\n\n const {\n drawLines, drawPoints, lineWidth, lineColor, pointSize, pointColor,\n } = this.options;\n\n if (drawLines && this.faceLandmarks instanceof FaceLandmarks68) {\n ctx.strokeStyle = lineColor;\n ctx.lineWidth = lineWidth;\n drawContour(ctx, this.faceLandmarks.getJawOutline());\n drawContour(ctx, this.faceLandmarks.getLeftEyeBrow());\n drawContour(ctx, this.faceLandmarks.getRightEyeBrow());\n drawContour(ctx, this.faceLandmarks.getNose());\n drawContour(ctx, this.faceLandmarks.getLeftEye(), true);\n drawContour(ctx, this.faceLandmarks.getRightEye(), true);\n drawContour(ctx, this.faceLandmarks.getMouth(), true);\n }\n\n if (drawPoints) {\n ctx.strokeStyle = pointColor;\n ctx.fillStyle = pointColor;\n\n const drawPoint = (pt: IPoint) => {\n ctx.beginPath();\n ctx.arc(pt.x, pt.y, pointSize, 0, 2 * Math.PI);\n ctx.fill();\n };\n this.faceLandmarks.positions.forEach(drawPoint);\n }\n }\n}\n\nexport type DrawFaceLandmarksInput = FaceLandmarks | WithFaceLandmarks>\n\nexport function drawFaceLandmarks(\n canvasArg: string | HTMLCanvasElement,\n faceLandmarks: DrawFaceLandmarksInput | Array,\n) {\n const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];\n faceLandmarksArray.forEach((f) => {\n // eslint-disable-next-line no-nested-ternary\n const landmarks = f instanceof FaceLandmarks\n ? f\n : (isWithFaceLandmarks(f) ? f.landmarks : undefined);\n if (!landmarks) {\n throw new Error('drawFaceLandmarks - expected faceExpressions to be FaceLandmarks | WithFaceLandmarks> or array thereof');\n }\n\n new DrawFaceLandmarks(landmarks).draw(canvasArg);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { fullyConnectedLayer } from '../common/fullyConnectedLayer';\nimport { seperateWeightMaps } from '../faceProcessor/util';\nimport { TinyXception } from '../xception/TinyXception';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport {\n AgeAndGenderPrediction, Gender, NetOutput, NetParams,\n} from './types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\n\nexport class AgeGenderNet extends NeuralNetwork {\n private _faceFeatureExtractor: TinyXception\n\n constructor(faceFeatureExtractor: TinyXception = new TinyXception(2)) {\n super('AgeGenderNet');\n this._faceFeatureExtractor = faceFeatureExtractor;\n }\n\n public get faceFeatureExtractor(): TinyXception {\n return this._faceFeatureExtractor;\n }\n\n public runNet(input: NetInput | tf.Tensor4D): NetOutput {\n const { params } = this;\n\n if (!params) {\n throw new Error(`${this._name} - load model before inference`);\n }\n\n return tf.tidy(() => {\n const bottleneckFeatures = input instanceof NetInput\n ? this.faceFeatureExtractor.forwardInput(input)\n : input;\n\n const pooled = tf.avgPool(bottleneckFeatures, [7, 7], [2, 2], 'valid').as2D(bottleneckFeatures.shape[0], -1);\n const age = fullyConnectedLayer(pooled, params.fc.age).as1D();\n const gender = fullyConnectedLayer(pooled, params.fc.gender);\n return { age, gender };\n });\n }\n\n public forwardInput(input: NetInput | tf.Tensor4D): NetOutput {\n return tf.tidy(() => {\n const { age, gender } = this.runNet(input);\n return { age, gender: tf.softmax(gender) };\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async predictAgeAndGender(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput);\n\n const ages = tf.unstack(out.age);\n const genders = tf.unstack(out.gender);\n const ageAndGenderTensors = ages.map((ageTensor, i) => ({\n ageTensor,\n genderTensor: genders[i],\n }));\n\n const predictionsByBatch = await Promise.all(\n ageAndGenderTensors.map(async ({ ageTensor, genderTensor }) => {\n const age = (await ageTensor.data())[0];\n const probMale = (await genderTensor.data())[0];\n const isMale = probMale > 0.5;\n const gender = isMale ? Gender.MALE : Gender.FEMALE;\n const genderProbability = isMale ? probMale : (1 - probMale);\n\n ageTensor.dispose();\n genderTensor.dispose();\n return { age, gender, genderProbability };\n }),\n );\n out.age.dispose();\n out.gender.dispose();\n\n return netInput.isBatchInput ? predictionsByBatch as AgeAndGenderPrediction[] : predictionsByBatch[0] as AgeAndGenderPrediction;\n }\n\n protected getDefaultModelName(): string {\n return 'age_gender_model';\n }\n\n public dispose(throwOnRedispose: boolean = true) {\n this.faceFeatureExtractor.dispose(throwOnRedispose);\n super.dispose(throwOnRedispose);\n }\n\n public loadClassifierParams(weights: Float32Array) {\n const { params, paramMappings } = this.extractClassifierParams(weights);\n this._params = params;\n this._paramMappings = paramMappings;\n }\n\n public extractClassifierParams(weights: Float32Array) {\n return extractParams(weights);\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap);\n\n this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap);\n\n return extractParamsFromWeightMap(classifierMap);\n }\n\n protected extractParams(weights: Float32Array) {\n const classifierWeightSize = (512 * 1 + 1) + (512 * 2 + 2);\n\n const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize);\n const classifierWeights = weights.slice(weights.length - classifierWeightSize);\n\n this.faceFeatureExtractor.extractWeights(featureExtractorWeights);\n return this.extractClassifierParams(classifierWeights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams, depthwiseSeparableConv } from '../common/index';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { range } from '../utils/index';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction conv(x: tf.Tensor4D, params: ConvParams, stride: [number, number]): tf.Tensor4D {\n return tf.add(tf.conv2d(x, params.filters, stride, 'same'), params.bias);\n}\n\nfunction reductionBlock(x: tf.Tensor4D, params: ReductionBlockParams, isActivateInput: boolean = true): tf.Tensor4D {\n let out = isActivateInput ? tf.relu(x) : x;\n out = depthwiseSeparableConv(out, params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = tf.maxPool(out, [3, 3], [2, 2], 'same');\n out = tf.add(out, conv(x, params.expansion_conv, [2, 2]));\n return out;\n}\n\nfunction mainBlock(x: tf.Tensor4D, params: MainBlockParams): tf.Tensor4D {\n let out = depthwiseSeparableConv(tf.relu(x), params.separable_conv0, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv1, [1, 1]);\n out = depthwiseSeparableConv(tf.relu(out), params.separable_conv2, [1, 1]);\n out = tf.add(out, x);\n return out;\n}\n\nexport class TinyXception extends NeuralNetwork {\n private _numMainBlocks: number\n\n constructor(numMainBlocks: number) {\n super('TinyXception');\n this._numMainBlocks = numMainBlocks;\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n if (!params) {\n throw new Error('TinyXception - load model before inference');\n }\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n let out = tf.relu(conv(normalized, params.entry_flow.conv_in, [2, 2]));\n out = reductionBlock(out, params.entry_flow.reduction_block_0, false);\n out = reductionBlock(out, params.entry_flow.reduction_block_1);\n range(this._numMainBlocks, 0, 1).forEach((idx) => {\n out = mainBlock(out, params.middle_flow[`main_block_${idx}`]);\n });\n out = reductionBlock(out, params.exit_flow.reduction_block);\n out = tf.relu(depthwiseSeparableConv(out, params.exit_flow.separable_conv, [1, 1]));\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_xception_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this._numMainBlocks);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights, this._numMainBlocks);\n }\n}\n", "import { extractConvParamsFactory, extractSeparableConvParamsFactory, extractWeightsFactory } from '../common/index';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n function extractReductionBlockParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(channels: number, mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(channels, channels, `${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParams(weights: Float32Array, numMainBlocks: number): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const entry_flow_conv_in = extractConvParams(3, 32, 3, 'entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams(32, 64, 'entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams(64, 128, 'entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(128, `middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams(128, 256, 'exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams(256, 512, 'exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { entry_flow, middle_flow, exit_flow },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors,\n extractWeightEntryFactory,\n loadSeparableConvParamsFactory,\n ParamMapping,\n} from '../common/index';\nimport { loadConvParamsFactory } from '../common/loadConvParamsFactory';\nimport { range } from '../utils/index';\nimport { MainBlockParams, ReductionBlockParams, TinyXceptionParams } from './types';\n\nfunction loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n const extractConvParams = loadConvParamsFactory(extractWeightEntry);\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n\n function extractReductionBlockParams(mappedPrefix: string): ReductionBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const expansion_conv = extractConvParams(`${mappedPrefix}/expansion_conv`);\n\n return { separable_conv0, separable_conv1, expansion_conv };\n }\n\n function extractMainBlockParams(mappedPrefix: string): MainBlockParams {\n const separable_conv0 = extractSeparableConvParams(`${mappedPrefix}/separable_conv0`);\n const separable_conv1 = extractSeparableConvParams(`${mappedPrefix}/separable_conv1`);\n const separable_conv2 = extractSeparableConvParams(`${mappedPrefix}/separable_conv2`);\n\n return { separable_conv0, separable_conv1, separable_conv2 };\n }\n\n return {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n numMainBlocks: number,\n): { params: TinyXceptionParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractSeparableConvParams,\n extractReductionBlockParams,\n extractMainBlockParams,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const entry_flow_conv_in = extractConvParams('entry_flow/conv_in');\n const entry_flow_reduction_block_0 = extractReductionBlockParams('entry_flow/reduction_block_0');\n const entry_flow_reduction_block_1 = extractReductionBlockParams('entry_flow/reduction_block_1');\n\n const entry_flow = {\n conv_in: entry_flow_conv_in,\n reduction_block_0: entry_flow_reduction_block_0,\n reduction_block_1: entry_flow_reduction_block_1,\n };\n\n const middle_flow = {};\n range(numMainBlocks, 0, 1).forEach((idx) => {\n middle_flow[`main_block_${idx}`] = extractMainBlockParams(`middle_flow/main_block_${idx}`);\n });\n\n const exit_flow_reduction_block = extractReductionBlockParams('exit_flow/reduction_block');\n const exit_flow_separable_conv = extractSeparableConvParams('exit_flow/separable_conv');\n\n const exit_flow = {\n reduction_block: exit_flow_reduction_block,\n separable_conv: exit_flow_separable_conv,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params: { entry_flow, middle_flow, exit_flow }, paramMappings };\n}\n", "import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings);\n\n const age = extractFCParams(512, 1, 'fc/age');\n const gender = extractFCParams(512, 2, 'fc/gender');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { fc: { age, gender } },\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping,\n} from '../common/index';\nimport { NetParams } from './types';\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractFcParams(prefix: string): FCParams {\n const weights = extractWeightEntry(`${prefix}/weights`, 2);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { weights, bias };\n }\n\n const params = {\n fc: {\n age: extractFcParams('fc/age'),\n gender: extractFcParams('fc/gender'),\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FCParams } from '../common/index';\n\n// eslint-disable-next-line no-shadow\nexport enum Gender {\n // eslint-disable-next-line no-unused-vars\n FEMALE = 'female',\n // eslint-disable-next-line no-unused-vars\n MALE = 'male'\n}\n\nexport type AgeAndGenderPrediction = {\n age: number\n gender: Gender\n genderProbability: number\n}\n\nexport type NetOutput = { age: tf.Tensor1D, gender: tf.Tensor2D }\n\nexport type NetParams = {\n fc: {\n age: FCParams\n gender: FCParams\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { IDimensions, Point } from '../classes/index';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceProcessor } from '../faceProcessor/FaceProcessor';\nimport { isEven } from '../utils/index';\n\nexport abstract class FaceLandmark68NetBase<\n TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams\n>\n extends FaceProcessor {\n public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {\n const inputDimensions = originalDimensions.map(({ width, height }) => {\n const scale = inputSize / Math.max(height, width);\n return {\n width: width * scale,\n height: height * scale,\n };\n });\n\n const batchSize = inputDimensions.length;\n\n return tf.tidy(() => {\n const createInterleavedTensor = (fillX: number, fillY: number) => tf.stack([tf.fill([68], fillX, 'float32'), tf.fill([68], fillY, 'float32')], 1).as2D(1, 136).as1D();\n\n // eslint-disable-next-line no-unused-vars\n const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {\n const { width, height } = inputDimensions[batchIdx];\n return cond(width, height) ? Math.abs(width - height) / 2 : 0;\n };\n\n const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h);\n const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w);\n\n const landmarkTensors = output\n .mul(tf.fill([batchSize, 136], inputSize, 'float32'))\n .sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n getPaddingX(batchIdx),\n getPaddingY(batchIdx),\n ))))\n .div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) => createInterleavedTensor(\n inputDimensions[batchIdx].width,\n inputDimensions[batchIdx].height,\n ))));\n\n return landmarkTensors as tf.Tensor2D;\n });\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n return tf.tidy(() => {\n const out = this.runNet(input);\n return this.postProcess(\n out,\n input.inputSize as number,\n input.inputDimensions.map(([height, width]) => ({ height, width })),\n );\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async detectLandmarks(input: TNetInput): Promise {\n const netInput = await toNetInput(input);\n const landmarkTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n\n const landmarksForBatch = await Promise.all(landmarkTensors.map(\n async (landmarkTensor, batchIdx) => {\n const landmarksArray = Array.from(await landmarkTensor.data());\n const xCoords = landmarksArray.filter((_, i) => isEven(i));\n const yCoords = landmarksArray.filter((_, i) => !isEven(i));\n\n return new FaceLandmarks68(\n Array(68).fill(0).map((_, i) => new Point(xCoords[i] as number, yCoords[i] as number)),\n {\n height: netInput.getInputHeight(batchIdx),\n width: netInput.getInputWidth(batchIdx),\n },\n );\n },\n ));\n\n landmarkTensors.forEach((t) => t.dispose());\n\n return netInput.isBatchInput ? landmarksForBatch as FaceLandmarks68[] : landmarksForBatch[0] as FaceLandmarks68;\n }\n\n protected getClassifierChannelsOut(): number {\n return 136;\n }\n}\n", "import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';\nimport { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68Net extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {\n super('FaceLandmark68Net', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 256;\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { denseBlock3 } from './denseBlock';\nimport { extractParamsFromWeightMapTiny } from './extractParamsFromWeightMapTiny';\nimport { extractParamsTiny } from './extractParamsTiny';\nimport { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';\n\nexport class TinyFaceFeatureExtractor extends NeuralNetwork implements IFaceFeatureExtractor {\n constructor() {\n super('TinyFaceFeatureExtractor');\n }\n\n public forwardInput(input: NetInput): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyFaceFeatureExtractor - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(112, true), 'float32');\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D;\n\n let out = denseBlock3(normalized, params.dense0, true);\n out = denseBlock3(out, params.dense1);\n out = denseBlock3(out, params.dense2);\n out = tf.avgPool(out, [14, 14], [2, 2], 'valid');\n\n return out;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n protected getDefaultModelName(): string {\n return 'face_feature_extractor_tiny_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMapTiny(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParamsTiny(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, ParamMapping } from '../common/index';\nimport { loadParamsFactory } from './loadParamsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsFromWeightMapTiny(\n weightMap: tf.NamedTensorMap,\n): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractDenseBlock3Params,\n } = loadParamsFactory(weightMap, paramMappings);\n\n const params = {\n dense0: extractDenseBlock3Params('dense0', true),\n dense1: extractDenseBlock3Params('dense1'),\n dense2: extractDenseBlock3Params('dense2'),\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import { extractWeightsFactory, ParamMapping } from '../common/index';\nimport { extractorsFactory } from './extractorsFactory';\nimport { TinyFaceFeatureExtractorParams } from './types';\n\nexport function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const {\n extractDenseBlock3Params,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true);\n const dense1 = extractDenseBlock3Params(32, 64, 'dense1');\n const dense2 = extractDenseBlock3Params(64, 128, 'dense2');\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n paramMappings,\n params: { dense0, dense1, dense2 },\n };\n}\n", "import { TinyFaceFeatureExtractor } from '../faceFeatureExtractor/TinyFaceFeatureExtractor';\nimport { TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';\nimport { FaceLandmark68NetBase } from './FaceLandmark68NetBase';\n\nexport class FaceLandmark68TinyNet extends FaceLandmark68NetBase {\n constructor(faceFeatureExtractor: TinyFaceFeatureExtractor = new TinyFaceFeatureExtractor()) {\n super('FaceLandmark68TinyNet', faceFeatureExtractor);\n }\n\n protected getDefaultModelName(): string {\n return 'face_landmark_68_tiny_model';\n }\n\n protected getClassifierChannelsIn(): number {\n return 128;\n }\n}\n", "import { FaceLandmark68Net } from './FaceLandmark68Net';\n\nexport * from './FaceLandmark68Net';\nexport * from './FaceLandmark68TinyNet';\nexport class FaceLandmarkNet extends FaceLandmark68Net {}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { normalize } from '../ops/index';\nimport { convDown } from './convLayer';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { residual, residualDown } from './residualLayer';\nimport { NetParams } from './types';\n\nexport class FaceRecognitionNet extends NeuralNetwork {\n constructor() {\n super('FaceRecognitionNet');\n }\n\n public forwardInput(input: NetInput): tf.Tensor2D {\n const { params } = this;\n\n if (!params) {\n throw new Error('FaceRecognitionNet - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(150, true), 'float32');\n\n const meanRgb = [122.782, 117.001, 104.298];\n const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D;\n\n let out = convDown(normalized, params.conv32_down);\n out = tf.maxPool(out, 3, 2, 'valid');\n\n out = residual(out, params.conv32_1);\n out = residual(out, params.conv32_2);\n out = residual(out, params.conv32_3);\n\n out = residualDown(out, params.conv64_down);\n out = residual(out, params.conv64_1);\n out = residual(out, params.conv64_2);\n out = residual(out, params.conv64_3);\n\n out = residualDown(out, params.conv128_down);\n out = residual(out, params.conv128_1);\n out = residual(out, params.conv128_2);\n\n out = residualDown(out, params.conv256_down);\n out = residual(out, params.conv256_1);\n out = residual(out, params.conv256_2);\n out = residualDown(out, params.conv256_down_out);\n\n const globalAvg = out.mean([1, 2]) as tf.Tensor2D;\n const fullyConnected = tf.matMul(globalAvg, params.fc);\n\n return fullyConnected;\n });\n }\n\n public async forward(input: TNetInput): Promise {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async computeFaceDescriptor(input: TNetInput): Promise {\n if (input?.shape?.some((dim) => dim <= 0)) return new Float32Array(128);\n const netInput = await toNetInput(input);\n const faceDescriptorTensors = tf.tidy(\n () => tf.unstack(this.forwardInput(netInput)),\n );\n const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map((t) => t.data())) as Float32Array[];\n faceDescriptorTensors.forEach((t) => t.dispose());\n return netInput.isBatchInput ? faceDescriptorsForBatch : faceDescriptorsForBatch[0];\n }\n\n protected getDefaultModelName(): string {\n return 'face_recognition_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { scale } from './scaleLayer';\nimport { ConvLayerParams } from './types';\n\nfunction convLayer(\n x: tf.Tensor4D,\n params: ConvLayerParams,\n strides: [number, number],\n withRelu: boolean,\n padding: 'valid' | 'same' = 'same',\n): tf.Tensor4D {\n const { filters, bias } = params.conv;\n\n let out = tf.conv2d(x, filters, strides, padding);\n out = tf.add(out, bias);\n out = scale(out, params.scale);\n return withRelu ? tf.relu(out) : out;\n}\n\nexport function conv(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], true);\n}\n\nexport function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [1, 1], false);\n}\n\nexport function convDown(x: tf.Tensor4D, params: ConvLayerParams) {\n return convLayer(x, params, [2, 2], true, 'valid');\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ScaleLayerParams } from './types';\n\nexport function scale(x: tf.Tensor4D, params: ScaleLayerParams): tf.Tensor4D {\n return tf.add(tf.mul(x, params.weights), params.biases);\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping,\n} from '../common/index';\nimport { isFloat } from '../utils/index';\nimport {\n ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {\n const weights = extractWeights(numFilterValues);\n const depth = weights.length / (numFilters * filterSize * filterSize);\n\n if (isFloat(depth)) {\n throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`);\n }\n\n return tf.tidy(\n () => tf.transpose(\n tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),\n [2, 3, 1, 0],\n ),\n );\n }\n\n function extractConvParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvParams {\n const filters = extractFilterValues(numFilterValues, numFilters, filterSize);\n const bias = tf.tensor1d(extractWeights(numFilters));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/bias` },\n );\n\n return { filters, bias };\n }\n\n function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {\n const weights = tf.tensor1d(extractWeights(numWeights));\n const biases = tf.tensor1d(extractWeights(numWeights));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/weights` },\n { paramPath: `${mappedPrefix}/biases` },\n );\n\n return {\n weights,\n biases,\n };\n }\n\n function extractConvLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n ): ConvLayerParams {\n const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`);\n const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`);\n\n return { conv, scale };\n }\n\n function extractResidualLayerParams(\n numFilterValues: number,\n numFilters: number,\n filterSize: number,\n mappedPrefix: string,\n isDown: boolean = false,\n ): ResidualLayerParams {\n const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`);\n const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`);\n\n return { conv1, conv2 };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n\n const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down');\n const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1');\n const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2');\n const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3');\n\n const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true);\n const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1');\n const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2');\n const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3');\n\n const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true);\n const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1');\n const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2');\n\n const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true);\n const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1');\n const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2');\n const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out');\n\n const fc = tf.tidy(\n () => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0]),\n );\n paramMappings.push({ paramPath: 'fc' });\n\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common/index';\nimport { isTensor2D } from '../utils/index';\nimport { ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractScaleLayerParams(prefix: string): ScaleLayerParams {\n const weights = extractWeightEntry(`${prefix}/scale/weights`, 1);\n const biases = extractWeightEntry(`${prefix}/scale/biases`, 1);\n\n return { weights, biases };\n }\n\n function extractConvLayerParams(prefix: string): ConvLayerParams {\n const filters = extractWeightEntry(`${prefix}/conv/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/conv/bias`, 1);\n const scale = extractScaleLayerParams(prefix);\n\n return { conv: { filters, bias }, scale };\n }\n\n function extractResidualLayerParams(prefix: string): ResidualLayerParams {\n return {\n conv1: extractConvLayerParams(`${prefix}/conv1`),\n conv2: extractConvLayerParams(`${prefix}/conv2`),\n };\n }\n\n return {\n extractConvLayerParams,\n extractResidualLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvLayerParams,\n extractResidualLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n const conv32_down = extractConvLayerParams('conv32_down');\n const conv32_1 = extractResidualLayerParams('conv32_1');\n const conv32_2 = extractResidualLayerParams('conv32_2');\n const conv32_3 = extractResidualLayerParams('conv32_3');\n\n const conv64_down = extractResidualLayerParams('conv64_down');\n const conv64_1 = extractResidualLayerParams('conv64_1');\n const conv64_2 = extractResidualLayerParams('conv64_2');\n const conv64_3 = extractResidualLayerParams('conv64_3');\n\n const conv128_down = extractResidualLayerParams('conv128_down');\n const conv128_1 = extractResidualLayerParams('conv128_1');\n const conv128_2 = extractResidualLayerParams('conv128_2');\n\n const conv256_down = extractResidualLayerParams('conv256_down');\n const conv256_1 = extractResidualLayerParams('conv256_1');\n const conv256_2 = extractResidualLayerParams('conv256_2');\n const conv256_down_out = extractResidualLayerParams('conv256_down_out');\n\n const { fc } = weightMap;\n paramMappings.push({ originalPath: 'fc', paramPath: 'fc' });\n\n if (!isTensor2D(fc)) {\n throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`);\n }\n\n const params = {\n conv32_down,\n conv32_1,\n conv32_2,\n conv32_3,\n conv64_down,\n conv64_1,\n conv64_2,\n conv64_3,\n conv128_down,\n conv128_1,\n conv128_2,\n conv256_down,\n conv256_1,\n conv256_2,\n conv256_down_out,\n fc,\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { conv, convDown, convNoRelu } from './convLayer';\nimport { ResidualLayerParams } from './types';\n\nexport function residual(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = conv(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n out = tf.add(out, x);\n out = tf.relu(out);\n return out;\n}\n\nexport function residualDown(x: tf.Tensor4D, params: ResidualLayerParams): tf.Tensor4D {\n let out = convDown(x, params.conv1);\n out = convNoRelu(out, params.conv2);\n\n let pooled = tf.avgPool(x, 2, 2, 'valid') as tf.Tensor4D;\n const zeros = tf.zeros(pooled.shape);\n const isPad = pooled.shape[3] !== out.shape[3];\n const isAdjustShape = pooled.shape[1] !== out.shape[1] || pooled.shape[2] !== out.shape[2];\n\n if (isAdjustShape) {\n const padShapeX = [...out.shape] as [number, number, number, number];\n padShapeX[1] = 1;\n const zerosW = tf.zeros(padShapeX);\n out = tf.concat([out, zerosW], 1);\n\n const padShapeY = [...out.shape] as [number, number, number, number];\n padShapeY[2] = 1;\n const zerosH = tf.zeros(padShapeY);\n out = tf.concat([out, zerosH], 2);\n }\n\n pooled = isPad ? tf.concat([pooled, zeros], 3) : pooled;\n out = tf.add(pooled, out) as tf.Tensor4D;\n\n out = tf.relu(out);\n return out;\n}\n", "import { FaceRecognitionNet } from './FaceRecognitionNet';\n\nexport * from './FaceRecognitionNet';\n\nexport function createFaceRecognitionNet(weights: Float32Array) {\n const net = new FaceRecognitionNet();\n net.extractWeights(weights);\n return net;\n}\n", "export type WithFaceDescriptor = TSource & {\n descriptor: Float32Array\n}\n\nexport function extendWithFaceDescriptor<\n TSource\n>(\n sourceObj: TSource,\n descriptor: Float32Array,\n): WithFaceDescriptor {\n const extension = { descriptor };\n return { ...sourceObj, ...extension };\n}\n", "export type WithAge = TSource & {\n age: number\n}\n\nexport function isWithAge(obj: any): obj is WithAge<{}> {\n return typeof obj.age === 'number';\n}\n\nexport function extendWithAge<\n TSource\n>(\n sourceObj: TSource,\n age: number,\n): WithAge {\n const extension = { age };\n return { ...sourceObj, ...extension };\n}\n", "import { Gender } from '../ageGenderNet/types';\nimport { isValidProbablitiy } from '../utils/index';\n\nexport type WithGender = TSource & {\n gender: Gender\n genderProbability: number\n}\n\nexport function isWithGender(obj: any): obj is WithGender<{}> {\n return (obj.gender === Gender.MALE || obj.gender === Gender.FEMALE)\n && isValidProbablitiy(obj.genderProbability);\n}\n\nexport function extendWithGender<\n TSource\n>(\n sourceObj: TSource,\n gender: Gender,\n genderProbability: number,\n): WithGender {\n const extension = { gender, genderProbability };\n return { ...sourceObj, ...extension };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { Rect } from '../classes/index';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { NetInput, TNetInput, toNetInput } from '../dom/index';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { mobileNetV1 } from './mobileNetV1';\nimport { nonMaxSuppression } from './nonMaxSuppression';\nimport { outputLayer } from './outputLayer';\nimport { predictionLayer } from './predictionLayer';\nimport { ISsdMobilenetv1Options, SsdMobilenetv1Options } from './SsdMobilenetv1Options';\nimport { NetParams } from './types';\n\nexport class SsdMobilenetv1 extends NeuralNetwork {\n constructor() {\n super('SsdMobilenetv1');\n }\n\n public forwardInput(input: NetInput) {\n const { params } = this;\n\n if (!params) {\n throw new Error('SsdMobilenetv1 - load model before inference');\n }\n\n return tf.tidy(() => {\n const batchTensor = tf.cast(input.toBatchTensor(512, false), 'float32');\n const x = tf.sub(tf.mul(batchTensor, tf.scalar(0.007843137718737125)), tf.scalar(1)) as tf.Tensor4D;\n const features = mobileNetV1(x, params.mobilenetv1);\n\n const {\n boxPredictions,\n classPredictions,\n } = predictionLayer(features.out, features.conv11, params.prediction_layer);\n\n return outputLayer(boxPredictions, classPredictions, params.output_layer);\n });\n }\n\n public async forward(input: TNetInput) {\n return this.forwardInput(await toNetInput(input));\n }\n\n public async locateFaces(\n input: TNetInput,\n options: ISsdMobilenetv1Options = {},\n ): Promise {\n const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);\n\n const netInput = await toNetInput(input);\n\n const {\n boxes: _boxes,\n scores: _scores,\n } = this.forwardInput(netInput);\n\n const boxes = _boxes[0];\n const scores = _scores[0];\n for (let i = 1; i < _boxes.length; i++) {\n _boxes[i].dispose();\n _scores[i].dispose();\n }\n\n const scoresData = Array.from(await scores.data());\n const iouThreshold = 0.5;\n const indices = nonMaxSuppression(\n boxes,\n scoresData as number[],\n maxResults,\n iouThreshold,\n minConfidence,\n );\n\n const reshapedDims = netInput.getReshapedInputDimensions(0);\n const inputSize = netInput.inputSize as number;\n const padX = inputSize / reshapedDims.width;\n const padY = inputSize / reshapedDims.height;\n\n const boxesData = boxes.arraySync();\n const results = indices\n .map((idx) => {\n const [top, bottom] = [\n Math.max(0, boxesData[idx][0]),\n Math.min(1.0, boxesData[idx][2]),\n ].map((val) => val * padY);\n const [left, right] = [\n Math.max(0, boxesData[idx][1]),\n Math.min(1.0, boxesData[idx][3]),\n ].map((val) => val * padX);\n return new FaceDetection(\n scoresData[idx] as number,\n new Rect(\n left,\n top,\n right - left,\n bottom - top,\n ),\n {\n height: netInput.getInputHeight(0),\n width: netInput.getInputWidth(0),\n },\n );\n });\n\n boxes.dispose();\n scores.dispose();\n return results;\n }\n\n protected getDefaultModelName(): string {\n return 'ssd_mobilenetv1_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap);\n }\n\n protected extractParams(weights: Float32Array) {\n return extractParams(weights);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ExtractWeightsFunction, ParamMapping, ConvParams, extractWeightsFactory,\n} from '../common/index';\nimport {\n MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n function extractDepthwiseConvParams(numChannels: number, mappedPrefix: string): MobileNetV1.DepthwiseConvParams {\n const filters = tf.tensor4d(extractWeights(3 * 3 * numChannels), [3, 3, numChannels, 1]);\n const batch_norm_scale = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_offset = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_mean = tf.tensor1d(extractWeights(numChannels));\n const batch_norm_variance = tf.tensor1d(extractWeights(numChannels));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/batch_norm_scale` },\n { paramPath: `${mappedPrefix}/batch_norm_offset` },\n { paramPath: `${mappedPrefix}/batch_norm_mean` },\n { paramPath: `${mappedPrefix}/batch_norm_variance` },\n );\n\n return {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n };\n }\n\n function extractConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n isPointwiseConv?: boolean,\n ): ConvParams {\n const filters = tf.tensor4d(\n extractWeights(channelsIn * channelsOut * filterSize * filterSize),\n [filterSize, filterSize, channelsIn, channelsOut],\n );\n const bias = tf.tensor1d(extractWeights(channelsOut));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/filters` },\n { paramPath: `${mappedPrefix}/${isPointwiseConv ? 'batch_norm_offset' : 'bias'}` },\n );\n\n return { filters, bias };\n }\n\n function extractPointwiseConvParams(\n channelsIn: number,\n channelsOut: number,\n filterSize: number,\n mappedPrefix: string,\n ): PointwiseConvParams {\n const {\n filters,\n bias,\n } = extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix, true);\n\n return {\n filters,\n batch_norm_offset: bias,\n };\n }\n\n function extractConvPairParams(\n channelsIn: number,\n channelsOut: number,\n mappedPrefix: string,\n ): MobileNetV1.ConvPairParams {\n const depthwise_conv = extractDepthwiseConvParams(channelsIn, `${mappedPrefix}/depthwise_conv`);\n const pointwise_conv = extractPointwiseConvParams(channelsIn, channelsOut, 1, `${mappedPrefix}/pointwise_conv`);\n\n return { depthwise_conv, pointwise_conv };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n const conv_0 = extractPointwiseConvParams(3, 32, 3, 'mobilenetv1/conv_0');\n const conv_1 = extractConvPairParams(32, 64, 'mobilenetv1/conv_1');\n const conv_2 = extractConvPairParams(64, 128, 'mobilenetv1/conv_2');\n const conv_3 = extractConvPairParams(128, 128, 'mobilenetv1/conv_3');\n const conv_4 = extractConvPairParams(128, 256, 'mobilenetv1/conv_4');\n const conv_5 = extractConvPairParams(256, 256, 'mobilenetv1/conv_5');\n const conv_6 = extractConvPairParams(256, 512, 'mobilenetv1/conv_6');\n const conv_7 = extractConvPairParams(512, 512, 'mobilenetv1/conv_7');\n const conv_8 = extractConvPairParams(512, 512, 'mobilenetv1/conv_8');\n const conv_9 = extractConvPairParams(512, 512, 'mobilenetv1/conv_9');\n const conv_10 = extractConvPairParams(512, 512, 'mobilenetv1/conv_10');\n const conv_11 = extractConvPairParams(512, 512, 'mobilenetv1/conv_11');\n const conv_12 = extractConvPairParams(512, 1024, 'mobilenetv1/conv_12');\n const conv_13 = extractConvPairParams(1024, 1024, 'mobilenetv1/conv_13');\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n conv_8,\n conv_9,\n conv_10,\n conv_11,\n conv_12,\n conv_13,\n };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n const conv_0 = extractPointwiseConvParams(1024, 256, 1, 'prediction_layer/conv_0');\n const conv_1 = extractPointwiseConvParams(256, 512, 3, 'prediction_layer/conv_1');\n const conv_2 = extractPointwiseConvParams(512, 128, 1, 'prediction_layer/conv_2');\n const conv_3 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_3');\n const conv_4 = extractPointwiseConvParams(256, 128, 1, 'prediction_layer/conv_4');\n const conv_5 = extractPointwiseConvParams(128, 256, 3, 'prediction_layer/conv_5');\n const conv_6 = extractPointwiseConvParams(256, 64, 1, 'prediction_layer/conv_6');\n const conv_7 = extractPointwiseConvParams(64, 128, 3, 'prediction_layer/conv_7');\n const box_encoding_0_predictor = extractConvParams(512, 12, 1, 'prediction_layer/box_predictor_0/box_encoding_predictor');\n const class_predictor_0 = extractConvParams(512, 9, 1, 'prediction_layer/box_predictor_0/class_predictor');\n const box_encoding_1_predictor = extractConvParams(1024, 24, 1, 'prediction_layer/box_predictor_1/box_encoding_predictor');\n const class_predictor_1 = extractConvParams(1024, 18, 1, 'prediction_layer/box_predictor_1/class_predictor');\n const box_encoding_2_predictor = extractConvParams(512, 24, 1, 'prediction_layer/box_predictor_2/box_encoding_predictor');\n const class_predictor_2 = extractConvParams(512, 18, 1, 'prediction_layer/box_predictor_2/class_predictor');\n const box_encoding_3_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_3/box_encoding_predictor');\n const class_predictor_3 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_3/class_predictor');\n const box_encoding_4_predictor = extractConvParams(256, 24, 1, 'prediction_layer/box_predictor_4/box_encoding_predictor');\n const class_predictor_4 = extractConvParams(256, 18, 1, 'prediction_layer/box_predictor_4/class_predictor');\n const box_encoding_5_predictor = extractConvParams(128, 24, 1, 'prediction_layer/box_predictor_5/box_encoding_predictor');\n const class_predictor_5 = extractConvParams(128, 18, 1, 'prediction_layer/box_predictor_5/class_predictor');\n\n const box_predictor_0 = {\n box_encoding_predictor: box_encoding_0_predictor,\n class_predictor: class_predictor_0,\n };\n const box_predictor_1 = {\n box_encoding_predictor: box_encoding_1_predictor,\n class_predictor: class_predictor_1,\n };\n const box_predictor_2 = {\n box_encoding_predictor: box_encoding_2_predictor,\n class_predictor: class_predictor_2,\n };\n const box_predictor_3 = {\n box_encoding_predictor: box_encoding_3_predictor,\n class_predictor: class_predictor_3,\n };\n const box_predictor_4 = {\n box_encoding_predictor: box_encoding_4_predictor,\n class_predictor: class_predictor_4,\n };\n const box_predictor_5 = {\n box_encoding_predictor: box_encoding_5_predictor,\n class_predictor: class_predictor_5,\n };\n return {\n conv_0,\n conv_1,\n conv_2,\n conv_3,\n conv_4,\n conv_5,\n conv_6,\n conv_7,\n box_predictor_0,\n box_predictor_1,\n box_predictor_2,\n box_predictor_3,\n box_predictor_4,\n box_predictor_5,\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(extractWeights, paramMappings);\n const mobilenetv1 = extractMobilenetV1Params();\n const prediction_layer = extractPredictionLayerParams();\n const extra_dim = tf.tensor3d(\n extractWeights(5118 * 4),\n [1, 5118, 4],\n );\n const output_layer = {\n extra_dim,\n };\n paramMappings.push({ paramPath: 'output_layer/extra_dim' });\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n\n return {\n params: {\n mobilenetv1,\n prediction_layer,\n output_layer,\n },\n paramMappings,\n };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport {\n ConvParams, disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping,\n} from '../common/index';\nimport { isTensor3D } from '../utils/index';\nimport {\n BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams,\n} from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractPointwiseConvParams(prefix: string, idx: number, mappedPrefix: string): PointwiseConvParams {\n const filters = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/weights`, 4, `${mappedPrefix}/filters`);\n const batch_norm_offset = extractWeightEntry(`${prefix}/Conv2d_${idx}_pointwise/convolution_bn_offset`, 1, `${mappedPrefix}/batch_norm_offset`);\n return { filters, batch_norm_offset };\n }\n\n function extractConvPairParams(idx: number): MobileNetV1.ConvPairParams {\n const mappedPrefix = `mobilenetv1/conv_${idx}`;\n const prefixDepthwiseConv = `MobilenetV1/Conv2d_${idx}_depthwise`;\n const mappedPrefixDepthwiseConv = `${mappedPrefix}/depthwise_conv`;\n const mappedPrefixPointwiseConv = `${mappedPrefix}/pointwise_conv`;\n\n const filters = extractWeightEntry(`${prefixDepthwiseConv}/depthwise_weights`, 4, `${mappedPrefixDepthwiseConv}/filters`);\n const batch_norm_scale = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/gamma`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_scale`);\n const batch_norm_offset = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/beta`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_offset`);\n const batch_norm_mean = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_mean`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_mean`);\n const batch_norm_variance = extractWeightEntry(`${prefixDepthwiseConv}/BatchNorm/moving_variance`, 1, `${mappedPrefixDepthwiseConv}/batch_norm_variance`);\n\n return {\n depthwise_conv: {\n filters,\n batch_norm_scale,\n batch_norm_offset,\n batch_norm_mean,\n batch_norm_variance,\n },\n pointwise_conv: extractPointwiseConvParams('MobilenetV1', idx, mappedPrefixPointwiseConv),\n };\n }\n\n function extractMobilenetV1Params(): MobileNetV1.Params {\n return {\n conv_0: extractPointwiseConvParams('MobilenetV1', 0, 'mobilenetv1/conv_0'),\n conv_1: extractConvPairParams(1),\n conv_2: extractConvPairParams(2),\n conv_3: extractConvPairParams(3),\n conv_4: extractConvPairParams(4),\n conv_5: extractConvPairParams(5),\n conv_6: extractConvPairParams(6),\n conv_7: extractConvPairParams(7),\n conv_8: extractConvPairParams(8),\n conv_9: extractConvPairParams(9),\n conv_10: extractConvPairParams(10),\n conv_11: extractConvPairParams(11),\n conv_12: extractConvPairParams(12),\n conv_13: extractConvPairParams(13),\n };\n }\n\n function extractConvParams(prefix: string, mappedPrefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/weights`, 4, `${mappedPrefix}/filters`);\n const bias = extractWeightEntry(`${prefix}/biases`, 1, `${mappedPrefix}/bias`);\n return { filters, bias };\n }\n\n function extractBoxPredictorParams(idx: number): BoxPredictionParams {\n const box_encoding_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/BoxEncodingPredictor`,\n `prediction_layer/box_predictor_${idx}/box_encoding_predictor`,\n );\n const class_predictor = extractConvParams(\n `Prediction/BoxPredictor_${idx}/ClassPredictor`,\n `prediction_layer/box_predictor_${idx}/class_predictor`,\n );\n return { box_encoding_predictor, class_predictor };\n }\n\n function extractPredictionLayerParams(): PredictionLayerParams {\n return {\n conv_0: extractPointwiseConvParams('Prediction', 0, 'prediction_layer/conv_0'),\n conv_1: extractPointwiseConvParams('Prediction', 1, 'prediction_layer/conv_1'),\n conv_2: extractPointwiseConvParams('Prediction', 2, 'prediction_layer/conv_2'),\n conv_3: extractPointwiseConvParams('Prediction', 3, 'prediction_layer/conv_3'),\n conv_4: extractPointwiseConvParams('Prediction', 4, 'prediction_layer/conv_4'),\n conv_5: extractPointwiseConvParams('Prediction', 5, 'prediction_layer/conv_5'),\n conv_6: extractPointwiseConvParams('Prediction', 6, 'prediction_layer/conv_6'),\n conv_7: extractPointwiseConvParams('Prediction', 7, 'prediction_layer/conv_7'),\n box_predictor_0: extractBoxPredictorParams(0),\n box_predictor_1: extractBoxPredictorParams(1),\n box_predictor_2: extractBoxPredictorParams(2),\n box_predictor_3: extractBoxPredictorParams(3),\n box_predictor_4: extractBoxPredictorParams(4),\n box_predictor_5: extractBoxPredictorParams(5),\n };\n }\n\n return {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n): { params: NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n const {\n extractMobilenetV1Params,\n extractPredictionLayerParams,\n } = extractorsFactory(weightMap, paramMappings);\n const extra_dim = weightMap['Output/extra_dim'];\n paramMappings.push({ originalPath: 'Output/extra_dim', paramPath: 'output_layer/extra_dim' });\n if (!isTensor3D(extra_dim)) {\n throw new Error(`expected weightMap['Output/extra_dim'] to be a Tensor3D, instead have ${extra_dim}`);\n }\n\n const params = {\n mobilenetv1: extractMobilenetV1Params(),\n prediction_layer: extractPredictionLayerParams(),\n output_layer: {\n extra_dim,\n },\n };\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { MobileNetV1 } from './types';\n\nconst epsilon = 0.0010000000474974513;\n\nfunction depthwiseConvLayer(\n x: tf.Tensor4D,\n params: MobileNetV1.DepthwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.depthwiseConv2d(x, params.filters, strides, 'same');\n out = tf.batchNorm(\n out,\n params.batch_norm_mean,\n params.batch_norm_variance,\n params.batch_norm_offset,\n params.batch_norm_scale,\n epsilon,\n );\n return tf.clipByValue(out, 0, 6);\n });\n}\n\nfunction getStridesForLayerIdx(layerIdx: number): [number, number] {\n return [2, 4, 6, 12].some((idx) => idx === layerIdx) ? [2, 2] : [1, 1];\n}\n\nexport function mobileNetV1(x: tf.Tensor4D, params: MobileNetV1.Params) {\n return tf.tidy(() => {\n let conv11;\n let out = pointwiseConvLayer(x, params.conv_0, [2, 2]);\n\n const convPairParams = [\n params.conv_1,\n params.conv_2,\n params.conv_3,\n params.conv_4,\n params.conv_5,\n params.conv_6,\n params.conv_7,\n params.conv_8,\n params.conv_9,\n params.conv_10,\n params.conv_11,\n params.conv_12,\n params.conv_13,\n ];\n\n convPairParams.forEach((param, i) => {\n const layerIdx = i + 1;\n const depthwiseConvStrides = getStridesForLayerIdx(layerIdx);\n out = depthwiseConvLayer(out, param.depthwise_conv, depthwiseConvStrides);\n out = pointwiseConvLayer(out, param.pointwise_conv, [1, 1]);\n if (layerIdx === 11) {\n conv11 = out;\n }\n });\n\n if (conv11 === null) {\n throw new Error('mobileNetV1 - output of conv layer 11 is null');\n }\n\n return {\n out,\n conv11: conv11 as any,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { PointwiseConvParams } from './types';\n\nexport function pointwiseConvLayer(\n x: tf.Tensor4D,\n params: PointwiseConvParams,\n strides: [number, number],\n) {\n return tf.tidy(() => {\n let out = tf.conv2d(x, params.filters, strides, 'same');\n out = tf.add(out, params.batch_norm_offset);\n return tf.clipByValue(out, 0, 6);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nfunction IOU(boxes: tf.Tensor2D, i: number, j: number) {\n const boxesData = boxes.arraySync();\n const yminI = Math.min(boxesData[i][0], boxesData[i][2]);\n const xminI = Math.min(boxesData[i][1], boxesData[i][3]);\n const ymaxI = Math.max(boxesData[i][0], boxesData[i][2]);\n const xmaxI = Math.max(boxesData[i][1], boxesData[i][3]);\n const yminJ = Math.min(boxesData[j][0], boxesData[j][2]);\n const xminJ = Math.min(boxesData[j][1], boxesData[j][3]);\n const ymaxJ = Math.max(boxesData[j][0], boxesData[j][2]);\n const xmaxJ = Math.max(boxesData[j][1], boxesData[j][3]);\n const areaI = (ymaxI - yminI) * (xmaxI - xminI);\n const areaJ = (ymaxJ - yminJ) * (xmaxJ - xminJ);\n if (areaI <= 0 || areaJ <= 0) {\n return 0.0;\n }\n const intersectionYmin = Math.max(yminI, yminJ);\n const intersectionXmin = Math.max(xminI, xminJ);\n const intersectionYmax = Math.min(ymaxI, ymaxJ);\n const intersectionXmax = Math.min(xmaxI, xmaxJ);\n const intersectionArea = Math.max(intersectionYmax - intersectionYmin, 0.0)\n * Math.max(intersectionXmax - intersectionXmin, 0.0);\n return intersectionArea / (areaI + areaJ - intersectionArea);\n}\n\nexport function nonMaxSuppression(\n boxes: tf.Tensor2D,\n scores: number[],\n maxOutputSize: number,\n iouThreshold: number,\n scoreThreshold: number,\n): number[] {\n const numBoxes = boxes.shape[0];\n const outputSize = Math.min(\n maxOutputSize,\n numBoxes,\n );\n\n const candidates = scores\n .map((score, boxIndex) => ({ score, boxIndex }))\n .filter((c) => c.score > scoreThreshold)\n .sort((c1, c2) => c2.score - c1.score);\n\n const suppressFunc = (x: number) => (x <= iouThreshold ? 1 : 0);\n const selected: number[] = [];\n\n candidates.forEach((c) => {\n if (selected.length >= outputSize) return;\n const originalScore = c.score;\n for (let j = selected.length - 1; j >= 0; --j) {\n const iou = IOU(boxes, c.boxIndex, selected[j]);\n if (iou === 0.0) continue;\n c.score *= suppressFunc(iou);\n if (c.score <= scoreThreshold) break;\n }\n if (originalScore === c.score) {\n selected.push(c.boxIndex);\n }\n });\n return selected;\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { OutputLayerParams } from './types';\n\nfunction getCenterCoordinatesAndSizesLayer(x: tf.Tensor2D) {\n const vec = tf.unstack(tf.transpose(x, [1, 0]));\n\n const sizes = [\n tf.sub(vec[2], vec[0]),\n tf.sub(vec[3], vec[1]),\n ];\n const centers = [\n tf.add(vec[0], tf.div(sizes[0], tf.scalar(2))),\n tf.add(vec[1], tf.div(sizes[1], tf.scalar(2))),\n ];\n return {\n sizes,\n centers,\n };\n}\n\nfunction decodeBoxesLayer(x0: tf.Tensor2D, x1: tf.Tensor2D) {\n const {\n sizes,\n centers,\n } = getCenterCoordinatesAndSizesLayer(x0);\n\n const vec = tf.unstack(tf.transpose(x1, [1, 0]));\n const div0_out = tf.div(tf.mul(tf.exp(tf.div(vec[2], tf.scalar(5))), sizes[0]), tf.scalar(2));\n const add0_out = tf.add(tf.mul(tf.div(vec[0], tf.scalar(10)), sizes[0]), centers[0]);\n const div1_out = tf.div(tf.mul(tf.exp(tf.div(vec[3], tf.scalar(5))), sizes[1]), tf.scalar(2));\n const add1_out = tf.add(tf.mul(tf.div(vec[1], tf.scalar(10)), sizes[1]), centers[1]);\n\n return tf.transpose(\n tf.stack([\n tf.sub(add0_out, div0_out),\n tf.sub(add1_out, div1_out),\n tf.add(add0_out, div0_out),\n tf.add(add1_out, div1_out),\n ]),\n [1, 0],\n );\n}\n\nexport function outputLayer(\n boxPredictions: tf.Tensor4D,\n classPredictions: tf.Tensor4D,\n params: OutputLayerParams,\n) {\n return tf.tidy(() => {\n const batchSize = boxPredictions.shape[0];\n\n let boxes = decodeBoxesLayer(\n tf.reshape(tf.tile(params.extra_dim, [batchSize, 1, 1]), [-1, 4]) as tf.Tensor2D,\n tf.reshape(boxPredictions, [-1, 4]) as tf.Tensor2D,\n );\n boxes = tf.reshape(\n boxes,\n [batchSize, (boxes.shape[0] / batchSize), 4],\n );\n\n const scoresAndClasses = tf.sigmoid(tf.slice(classPredictions, [0, 0, 1], [-1, -1, -1]));\n let scores = tf.slice(scoresAndClasses, [0, 0, 0], [-1, -1, 1]) as tf.Tensor;\n\n scores = tf.reshape(\n scores,\n [batchSize, scores.shape[1] as number],\n );\n\n const boxesByBatch = tf.unstack(boxes) as tf.Tensor2D[];\n const scoresByBatch = tf.unstack(scores) as tf.Tensor1D[];\n\n return {\n boxes: boxesByBatch,\n scores: scoresByBatch,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { boxPredictionLayer } from './boxPredictionLayer';\nimport { pointwiseConvLayer } from './pointwiseConvLayer';\nimport { PredictionLayerParams } from './types';\n\nexport function predictionLayer(\n x: tf.Tensor4D,\n conv11: tf.Tensor4D,\n params: PredictionLayerParams,\n) {\n return tf.tidy(() => {\n const conv0 = pointwiseConvLayer(x, params.conv_0, [1, 1]);\n const conv1 = pointwiseConvLayer(conv0, params.conv_1, [2, 2]);\n const conv2 = pointwiseConvLayer(conv1, params.conv_2, [1, 1]);\n const conv3 = pointwiseConvLayer(conv2, params.conv_3, [2, 2]);\n const conv4 = pointwiseConvLayer(conv3, params.conv_4, [1, 1]);\n const conv5 = pointwiseConvLayer(conv4, params.conv_5, [2, 2]);\n const conv6 = pointwiseConvLayer(conv5, params.conv_6, [1, 1]);\n const conv7 = pointwiseConvLayer(conv6, params.conv_7, [2, 2]);\n\n const boxPrediction0 = boxPredictionLayer(conv11, params.box_predictor_0);\n const boxPrediction1 = boxPredictionLayer(x, params.box_predictor_1);\n const boxPrediction2 = boxPredictionLayer(conv1, params.box_predictor_2);\n const boxPrediction3 = boxPredictionLayer(conv3, params.box_predictor_3);\n const boxPrediction4 = boxPredictionLayer(conv5, params.box_predictor_4);\n const boxPrediction5 = boxPredictionLayer(conv7, params.box_predictor_5);\n\n const boxPredictions = tf.concat([\n boxPrediction0.boxPredictionEncoding,\n boxPrediction1.boxPredictionEncoding,\n boxPrediction2.boxPredictionEncoding,\n boxPrediction3.boxPredictionEncoding,\n boxPrediction4.boxPredictionEncoding,\n boxPrediction5.boxPredictionEncoding,\n ], 1) as tf.Tensor4D;\n\n const classPredictions = tf.concat([\n boxPrediction0.classPrediction,\n boxPrediction1.classPrediction,\n boxPrediction2.classPrediction,\n boxPrediction3.classPrediction,\n boxPrediction4.classPrediction,\n boxPrediction5.classPrediction,\n ], 1) as tf.Tensor4D;\n\n return {\n boxPredictions,\n classPredictions,\n };\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { convLayer } from '../common/index';\nimport { BoxPredictionParams } from './types';\n\nexport function boxPredictionLayer(\n x: tf.Tensor4D,\n params: BoxPredictionParams,\n) {\n return tf.tidy(() => {\n const batchSize = x.shape[0];\n const boxPredictionEncoding = tf.reshape(\n convLayer(x, params.box_encoding_predictor),\n [batchSize, -1, 1, 4],\n );\n const classPrediction = tf.reshape(\n convLayer(x, params.class_predictor),\n [batchSize, -1, 3],\n );\n return { boxPredictionEncoding, classPrediction };\n });\n}\n", "export interface ISsdMobilenetv1Options {\n minConfidence?: number\n maxResults?: number\n}\n\nexport class SsdMobilenetv1Options {\n protected _name: string = 'SsdMobilenetv1Options'\n\n private _minConfidence: number\n\n private _maxResults: number\n\n constructor({ minConfidence, maxResults }: ISsdMobilenetv1Options = {}) {\n this._minConfidence = minConfidence || 0.5;\n this._maxResults = maxResults || 100;\n\n if (typeof this._minConfidence !== 'number' || this._minConfidence <= 0 || this._minConfidence >= 1) {\n throw new Error(`${this._name} - expected minConfidence to be a number between 0 and 1`);\n }\n\n if (typeof this._maxResults !== 'number') {\n throw new Error(`${this._name} - expected maxResults to be a number`);\n }\n }\n\n get minConfidence(): number { return this._minConfidence; }\n\n get maxResults(): number { return this._maxResults; }\n}\n", "import { SsdMobilenetv1 } from './SsdMobilenetv1';\n\nexport * from './SsdMobilenetv1';\nexport * from './SsdMobilenetv1Options';\n\nexport function createSsdMobilenetv1(weights: Float32Array) {\n const net = new SsdMobilenetv1();\n net.extractWeights(weights);\n return net;\n}\n\nexport function createFaceDetectionNet(weights: Float32Array) {\n return createSsdMobilenetv1(weights);\n}\n\n// alias for backward compatibily\nexport class FaceDetectionNet extends SsdMobilenetv1 {}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(0.738768, 0.874946),\n new Point(2.42204, 2.65704),\n new Point(4.30971, 7.04493),\n new Point(10.246, 4.59428),\n new Point(12.6868, 11.8741),\n];\n\nexport const BOX_ANCHORS_SEPARABLE = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB_SEPARABLE: [number, number, number] = [117.001, 114.697, 97.404];\n\nexport const DEFAULT_MODEL_NAME = 'tiny_yolov2_model';\nexport const DEFAULT_MODEL_NAME_SEPARABLE_CONV = 'tiny_yolov2_separable_conv_model';\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { BoundingBox } from '../classes/BoundingBox';\nimport { Dimensions } from '../classes/Dimensions';\nimport { ObjectDetection } from '../classes/ObjectDetection';\nimport { convLayer } from '../common/index';\nimport { ConvParams, SeparableConvParams } from '../common/types';\nimport { toNetInput } from '../dom/index';\nimport { NetInput } from '../dom/NetInput';\nimport { TNetInput } from '../dom/types';\nimport { NeuralNetwork } from '../NeuralNetwork';\nimport { sigmoid } from '../ops/index';\nimport { nonMaxSuppression } from '../ops/nonMaxSuppression';\nimport { normalize } from '../ops/normalize';\nimport { TinyYolov2Config, validateConfig } from './config';\nimport { convWithBatchNorm } from './convWithBatchNorm';\nimport { depthwiseSeparableConv } from './depthwiseSeparableConv';\nimport { extractParams } from './extractParams';\nimport { extractParamsFromWeightMap } from './extractParamsFromWeightMap';\nimport { leaky } from './leaky';\nimport { ITinyYolov2Options, TinyYolov2Options } from './TinyYolov2Options';\nimport { DefaultTinyYolov2NetParams, MobilenetParams, TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2Base extends NeuralNetwork {\n public static DEFAULT_FILTER_SIZES = [3, 16, 32, 64, 128, 256, 512, 1024, 1024];\n\n private _config: TinyYolov2Config\n\n constructor(config: TinyYolov2Config) {\n super('TinyYolov2');\n validateConfig(config);\n this._config = config;\n }\n\n public get config(): TinyYolov2Config {\n return this._config;\n }\n\n public get withClassScores(): boolean {\n return this.config.withClassScores || this.config.classes.length > 1;\n }\n\n public get boxEncodingSize(): number {\n return 5 + (this.withClassScores ? this.config.classes.length : 0);\n }\n\n public runTinyYolov2(x: tf.Tensor4D, params: DefaultTinyYolov2NetParams): tf.Tensor4D {\n let out = convWithBatchNorm(x, params.conv0);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = convWithBatchNorm(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = convWithBatchNorm(out, params.conv6);\n out = convWithBatchNorm(out, params.conv7);\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public runMobilenet(x: tf.Tensor4D, params: MobilenetParams): tf.Tensor4D {\n let out = this.config.isFirstLayerConv2d\n ? leaky(convLayer(x, params.conv0 as ConvParams, 'valid', false))\n : depthwiseSeparableConv(x, params.conv0 as SeparableConvParams);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv1);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv2);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv3);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv4);\n out = tf.maxPool(out, [2, 2], [2, 2], 'same');\n out = depthwiseSeparableConv(out, params.conv5);\n out = tf.maxPool(out, [2, 2], [1, 1], 'same');\n out = params.conv6 ? depthwiseSeparableConv(out, params.conv6) : out;\n out = params.conv7 ? depthwiseSeparableConv(out, params.conv7) : out;\n return convLayer(out, params.conv8, 'valid', false);\n }\n\n public forwardInput(input: NetInput, inputSize: number): tf.Tensor4D {\n const { params } = this;\n\n if (!params) {\n throw new Error('TinyYolov2 - load model before inference');\n }\n\n return tf.tidy(() => {\n let batchTensor = tf.cast(input.toBatchTensor(inputSize, false), 'float32');\n batchTensor = this.config.meanRgb\n ? normalize(batchTensor, this.config.meanRgb)\n : batchTensor;\n batchTensor = batchTensor.div(tf.scalar(256)) as tf.Tensor4D;\n return this.config.withSeparableConvs\n ? this.runMobilenet(batchTensor, params as MobilenetParams)\n : this.runTinyYolov2(batchTensor, params as DefaultTinyYolov2NetParams);\n });\n }\n\n public async forward(input: TNetInput, inputSize: number): Promise {\n return this.forwardInput(await toNetInput(input), inputSize);\n }\n\n public async detect(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise {\n const { inputSize, scoreThreshold } = new TinyYolov2Options(forwardParams);\n const netInput = await toNetInput(input);\n const out = await this.forwardInput(netInput, inputSize);\n const out0 = tf.tidy(() => tf.unstack(out)[0].expandDims()) as tf.Tensor4D;\n const inputDimensions = {\n width: netInput.getInputWidth(0),\n height: netInput.getInputHeight(0),\n };\n\n const results = await this.extractBoxes(out0, netInput.getReshapedInputDimensions(0), scoreThreshold);\n out.dispose();\n out0.dispose();\n\n const boxes = results.map((res) => res.box);\n const scores = results.map((res) => res.score);\n const classScores = results.map((res) => res.classScore);\n const classNames = results.map((res) => this.config.classes[res.label]);\n\n const indices = nonMaxSuppression(\n boxes.map((box) => box.rescale(inputSize)),\n scores,\n this.config.iouThreshold,\n true,\n );\n\n const detections = indices.map((idx) => new ObjectDetection(\n scores[idx],\n classScores[idx],\n classNames[idx],\n boxes[idx],\n inputDimensions,\n ));\n return detections;\n }\n\n protected getDefaultModelName(): string {\n return '';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap) {\n return extractParamsFromWeightMap(weightMap, this.config);\n }\n\n protected extractParams(weights: Float32Array) {\n const filterSizes = this.config.filterSizes || TinyYolov2Base.DEFAULT_FILTER_SIZES;\n\n const numFilters = filterSizes ? filterSizes.length : undefined;\n if (numFilters !== 7 && numFilters !== 8 && numFilters !== 9) {\n throw new Error(`TinyYolov2 - expected 7 | 8 | 9 convolutional filters, but found ${numFilters} filterSizes in config`);\n }\n return extractParams(weights, this.config, this.boxEncodingSize, filterSizes);\n }\n\n protected async extractBoxes(\n outputTensor: tf.Tensor4D,\n inputBlobDimensions: Dimensions,\n scoreThreshold?: number,\n ) {\n const { width, height } = inputBlobDimensions;\n const inputSize = Math.max(width, height);\n const correctionFactorX = inputSize / width;\n const correctionFactorY = inputSize / height;\n\n const numCells = outputTensor.shape[1];\n const numBoxes = this.config.anchors.length;\n\n const [boxesTensor, scoresTensor, classScoresTensor] = tf.tidy(() => {\n const reshaped = outputTensor.reshape([numCells, numCells, numBoxes, this.boxEncodingSize]);\n\n const boxes = reshaped.slice([0, 0, 0, 0], [numCells, numCells, numBoxes, 4]);\n const scores = reshaped.slice([0, 0, 0, 4], [numCells, numCells, numBoxes, 1]);\n const classScores = this.withClassScores\n ? tf.softmax(reshaped.slice([0, 0, 0, 5], [numCells, numCells, numBoxes, this.config.classes.length]), 3)\n : tf.scalar(0);\n return [boxes, scores, classScores];\n });\n\n const results = [] as any;\n const scoresData = await scoresTensor.array();\n const boxesData = await boxesTensor.array();\n for (let row = 0; row < numCells; row++) {\n for (let col = 0; col < numCells; col++) {\n for (let anchor = 0; anchor < numBoxes; anchor++) {\n const score = sigmoid(scoresData[row][col][anchor][0]);\n if (!scoreThreshold || score > scoreThreshold) {\n const ctX = ((col + sigmoid(boxesData[row][col][anchor][0])) / numCells) * correctionFactorX;\n const ctY = ((row + sigmoid(boxesData[row][col][anchor][1])) / numCells) * correctionFactorY;\n const widthLocal = ((Math.exp(boxesData[row][col][anchor][2]) * this.config.anchors[anchor].x) / numCells) * correctionFactorX;\n const heightLocal = ((Math.exp(boxesData[row][col][anchor][3]) * this.config.anchors[anchor].y) / numCells) * correctionFactorY;\n const x = (ctX - (widthLocal / 2));\n const y = (ctY - (heightLocal / 2));\n const pos = { row, col, anchor };\n const { classScore, label } = this.withClassScores\n ? await this.extractPredictedClass(classScoresTensor as tf.Tensor4D, pos)\n : { classScore: 1, label: 0 };\n results.push({\n box: new BoundingBox(x, y, x + widthLocal, y + heightLocal),\n score,\n classScore: score * classScore,\n label,\n ...pos,\n });\n }\n }\n }\n }\n\n boxesTensor.dispose();\n scoresTensor.dispose();\n classScoresTensor.dispose();\n return results;\n }\n\n private async extractPredictedClass(classesTensor: tf.Tensor4D, pos: { row: number, col: number, anchor: number }) {\n const { row, col, anchor } = pos;\n const classesData = await classesTensor.array();\n return Array(this.config.classes.length).fill(0)\n .map((_, i) => classesData[row][col][anchor][i])\n .map((classScore, label) => ({\n classScore,\n label,\n }))\n .reduce((max, curr) => (max.classScore > curr.classScore ? max : curr));\n }\n}\n", "import { Point } from '../classes/Point';\n\nexport type TinyYolov2Config = {\n withSeparableConvs: boolean\n iouThreshold: number\n anchors: Point[]\n classes: string[]\n meanRgb?: [number, number, number]\n withClassScores?: boolean,\n filterSizes?: number[]\n isFirstLayerConv2d?: boolean\n}\n\nconst isNumber = (arg: any) => typeof arg === 'number';\n\nexport function validateConfig(config: any) {\n if (!config) {\n throw new Error(`invalid config: ${config}`);\n }\n\n if (typeof config.withSeparableConvs !== 'boolean') {\n throw new Error(`config.withSeparableConvs has to be a boolean, have: ${config.withSeparableConvs}`);\n }\n\n if (!isNumber(config.iouThreshold) || config.iouThreshold < 0 || config.iouThreshold > 1.0) {\n throw new Error(`config.iouThreshold has to be a number between [0, 1], have: ${config.iouThreshold}`);\n }\n\n if (\n !Array.isArray(config.classes)\n || !config.classes.length\n || !config.classes.every((c: any) => typeof c === 'string')\n ) {\n throw new Error(`config.classes has to be an array class names: string[], have: ${JSON.stringify(config.classes)}`);\n }\n\n if (\n !Array.isArray(config.anchors)\n || !config.anchors.length\n || !config.anchors.map((a: any) => a || {}).every((a: any) => isNumber(a.x) && isNumber(a.y))\n ) {\n throw new Error(`config.anchors has to be an array of { x: number, y: number }, have: ${JSON.stringify(config.anchors)}`);\n }\n\n if (config.meanRgb && (\n !Array.isArray(config.meanRgb)\n || config.meanRgb.length !== 3\n || !config.meanRgb.every(isNumber)\n )) {\n throw new Error(`config.meanRgb has to be an array of shape [number, number, number], have: ${JSON.stringify(config.meanRgb)}`);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { leaky } from './leaky';\nimport { ConvWithBatchNorm } from './types';\n\nexport function convWithBatchNorm(x: tf.Tensor4D, params: ConvWithBatchNorm): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n out = tf.conv2d(out, params.conv.filters, [1, 1], 'valid');\n out = tf.sub(out, params.bn.sub);\n out = tf.mul(out, params.bn.truediv);\n out = tf.add(out, params.conv.bias);\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nexport function leaky(x: tf.Tensor4D): tf.Tensor4D {\n return tf.tidy(() => {\n const min = tf.mul(x, tf.scalar(0.10000000149011612));\n return tf.add(tf.relu(tf.sub(x, min)), min);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { SeparableConvParams } from '../common/types';\nimport { leaky } from './leaky';\n\nexport function depthwiseSeparableConv(x: tf.Tensor4D, params: SeparableConvParams): tf.Tensor4D {\n return tf.tidy(() => {\n let out = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]]) as tf.Tensor4D;\n out = tf.separableConv2d(out, params.depthwise_filter, params.pointwise_filter, [1, 1], 'valid');\n out = tf.add(out, params.bias);\n return leaky(out);\n });\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { extractConvParamsFactory } from '../common/index';\nimport { extractSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightsFactory } from '../common/extractWeightsFactory';\nimport { ExtractWeightsFunction, ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {\n const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings);\n\n function extractBatchNormParams(size: number, mappedPrefix: string): BatchNorm {\n const sub = tf.tensor1d(extractWeights(size));\n const truediv = tf.tensor1d(extractWeights(size));\n\n paramMappings.push(\n { paramPath: `${mappedPrefix}/sub` },\n { paramPath: `${mappedPrefix}/truediv` },\n );\n return { sub, truediv };\n }\n\n function extractConvWithBatchNormParams(channelsIn: number, channelsOut: number, mappedPrefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv`);\n const bn = extractBatchNormParams(channelsOut, `${mappedPrefix}/bn`);\n return { conv, bn };\n }\n const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings);\n\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParams(\n weights: Float32Array,\n config: TinyYolov2Config,\n boxEncodingSize: number,\n filterSizes: number[],\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const {\n extractWeights,\n getRemainingWeights,\n } = extractWeightsFactory(weights);\n\n const paramMappings: ParamMapping[] = [];\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(extractWeights, paramMappings);\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = config.isFirstLayerConv2d\n ? extractConvParams(s0, s1, 3, 'conv0')\n : extractSeparableConvParams(s0, s1, 'conv0');\n const conv1 = extractSeparableConvParams(s1, s2, 'conv1');\n const conv2 = extractSeparableConvParams(s2, s3, 'conv2');\n const conv3 = extractSeparableConvParams(s3, s4, 'conv3');\n const conv4 = extractSeparableConvParams(s4, s5, 'conv4');\n const conv5 = extractSeparableConvParams(s5, s6, 'conv5');\n const conv6 = s7 ? extractSeparableConvParams(s6, s7, 'conv6') : undefined;\n const conv7 = s8 ? extractSeparableConvParams(s7, s8, 'conv7') : undefined;\n const conv8 = extractConvParams(s8 || s7 || s6, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n } else {\n const [s0, s1, s2, s3, s4, s5, s6, s7, s8] = filterSizes;\n const conv0 = extractConvWithBatchNormParams(s0, s1, 'conv0');\n const conv1 = extractConvWithBatchNormParams(s1, s2, 'conv1');\n const conv2 = extractConvWithBatchNormParams(s2, s3, 'conv2');\n const conv3 = extractConvWithBatchNormParams(s3, s4, 'conv3');\n const conv4 = extractConvWithBatchNormParams(s4, s5, 'conv4');\n const conv5 = extractConvWithBatchNormParams(s5, s6, 'conv5');\n const conv6 = extractConvWithBatchNormParams(s6, s7, 'conv6');\n const conv7 = extractConvWithBatchNormParams(s7, s8, 'conv7');\n const conv8 = extractConvParams(s8, 5 * boxEncodingSize, 1, 'conv8');\n params = {\n conv0, conv1, conv2, conv3, conv4, conv5, conv6, conv7, conv8,\n };\n }\n if (getRemainingWeights().length !== 0) {\n throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`);\n }\n return { params, paramMappings };\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { ConvParams } from '../common/index';\nimport { disposeUnusedWeightTensors } from '../common/disposeUnusedWeightTensors';\nimport { loadSeparableConvParamsFactory } from '../common/extractSeparableConvParamsFactory';\nimport { extractWeightEntryFactory } from '../common/extractWeightEntryFactory';\nimport { ParamMapping } from '../common/types';\nimport { TinyYolov2Config } from './config';\nimport { BatchNorm, ConvWithBatchNorm, TinyYolov2NetParams } from './types';\n\nfunction extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {\n const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings);\n\n function extractBatchNormParams(prefix: string): BatchNorm {\n const sub = extractWeightEntry(`${prefix}/sub`, 1);\n const truediv = extractWeightEntry(`${prefix}/truediv`, 1);\n return { sub, truediv };\n }\n\n function extractConvParams(prefix: string): ConvParams {\n const filters = extractWeightEntry(`${prefix}/filters`, 4);\n const bias = extractWeightEntry(`${prefix}/bias`, 1);\n return { filters, bias };\n }\n\n function extractConvWithBatchNormParams(prefix: string): ConvWithBatchNorm {\n const conv = extractConvParams(`${prefix}/conv`);\n const bn = extractBatchNormParams(`${prefix}/bn`);\n return { conv, bn };\n }\n\n const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry);\n return {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n };\n}\n\nexport function extractParamsFromWeightMap(\n weightMap: tf.NamedTensorMap,\n config: TinyYolov2Config,\n): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n const paramMappings: ParamMapping[] = [];\n\n const {\n extractConvParams,\n extractConvWithBatchNormParams,\n extractSeparableConvParams,\n } = extractorsFactory(weightMap, paramMappings);\n\n let params: TinyYolov2NetParams;\n\n if (config.withSeparableConvs) {\n // eslint-disable-next-line no-mixed-operators\n const numFilters = (config.filterSizes && config.filterSizes.length || 9);\n params = {\n conv0: config.isFirstLayerConv2d ? extractConvParams('conv0') : extractSeparableConvParams('conv0'),\n conv1: extractSeparableConvParams('conv1'),\n conv2: extractSeparableConvParams('conv2'),\n conv3: extractSeparableConvParams('conv3'),\n conv4: extractSeparableConvParams('conv4'),\n conv5: extractSeparableConvParams('conv5'),\n conv6: numFilters > 7 ? extractSeparableConvParams('conv6') : undefined,\n conv7: numFilters > 8 ? extractSeparableConvParams('conv7') : undefined,\n conv8: extractConvParams('conv8'),\n };\n } else {\n params = {\n conv0: extractConvWithBatchNormParams('conv0'),\n conv1: extractConvWithBatchNormParams('conv1'),\n conv2: extractConvWithBatchNormParams('conv2'),\n conv3: extractConvWithBatchNormParams('conv3'),\n conv4: extractConvWithBatchNormParams('conv4'),\n conv5: extractConvWithBatchNormParams('conv5'),\n conv6: extractConvWithBatchNormParams('conv6'),\n conv7: extractConvWithBatchNormParams('conv7'),\n conv8: extractConvParams('conv8'),\n };\n }\n\n disposeUnusedWeightTensors(weightMap, paramMappings);\n return { params, paramMappings };\n}\n", "export interface ITinyYolov2Options {\n inputSize?: number\n scoreThreshold?: number\n}\n\nexport class TinyYolov2Options {\n protected _name: string = 'TinyYolov2Options'\n\n private _inputSize: number\n\n private _scoreThreshold: number\n\n constructor({ inputSize, scoreThreshold }: ITinyYolov2Options = {}) {\n this._inputSize = inputSize || 416;\n this._scoreThreshold = scoreThreshold || 0.5;\n\n if (typeof this._inputSize !== 'number' || this._inputSize % 32 !== 0) {\n throw new Error(`${this._name} - expected inputSize to be a number divisible by 32`);\n }\n\n if (typeof this._scoreThreshold !== 'number' || this._scoreThreshold <= 0 || this._scoreThreshold >= 1) {\n throw new Error(`${this._name} - expected scoreThreshold to be a number between 0 and 1`);\n }\n }\n\n get inputSize(): number { return this._inputSize; }\n\n get scoreThreshold(): number { return this._scoreThreshold; }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/types';\nimport { TNetInput } from '../dom/types';\nimport {\n BOX_ANCHORS,\n BOX_ANCHORS_SEPARABLE,\n DEFAULT_MODEL_NAME,\n DEFAULT_MODEL_NAME_SEPARABLE_CONV,\n IOU_THRESHOLD,\n MEAN_RGB_SEPARABLE,\n} from './const';\nimport { TinyYolov2Base } from './TinyYolov2Base';\nimport { ITinyYolov2Options } from './TinyYolov2Options';\nimport { TinyYolov2NetParams } from './types';\n\nexport class TinyYolov2 extends TinyYolov2Base {\n constructor(withSeparableConvs: boolean = true) {\n const config = {\n withSeparableConvs,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n ...(withSeparableConvs\n ? {\n anchors: BOX_ANCHORS_SEPARABLE,\n meanRgb: MEAN_RGB_SEPARABLE,\n }\n : {\n anchors: BOX_ANCHORS,\n withClassScores: true,\n }),\n };\n\n super(config);\n }\n\n public get withSeparableConvs(): boolean {\n return this.config.withSeparableConvs;\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return this.withSeparableConvs ? DEFAULT_MODEL_NAME_SEPARABLE_CONV : DEFAULT_MODEL_NAME;\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { TinyYolov2 } from './TinyYolov2';\n\nexport * from './TinyYolov2Options';\nexport * from './config';\nexport * from './types';\nexport { TinyYolov2 };\n\nexport function createTinyYolov2(weights: Float32Array, withSeparableConvs: boolean = true) {\n const net = new TinyYolov2(withSeparableConvs);\n net.extractWeights(weights);\n return net;\n}\n", "import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\n\nexport interface ITinyFaceDetectorOptions extends ITinyYolov2Options {}\n\nexport class TinyFaceDetectorOptions extends TinyYolov2Options {\n protected _name: string = 'TinyFaceDetectorOptions'\n}\n", "export class ComposableTask {\n public async then(\n // eslint-disable-next-line no-unused-vars\n onfulfilled: (value: T) => T | PromiseLike,\n ): Promise {\n return onfulfilled(await this.run());\n }\n\n public async run(): Promise {\n throw new Error('ComposableTask - run is not implemented');\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class DetectFaceLandmarksTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected useTinyLandmarkNet: boolean,\n ) {\n super();\n }\n\n protected get landmarkNet(): FaceLandmark68Net | FaceLandmark68TinyNet {\n return this.useTinyLandmarkNet\n ? nets.faceLandmark68TinyNet\n : nets.faceLandmark68Net;\n }\n}\n\nexport class DetectAllFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n const detections = parentResults.map((res) => res.detection);\n\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, detections)\n : await extractFaces(this.input, detections);\n\n const faceLandmarksByFace = await Promise.all(faces.map(\n (face) => this.landmarkNet.detectLandmarks(face),\n )) as FaceLandmarks68[];\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return parentResults.map((parentResult, i) => extendWithFaceLandmarks(parentResult, faceLandmarksByFace[i]));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class DetectSingleFaceLandmarksTask<\n TSource extends WithFaceDetection<{}>\n> extends DetectFaceLandmarksTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { detection } = parentResult;\n const faces: Array = this.input instanceof tf.Tensor\n ? await extractFaceTensors(this.input, [detection])\n : await extractFaces(this.input, [detection]);\n\n const landmarks = await this.landmarkNet.detectLandmarks(faces[0]) as FaceLandmarks68;\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return extendWithFaceLandmarks(parentResult, landmarks);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { extractFaces, extractFaceTensors, TNetInput } from '../dom/index';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { isWithFaceLandmarks, WithFaceLandmarks } from '../factories/WithFaceLandmarks';\n\nexport async function extractAllFacesAndComputeResults, TResult>(\n parentResults: TSource[],\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResults: (faces: Array) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment: (parentResult: WithFaceLandmarks) => FaceDetection = ({ alignedRect }) => alignedRect,\n) {\n const faceBoxes = parentResults.map((parentResult) => (isWithFaceLandmarks(parentResult)\n ? getRectForAlignment(parentResult)\n : parentResult.detection));\n const faces: Array = extractedFaces || (\n input instanceof tf.Tensor\n ? await extractFaceTensors(input, faceBoxes)\n : await extractFaces(input, faceBoxes)\n );\n\n const results = await computeResults(faces);\n\n faces.forEach((f) => f instanceof tf.Tensor && f.dispose());\n\n return results;\n}\n\nexport async function extractSingleFaceAndComputeResult, TResult>(\n parentResult: TSource,\n input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n computeResult: (face: HTMLCanvasElement | tf.Tensor3D) => Promise,\n extractedFaces?: Array | null,\n // eslint-disable-next-line no-unused-vars\n getRectForAlignment?: (parentResultLocal: WithFaceLandmarks) => FaceDetection,\n) {\n return extractAllFacesAndComputeResults(\n [parentResult],\n input,\n async (faces) => computeResult(faces[0]),\n extractedFaces,\n getRectForAlignment,\n );\n}\n", "import { Point } from '../classes/index';\n\nexport const IOU_THRESHOLD = 0.4;\n\nexport const BOX_ANCHORS = [\n new Point(1.603231, 2.094468),\n new Point(6.041143, 7.080126),\n new Point(2.882459, 3.518061),\n new Point(4.266906, 5.178857),\n new Point(9.041765, 10.66308),\n];\n\nexport const MEAN_RGB: [number, number, number] = [117.001, 114.697, 97.404];\n", "import * as tf from '../../dist/tfjs.esm';\n\nimport { FaceDetection, Point } from '../classes/index';\nimport { ParamMapping } from '../common/index';\nimport { TNetInput } from '../dom/index';\nimport { ITinyYolov2Options } from '../tinyYolov2/index';\nimport { TinyYolov2Base } from '../tinyYolov2/TinyYolov2Base';\nimport { TinyYolov2NetParams } from '../tinyYolov2/types';\nimport { BOX_ANCHORS, IOU_THRESHOLD, MEAN_RGB } from './const';\n\nexport class TinyFaceDetector extends TinyYolov2Base {\n constructor() {\n const config = {\n withSeparableConvs: true,\n iouThreshold: IOU_THRESHOLD,\n classes: ['face'],\n anchors: BOX_ANCHORS,\n meanRgb: MEAN_RGB,\n isFirstLayerConv2d: true,\n filterSizes: [3, 16, 32, 64, 128, 256, 512],\n };\n\n super(config);\n }\n\n public get anchors(): Point[] {\n return this.config.anchors;\n }\n\n public async locateFaces(input: TNetInput, forwardParams: ITinyYolov2Options): Promise {\n const objectDetections = await this.detect(input, forwardParams);\n return objectDetections.map((det) => new FaceDetection(det.score, det.relativeBox, { width: det.imageWidth, height: det.imageHeight }));\n }\n\n protected getDefaultModelName(): string {\n return 'tiny_face_detector_model';\n }\n\n protected extractParamsFromWeightMap(weightMap: tf.NamedTensorMap): { params: TinyYolov2NetParams, paramMappings: ParamMapping[] } {\n return super.extractParamsFromWeightMap(weightMap);\n }\n}\n", "import { AgeGenderNet } from '../ageGenderNet/AgeGenderNet';\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { FaceLandmarks68 } from '../classes/FaceLandmarks68';\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressionNet } from '../faceExpressionNet/FaceExpressionNet';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { FaceLandmark68Net } from '../faceLandmarkNet/FaceLandmark68Net';\nimport { FaceLandmark68TinyNet } from '../faceLandmarkNet/FaceLandmark68TinyNet';\nimport { FaceRecognitionNet } from '../faceRecognitionNet/FaceRecognitionNet';\nimport { SsdMobilenetv1 } from '../ssdMobilenetv1/SsdMobilenetv1';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetector } from '../tinyFaceDetector/TinyFaceDetector';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { ITinyYolov2Options, TinyYolov2 } from '../tinyYolov2/index';\n\nexport const nets = {\n ssdMobilenetv1: new SsdMobilenetv1(),\n tinyFaceDetector: new TinyFaceDetector(),\n tinyYolov2: new TinyYolov2(),\n faceLandmark68Net: new FaceLandmark68Net(),\n faceLandmark68TinyNet: new FaceLandmark68TinyNet(),\n faceRecognitionNet: new FaceRecognitionNet(),\n faceExpressionNet: new FaceExpressionNet(),\n ageGenderNet: new AgeGenderNet(),\n};\n\n/**\n * Attempts to detect all faces in an image using SSD Mobilenetv1 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see SsdMobilenetv1Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const ssdMobilenetv1 = (input: TNetInput, options: SsdMobilenetv1Options): Promise => nets.ssdMobilenetv1.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Face Detector.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyFaceDetectorOptions constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyFaceDetector = (input: TNetInput, options: TinyFaceDetectorOptions): Promise => nets.tinyFaceDetector.locateFaces(input, options);\n\n/**\n * Attempts to detect all faces in an image using the Tiny Yolov2 Network.\n *\n * @param input The input image.\n * @param options (optional, default: see TinyYolov2Options constructor for default parameters).\n * @returns Bounding box of each face with score.\n */\nexport const tinyYolov2 = (input: TNetInput, options: ITinyYolov2Options): Promise => nets.tinyYolov2.locateFaces(input, options);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarks = (input: TNetInput): Promise => nets.faceLandmark68Net.detectLandmarks(input);\n\n/**\n * Detects the 68 point face landmark positions of the face shown in an image\n * using a tinier version of the 68 point face landmark model, which is slightly\n * faster at inference, but also slightly less accurate.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns 68 point face landmarks or array thereof in case of batch input.\n */\nexport const detectFaceLandmarksTiny = (input: TNetInput): Promise => nets.faceLandmark68TinyNet.detectLandmarks(input);\n\n/**\n * Computes a 128 entry vector (face descriptor / face embeddings) from the face shown in an image,\n * which uniquely represents the features of that persons face. The computed face descriptor can\n * be used to measure the similarity between faces, by computing the euclidean distance of two\n * face descriptors.\n *\n * @param inputs The face image extracted from the aligned bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Face descriptor with 128 entries or array thereof in case of batch input.\n */\nexport const computeFaceDescriptor = (input: TNetInput): Promise => nets.faceRecognitionNet.computeFaceDescriptor(input);\n\n/**\n * Recognizes the facial expressions from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Facial expressions with corresponding probabilities or array thereof in case of batch input.\n */\nexport const recognizeFaceExpressions = (input: TNetInput): Promise => nets.faceExpressionNet.predictExpressions(input);\n\n/**\n * Predicts age and gender from a face image.\n *\n * @param inputs The face image extracted from the bounding box of a face. Can\n * also be an array of input images, which will be batch processed.\n * @returns Predictions with age, gender and gender probability or array thereof in case of batch input.\n */\nexport const predictAgeAndGender = (input: TNetInput): Promise => nets.ageGenderNet.predictAgeAndGender(input);\n\nexport const loadSsdMobilenetv1Model = (url: string) => nets.ssdMobilenetv1.load(url);\nexport const loadTinyFaceDetectorModel = (url: string) => nets.tinyFaceDetector.load(url);\nexport const loadTinyYolov2Model = (url: string) => nets.tinyYolov2.load(url);\nexport const loadFaceLandmarkModel = (url: string) => nets.faceLandmark68Net.load(url);\nexport const loadFaceLandmarkTinyModel = (url: string) => nets.faceLandmark68TinyNet.load(url);\nexport const loadFaceRecognitionModel = (url: string) => nets.faceRecognitionNet.load(url);\nexport const loadFaceExpressionModel = (url: string) => nets.faceExpressionNet.load(url);\nexport const loadAgeGenderModel = (url: string) => nets.ageGenderNet.load(url);\n\n// backward compatibility\nexport const loadFaceDetectionModel = loadSsdMobilenetv1Model;\nexport const locateFaces = ssdMobilenetv1;\nexport const detectLandmarks = detectFaceLandmarks;\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { TNetInput } from '../dom/index';\nimport { FaceExpressions } from '../faceExpressionNet/FaceExpressions';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { extendWithFaceExpressions, WithFaceExpressions } from '../factories/WithFaceExpressions';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderTask,\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\n\nexport class PredictFaceExpressionsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const faceExpressionsByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map(\n (parentResult, i) => extendWithFaceExpressions(parentResult, faceExpressionsByFace[i]),\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictFaceExpressionsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const faceExpressions = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceExpressionNet.predictExpressions(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithFaceExpressions(parentResult, faceExpressions);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(this, this.input);\n }\n}\n\nexport class PredictAllFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleFaceExpressionsWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleFaceExpressionsTask {\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport * as tf from '../../dist/tfjs.esm';\n\nimport { AgeAndGenderPrediction } from '../ageGenderNet/types';\nimport { TNetInput } from '../dom/index';\nimport { extendWithAge, WithAge } from '../factories/WithAge';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { extendWithGender, WithGender } from '../factories/WithGender';\nimport { ComposableTask } from './ComposableTask';\nimport { ComputeAllFaceDescriptorsTask, ComputeSingleFaceDescriptorTask } from './ComputeFaceDescriptorsTasks';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllFaceExpressionsTask,\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class PredictAgeAndGenderTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected extractedFaces?: Array,\n ) {\n super();\n }\n}\n\nexport class PredictAllAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase>[], TSource[]> {\n public async run(): Promise>[]> {\n const parentResults = await this.parentTask;\n\n const ageAndGenderByFace = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n async (faces) => Promise.all(faces.map(\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n )),\n this.extractedFaces,\n );\n\n return parentResults.map((parentResult, i) => {\n const { age, gender, genderProbability } = ageAndGenderByFace[i];\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n });\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderTask<\n TSource extends WithFaceDetection<{}>\n> extends PredictAgeAndGenderTaskBase> | undefined, TSource | undefined> {\n public async run(): Promise> | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n\n const { age, gender, genderProbability } = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.ageGenderNet.predictAgeAndGender(face) as Promise,\n this.extractedFaces,\n );\n\n return extendWithAge(extendWithGender(parentResult, gender, genderProbability), age);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(this, this.input);\n }\n}\n\nexport class PredictAllAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictAllAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptors() {\n return new ComputeAllFaceDescriptorsTask(this, this.input);\n }\n}\n\nexport class PredictSingleAgeAndGenderWithFaceAlignmentTask<\n TSource extends WithFaceLandmarks>\n> extends PredictSingleAgeAndGenderTask {\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withFaceDescriptor() {\n return new ComputeSingleFaceDescriptorTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDescriptor, WithFaceDescriptor } from '../factories/WithFaceDescriptor';\nimport { WithFaceDetection } from '../factories/WithFaceDetection';\nimport { WithFaceLandmarks } from '../factories/WithFaceLandmarks';\nimport { ComposableTask } from './ComposableTask';\nimport { extractAllFacesAndComputeResults, extractSingleFaceAndComputeResult } from './extractFacesAndComputeResults';\nimport { nets } from './nets';\nimport {\n PredictAllAgeAndGenderWithFaceAlignmentTask,\n PredictSingleAgeAndGenderWithFaceAlignmentTask,\n} from './PredictAgeAndGenderTask';\nimport {\n PredictAllFaceExpressionsWithFaceAlignmentTask,\n PredictSingleFaceExpressionsWithFaceAlignmentTask,\n} from './PredictFaceExpressionsTask';\n\nexport class ComputeFaceDescriptorsTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected parentTask: ComposableTask | Promise,\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n ) {\n super();\n }\n}\n\nexport class ComputeAllFaceDescriptorsTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase[], TSource[]> {\n public async run(): Promise[]> {\n const parentResults = await this.parentTask;\n\n const descriptors = await extractAllFacesAndComputeResults(\n parentResults,\n this.input,\n (faces) => Promise.all(faces.map((face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise)),\n null,\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return descriptors.map((descriptor, i) => extendWithFaceDescriptor(parentResults[i], descriptor));\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n\nexport class ComputeSingleFaceDescriptorTask<\n TSource extends WithFaceLandmarks>\n> extends ComputeFaceDescriptorsTaskBase | undefined, TSource | undefined> {\n public async run(): Promise | undefined> {\n const parentResult = await this.parentTask;\n if (!parentResult) {\n return undefined;\n }\n const descriptor = await extractSingleFaceAndComputeResult(\n parentResult,\n this.input,\n (face) => nets.faceRecognitionNet.computeFaceDescriptor(face) as Promise,\n null,\n // eslint-disable-next-line no-shadow\n (parentResult) => parentResult.landmarks.align(null, { useDlibAlignment: true }),\n );\n\n return extendWithFaceDescriptor(parentResult, descriptor);\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsWithFaceAlignmentTask(this, this.input);\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderWithFaceAlignmentTask(this, this.input);\n }\n}\n", "/* eslint-disable max-classes-per-file */\nimport { FaceDetection } from '../classes/FaceDetection';\nimport { TNetInput } from '../dom/index';\nimport { extendWithFaceDetection, WithFaceDetection } from '../factories/WithFaceDetection';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { TinyFaceDetectorOptions } from '../tinyFaceDetector/TinyFaceDetectorOptions';\nimport { TinyYolov2Options } from '../tinyYolov2/index';\nimport { ComposableTask } from './ComposableTask';\nimport { DetectAllFaceLandmarksTask, DetectSingleFaceLandmarksTask } from './DetectFaceLandmarksTasks';\nimport { nets } from './nets';\nimport { PredictAllAgeAndGenderTask, PredictSingleAgeAndGenderTask } from './PredictAgeAndGenderTask';\nimport { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from './PredictFaceExpressionsTask';\nimport { FaceDetectionOptions } from './types';\n\nexport class DetectFacesTaskBase extends ComposableTask {\n constructor(\n // eslint-disable-next-line no-unused-vars\n protected input: TNetInput,\n // eslint-disable-next-line no-unused-vars\n protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n ) {\n super();\n }\n}\n\nexport class DetectAllFacesTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const { input, options } = this;\n\n // eslint-disable-next-line no-nested-ternary\n const faceDetectionFunction = options instanceof TinyFaceDetectorOptions\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyFaceDetector.locateFaces(input, options)\n : (\n // eslint-disable-next-line no-nested-ternary\n options instanceof SsdMobilenetv1Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.ssdMobilenetv1.locateFaces(input, options)\n : (\n options instanceof TinyYolov2Options\n // eslint-disable-next-line no-shadow\n ? (input: TNetInput) => nets.tinyYolov2.locateFaces(input, options)\n : null\n )\n );\n\n if (!faceDetectionFunction) {\n throw new Error('detectFaces - expected options to be instance of TinyFaceDetectorOptions | SsdMobilenetv1Options | MtcnnOptions | TinyYolov2Options');\n }\n\n return faceDetectionFunction(input);\n }\n\n private runAndExtendWithFaceDetections(): Promise[]> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise[]>(async (resolve) => {\n const detections = await this.run();\n resolve(detections.map((detection) => extendWithFaceDetection({}, detection)));\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectAllFaceLandmarksTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictAllFaceExpressionsTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictAllAgeAndGenderTask(\n this.runAndExtendWithFaceDetections(),\n this.input,\n );\n }\n}\n\nexport class DetectSingleFaceTask extends DetectFacesTaskBase {\n public async run(): Promise {\n const faceDetections = await new DetectAllFacesTask(this.input, this.options);\n let faceDetectionWithHighestScore = faceDetections[0];\n faceDetections.forEach((faceDetection) => {\n if (faceDetection.score > faceDetectionWithHighestScore.score) {\n faceDetectionWithHighestScore = faceDetection;\n }\n });\n return faceDetectionWithHighestScore;\n }\n\n private runAndExtendWithFaceDetection(): Promise | undefined> {\n // eslint-disable-next-line no-async-promise-executor\n return new Promise | undefined>(async (resolve) => {\n const detection = await this.run();\n resolve(detection ? extendWithFaceDetection<{}>({}, detection) : undefined);\n });\n }\n\n withFaceLandmarks(useTinyLandmarkNet: boolean = false) {\n return new DetectSingleFaceLandmarksTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n useTinyLandmarkNet,\n );\n }\n\n withFaceExpressions() {\n return new PredictSingleFaceExpressionsTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n\n withAgeAndGender() {\n return new PredictSingleAgeAndGenderTask(\n this.runAndExtendWithFaceDetection(),\n this.input,\n );\n }\n}\n", "import { TNetInput } from '../dom/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/SsdMobilenetv1Options';\nimport { DetectAllFacesTask, DetectSingleFaceTask } from './DetectFacesTasks';\nimport { FaceDetectionOptions } from './types';\n\nexport function detectSingleFace(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectSingleFaceTask {\n return new DetectSingleFaceTask(input, options);\n}\n\nexport function detectAllFaces(\n input: TNetInput,\n options: FaceDetectionOptions = new SsdMobilenetv1Options(),\n): DetectAllFacesTask {\n return new DetectAllFacesTask(input, options);\n}\n", "import { TNetInput } from '../dom/index';\nimport { WithFaceDescriptor, WithFaceDetection, WithFaceLandmarks } from '../factories/index';\nimport { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';\nimport { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';\nimport { detectAllFaces } from './detectFaces';\n\n// export allFaces API for backward compatibility\n\nexport async function allFacesSsdMobilenetv1(\n input: TNetInput,\n minConfidence?: number,\n): Promise>>[]> {\n return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport async function allFacesTinyYolov2(\n input: TNetInput,\n forwardParams: ITinyYolov2Options = {},\n): Promise>>[]> {\n return detectAllFaces(input, new TinyYolov2Options(forwardParams))\n .withFaceLandmarks()\n .withFaceDescriptors();\n}\n\nexport const allFaces = allFacesSsdMobilenetv1;\n", "export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {\n if (arr1.length !== arr2.length) throw new Error('euclideanDistance: arr1.length !== arr2.length');\n\n const desc1 = Array.from(arr1);\n const desc2 = Array.from(arr2);\n\n return Math.sqrt(\n desc1\n .map((val, i) => val - desc2[i])\n .reduce((res, diff) => res + (diff ** 2), 0),\n );\n}\n", "import { FaceMatch } from '../classes/FaceMatch';\nimport { LabeledFaceDescriptors } from '../classes/LabeledFaceDescriptors';\nimport { euclideanDistance } from '../euclideanDistance';\nimport { WithFaceDescriptor } from '../factories/index';\n\nexport class FaceMatcher {\n private _labeledDescriptors: LabeledFaceDescriptors[]\n\n private _distanceThreshold: number\n\n constructor(\n inputs: LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>,\n distanceThreshold: number = 0.6,\n ) {\n this._distanceThreshold = distanceThreshold;\n\n const inputArray = Array.isArray(inputs) ? inputs : [inputs];\n\n if (!inputArray.length) {\n throw new Error('FaceRecognizer.constructor - expected atleast one input');\n }\n\n let count = 1;\n const createUniqueLabel = () => `person ${count++}`;\n\n this._labeledDescriptors = inputArray.map((desc) => {\n if (desc instanceof LabeledFaceDescriptors) {\n return desc;\n }\n\n if (desc instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc]);\n }\n\n if (desc.descriptor && desc.descriptor instanceof Float32Array) {\n return new LabeledFaceDescriptors(createUniqueLabel(), [desc.descriptor]);\n }\n\n throw new Error('FaceRecognizer.constructor - expected inputs to be of type LabeledFaceDescriptors | WithFaceDescriptor | Float32Array | Array | Float32Array>');\n });\n }\n\n public get labeledDescriptors(): LabeledFaceDescriptors[] { return this._labeledDescriptors; }\n\n public get distanceThreshold(): number { return this._distanceThreshold; }\n\n public computeMeanDistance(queryDescriptor: Float32Array, descriptors: Float32Array[]): number {\n return descriptors\n .map((d) => euclideanDistance(d, queryDescriptor))\n .reduce((d1, d2) => d1 + d2, 0)\n / (descriptors.length || 1);\n }\n\n public matchDescriptor(queryDescriptor: Float32Array): FaceMatch {\n return this.labeledDescriptors\n .map(({ descriptors, label }) => new FaceMatch(\n label,\n this.computeMeanDistance(queryDescriptor, descriptors),\n ))\n .reduce((best, curr) => (best.distance < curr.distance ? best : curr));\n }\n\n public findBestMatch(queryDescriptor: Float32Array): FaceMatch {\n const bestMatch = this.matchDescriptor(queryDescriptor);\n return bestMatch.distance < this.distanceThreshold\n ? bestMatch\n : new FaceMatch('unknown', bestMatch.distance);\n }\n\n public toJSON(): any {\n return {\n distanceThreshold: this.distanceThreshold,\n labeledDescriptors: this.labeledDescriptors.map((ld) => ld.toJSON()),\n };\n }\n\n public static fromJSON(json: any): FaceMatcher {\n const labeledDescriptors = json.labeledDescriptors\n .map((ld: any) => LabeledFaceDescriptors.fromJSON(ld));\n return new FaceMatcher(labeledDescriptors, json.distanceThreshold);\n }\n}\n", "import { TinyFaceDetector } from './TinyFaceDetector';\n\nexport * from './TinyFaceDetector';\nexport * from './TinyFaceDetectorOptions';\n\nexport function createTinyFaceDetector(weights: Float32Array) {\n const net = new TinyFaceDetector();\n net.extractWeights(weights);\n return net;\n}\n", "import { Dimensions, IDimensions } from './classes/index';\nimport { FaceDetection } from './classes/FaceDetection';\nimport { FaceLandmarks } from './classes/FaceLandmarks';\nimport { extendWithFaceDetection, isWithFaceDetection } from './factories/WithFaceDetection';\nimport { extendWithFaceLandmarks, isWithFaceLandmarks } from './factories/WithFaceLandmarks';\n\nexport function resizeResults(results: T, dimensions: IDimensions): T {\n const { width, height } = new Dimensions(dimensions.width, dimensions.height);\n\n if (width <= 0 || height <= 0) {\n throw new Error(`resizeResults - invalid dimensions: ${JSON.stringify({ width, height })}`);\n }\n\n if (Array.isArray(results)) {\n // return results.map(obj => resizeResults(obj, { width, height })) as any as T\n return (results as Array).map((obj) => resizeResults(obj, { width, height } as IDimensions)) as any as T;\n }\n\n if (isWithFaceLandmarks(results)) {\n const resizedDetection = results.detection.forSize(width, height);\n const resizedLandmarks = results.unshiftedLandmarks.forSize(resizedDetection.box.width, resizedDetection.box.height);\n return extendWithFaceLandmarks(extendWithFaceDetection(results, resizedDetection), resizedLandmarks);\n }\n\n if (isWithFaceDetection(results)) {\n return extendWithFaceDetection(results, results.detection.forSize(width, height));\n }\n\n if (results instanceof FaceLandmarks || results instanceof FaceDetection) {\n return (results as any).forSize(width, height);\n }\n\n return results;\n}\n"], + "mappings": ";;;;;;;wlCAGA,GAAA,GAAc,GAAA,qCCHd,6CAAO,cACL,MAAO,OAAO,SAAW,UACpB,IACA,MAAO,KAAW,aAGlB,MAAO,UAAY,aAAe,CAAC,CAAC,QAAQ,WCNnD,6xFAAA,OAAoB,OCApB,qRCEO,YACL,EACA,EACA,EAAoB,IAUpB,GARA,EAAI,YAEJ,EAAO,MAAM,GAAG,QAAQ,CAAC,CAAE,IAAG,KAAK,KACjC,GAAM,GAAO,EAAO,GACpB,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,KAGZ,GACF,GAAM,GAAO,EAAO,EAAO,OAAS,GAC9B,EAAK,EAAO,GAClB,GAAI,CAAC,GAAQ,CAAC,EACZ,OAGF,EAAI,OAAO,EAAK,EAAG,EAAK,GACxB,EAAI,OAAO,EAAG,EAAG,EAAG,GAGtB,EAAI,SC1BN,2RAAA,OAAoB,OCApB,YAYE,YAAY,EAAe,GACzB,GAAI,CAAC,GAAc,IAAU,CAAC,GAAc,GAC1C,KAAM,IAAI,OAAM,wFAAwF,KAAK,UAAU,CAAE,QAAO,cAGlI,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,QAEnC,UACL,MAAO,IAAI,GAAW,EAAI,KAAK,MAAO,EAAI,KAAK,UDrB5C,YAAkB,EAAa,GACpC,MAAO,aAAqB,YAAU,EAAO,MAAM,SAAW,EAGzD,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,WAAoB,GACzB,MAAO,IAAS,EAAQ,GAGnB,YAAiB,GACtB,MAAO,GAAM,GAAM,EAGd,YAAgB,GACrB,MAAO,GAAM,GAAM,EAGd,YAAe,EAAa,EAAe,GAChD,GAAM,GAAI,IAAM,EAChB,MAAO,MAAK,MAAM,EAAM,GAAK,EAGxB,YAAsB,GAC3B,MAAO,IAAO,EAAI,OAAS,EAAI,OAG1B,YAAmC,CAAE,QAAO,UAAuB,GACxE,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,IAAI,GAAW,KAAK,MAAM,EAAQ,GAAQ,KAAK,MAAM,EAAS,IAGhE,YAAwB,GAC7B,MAAO,GAAI,OAAO,CAAC,EAAK,IAAO,EAAI,IAAI,GAAK,GAAI,GAAM,EAAG,IACtD,IAAI,GAAI,GAAM,EAAI,OAAQ,EAAI,SAG5B,YAAe,EAAa,EAAe,GAChD,MAAO,OAAM,GAAK,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,EAAS,EAAI,GAGhD,YAAuB,GAC5B,MAAO,CAAC,CAAC,GAAQ,IAAQ,UAAc,IAAQ,WAAc,CAAC,OAAO,MAAM,IAAQ,IAAQ,EAGtF,YAA4B,GACjC,MAAO,IAAc,IAAQ,GAAO,GAAK,GAAO,EE7DlD,YAUE,YAAY,EAAW,GACrB,KAAK,GAAK,EACV,KAAK,GAAK,KAGR,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,GAEvB,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,IAAI,GACT,MAAO,IAAI,GAAM,KAAK,EAAI,EAAG,EAAG,KAAK,EAAI,EAAG,GAGvC,MACL,MAAO,IAAI,GAAM,KAAK,IAAI,KAAK,GAAI,KAAK,IAAI,KAAK,IAG5C,YACL,MAAO,MAAK,KAAM,KAAK,GAAK,EAAM,KAAK,GAAK,GAGvC,QACL,MAAO,IAAI,GAAM,KAAK,MAAM,KAAK,GAAI,KAAK,MAAM,KAAK,MC5CzD,kBAOgB,QAAO,GACnB,MAAO,CAAC,CAAC,GAAQ,CAAC,EAAK,EAAG,EAAK,EAAG,EAAK,MAAO,EAAK,QAAQ,MAAM,UAGrD,kBAAiB,EAAU,EAAgB,EAAmC,IAC1F,GAAI,CAAC,EAAI,OAAO,GACd,KAAM,IAAI,OAAM,GAAG,oBAAyB,KAAK,UAAU,2DAG7D,GAAI,CAAC,GAA4B,GAAI,MAAQ,GAAK,EAAI,OAAS,GAC7D,KAAM,IAAI,OAAM,GAAG,cAAmB,EAAI,sBAAsB,EAAI,oCAYxE,YAAY,EAA4B,EAAmC,IACzE,GAAM,GAAO,GAAQ,GAEf,EAAS,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAO,EAAI,QAAQ,MAAM,IAC1D,EAAS,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAAQ,MAAM,IAE3D,GAAI,CAAC,GAAU,CAAC,EACd,KAAM,IAAI,OAAM,2EAA2E,KAAK,UAAU,MAG5G,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,EAC1B,CAAC,EAAI,EAAG,EAAI,EAAG,EAAI,MAAO,EAAI,QAC9B,CAAC,EAAI,KAAM,EAAI,IAAK,EAAI,MAAQ,EAAI,KAAM,EAAI,OAAS,EAAI,KAE/D,EAAI,iBAAiB,CACnB,IAAG,IAAG,QAAO,UACZ,kBAAmB,GAEtB,KAAK,GAAK,EACV,KAAK,GAAK,EACV,KAAK,OAAS,EACd,KAAK,QAAU,KAGN,KAAc,MAAO,MAAK,MAE1B,KAAc,MAAO,MAAK,MAE1B,SAAkB,MAAO,MAAK,UAE9B,UAAmB,MAAO,MAAK,WAE/B,QAAiB,MAAO,MAAK,KAE7B,OAAgB,MAAO,MAAK,KAE5B,SAAkB,MAAO,MAAK,EAAI,KAAK,SAEvC,UAAmB,MAAO,MAAK,EAAI,KAAK,UAExC,QAAiB,MAAO,MAAK,MAAQ,KAAK,UAE1C,WAAmB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,QAEpD,YAAoB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAEtD,cAAsB,MAAO,IAAI,GAAM,KAAK,KAAM,KAAK,WAEvD,eAAuB,MAAO,IAAI,GAAM,KAAK,MAAO,KAAK,QAE7D,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QACL,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAAC,KAAK,EAAG,KAAK,EAAG,KAAK,MAAO,KAAK,QAC7D,IAAI,AAAC,GAAQ,KAAK,MAAM,IAC3B,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,WACL,GAAI,CACF,IAAG,IAAG,QAAO,UACX,KACE,EAAO,KAAK,IAAI,EAAQ,GAC9B,MAAI,GAAQ,GACV,IAAM,EAAO,EACb,GAAS,GAEP,EAAS,GACX,IAAM,EAAO,EACb,GAAU,GAGL,GAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,QAAQ,GACb,GAAM,GAAS,GAAa,GAAM,EAAkB,MAAQ,EACtD,EAAS,GAAa,GAAM,EAAkB,OAAS,EAC7D,MAAO,IAAI,GAAI,CACb,EAAG,KAAK,EAAI,EACZ,EAAG,KAAK,EAAI,EACZ,MAAO,KAAK,MAAQ,EACpB,OAAQ,KAAK,OAAS,IAInB,IAAI,EAAc,GACvB,GAAM,CAAC,EAAG,EAAG,EAAO,GAAU,CAC5B,KAAK,EAAK,EAAO,EACjB,KAAK,EAAK,EAAO,EACjB,KAAK,MAAQ,EACb,KAAK,OAAS,GAEhB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,mBAAmB,EAAkB,GAC1C,GAAM,CACJ,IAAG,IAAG,QAAO,UACX,KACE,EAAW,KAAK,IAAI,EAAG,GACvB,EAAW,KAAK,IAAI,EAAG,GAEvB,EAAW,EAAQ,EACnB,EAAY,EAAS,EACrB,EAAe,KAAK,IAAI,EAAU,EAAW,GAC7C,EAAgB,KAAK,IAAI,EAAW,EAAY,GAEtD,MAAQ,IAAI,GAAI,CACd,EAAG,EAAU,EAAG,EAAU,MAAO,EAAc,OAAQ,IACrD,QAGC,MAAM,EAAY,GACvB,GAAM,CAAE,QAAO,UAAW,KACpB,EAAI,KAAK,EAAI,EACb,EAAI,KAAK,EAAI,EAEnB,MAAO,IAAI,GAAI,CACb,IAAG,IAAG,QAAO,WAIV,aAAa,EAAqB,GACvC,GAAM,GAAI,KAAK,MAAQ,EACjB,EAAI,KAAK,OAAS,EAElB,EAAK,EACL,EAAK,EACP,EAAM,EACN,EAAM,EAEN,EAAI,KAAK,KACT,EAAI,KAAK,IACT,EAAK,KAAK,MACV,EAAK,KAAK,OAEd,MAAI,GAAK,GACP,GAAM,CAAC,EAAK,EAAa,EACzB,EAAK,GAEH,EAAK,GACP,GAAM,CAAC,EAAK,EAAc,EAC1B,EAAK,GAEH,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAEF,EAAI,GACN,GAAM,EAAI,EACV,EAAI,GAGC,CACL,KAAI,MAAK,KAAI,MAAK,IAAG,KAAI,IAAG,KAAI,IAAG,KAIhC,UAAU,GACf,MAAO,IAAI,GAAI,CACb,KAAM,KAAK,KAAQ,EAAO,KAAO,KAAK,MACtC,IAAK,KAAK,IAAO,EAAO,IAAM,KAAK,OACnC,MAAO,KAAK,MAAS,EAAO,MAAQ,KAAK,MACzC,OAAQ,KAAK,OAAU,EAAO,OAAS,KAAK,SAC3C,WAAW,UC9MlB,oBASiC,GAC/B,YAAY,EAAc,EAAa,EAAe,EAAgB,EAAmC,IACvG,MAAM,CACJ,OAAM,MAAK,QAAO,UACjB,KCbP,aAeE,YACE,EACA,EACA,EACA,EACA,GAEA,KAAK,WAAa,GAAI,GAAW,EAAU,MAAO,EAAU,QAC5D,KAAK,OAAS,EACd,KAAK,YAAc,EACnB,KAAK,WAAa,EAClB,KAAK,KAAO,GAAI,GAAI,GAAa,QAAQ,KAAK,eAGrC,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,eAEnC,aAAsB,MAAO,MAAK,cAElC,OAAa,MAAO,MAAK,QAEzB,aAA0B,MAAO,MAAK,cAEtC,cAAuB,MAAO,MAAK,UAAU,SAE7C,eAAwB,MAAO,MAAK,UAAU,UAE9C,eAAqB,MAAO,IAAI,GAAI,KAAK,MAAM,QAAQ,KAAK,UAAU,WAE1E,QAAQ,EAAe,GAC5B,MAAO,IAAI,IACT,KAAK,MACL,KAAK,WACL,KAAK,UACL,KAAK,YACL,CAAE,QAAO,aCnDf,mBAUmC,IACjC,YACE,EACA,EACA,GAEA,MAAM,EAAO,EAAO,GAAI,EAAa,GAGhC,QAAQ,EAAe,GAC5B,GAAM,CAAE,QAAO,cAAa,aAAc,MAAM,QAAQ,EAAO,GAC/D,MAAO,IAAI,GAAc,EAAO,EAAa,KCnB1C,YAAa,EAAW,EAAW,EAAiB,IACzD,GAAM,GAAQ,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,MAAO,EAAK,OAAS,KAAK,IAAI,EAAK,KAAM,EAAK,OAClF,EAAS,KAAK,IAAI,EAAK,KAAK,IAAI,EAAK,OAAQ,EAAK,QAAU,KAAK,IAAI,EAAK,IAAK,EAAK,MACpF,EAAe,EAAQ,EAE7B,MAAO,GACH,EAAgB,GAAK,KAAO,EAAK,KAAO,GACxC,EAAe,KAAK,IAAI,EAAK,KAAM,EAAK,MCPvC,YAAiB,GACtB,GAAM,GAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAK,EAAI,IAAI,AAAC,GAAO,EAAG,GACxB,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAI,EAAM,EAAI,EAAM,UAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAClD,EAAO,EAAG,OAAO,CAAC,EAAK,IAAO,EAAM,EAAI,EAAI,EAAM,GAExD,MAAO,IAAI,IAAY,EAAM,EAAM,EAAM,GCPpC,YACL,EACA,EACA,EACA,EAAiB,IAEjB,GAAI,GAAuB,EACxB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAC/B,IAAI,AAAC,GAAM,EAAE,UAEV,EAAiB,GAEvB,KAAO,EAAqB,OAAS,IACnC,GAAM,GAAO,EAAqB,MAClC,EAAK,KAAK,GAEV,GAAM,GAAU,EAEV,EAAoB,GAC1B,OAAS,GAAI,EAAG,EAAI,EAAQ,OAAQ,KAClC,GAAM,GAAM,EAAQ,GAEd,EAAU,EAAM,GAChB,EAAS,EAAM,GAErB,EAAQ,KAAK,GAAI,EAAS,EAAQ,IAGpC,EAAuB,EAAqB,OAC1C,CAAC,EAAG,IAAM,EAAQ,IAAM,GAI5B,MAAO,GCrCT,OAAoB,OAEb,YAAmB,EAAgB,GACxC,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAG,EAAG,GAAK,EACZ,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAQ,AAAG,QAAK,CAAC,GAAG,EAAE,MAAM,MAAM,EAAG,GAAI,GAAI,EAAG,WAChD,EAAU,AAAG,UAAO,CAAC,EAAO,EAAO,GAAQ,GAEjD,MAAO,AAAG,QAAI,EAAG,KCVrB,OAAoB,OAUb,YACL,EACA,EAAyB,IAEzB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAQ,GAAS,EAAU,MAAM,MAAM,GAC9C,GAAI,IAAW,EACb,MAAO,GAGT,GAAM,GAAU,KAAK,IAAI,EAAS,GAC5B,EAAgB,KAAK,MAAM,EAAW,GAAgB,GAAM,IAC5D,EAAc,EAAS,EAAQ,EAAI,EAEnC,EAAsB,AAAC,IAC3B,GAAM,GAAqB,EAAU,MAAM,QAC3C,SAAmB,GAAe,EAC3B,AAAG,QAAK,EAAoB,EAAG,YAGlC,EAAsB,EAAoB,GAC1C,EAAyB,EAAW,EAAoB,MAAM,GAM9D,EAAiB,CAJM,GAAiB,EAC1C,EAAoB,GACpB,KAIF,EACA,GAEC,OAAO,AAAC,GAAM,CAAC,CAAC,GAEhB,IAAI,AAAC,GAAiB,AAAG,QAAK,EAAG,YACpC,MAAO,AAAG,WAAO,EAAgB,KC7C9B,YAAsB,GAC3B,GAAM,GAAQ,EAAW,QACzB,OAAS,GAAI,EAAM,OAAS,EAAG,EAAI,EAAG,KACpC,GAAM,GAAI,KAAK,MAAM,KAAK,SAAY,GAAI,IACpC,EAAI,EAAM,GAChB,EAAM,GAAK,EAAM,GACjB,EAAM,GAAK,EAEb,MAAO,GCDF,YAAiB,GACtB,MAAO,GAAK,GAAI,KAAK,IAAI,CAAC,IAGrB,YAAwB,GAC7B,MAAO,MAAK,IAAI,EAAK,GAAI,ICZ3B,oBAS0B,GACxB,YAAY,EAAW,EAAW,EAAe,EAAgB,EAAmC,IAClG,MAAM,CACJ,IAAG,IAAG,QAAO,UACZ,KCHP,GAAM,IAAO,GACP,GAAO,IACP,GAAW,IAZjB,QA0BE,YACE,EACA,EACA,EAAe,GAAI,GAAM,EAAG,IAE5B,GAAM,CAAE,QAAO,UAAW,EAC1B,KAAK,SAAW,GAAI,GAAW,EAAO,GACtC,KAAK,OAAS,EACd,KAAK,WAAa,EAA8B,IAC9C,AAAC,GAAO,EAAG,IAAI,GAAI,GAAM,EAAO,IAAS,IAAI,OAItC,SAAiB,MAAO,IAAI,GAAM,KAAK,OAAO,EAAG,KAAK,OAAO,MAE7D,cAAuB,MAAO,MAAK,SAAS,SAE5C,eAAwB,MAAO,MAAK,SAAS,UAE7C,aAAuB,MAAO,MAAK,cAEnC,qBACT,MAAO,MAAK,WAAW,IACrB,AAAC,GAAO,EAAG,IAAI,KAAK,QAAQ,IAAI,GAAI,GAAM,KAAK,WAAY,KAAK,eAI7D,QAAiC,EAAe,GACrD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,CAAE,QAAO,WAIN,QAAiC,EAAW,GACjD,MAAO,IAAK,MAAK,YACf,KAAK,kBACL,KAAK,SACL,GAAI,GAAM,EAAG,IAIV,aAAsC,GAC3C,MAAO,MAAK,QAAQ,EAAG,EAAG,EAAG,GAcxB,MACL,EACA,EAAkE,IAElE,GAAI,GACF,GAAM,GAAM,YAAqB,GAC7B,EAAU,IAAI,QACd,GAAI,GAAI,GAEZ,MAAO,MAAK,QAAQ,EAAI,EAAG,EAAI,GAAG,MAAM,KAAM,GAGhD,GAAM,CAAE,mBAAkB,iBAAkB,CAAE,iBAAkB,GAAO,cAAe,MAAQ,GAE9F,MAAI,GACK,KAAK,YAGP,KAAK,aAAa,GAGnB,YACN,GAAM,GAAU,KAAK,2BAEf,CAAC,EAAe,EAAgB,GAAe,EAC/C,EAAc,AAAC,GAAc,EAAY,IAAI,GAAI,YACjD,EAAkB,GAAY,GAAiB,EAAY,IAAmB,EAE9E,EAAO,KAAK,MAAM,EAAiB,IAEnC,EAAW,GAAe,GAE1B,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAChD,EAAI,KAAK,MAAM,KAAK,IAAI,EAAG,EAAS,EAAK,GAAO,IAEtD,MAAO,IAAI,IAAK,EAAG,EAAG,KAAK,IAAI,EAAM,KAAK,WAAa,GAAI,KAAK,IAAI,EAAM,KAAK,YAAc,IAGvF,aAAa,GACnB,GAAM,GAAM,GAAQ,KAAK,WACzB,MAAO,GAAI,IAAI,EAAI,MAAQ,EAAS,EAAI,OAAS,GAGzC,2BACR,KAAM,IAAI,OAAM,4DC/HpB,oBAIoC,GACxB,2BACR,GAAM,GAAM,KAAK,UACjB,MAAO,CACL,EAAI,GACJ,EAAI,GACJ,GAAe,CAAC,EAAI,GAAI,EAAI,QCVlC,oBAIqC,GAC5B,gBACL,MAAO,MAAK,UAAU,MAAM,EAAG,IAG1B,iBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,kBACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,UACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,aACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,cACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAG3B,WACL,MAAO,MAAK,UAAU,MAAM,GAAI,IAGxB,2BACR,MAAO,CACL,KAAK,aACL,KAAK,cACL,KAAK,YACL,IAAI,MCtCV,aAYE,YAAY,EAAe,GACzB,KAAK,OAAS,EACd,KAAK,UAAY,KAGR,SAAkB,MAAO,MAAK,UAE9B,YAAqB,MAAO,MAAK,UAErC,SAAS,EAAwB,IACtC,MAAO,GAAG,KAAK,QAAQ,EAAe,KAAK,GAAM,KAAK,aAAe,OCtBzE,oBAKgC,SAChB,yBAAwB,EAAU,GAG9C,GAFA,EAAI,iBAAiB,EAAK,GAEtB,CAAC,GAAc,EAAI,OACrB,KAAM,IAAI,OAAM,GAAG,gCAAqC,EAAI,yBAMhE,YAAY,EAAiC,GAC3C,MAAM,GACN,KAAK,OAAS,KAGL,SAAkB,MAAO,MAAK,SCrB3C,aAKE,YAAY,EAAe,GACzB,GAAM,MAAO,IAAU,SACrB,KAAM,IAAI,OAAM,sEAGlB,GAAI,CAAC,MAAM,QAAQ,IAAgB,EAAY,KAAK,AAAC,GAAS,CAAE,aAAgB,gBAC9E,KAAM,IAAI,OAAM,4FAGlB,KAAK,OAAS,EACd,KAAK,aAAe,KAGX,SAAkB,MAAO,MAAK,UAE9B,eAAgC,MAAO,MAAK,aAEhD,SACL,MAAO,CACL,MAAO,KAAK,MACZ,YAAa,KAAK,YAAY,IAAI,AAAC,GAAM,MAAM,KAAK,WAI1C,UAAS,GACrB,GAAM,GAAc,EAAK,YAAY,IAAI,AAAC,GAAW,GAAI,cAAa,IACtE,MAAO,IAAI,IAAuB,EAAK,MAAO,KC/BlD,oBAKkC,UAClB,2BAA0B,EAAU,GAGhD,GAFA,GAAW,wBAAwB,EAAK,GAGtC,CAAC,GAAmB,EAAI,QACrB,CAAC,GAAmB,EAAI,YAE3B,KAAM,IAAI,OAAM,GAAG,kCAAuC,EAAI,eAAe,EAAI,6CAQrF,YAAY,EAAiC,EAAe,EAAe,GACzE,MAAM,EAAK,GACX,KAAK,OAAS,EACd,KAAK,YAAc,KAGV,SAAkB,MAAO,MAAK,UAE9B,cAAuB,MAAO,MAAK,cCvBzC,YAA6B,GAClC,MAAO,GAAI,oBAAqB,GAG3B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,cCdf,cACL,GAAM,GAAQ,OAAO,MACrB,GAAI,CAAC,EAAO,KAAM,IAAI,OAAM,gEAE5B,GAAM,GAAW,KACf,KAAM,IAAI,OAAM,gEAGlB,MAAO,CACL,OAAQ,kBACR,yBACA,MAAO,iBACP,UACA,MAAO,iBACP,oBAAqB,IAAM,SAAS,cAAc,UAClD,mBAAoB,IAAM,SAAS,cAAc,OACjD,QACA,YCjBG,YAA0B,GAC/B,GAAI,GAAiB,GAErB,GAAI,CAAC,EACH,IAEE,EAAa,oBACN,GACP,EAAiB,EAAI,WAYzB,MAAO,CACL,SATe,EACb,AAAC,GAAqB,GAAI,SAAgB,CAAC,EAAS,KACpD,EAAG,SAAS,EAAU,CAAC,EAAU,IAAoB,EAAM,EAAO,GAAO,EAAQ,MAEjF,KACA,KAAM,IAAI,OAAM,qEAAqE,OCfpF,cAEL,GAAM,GAAS,OAAO,QAAa,OAAO,kBACpC,EAAQ,OAAO,OAAS,OAAO,iBAE/B,EAAsB,KAC1B,GAAI,EAAQ,MAAO,IAAI,GACvB,KAAM,IAAI,OAAM,+EAGZ,EAAqB,KACzB,GAAI,EAAO,MAAO,IAAI,GACtB,KAAM,IAAI,OAAM,6EAGZ,EAAQ,OAAO,MAGf,EAAa,KAEnB,MAAO,CACL,OAAQ,GAAU,QAClB,yBAA0B,OAAO,0BAA4B,QAC7D,MAAO,GAAS,QAChB,UAAW,OAAO,WAAa,QAC/B,MAAO,OAAO,kBAAoB,QAClC,sBACA,qBACA,WACG,GCjCA,cACL,MAAO,OAAO,SAAW,UACpB,MAAO,WAAa,aACpB,MAAO,mBAAqB,aAC5B,MAAO,oBAAsB,aAC7B,MAAO,mBAAqB,aAC5B,MAAO,YAAc,aACrB,MAAO,2BAA6B,YCH3C,OAAyB,QAGrB,EAEJ,cACE,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,yEAElB,MAAO,GAGT,YAAgB,GACd,EAAc,EAGhB,cAGE,MAAI,MAAoB,GAAO,MAC3B,cAAmB,GAAO,MACvB,KAGT,YAAqB,GAKnB,GAJK,GACH,KAGE,CAAC,EACH,KAAM,IAAI,OAAM,8EAGlB,GAAM,CAAE,SAAS,EAAY,OAAQ,QAAQ,EAAY,OAAU,EACnE,EAAY,OAAS,EACrB,EAAY,MAAQ,EACpB,EAAY,oBAAsB,EAAI,qBAAwB,KAAM,GAAI,IACxE,EAAY,mBAAqB,EAAI,oBAAuB,KAAM,GAAI,IAEtE,EAAY,UAAY,EAAI,WAAa,EAAY,UACrD,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,MAAQ,EAAI,OAAS,EAAY,MAC7C,EAAY,SAAW,EAAI,UAAY,EAAY,SAG9C,GAAM,GAAM,CACjB,UACA,UACA,cACA,oBACA,oBACA,mBACA,eACA,aACA,sBAGF,KC3DO,YAAsB,GAC3B,MAAI,CAAC,EAAI,YAAc,MAAO,IAAQ,SAC7B,SAAS,eAAe,GAE1B,ECHF,WAA6B,GAClC,GAAM,CAAE,SAAQ,4BAA6B,EAAI,SAEjD,GAAI,YAAqB,GACvB,MAAO,GAGT,GAAM,GAAS,GAAa,GAE5B,GAAI,CAAE,aAAkB,IACtB,KAAM,IAAI,OAAM,kEAGlB,GAAM,GAAM,EAAO,WAAW,MAC9B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,GCfF,GAAK,IAAL,UAAK,GAEV,WAAW,WAEX,YAAY,YAEZ,cAAc,cAEd,eAAe,iBARL,aANZ,aAuCE,YAAY,EAAiC,IAC3C,GAAM,CACJ,iBAAgB,kBAAiB,YAAW,WAAU,YAAW,WAC/D,EACJ,KAAK,eAAiB,GAAkB,GAAe,SACvD,KAAK,gBAAkB,GAAmB,qBAC1C,KAAK,UAAY,GAAa,yBAC9B,KAAK,SAAW,GAAY,GAC5B,KAAK,UAAY,GAAa,UAC9B,KAAK,QAAU,GAAW,IAhD9B,SA2DE,YACE,EACA,EACA,EAAiC,IAGjC,KAAK,KAAO,MAAO,IAAS,SACxB,CAAC,GACA,YAAgB,IAAgB,EAAK,KAAO,EACjD,KAAK,OAAS,EACd,KAAK,QAAU,GAAI,IAAqB,GAG1C,aAAa,GACX,GAAM,CAAE,WAAY,KAAK,QACzB,MAAO,MAAK,KAAK,IAAI,AAAC,GAAM,EAAI,YAAY,GAAG,OAAO,OAAO,CAAC,EAAI,IAAQ,EAAK,EAAK,EAAK,EAAK,GAAM,EAAI,EAG1G,gBACE,GAAM,CAAE,WAAU,WAAY,KAAK,QACnC,MAAO,MAAK,KAAK,OAAS,EAAY,EAAI,EAG5C,aAAa,EAA+B,GAC1C,GAAM,CAAE,kBAAmB,KAAK,QAC1B,EAAc,IAAmB,GAAe,cAAgB,IAAmB,GAAe,UAClG,EAAa,IAAmB,GAAe,aAAe,IAAmB,GAAe,aAEhG,EAAiB,KAAK,aAAa,GACnC,EAAkB,KAAK,gBACvB,EAAK,EAAc,KAAK,OAAO,EAAI,EAAiB,KAAK,OAAO,EAChE,EAAI,EAAa,KAAK,OAAO,EAAI,EAAkB,KAAK,OAAO,EAGrE,GAAI,GACF,GAAM,CAAE,QAAO,UAAW,EACpB,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAQ,GAAiB,GACrD,EAAO,KAAK,IAAI,KAAK,IAAI,EAAG,EAAS,GAAkB,GAC7D,MAAO,CAAE,EAAG,EAAM,EAAG,GAEvB,MAAO,CAAE,IAAG,KAGd,KAAK,GACH,GAAM,GAAS,GAAa,GACtB,EAAM,EAAoB,GAE1B,CACJ,kBAAiB,YAAW,WAAU,YAAW,WAC/C,KAAK,QAET,EAAI,KAAO,GAAG,OAAc,IAC5B,GAAM,GAAe,KAAK,aAAa,GACjC,EAAa,KAAK,gBAExB,EAAI,UAAY,EAChB,GAAM,GAAY,KAAK,aAAa,EAAK,GACzC,EAAI,SAAS,EAAU,EAAG,EAAU,EAAG,EAAc,GAErD,EAAI,UAAY,EAChB,KAAK,KAAK,QAAQ,CAAC,EAAU,KAC3B,GAAM,GAAI,EAAU,EAAU,EACxB,EAAI,EAAU,EAAU,EAAM,GAAI,GAAK,EAC7C,EAAI,SAAS,EAAU,EAAG,OC1HhC,aAuBE,YAAY,EAA2B,IACrC,GAAM,CACJ,WAAU,YAAW,QAAO,oBAC1B,EACJ,KAAK,SAAW,GAAY,qBAC5B,KAAK,UAAY,GAAa,EAC9B,KAAK,MAAQ,EAEb,GAAM,GAA0B,CAC9B,eAAgB,GAAe,YAC/B,gBAAiB,KAAK,UAExB,KAAK,iBAAmB,GAAI,IAAqB,IAAK,KAA4B,MAnCtF,SA4CE,YACE,EACA,EAA2B,IAE3B,KAAK,IAAM,GAAI,GAAI,GACnB,KAAK,QAAU,GAAI,IAAe,GAGpC,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CAAE,WAAU,aAAc,KAAK,QAE/B,CACJ,IAAG,IAAG,QAAO,UACX,KAAK,IACT,EAAI,YAAc,EAClB,EAAI,UAAY,EAChB,EAAI,WAAW,EAAG,EAAG,EAAO,GAE5B,GAAM,CAAE,SAAU,KAAK,QACvB,AAAI,GACF,GAAI,IAAc,CAAC,GAAQ,CAAE,EAAG,EAAK,EAAY,EAAI,KAAK,KAAK,QAAQ,kBAAkB,KAAK,KC1D7F,YACL,EACA,GAIA,AAFwB,OAAM,QAAQ,GAAc,EAAa,CAAC,IAElD,QAAQ,AAAC,IAEvB,GAAM,GAAQ,YAAe,GACzB,EAAI,MACH,GAAoB,GAAO,EAAI,UAAU,MAAQ,OAGhD,EAAM,YAAe,GACvB,EAAI,IACH,GAAoB,GAAO,EAAI,UAAU,IAAM,GAAI,GAAI,GAEtD,EAAQ,EAAQ,GAAG,GAAM,KAAW,OAC1C,GAAI,IAAQ,EAAK,CAAE,UAAS,KAAK,KC1BrC,OAAoB,OCEb,YAAuB,GAC5B,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAQ,aAAiB,IAAS,EAAM,UAClC,YAAiB,IAAS,EAAM,YAAc,ECH/C,YAA0B,GAE/B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,GAAI,YAAiB,GAAI,SAAS,QAAU,GAAc,GACxD,MAAO,GAAQ,MAGjB,WAAiB,GACf,AAAI,CAAC,EAAE,eAEP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAO,IAGT,WAAgB,GACd,AAAI,CAAC,EAAE,eACP,GAAE,cAAc,oBAAoB,OAAQ,GAC5C,EAAE,cAAc,oBAAoB,QAAS,GAC7C,EAAQ,IAGV,EAAM,iBAAiB,OAAQ,GAC/B,EAAM,iBAAiB,QAAS,KCxB7B,YAAuB,GAC5B,MAAO,IAAI,SAAQ,CAAC,EAAS,KAC3B,AAAM,YAAe,OAAO,EAAO,GAAI,OAAM,qDAC7C,GAAM,GAAS,GAAI,YACnB,EAAO,OAAS,KACd,AAAI,MAAO,GAAO,QAAW,UAAU,EAAO,GAAI,OAAM,qEACxD,GAAM,GAAM,EAAI,SAAS,qBACzB,EAAI,OAAS,IAAM,EAAQ,GAC3B,EAAI,QAAU,EACd,EAAI,IAAM,EAAO,QAEnB,EAAO,QAAU,EACjB,EAAO,cAAc,KCXlB,YAA4B,GACjC,GAAM,CAAE,QAAO,SAAU,EAAI,SAE7B,MAAI,aAAiB,GACZ,GAAI,GAAW,EAAM,aAAc,EAAM,eAE9C,YAAiB,GACZ,GAAI,GAAW,EAAM,WAAY,EAAM,aAEzC,GAAI,GAAW,EAAM,MAAO,EAAM,QCNpC,YAAsB,CAAE,QAAO,WACpC,GAAM,CAAE,uBAAwB,EAAI,SAC9B,EAAS,IACf,SAAO,MAAQ,EACf,EAAO,OAAS,EACT,EAGF,YAA+B,EAAwD,GAC5F,GAAM,CAAE,aAAc,EAAI,SAE1B,GAAI,CAAE,aAAiB,KAAc,CAAC,GAAc,GAClD,KAAM,IAAI,OAAM,8DAGlB,GAAM,CAAE,QAAO,UAAW,GAAQ,GAAmB,GAC/C,EAAS,GAAa,CAAE,QAAO,WAErC,MAAI,aAAiB,GACnB,EAAoB,GAAQ,aAAa,EAAO,EAAG,GAEnD,EAAoB,GAAQ,UAAU,EAAO,EAAG,EAAG,EAAO,GAErD,EC7BT,OAAoB,OAKpB,kBACE,EACA,GAEA,GAAM,GAAe,GAAU,EAAI,SAAS,sBAEtC,CAAC,EAAQ,EAAO,GAAe,EAAU,MAAM,MAAM,EAAW,GAAa,EAAI,GACjF,EAAc,AAAG,QAAK,IAAM,EAAU,KAAK,EAAQ,EAAO,GAAa,SAC7E,YAAM,AAAG,YAAQ,SAAS,EAAa,GAEvC,EAAY,UAEL,ECfF,YAAwB,GAC7B,GAAM,CAAE,QAAO,SAAQ,SAAU,EAAI,SAErC,MAAO,aAAiB,IACnB,YAAiB,IACjB,YAAiB,GCPxB,MAAoB,OCKb,YAAuB,EAA6C,EAAmB,EAAuB,IACnH,GAAM,CAAE,QAAO,UAAW,EAAI,SAE9B,GAAI,CAAE,aAAiB,IAAS,YAAiB,IAC/C,KAAM,IAAI,OAAM,4EAGlB,GAAM,GAAO,GAAmB,GAC1B,EAAQ,EAAY,KAAK,IAAI,EAAK,OAAQ,EAAK,OAC/C,EAAQ,EAAQ,EAAK,MACrB,EAAS,EAAQ,EAAK,OAEtB,EAAe,GAAa,CAAE,MAAO,EAAW,OAAQ,IACxD,EAAc,YAAiB,GAAS,EAAQ,GAAsB,GAEtE,EAAS,KAAK,IAAI,EAAQ,GAAU,EACpC,EAAK,GAAe,EAAQ,EAAS,EAAS,EAC9C,EAAK,GAAe,EAAS,EAAQ,EAAS,EACpD,SAAoB,GAAc,UAAU,EAAa,EAAI,EAAI,EAAO,GAEjE,EDzBT,aAyBE,YACE,EACA,EAA6B,IAdvB,mBAAkD,GAElD,eAAiC,GAIjC,wBAA8B,GAE9B,sBAA+B,GAQrC,GAAI,CAAC,MAAM,QAAQ,GACjB,KAAM,IAAI,OAAM,4HAA4H,KAG9I,KAAK,mBAAqB,EAC1B,KAAK,WAAa,EAAO,OAEzB,EAAO,QAAQ,CAAC,EAAO,KACrB,GAAI,GAAW,IACb,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAO,EAAM,MACnC,OAGF,GAAI,EAAW,IACb,GAAM,GAAa,EAAc,MAAM,GACvC,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,yCAAyC,8CAG3D,KAAK,cAAc,GAAO,EAC1B,KAAK,iBAAiB,GAAQ,EAAc,MAAM,MAAM,GACxD,OAGF,GAAM,GAAU,YAAyB,GAAI,SAAS,OAAS,EAAQ,GAAsB,GAC7F,KAAK,UAAU,GAAO,EACtB,KAAK,iBAAiB,GAAO,CAAC,EAAO,OAAQ,EAAO,MAAO,QAIpD,gBACT,MAAO,MAAK,iBAGH,YACT,MAAO,MAAK,aAGH,gBACT,MAAO,MAAK,UAAY,GAAK,KAAK,sBAGzB,aACT,MAAO,MAAK,cAGH,mBACT,MAAO,MAAK,oBAGH,aACT,MAAO,MAAK,cAGH,2BACT,MAAO,IAAM,KAAK,UAAW,EAAG,GAAG,IACjC,CAAC,EAAG,IAAa,KAAK,2BAA2B,IAI9C,SAAS,GACd,MAAO,MAAK,SAAS,IAAa,KAAK,aAAa,GAG/C,mBAAmB,GACxB,MAAO,MAAK,iBAAiB,GAGxB,eAAe,GACpB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,cAAc,GACnB,MAAO,MAAK,iBAAiB,GAAU,GAGlC,2BAA2B,GAChC,GAAI,MAAO,MAAK,WAAc,SAC5B,KAAM,IAAI,OAAM,yFAGlB,GAAM,GAAQ,KAAK,cAAc,GAC3B,EAAS,KAAK,eAAe,GACnC,MAAO,IAA0B,CAAE,QAAO,UAAU,KAAK,WAYpD,cAAc,EAAmB,EAA0B,IAChE,YAAK,WAAa,EAEX,AAAG,OAAK,KACb,GAAM,GAAe,GAAM,KAAK,UAAW,EAAG,GAAG,IAAI,AAAC,IACpD,GAAM,GAAQ,KAAK,SAAS,GAE5B,GAAI,YAAoB,WAEtB,GAAI,GAAY,EAAW,GAAS,EAAQ,EAAM,aAElD,SAAY,GAAY,EAAW,GAE/B,GAAU,MAAM,KAAO,GAAa,EAAU,MAAM,KAAO,IAC7D,GAAY,AAAG,QAAM,eAAe,EAAW,CAAC,EAAW,KAGtD,EAAU,KAAK,EAAW,EAAW,GAG9C,GAAI,YAAiB,GAAI,SAAS,OAChC,MAAO,AAAG,WAAQ,WAAW,GAAc,EAAO,EAAW,IAG/D,KAAM,IAAI,OAAM,+BAA+B,8FAAqG,OAOtJ,MAHoB,AAAG,SAAM,EAAa,IAAI,AAAC,GAAM,AAAG,OAAK,EAAG,aAAa,KAAK,KAAK,UAAW,EAAW,EAAW,OE3I9H,iBAAiC,GAC/B,GAAI,YAAkB,IACpB,MAAO,GAGT,GAAM,GAAgB,MAAM,QAAQ,GAChC,EACA,CAAC,GAEL,GAAI,CAAC,EAAc,OACjB,KAAM,IAAI,OAAM,4CAGlB,GAAM,GAAa,AAAC,GAAiB,MAAM,QAAQ,GAAU,mBAAmB,KAAS,GAEnF,EAAa,EAAc,IAAI,IAErC,SAAW,QAAQ,CAAC,EAAO,KACzB,GAAI,CAAC,GAAe,IAAU,CAAC,GAAW,IAAU,CAAC,EAAW,GAC9D,KAAI,OAAO,GAAc,IAAO,SACxB,GAAI,OAAM,eAAe,EAAW,sEAAsE,EAAc,MAG1H,GAAI,OAAM,eAAe,EAAW,iIAG5C,GAAI,EAAW,IAEb,GAAM,GAAY,EAAM,MAAM,GAC9B,GAAI,IAAc,EAChB,KAAM,IAAI,OAAM,eAAe,EAAW,iCAAiC,iDAMjF,KAAM,SAAQ,IACZ,EAAW,IAAI,AAAC,GAAU,GAAe,IAAU,GAAiB,KAG/D,GAAI,IAAS,EAAY,MAAM,QAAQ,ICtChD,kBACE,EACA,GAEA,GAAM,CAAE,UAAW,EAAI,SAEnB,EAAS,EAEb,GAAI,CAAE,aAAiB,KACrB,GAAM,GAAW,KAAM,GAAW,GAElC,GAAI,EAAS,UAAY,EACvB,KAAM,IAAI,OAAM,8CAGlB,GAAM,GAAiB,EAAS,SAAS,GACzC,EAAS,YAA0B,GAC/B,EACA,KAAM,IAAoB,GAGhC,GAAM,GAAM,EAAoB,GAQhC,MAAO,AAPO,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAO,MAAO,EAAO,QAAQ,IAAI,QAC7C,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAO,MAAO,EAAO,SAE/C,IAAI,CAAC,CAChB,IAAG,IAAG,QAAO,aAEb,GAAM,GAAU,GAAa,CAAE,QAAO,WACtC,SAAoB,GACjB,aAAa,EAAI,aAAa,EAAG,EAAG,EAAO,GAAS,EAAG,GACnD,ICnDX,OAAoB,OAgBpB,kBACE,EACA,GAEA,GAAI,CAAC,GAAW,IAAgB,CAAC,EAAW,GAC1C,KAAM,IAAI,OAAM,6DAGlB,GAAI,EAAW,IAAgB,EAAY,MAAM,GAAK,EACpD,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,CAAC,EAAW,EAAU,GAAe,EAAY,MAAM,MAAM,EAAW,GAAe,EAAI,GAajG,MAJoB,AAPN,GAAW,IACvB,AAAC,GAAS,YAAe,GACrB,EAAI,QAAQ,EAAU,GAAW,IACjC,GAEH,IAAI,AAAC,GAAQ,EAAI,mBAAmB,EAAU,IAEvB,IAAI,CAAC,CAC7B,IAAG,IAAG,QAAO,YACT,AAAG,WAAQ,EAAY,KAAK,EAAW,EAAU,GAAc,CAAC,EAAG,EAAG,GAAI,CAAC,EAAQ,EAAO,OCtCpG,kBACE,EAEA,GAEA,GAAM,CAAE,SAAU,EAAI,SAChB,EAAM,KAAM,GAAM,EAAK,GAC7B,GAAI,CAAE,GAAI,OAAS,KACjB,KAAM,IAAI,OAAM,qBAAqB,EAAI,WAAW,EAAI,yBAAyB,EAAI,OAEvF,MAAO,GCTT,kBAAiC,GAC/B,GAAM,GAAM,KAAM,IAAa,GACzB,EAAO,KAAO,GAAK,OAEzB,GAAI,CAAC,EAAK,KAAK,WAAW,UACxB,KAAM,IAAI,OAAM,wEAAwE,EAAK,kBAAkB,EAAI,OAErH,MAAO,IAAc,GCRvB,kBAAmC,GACjC,MAAQ,MAAM,IAAa,IAAM,OCDnC,kBAAsC,GACpC,MAAO,IAAI,cAAa,KAAO,MAAM,IAAa,IAAM,eCH1D,OAAoB,OCAb,YAAsB,EAAyB,GACpD,GAAM,GAA0B,GAAG,0BAEnC,GAAI,CAAC,EACH,MAAO,CACL,aAAc,GACd,YAAa,GAIjB,GAAI,IAAQ,IACV,MAAO,CACL,aAAc,IACd,YAAa,IAAI,KAIrB,GAAM,GAAW,EAAI,WAAW,WAAa,UAAY,EAAI,WAAW,YAAc,WAAa,GACnG,EAAM,EAAI,QAAQ,EAAU,IAE5B,GAAM,GAAQ,EAAI,MAAM,KAAK,OAAO,AAAC,GAAM,GAErC,EAAe,EAAI,SAAS,SAC9B,EAAM,EAAM,OAAS,GACrB,EAEA,EAAe,EAAY,GAAI,SAAS,SAAW,EAAM,MAAM,EAAG,EAAM,OAAS,GAAK,GAAO,KAAK,KACtG,SAAe,EAAI,WAAW,KAAO,IAAI,IAAiB,EAEnD,CACL,eACA,YAAa,IAAiB,IAAM,IAAI,IAAiB,GAAG,KAAgB,KD1BhF,kBACE,EACA,GAEA,GAAM,CAAE,cAAa,gBAAiB,GAAa,EAAK,GAClD,EAAW,KAAM,IAAuC,GAE9D,MAAO,AAAG,OAAG,YAAY,EAAU,GET9B,YAAyB,EAAoB,EAAwB,EAA8B,IACxG,GAAM,CAAE,QAAO,UAAW,EACtB,GAAmB,GACnB,EACJ,SAAM,MAAQ,EACd,EAAM,OAAS,EACR,CAAE,QAAO,UCTlB,OAAoB,OCApB,OAAoB,OAApB,YAQE,YAAY,GAIF,aAAkC,OAElC,oBAAiC,GALzC,KAAK,MAAQ,KASJ,UAAmC,MAAO,MAAK,WAE/C,iBAAkC,MAAO,MAAK,kBAE9C,YAAsB,MAAO,CAAC,CAAC,KAAK,OAExC,iBAAiB,GACtB,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,MAAO,GAAI,GAGN,sBAAsB,EAAmB,GAC9C,GAAM,CAAE,MAAK,WAAY,KAAK,qBAAqB,GACnD,EAAI,GAAS,UACb,EAAI,GAAW,EAGV,eACL,MAAO,MAAK,eAAe,IAAI,CAAC,CAAE,eAAiB,EACjD,KAAM,EACN,OAAQ,KAAK,iBAAiB,MAI3B,qBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,EAAM,iBAAqB,cAGnE,kBACL,MAAO,MAAK,eAAe,OAAO,AAAC,GAAU,CAAE,GAAM,iBAAqB,eAGrE,WACL,KAAK,kBAAkB,QAAQ,CAAC,CAAE,OAAM,aACtC,KAAK,sBAAsB,EAAM,EAAO,cAIrC,SACL,KAAK,qBAAqB,QAAQ,CAAC,CAAE,OAAM,OAAQ,MACjD,GAAM,GAAS,AAAG,UAAO,EAAS,YAClC,EAAS,UACT,KAAK,sBAAsB,EAAM,KAI9B,QAAQ,EAA4B,IACzC,KAAK,eAAe,QAAQ,AAAC,IAC3B,GAAI,GAAoB,EAAM,OAAO,WACnC,KAAM,IAAI,OAAM,mDAAmD,EAAM,QAE3E,EAAM,OAAO,YAEf,KAAK,QAAU,OAGV,kBACL,MAAO,IAAI,cACT,KAAK,eACF,IAAI,CAAC,CAAE,YAAa,MAAM,KAAK,EAAO,aACtC,OAAO,CAAC,EAAM,IAAQ,EAAK,OAAO,UAI5B,MAAK,GAChB,GAAI,YAAwB,eAC1B,KAAK,eAAe,GACpB,OAEF,KAAM,MAAK,YAAY,QAGZ,aAAY,GACvB,GAAI,GAAO,MAAO,IAAQ,SACxB,KAAM,IAAI,OAAM,GAAG,KAAK,0CAE1B,GAAM,GAAY,KAAM,IAAc,EAAK,KAAK,uBAChD,KAAK,kBAAkB,QAGZ,cAAa,GACxB,GAAI,GAAY,MAAO,IAAa,SAClC,KAAM,IAAI,OAAM,GAAG,KAAK,iDAE1B,GAAM,CAAE,YAAa,EAAI,SACnB,CAAE,cAAa,gBAAiB,GAAa,EAAU,KAAK,uBAC5D,EAAuB,AAAC,GAAwB,QAAQ,IAAI,EAAU,IAAI,AAAC,GAAO,EAAS,GAAI,KAAK,AAAC,GAAQ,EAAI,UACjH,EAAc,AAAG,MAAG,qBAAqB,GACzC,EAAW,KAAK,MAAO,MAAM,GAAS,IAAc,YACpD,EAAY,KAAM,GAAY,EAAU,GAC9C,KAAK,kBAAkB,GAGlB,kBAAkB,GACvB,GAAM,CAAE,gBAAe,UAAW,KAAK,2BAA2B,GAClE,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGV,eAAe,GACpB,GAAM,CAAE,gBAAe,UAAW,KAAK,cAAc,GACrD,KAAK,eAAiB,EACtB,KAAK,QAAU,EAGT,qBAAqB,GAC3B,GAAI,CAAC,KAAK,OACR,KAAM,IAAI,OAAM,qDAGlB,GAAM,GAAS,EAAU,MAAM,KAAK,OAAO,CAAC,EAAoD,KAE9F,GAAI,CAAC,EAAI,QAAQ,eAAe,GAC9B,KAAM,IAAI,OAAM,wDAAwD,eAAqB,KAE/F,MAAO,CAAE,IAAK,EAAI,QAAS,UAAS,QAAS,EAAI,QAAQ,KACxD,CAAE,QAAS,KAAK,SAEb,CAAE,MAAK,WAAY,EACzB,GAAI,CAAC,GAAO,CAAC,GAAW,CAAE,GAAI,YAAuB,YACnD,KAAM,IAAI,OAAM,8DAA8D,KAGhF,MAAO,CAAE,MAAK,aC7IlB,MAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,iBAAkB,EAAO,iBAAkB,EAAQ,QAC1F,SAAM,AAAG,OAAI,EAAK,EAAO,MAClB,IDNJ,YACL,EACA,EACA,EAAwB,IAExB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,CAAC,EAAG,GAAI,QACrE,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,CAAC,EAAG,KAE7E,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,OAItC,YACL,EACA,EACA,EAAwB,GACxB,EAAuB,IAEvB,MAAO,AAAG,QAAK,KACb,GAAM,GAAO,AAAG,OACd,EACI,AAAG,MACH,AAAG,SAAO,EAAI,EAAiB,MAAqB,QAAS,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,GAAI,QAC5F,EAAiB,MAAM,MAEvB,EAAuB,EAAG,EAAiB,MAA8B,EAAc,CAAC,EAAG,GAAK,CAAC,EAAG,KAEpG,EAAO,EAAuB,EAAM,EAAiB,MAAO,CAAC,EAAG,IAEhE,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,IAC3B,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAE/D,EAAM,AAAG,OAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,KACxC,EAAO,EAAuB,EAAK,EAAiB,MAAO,CAAC,EAAG,IAErE,MAAO,AAAG,QAAK,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,AAAG,MAAI,EAAM,QEpD1D,OAAoB,OAIb,YACL,EACA,EACA,EAA4B,OAC5B,EAAoB,IAEpB,MAAO,AAAG,SAAK,KACb,GAAM,GAAM,AAAG,OACb,AAAG,UAAO,EAAG,EAAO,QAAS,CAAC,EAAG,GAAI,GACrC,EAAO,MAGT,MAAO,GAAW,AAAG,QAAK,GAAO,ICd9B,WAAoC,EAAgB,GACzD,OAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,AAAK,EAAc,KAAK,AAAC,GAAO,EAAG,eAAiB,IAClD,EAAU,GAAM,YCLtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,EACA,KAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,SCzBtB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,CACL,EACA,EACA,KAEA,GAAM,GAAa,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAY,IAChF,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CACL,QAAS,EACT,KAAM,ICvBZ,OAAoB,OCApB,aAsBE,YAES,EAEA,EAEA,GAJA,wBAEA,wBAEA,cDxBJ,YACL,EACA,GAEA,MAAO,CAAC,EAAoB,EAAqB,KAC/C,GAAM,GAAmB,AAAG,YAAS,EAAe,EAAI,EAAI,GAAa,CAAC,EAAG,EAAG,EAAY,IACtF,EAAmB,AAAG,YAAS,EAAe,EAAa,GAAc,CAAC,EAAG,EAAG,EAAY,IAC5F,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,WAGX,GAAI,IACT,EACA,EACA,IAKC,YAEL,GAEA,MAAO,AAAC,KACN,GAAM,GAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAmB,EAAgC,GAAG,qBAA2B,GACjF,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,IAAI,IACT,EACA,EACA,IEpCC,WAAmC,EAAgB,GACxD,MAAO,CAAC,EAAsB,EAAmB,KAC/C,GAAM,GAAS,EAAU,GAEzB,GAAI,CAAC,GAAS,EAAQ,GACpB,KAAM,IAAI,OAAM,sBAAsB,oBAA+B,oBAA4B,KAGnG,SAAc,KACZ,CAAE,eAAc,UAAW,GAAc,IAGpC,GCfJ,WAA+B,GACpC,GAAI,GAAmB,EAEvB,WAAwB,GACtB,GAAM,GAAM,EAAiB,MAAM,EAAG,GACtC,SAAmB,EAAiB,MAAM,GACnC,EAGT,aACE,MAAO,GAGT,MAAO,CACL,iBACA,uBCPG,YAA2B,EAAwC,GACxE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,GAAQ,EACV,EAAkB,EAAY,EAAa,EAAG,GAAG,WACjD,EAA2B,EAAY,EAAa,GAAG,WACrD,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAChE,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAoB,EAAqB,EAAsB,EAAwB,IACvH,GAAM,CAAE,QAAO,QAAO,SAAU,EAAyB,EAAY,EAAa,EAAc,GAC1F,EAAQ,EAA2B,EAAa,EAAa,GAAG,WAEtE,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAC3C,EAAS,EAAyB,IAAK,IAAK,UAElD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CACN,SAAQ,SAAQ,SAAQ,WCvBvB,YAA+B,GACpC,MAAO,AAAC,KACN,GAAM,GAAU,EAAgC,GAAG,YAAkB,GAC/D,EAAO,EAAgC,GAAG,SAAe,GAE/D,MAAO,CAAE,UAAS,SCNf,YAA2B,EAAgB,GAChD,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CAAE,QAAO,QAAO,SAGzB,WAAkC,EAAgB,EAAwB,IACxE,GAAM,GAAQ,EACV,EAAkB,GAAG,WACrB,EAA2B,GAAG,WAC5B,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WACtC,EAAQ,EAA2B,GAAG,WAE5C,MAAO,CACL,QAAO,QAAO,QAAO,SAIzB,MAAO,CACL,2BACA,4BC7BG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBhBxBnB,oBAU0C,GACxC,cACE,MAAM,wBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,sDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAE/B,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,+BAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KiBlDzB,OAAoB,OCApB,OAAoB,OAIb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,IAAM,AAAG,OACtB,AAAG,UAAO,EAAG,EAAO,SACpB,EAAO,OCPJ,YAAuB,EAAuB,EAAoB,GACvE,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAIpB,EAAK,AAFa,GAAuB,EAAgB,GAEpC,EAAY,EAAa,MAEpD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,OCdP,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,EAAgB,OAGtB,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,YAA4B,GACjC,GAAM,GAAyC,GACzC,EAAmC,GAEzC,cAAO,KAAK,GAAW,QAAQ,AAAC,IAC9B,GAAM,GAAM,EAAI,WAAW,MAAQ,EAAgB,EACnD,EAAI,GAAO,EAAU,KAGhB,CAAE,sBAAqB,iBJXhC,oBAkBU,GAGR,YAAY,EAAe,GACzB,MAAM,GACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBASP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EACJ,MAAO,IAAoB,EAAmB,KAAK,EAAmB,MAAM,GAAI,IAAK,EAAO,MAIzF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,EAAS,KAAK,0BAA2B,KAAK,4BAG3D,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAM,KAAK,0BACX,EAAO,KAAK,2BACZ,EAAwB,EAAO,EAAO,EAEtC,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KKnFjC,GAAM,IAAyB,CAAC,UAAW,QAAS,MAAO,QAAS,UAAW,YAAa,aAAnG,SAiBE,YAAY,GACV,GAAI,EAAc,SAAW,EAC3B,KAAM,IAAI,OAAM,8EAA8E,EAAc,UAG9G,GAAuB,QAAQ,CAAC,EAAY,KAC1C,KAAK,GAAc,EAAc,KAIrC,gBACE,MAAO,IACJ,IAAI,AAAC,GAAgB,EAAE,aAAY,YAAa,KAAK,MACrD,KAAK,CAAC,EAAI,IAAO,EAAG,YAAc,EAAG,e1C9B5C,oBAQuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGtB,aAAa,GAClB,MAAO,AAAG,SAAK,IAAM,AAAG,WAAQ,KAAK,OAAO,UAGjC,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,oBAAmB,GAC9B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAC9B,EAAsB,KAAM,SAAQ,IAAI,AAAG,WAAQ,GAAK,IAAI,KAAO,KACvE,GAAM,GAAO,KAAM,GAAE,OACrB,SAAE,UACK,KAET,EAAI,UAEJ,GAAM,GAAqB,EACxB,IAAI,AAAC,GAAiB,GAAI,IAAgB,IAE7C,MAAO,GAAS,aACZ,EACA,EAAmB,GAGf,sBACR,MAAO,wBAGC,0BACR,MAAO,KAGC,2BACR,MAAO,K2C1CJ,YAA+B,GACpC,MAAO,GAAI,sBAAuB,IAG7B,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,gBCPf,YACL,EACA,EACA,EAAgB,GAChB,GAIA,AAF6B,OAAM,QAAQ,GAAmB,EAAkB,CAAC,IAE5D,QAAQ,AAAC,IAE5B,GAAM,GAAO,YAAa,IACtB,EACC,GAAsB,GAAK,EAAE,YAAc,OAChD,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mHAIlB,GAAM,GAAmB,AADV,EAAK,gBACY,OAAO,AAAC,GAAc,EAAU,YAAc,GAExE,EAAS,GAAoB,GAC/B,EAAE,UAAU,IAAI,WACf,GAAmB,GAAI,GAAM,EAAG,GAMrC,AAJsB,GAAI,IACxB,EAAiB,IAAI,AAAC,GAAc,GAAG,EAAU,eAAe,GAAM,EAAU,iBAChF,GAEY,KAAK,KCxBhB,YAA6B,GAClC,MAAO,IAAoB,IAEtB,EAAI,oBAAwB,IAE5B,EAAI,6BAAiC,IAErC,EAAI,sBAA0B,GAG9B,YAEoD,EAAoB,GAC7E,GAAM,CAAE,IAAK,GAAU,EAAU,UAC3B,EAAY,EAAmB,QAAwB,EAAM,EAAG,EAAM,GAEtE,EAAO,EAAU,QACjB,CAAE,aAAc,EAAU,UAC1B,EAAc,GAAI,GAAc,EAAU,UAAU,MAAO,EAAK,QAAQ,EAAU,WAAY,GAQpG,MAAO,IAAK,KANM,CAChB,YACA,qBACA,gBCpCJ,aA+BE,YAAY,EAAqC,IAC/C,GAAM,CACJ,YAAY,GAAM,aAAa,GAAM,YAAW,YAAW,YAAW,cACpE,EACJ,KAAK,UAAY,EACjB,KAAK,WAAa,EAClB,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,EAC9B,KAAK,UAAY,GAAa,uBAC9B,KAAK,WAAa,GAAc,yBAxCpC,SAiDE,YACE,EACA,EAAqC,IAErC,KAAK,cAAgB,EACrB,KAAK,QAAU,GAAI,IAAyB,GAG9C,KAAK,GACH,GAAM,GAAM,EAAoB,GAE1B,CACJ,YAAW,aAAY,YAAW,YAAW,YAAW,cACtD,KAAK,QAcT,GAZI,GAAa,KAAK,wBAAyB,KAC7C,GAAI,YAAc,EAClB,EAAI,UAAY,EAChB,GAAY,EAAK,KAAK,cAAc,iBACpC,GAAY,EAAK,KAAK,cAAc,kBACpC,GAAY,EAAK,KAAK,cAAc,mBACpC,GAAY,EAAK,KAAK,cAAc,WACpC,GAAY,EAAK,KAAK,cAAc,aAAc,IAClD,GAAY,EAAK,KAAK,cAAc,cAAe,IACnD,GAAY,EAAK,KAAK,cAAc,WAAY,KAG9C,GACF,EAAI,YAAc,EAClB,EAAI,UAAY,EAEhB,GAAM,GAAY,AAAC,IACjB,EAAI,YACJ,EAAI,IAAI,EAAG,EAAG,EAAG,EAAG,EAAW,EAAG,EAAI,KAAK,IAC3C,EAAI,QAEN,KAAK,cAAc,UAAU,QAAQ,MAOpC,YACL,EACA,GAGA,AAD2B,OAAM,QAAQ,GAAiB,EAAgB,CAAC,IACxD,QAAQ,AAAC,IAE1B,GAAM,GAAY,YAAa,GAC3B,EACC,GAAoB,GAAK,EAAE,UAAY,OAC5C,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gIAGlB,GAAI,IAAkB,GAAW,KAAK,qBC1G1C,OAAoB,OCApB,MAAoB,OCKpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAC7D,EAA6B,GAAkC,EAAgB,GAErF,WAAqC,EAAoB,EAAqB,GAC5E,GAAM,GAAkB,EAA2B,EAAY,EAAa,GAAG,qBACzE,EAAkB,EAA2B,EAAa,EAAa,GAAG,qBAC1E,EAAiB,EAAkB,EAAY,EAAa,EAAG,GAAG,oBAExE,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,EAAkB,GAChD,GAAM,GAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBACpE,EAAkB,EAA2B,EAAU,EAAU,GAAG,qBAE1E,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YAAuB,EAAuB,GACnD,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAgB,GAEhC,EAAqB,EAAkB,EAAG,GAAI,EAAG,sBACjD,EAA+B,EAA4B,GAAI,GAAI,gCACnE,EAA+B,EAA4B,GAAI,IAAK,gCAEpE,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,IAAK,0BAA0B,OAG3F,GAAM,GAA4B,EAA4B,IAAK,IAAK,6BAClE,EAA2B,EAA2B,IAAK,IAAK,4BAEhE,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,aAAY,cAAa,cCjEvC,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAE1D,EAAoB,GAAsB,GAC1C,EAA6B,GAA+B,GAElE,WAAqC,GACnC,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAiB,EAAkB,GAAG,oBAE5C,MAAO,CAAE,kBAAiB,kBAAiB,kBAG7C,WAAgC,GAC9B,GAAM,GAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAChD,EAAkB,EAA2B,GAAG,qBAEtD,MAAO,CAAE,kBAAiB,kBAAiB,mBAG7C,MAAO,CACL,oBACA,6BACA,8BACA,0BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,6BACA,8BACA,0BACE,GAAkB,EAAW,GAE3B,EAAqB,EAAkB,sBACvC,EAA+B,EAA4B,gCAC3D,EAA+B,EAA4B,gCAE3D,EAAa,CACjB,QAAS,EACT,kBAAmB,EACnB,kBAAmB,GAGf,EAAc,GACpB,GAAM,EAAe,EAAG,GAAG,QAAQ,AAAC,IAClC,EAAY,cAAc,KAAS,EAAuB,0BAA0B,OAGtF,GAAM,GAA4B,EAA4B,6BACxD,EAA2B,EAA2B,4BAEtD,EAAY,CAChB,gBAAiB,EACjB,eAAgB,GAGlB,SAA2B,EAAW,GAE/B,CAAE,OAAQ,CAAE,aAAY,cAAa,aAAa,iBFrE3D,YAAc,EAAgB,EAAoB,GAChD,MAAO,AAAG,OAAI,AAAG,SAAO,EAAG,EAAO,QAAS,EAAQ,QAAS,EAAO,MAGrE,YAAwB,EAAgB,EAA8B,EAA2B,IAC/F,GAAI,GAAM,EAAkB,AAAG,OAAK,GAAK,EACzC,SAAM,EAAuB,EAAK,EAAO,gBAAiB,CAAC,EAAG,IAC9D,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,AAAG,MAAI,EAAK,GAAK,EAAG,EAAO,eAAgB,CAAC,EAAG,KAC9C,EAGT,YAAmB,EAAgB,GACjC,GAAI,GAAM,EAAuB,AAAG,OAAK,GAAI,EAAO,gBAAiB,CAAC,EAAG,IACzE,SAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,EAAuB,AAAG,OAAK,GAAM,EAAO,gBAAiB,CAAC,EAAG,IACvE,EAAM,AAAG,MAAI,EAAK,GACX,EA7BT,oBAgCkC,GAGhC,YAAY,GACV,MAAM,gBACN,KAAK,eAAiB,EAGjB,aAAa,GAClB,GAAM,CAAE,UAAW,KACnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,8CAElB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAC7D,EAAM,AAAG,OAAK,GAAK,EAAY,EAAO,WAAW,QAAS,CAAC,EAAG,KAClE,SAAM,GAAe,EAAK,EAAO,WAAW,kBAAmB,IAC/D,EAAM,GAAe,EAAK,EAAO,WAAW,mBAC5C,GAAM,KAAK,eAAgB,EAAG,GAAG,QAAQ,AAAC,IACxC,EAAM,GAAU,EAAK,EAAO,YAAY,cAAc,QAExD,EAAM,GAAe,EAAK,EAAO,UAAU,iBAC3C,EAAM,AAAG,OAAK,EAAuB,EAAK,EAAO,UAAU,eAAgB,CAAC,EAAG,KACxE,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,sBAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,gBAG1C,cAAc,GACtB,MAAO,IAAc,EAAS,KAAK,kBGvEhC,YAAuB,GAC5B,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAkB,GAAuB,EAAgB,GAEzD,EAAM,EAAgB,IAAK,EAAG,UAC9B,EAAS,EAAgB,IAAK,EAAG,aAEvC,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,GAAI,CAAE,MAAK,YCflB,YACL,GAEA,GAAM,GAAgC,GAEhC,EAAqB,EAA0B,EAAW,GAEhE,WAAyB,GACvB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,GAAM,GAAS,CACb,GAAI,CACF,IAAK,EAAgB,UACrB,OAAQ,EAAgB,eAI5B,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCxBZ,GAAK,IAAL,UAAK,GAEV,SAAS,SAET,OAAO,SAJG,aNLZ,oBAakC,GAGhC,YAAY,EAAqC,GAAI,IAAa,IAChE,MAAM,gBACN,KAAK,sBAAwB,KAGpB,wBACT,MAAO,MAAK,sBAGP,OAAO,GACZ,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,GAAG,KAAK,uCAG1B,MAAO,AAAG,SAAK,KACb,GAAM,GAAqB,YAAiB,IACxC,KAAK,qBAAqB,aAAa,GACvC,EAEE,EAAS,AAAG,WAAQ,EAAoB,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,SAAS,KAAK,EAAmB,MAAM,GAAI,IACnG,EAAM,GAAoB,EAAQ,EAAO,GAAG,KAAK,OACjD,EAAS,GAAoB,EAAQ,EAAO,GAAG,QACrD,MAAO,CAAE,MAAK,YAIX,aAAa,GAClB,MAAO,AAAG,SAAK,KACb,GAAM,CAAE,MAAK,UAAW,KAAK,OAAO,GACpC,MAAO,CAAE,MAAK,OAAQ,AAAG,WAAQ,WAIxB,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,qBAAoB,GAC/B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,GAE9B,EAAO,AAAG,WAAQ,EAAI,KACtB,EAAU,AAAG,WAAQ,EAAI,QACzB,EAAsB,EAAK,IAAI,CAAC,EAAW,IAAO,EACtD,YACA,aAAc,EAAQ,MAGlB,EAAqB,KAAM,SAAQ,IACvC,EAAoB,IAAI,MAAO,CAAE,YAAW,mBAC1C,GAAM,GAAO,MAAM,GAAU,QAAQ,GAC/B,EAAY,MAAM,GAAa,QAAQ,GACvC,EAAS,EAAW,GACpB,EAAS,EAAS,GAAO,KAAO,GAAO,OACvC,EAAoB,EAAS,EAAY,EAAI,EAEnD,SAAU,UACV,EAAa,UACN,CAAE,MAAK,SAAQ,wBAG1B,SAAI,IAAI,UACR,EAAI,OAAO,UAEJ,EAAS,aAAe,EAAiD,EAAmB,GAG3F,sBACR,MAAO,mBAGF,QAAQ,EAA4B,IACzC,KAAK,qBAAqB,QAAQ,GAClC,MAAM,QAAQ,GAGT,qBAAqB,GAC1B,GAAM,CAAE,SAAQ,iBAAkB,KAAK,wBAAwB,GAC/D,KAAK,QAAU,EACf,KAAK,eAAiB,EAGjB,wBAAwB,GAC7B,MAAO,IAAc,GAGb,2BAA2B,GACnC,GAAM,CAAE,sBAAqB,iBAAkB,GAAmB,GAElE,YAAK,qBAAqB,kBAAkB,GAErC,GAA2B,GAG1B,cAAc,GACtB,GAAM,GAAwB,IAAM,EAAI,EAAM,KAAM,EAAI,GAElD,EAA0B,EAAQ,MAAM,EAAG,EAAQ,OAAS,GAC5D,EAAoB,EAAQ,MAAM,EAAQ,OAAS,GAEzD,YAAK,qBAAqB,eAAe,GAClC,KAAK,wBAAwB,KOvHxC,MAAoB,OAApB,oBAYU,IACD,YAAY,EAAqB,EAAmB,GACzD,GAAM,GAAkB,EAAmB,IAAI,CAAC,CAAE,QAAO,aACvD,GAAM,GAAQ,EAAY,KAAK,IAAI,EAAQ,GAC3C,MAAO,CACL,MAAO,EAAQ,EACf,OAAQ,EAAS,KAIf,EAAY,EAAgB,OAElC,MAAO,AAAG,QAAK,KACb,GAAM,GAA0B,CAAC,EAAe,IAAkB,AAAG,QAAM,CAAC,AAAG,OAAK,CAAC,IAAK,EAAO,WAAY,AAAG,OAAK,CAAC,IAAK,EAAO,YAAa,GAAG,KAAK,EAAG,KAAK,OAGzJ,EAAa,CAAC,EAAkB,KACpC,GAAM,CAAE,QAAO,UAAW,EAAgB,GAC1C,MAAO,GAAK,EAAO,GAAU,KAAK,IAAI,EAAQ,GAAU,EAAI,GAGxD,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GACvE,EAAc,AAAC,GAAqB,EAAW,EAAU,CAAC,EAAG,IAAM,EAAI,GAa7E,MAXwB,GACrB,IAAI,AAAG,OAAK,CAAC,EAAW,KAAM,EAAW,YACzC,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAY,GACZ,EAAY,OAEb,IAAI,AAAG,QAAM,MAAM,KAAK,MAAM,GAAY,CAAC,EAAG,IAAa,EAC1D,EAAgB,GAAU,MAC1B,EAAgB,GAAU,aAO3B,aAAa,GAClB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,KAAK,OAAO,GACxB,MAAO,MAAK,YACV,EACA,EAAM,UACN,EAAM,gBAAgB,IAAI,CAAC,CAAC,EAAQ,KAAY,EAAE,SAAQ,mBAKnD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,iBAAgB,GAC3B,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAkB,AAAG,OACzB,IAAM,AAAG,UAAQ,KAAK,aAAa,KAG/B,EAAoB,KAAM,SAAQ,IAAI,EAAgB,IAC1D,MAAO,EAAgB,KACrB,GAAM,GAAiB,MAAM,KAAK,KAAM,GAAe,QACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,GAAO,IACjD,EAAU,EAAe,OAAO,CAAC,EAAG,IAAM,CAAC,GAAO,IAExD,MAAO,IAAI,IACT,MAAM,IAAI,KAAK,GAAG,IAAI,CAAC,EAAG,IAAM,GAAI,GAAM,EAAQ,GAAc,EAAQ,KACxE,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,QAMtC,SAAgB,QAAQ,AAAC,GAAM,EAAE,WAE1B,EAAS,aAAe,EAAyC,EAAkB,GAGlF,2BACR,MAAO,OC9FX,oBAIuC,IACrC,YAAY,EAA6C,GAAI,KAC3D,MAAM,oBAAqB,GAGnB,sBACR,MAAO,yBAGC,0BACR,MAAO,OCdX,OAAoB,OCMb,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,4BACE,GAAkB,EAAW,GAE3B,EAAS,CACb,OAAQ,EAAyB,SAAU,IAC3C,OAAQ,EAAyB,UACjC,OAAQ,EAAyB,WAGnC,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBCnBZ,YAA2B,GAChC,GAAM,GAAgC,GAEhC,CACJ,iBACA,uBACE,EAAsB,GAEpB,CACJ,4BACE,GAAkB,EAAgB,GAEhC,EAAS,EAAyB,EAAG,GAAI,SAAU,IACnD,EAAS,EAAyB,GAAI,GAAI,UAC1C,EAAS,EAAyB,GAAI,IAAK,UAEjD,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,gBACA,OAAQ,CAAE,SAAQ,SAAQ,WF1B9B,oBAU8C,GAC5C,cACE,MAAM,4BAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,0DAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAO,WAEtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,UAAO,MAE7D,EAAM,GAAY,EAAY,EAAO,OAAQ,IACjD,SAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,GAAY,EAAK,EAAO,QAC9B,EAAM,AAAG,WAAQ,EAAK,CAAC,GAAI,IAAK,CAAC,EAAG,GAAI,SAEjC,SAIE,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,IAGlC,sBACR,MAAO,oCAGC,2BAA2B,GACnC,MAAO,IAA+B,GAG9B,cAAc,GACtB,MAAO,IAAkB,KGjD7B,oBAI2C,IACzC,YAAY,EAAiD,GAAI,KAC/D,MAAM,wBAAyB,GAGvB,sBACR,MAAO,8BAGC,0BACR,MAAO,OCdX,oBAIqC,MCJrC,MAAoB,OCApB,OAAoB,OCApB,OAAoB,OAIb,YAAe,EAAgB,GACpC,MAAO,AAAG,QAAI,AAAG,OAAI,EAAG,EAAO,SAAU,EAAO,QDAlD,YACE,EACA,EACA,EACA,EACA,EAA4B,QAE5B,GAAM,CAAE,UAAS,QAAS,EAAO,KAE7B,EAAM,AAAG,UAAO,EAAG,EAAS,EAAS,GACzC,SAAM,AAAG,OAAI,EAAK,GAClB,EAAM,GAAM,EAAK,EAAO,OACjB,EAAW,AAAG,QAAK,GAAO,EAG5B,YAAc,EAAgB,GACnC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAoB,EAAgB,GACzC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,IAG/B,YAAkB,EAAgB,GACvC,MAAO,IAAU,EAAG,EAAQ,CAAC,EAAG,GAAI,GAAM,SE7B5C,MAAoB,OAUpB,YAA2B,EAAwC,GACjE,WAA6B,EAAyB,EAAoB,GACxE,GAAM,GAAU,EAAe,GACzB,EAAQ,EAAQ,OAAU,GAAa,EAAa,GAE1D,GAAI,GAAQ,GACV,KAAM,IAAI,OAAM,+BAA+B,sBAA0B,EAAQ,uBAAuB,kBAA2B,KAGrI,MAAO,AAAG,QACR,IAAM,AAAG,YACP,AAAG,WAAS,EAAS,CAAC,EAAY,EAAO,EAAY,IACrD,CAAC,EAAG,EAAG,EAAG,KAKhB,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAU,EAAoB,EAAiB,EAAY,GAC3D,EAAO,AAAG,WAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,WAGX,CAAE,UAAS,QAGpB,WAAiC,EAAoB,GACnD,GAAM,GAAU,AAAG,WAAS,EAAe,IACrC,EAAS,AAAG,WAAS,EAAe,IAE1C,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,aAGX,CACL,UACA,UAIJ,WACE,EACA,EACA,EACA,GAEA,GAAM,GAAO,EAAkB,EAAiB,EAAY,EAAY,GAAG,UACrE,EAAQ,EAAwB,EAAY,GAAG,WAErD,MAAO,CAAE,OAAM,SAGjB,WACE,EACA,EACA,EACA,EACA,EAAkB,IAElB,GAAM,GAAQ,EAAwB,GAAS,GAAM,GAAK,EAAiB,EAAY,EAAY,GAAG,WAChG,EAAQ,EAAuB,EAAiB,EAAY,EAAY,GAAG,WAEjF,MAAO,CAAE,QAAO,SAGlB,MAAO,CACL,yBACA,8BAIG,YAAuB,GAC5B,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAgB,GAEhC,EAAc,EAAuB,KAAM,GAAI,EAAG,eAClD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YACnD,EAAW,EAA2B,KAAM,GAAI,EAAG,YAEnD,EAAc,EAA2B,MAAO,GAAI,EAAG,cAAe,IACtE,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YACpD,EAAW,EAA2B,MAAO,GAAI,EAAG,YAEpD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aAEvD,EAAe,EAA2B,OAAQ,IAAK,EAAG,eAAgB,IAC1E,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAY,EAA2B,OAAQ,IAAK,EAAG,aACvD,EAAmB,EAA2B,OAAQ,IAAK,EAAG,oBAE9D,EAAK,AAAG,OACZ,IAAM,AAAG,YAAU,AAAG,WAAS,EAAe,IAAM,KAAM,CAAC,IAAK,MAAO,CAAC,EAAG,KAI7E,GAFA,EAAc,KAAK,CAAE,UAAW,OAE5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAsB1E,MAAO,CAAE,OAnBM,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGe,iBChJnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAiC,GAC/B,GAAM,GAAU,EAAmB,GAAG,kBAAwB,GACxD,EAAS,EAAmB,GAAG,iBAAuB,GAE5D,MAAO,CAAE,UAAS,UAGpB,WAAgC,GAC9B,GAAM,GAAU,EAAmB,GAAG,iBAAuB,GACvD,EAAO,EAAmB,GAAG,cAAoB,GACjD,EAAQ,EAAwB,GAEtC,MAAO,CAAE,KAAM,CAAE,UAAS,QAAQ,SAGpC,WAAoC,GAClC,MAAO,CACL,MAAO,EAAuB,GAAG,WACjC,MAAO,EAAuB,GAAG,YAIrC,MAAO,CACL,yBACA,8BAIG,YACL,GAEA,GAAM,GAAgC,GAEhC,CACJ,yBACA,8BACE,GAAkB,EAAW,GAE3B,EAAc,EAAuB,eACrC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAc,EAA2B,eACzC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YACtC,EAAW,EAA2B,YAEtC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aAEvC,EAAe,EAA2B,gBAC1C,EAAY,EAA2B,aACvC,EAAY,EAA2B,aACvC,EAAmB,EAA2B,oBAE9C,CAAE,MAAO,EAGf,GAFA,EAAc,KAAK,CAAE,aAAc,KAAM,UAAW,OAEhD,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yDAAyD,KAG3E,GAAM,GAAS,CACb,cACA,WACA,WACA,WACA,cACA,WACA,WACA,WACA,eACA,YACA,YACA,eACA,YACA,YACA,mBACA,MAGF,SAA2B,EAAW,GAE/B,CAAE,SAAQ,iBC9FnB,MAAoB,OAKb,YAAkB,EAAgB,GACvC,GAAI,GAAM,GAAK,EAAG,EAAO,OACzB,SAAM,GAAW,EAAK,EAAO,OAC7B,EAAM,AAAG,MAAI,EAAK,GAClB,EAAM,AAAG,OAAK,GACP,EAGF,YAAsB,EAAgB,GAC3C,GAAI,GAAM,GAAS,EAAG,EAAO,OAC7B,EAAM,GAAW,EAAK,EAAO,OAE7B,GAAI,GAAS,AAAG,UAAQ,EAAG,EAAG,EAAG,SAC3B,EAAQ,AAAG,QAAkB,EAAO,OACpC,EAAQ,EAAO,MAAM,KAAO,EAAI,MAAM,GAG5C,GAFsB,EAAO,MAAM,KAAO,EAAI,MAAM,IAAM,EAAO,MAAM,KAAO,EAAI,MAAM,IAGtF,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAE/B,GAAM,GAAY,CAAC,GAAG,EAAI,OAC1B,EAAU,GAAK,EACf,GAAM,GAAS,AAAG,QAAkB,GACpC,EAAM,AAAG,SAAO,CAAC,EAAK,GAAS,GAGjC,SAAS,EAAQ,AAAG,SAAO,CAAC,EAAQ,GAAQ,GAAK,EACjD,EAAM,AAAG,MAAI,EAAQ,GAErB,EAAM,AAAG,OAAK,GACP,ELtCT,oBAWwC,GACtC,cACE,MAAM,sBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,oDAGlB,MAAO,AAAG,QAAK,KACb,GAAM,GAAc,AAAG,OAAK,EAAM,cAAc,IAAK,IAAO,WAGtD,EAAa,GAAU,EADb,CAAC,QAAS,QAAS,UACgB,IAAI,AAAG,SAAO,MAE7D,EAAM,GAAS,EAAY,EAAO,aACtC,EAAM,AAAG,UAAQ,EAAK,EAAG,EAAG,SAE5B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,aAC/B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAC3B,EAAM,GAAS,EAAK,EAAO,UAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAE3B,EAAM,GAAa,EAAK,EAAO,cAC/B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAS,EAAK,EAAO,WAC3B,EAAM,GAAa,EAAK,EAAO,kBAE/B,GAAM,GAAY,EAAI,KAAK,CAAC,EAAG,IAG/B,MAFuB,AAAG,UAAO,EAAW,EAAO,WAM1C,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,uBAAsB,GA7DrC,MA8DI,GAAI,oBAAO,QAAP,cAAc,KAAK,AAAC,GAAQ,GAAO,GAAI,MAAO,IAAI,cAAa,KACnE,GAAM,GAAW,KAAM,GAAW,GAC5B,EAAwB,AAAG,OAC/B,IAAM,AAAG,UAAQ,KAAK,aAAa,KAE/B,EAA0B,KAAM,SAAQ,IAAI,EAAsB,IAAI,AAAC,GAAM,EAAE,SACrF,SAAsB,QAAQ,AAAC,GAAM,EAAE,WAChC,EAAS,aAAe,EAA0B,EAAwB,GAGzE,sBACR,MAAO,yBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KM7ElB,YAAkC,GACvC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECHF,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,eCNf,YAAmB,GACxB,MAAO,OAAO,GAAI,KAAQ,SAGrB,YAGL,EACA,GAGA,MAAO,IAAK,KADM,CAAE,QCNf,YAAsB,GAC3B,MAAQ,GAAI,SAAW,GAAO,MAAQ,EAAI,SAAW,GAAO,SACvD,GAAmB,EAAI,mBAGvB,YAGL,EACA,EACA,GAGA,MAAO,IAAK,KADM,CAAE,SAAQ,sBCpB9B,OAAoB,OCApB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,WAAoC,EAAqB,GACvD,GAAM,GAAU,AAAG,YAAS,EAAe,EAAI,EAAI,GAAc,CAAC,EAAG,EAAG,EAAa,IAC/E,EAAmB,AAAG,YAAS,EAAe,IAC9C,EAAoB,AAAG,YAAS,EAAe,IAC/C,EAAkB,AAAG,YAAS,EAAe,IAC7C,EAAsB,AAAG,YAAS,EAAe,IAEvD,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,sBAChB,CAAE,UAAW,GAAG,uBAChB,CAAE,UAAW,GAAG,qBAChB,CAAE,UAAW,GAAG,0BAGX,CACL,UACA,mBACA,oBACA,kBACA,uBAIJ,WACE,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAU,AAAG,YACjB,EAAe,EAAa,EAAc,EAAa,GACvD,CAAC,EAAY,EAAY,EAAY,IAEjC,EAAO,AAAG,YAAS,EAAe,IAExC,SAAc,KACZ,CAAE,UAAW,GAAG,aAChB,CAAE,UAAW,GAAG,KAAgB,EAAkB,oBAAsB,WAGnE,CAAE,UAAS,QAGpB,WACE,EACA,EACA,EACA,GAEA,GAAM,CACJ,UACA,QACE,EAAkB,EAAY,EAAa,EAAY,EAAc,IAEzE,MAAO,CACL,UACA,kBAAmB,GAIvB,WACE,EACA,EACA,GAEA,GAAM,GAAiB,EAA2B,EAAY,GAAG,oBAC3D,EAAiB,EAA2B,EAAY,EAAa,EAAG,GAAG,oBAEjF,MAAO,CAAE,iBAAgB,kBAG3B,aACE,GAAM,GAAS,EAA2B,EAAG,GAAI,EAAG,sBAC9C,EAAS,EAAsB,GAAI,GAAI,sBACvC,EAAS,EAAsB,GAAI,IAAK,sBACxC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAS,EAAsB,IAAK,IAAK,sBACzC,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,IAAK,uBAC1C,EAAU,EAAsB,IAAK,KAAM,uBAC3C,EAAU,EAAsB,KAAM,KAAM,uBAClD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,UACA,UACA,UACA,WAIJ,aACE,GAAM,GAAS,EAA2B,KAAM,IAAK,EAAG,2BAClD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,IAAK,EAAG,2BACjD,EAAS,EAA2B,IAAK,GAAI,EAAG,2BAChD,EAAS,EAA2B,GAAI,IAAK,EAAG,2BAChD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,EAAG,EAAG,oDACjD,EAA2B,EAAkB,KAAM,GAAI,EAAG,2DAC1D,EAAoB,EAAkB,KAAM,GAAI,EAAG,oDACnD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,EAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,EAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDAClD,GAA2B,EAAkB,IAAK,GAAI,EAAG,2DACzD,GAAoB,EAAkB,IAAK,GAAI,EAAG,oDA0BxD,MAAO,CACL,SACA,SACA,SACA,SACA,SACA,SACA,SACA,SACA,gBAjCsB,CACtB,uBAAwB,EACxB,gBAAiB,GAgCjB,gBA9BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA6BjB,gBA3BsB,CACtB,uBAAwB,EACxB,gBAAiB,GA0BjB,gBAxBsB,CACtB,uBAAwB,GACxB,gBAAiB,IAuBjB,gBArBsB,CACtB,uBAAwB,EACxB,gBAAiB,IAoBjB,gBAlBsB,CACtB,uBAAwB,GACxB,gBAAiB,KAoBrB,MAAO,CACL,2BACA,gCAIG,YAAuB,GAC5B,GAAM,GAAgC,GAChC,CACJ,iBACA,uBACE,EAAsB,GACpB,CACJ,2BACA,gCACE,GAAkB,EAAgB,GAChC,EAAc,IACd,EAAmB,IAKnB,EAAe,CACnB,UALgB,AAAG,YACnB,EAAe,KAAO,GACtB,CAAC,EAAG,KAAM,KAMZ,GADA,EAAc,KAAK,CAAE,UAAW,2BAC5B,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAG1E,MAAO,CACL,OAAQ,CACN,cACA,mBACA,gBAEF,iBC9MJ,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAoC,EAAgB,EAAa,GAC/D,GAAM,GAAU,EAAmB,GAAG,YAAiB,sBAAyB,EAAG,GAAG,aAChF,EAAoB,EAAmB,GAAG,YAAiB,oCAAuC,EAAG,GAAG,uBAC9G,MAAO,CAAE,UAAS,qBAGpB,WAA+B,GAC7B,GAAM,GAAe,oBAAoB,IACnC,EAAsB,sBAAsB,cAC5C,EAA4B,GAAG,mBAC/B,EAA4B,GAAG,mBAE/B,EAAU,EAAmB,GAAG,sBAAyC,EAAG,GAAG,aAC/E,EAAmB,EAAmB,GAAG,oBAAuC,EAAG,GAAG,sBACtF,EAAoB,EAAmB,GAAG,mBAAsC,EAAG,GAAG,uBACtF,EAAkB,EAAmB,GAAG,0BAA6C,EAAG,GAAG,qBAC3F,EAAsB,EAAmB,GAAG,8BAAiD,EAAG,GAAG,yBAEzG,MAAO,CACL,eAAgB,CACd,UACA,mBACA,oBACA,kBACA,uBAEF,eAAgB,EAA2B,cAAe,EAAK,IAInE,aACE,MAAO,CACL,OAAQ,EAA2B,cAAe,EAAG,sBACrD,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,OAAQ,EAAsB,GAC9B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,IAC/B,QAAS,EAAsB,KAInC,WAA2B,EAAgB,GACzC,GAAM,GAAU,EAAmB,GAAG,YAAkB,EAAG,GAAG,aACxD,EAAO,EAAmB,GAAG,WAAiB,EAAG,GAAG,UAC1D,MAAO,CAAE,UAAS,QAGpB,WAAmC,GACjC,GAAM,GAAyB,EAC7B,2BAA2B,yBAC3B,kCAAkC,4BAE9B,EAAkB,EACtB,2BAA2B,mBAC3B,kCAAkC,qBAEpC,MAAO,CAAE,yBAAwB,mBAGnC,aACE,MAAO,CACL,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,OAAQ,EAA2B,aAAc,EAAG,2BACpD,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,GAC3C,gBAAiB,EAA0B,IAI/C,MAAO,CACL,2BACA,gCAIG,YACL,GAEA,GAAM,GAAgC,GAChC,CACJ,2BACA,gCACE,GAAkB,EAAW,GAC3B,EAAY,EAAU,oBAE5B,GADA,EAAc,KAAK,CAAE,aAAc,mBAAoB,UAAW,2BAC9D,CAAC,GAAW,GACd,KAAM,IAAI,OAAM,yEAAyE,KAG3F,GAAM,GAAS,CACb,YAAa,IACb,iBAAkB,IAClB,aAAc,CACZ,cAIJ,SAA2B,EAAW,GAC/B,CAAE,SAAQ,iBChInB,OAAoB,OCApB,OAAoB,OAIb,WACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,UAAO,EAAG,EAAO,QAAS,EAAS,QAChD,SAAM,AAAG,OAAI,EAAK,EAAO,mBAClB,AAAG,eAAY,EAAK,EAAG,KDPlC,GAAM,IAAU,qBAEhB,YACE,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,mBAAgB,EAAG,EAAO,QAAS,EAAS,QACzD,SAAM,AAAG,aACP,EACA,EAAO,gBACP,EAAO,oBACP,EAAO,kBACP,EAAO,iBACP,IAEK,AAAG,eAAY,EAAK,EAAG,KAIlC,YAA+B,GAC7B,MAAO,CAAC,EAAG,EAAG,EAAG,IAAI,KAAK,AAAC,GAAQ,IAAQ,GAAY,CAAC,EAAG,GAAK,CAAC,EAAG,GAG/D,YAAqB,EAAgB,GAC1C,MAAO,AAAG,SAAK,KACb,GAAI,GACA,EAAM,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IA4BnD,GAVA,AAhBuB,CACrB,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,OACP,EAAO,QACP,EAAO,QACP,EAAO,QACP,EAAO,SAGM,QAAQ,CAAC,EAAO,KAC7B,GAAM,GAAW,EAAI,EACf,EAAuB,GAAsB,GACnD,EAAM,GAAmB,EAAK,EAAM,eAAgB,GACpD,EAAM,EAAmB,EAAK,EAAM,eAAgB,CAAC,EAAG,IACpD,IAAa,IACf,GAAS,KAIT,IAAW,KACb,KAAM,IAAI,OAAM,iDAGlB,MAAO,CACL,MACA,OAAQ,KEjEd,YAAa,EAAoB,EAAW,GAC1C,GAAM,GAAY,EAAM,YAClB,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAQ,KAAK,IAAI,EAAU,GAAG,GAAI,EAAU,GAAG,IAC/C,EAAS,GAAQ,GAAU,GAAQ,GACnC,EAAS,GAAQ,GAAU,GAAQ,GACzC,GAAI,GAAS,GAAK,GAAS,EACzB,MAAO,GAET,GAAM,GAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAO,GACnC,EAAmB,KAAK,IAAI,EAAmB,EAAkB,GACjE,KAAK,IAAI,EAAmB,EAAkB,GACpD,MAAO,GAAoB,GAAQ,EAAQ,GAGtC,YACL,EACA,EACA,EACA,EACA,GAEA,GAAM,GAAW,EAAM,MAAM,GACvB,EAAa,KAAK,IACtB,EACA,GAGI,EAAa,EAChB,IAAI,CAAC,EAAO,IAAc,EAAE,QAAO,cACnC,OAAO,AAAC,GAAM,EAAE,MAAQ,GACxB,KAAK,CAAC,EAAI,IAAO,EAAG,MAAQ,EAAG,OAE5B,EAAe,AAAC,GAAe,GAAK,EAAe,EAAI,EACvD,EAAqB,GAE3B,SAAW,QAAQ,AAAC,IAClB,GAAI,EAAS,QAAU,EAAY,OACnC,GAAM,GAAgB,EAAE,MACxB,OAAS,GAAI,EAAS,OAAS,EAAG,GAAK,EAAG,EAAE,GAC1C,GAAM,GAAM,GAAI,EAAO,EAAE,SAAU,EAAS,IAC5C,GAAI,IAAQ,GACZ,GAAE,OAAS,EAAa,GACpB,EAAE,OAAS,GAAgB,MAEjC,AAAI,IAAkB,EAAE,OACtB,EAAS,KAAK,EAAE,YAGb,EC5DT,MAAoB,OAIpB,YAA2C,GACzC,GAAM,GAAM,AAAG,UAAQ,AAAG,YAAU,EAAG,CAAC,EAAG,KAErC,EAAQ,CACZ,AAAG,MAAI,EAAI,GAAI,EAAI,IACnB,AAAG,MAAI,EAAI,GAAI,EAAI,KAEf,EAAU,CACd,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,KAC1C,AAAG,MAAI,EAAI,GAAI,AAAG,MAAI,EAAM,GAAI,AAAG,SAAO,MAE5C,MAAO,CACL,QACA,WAIJ,YAA0B,EAAiB,GACzC,GAAM,CACJ,QACA,WACE,GAAkC,GAEhC,EAAM,AAAG,UAAQ,AAAG,YAAU,EAAI,CAAC,EAAG,KACtC,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAC3E,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,AAAG,SAAO,IACpF,EAAW,AAAG,MAAI,AAAG,MAAI,AAAG,MAAI,EAAI,GAAI,AAAG,SAAO,KAAM,EAAM,IAAK,EAAQ,IAEjF,MAAO,AAAG,aACR,AAAG,QAAM,CACP,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,GACjB,AAAG,MAAI,EAAU,KAEnB,CAAC,EAAG,IAID,YACL,EACA,EACA,GAEA,MAAO,AAAG,QAAK,KACb,GAAM,GAAY,EAAe,MAAM,GAEnC,EAAQ,GACV,AAAG,UAAQ,AAAG,OAAK,EAAO,UAAW,CAAC,EAAW,EAAG,IAAK,CAAC,GAAI,IAC9D,AAAG,UAAQ,EAAgB,CAAC,GAAI,KAElC,EAAQ,AAAG,UACT,EACA,CAAC,EAAY,EAAM,MAAM,GAAK,EAAY,IAG5C,GAAM,GAAmB,AAAG,UAAQ,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,MAC/E,EAAS,AAAG,QAAM,EAAkB,CAAC,EAAG,EAAG,GAAI,CAAC,GAAI,GAAI,IAE5D,EAAS,AAAG,UACV,EACA,CAAC,EAAW,EAAO,MAAM,KAG3B,GAAM,GAAe,AAAG,UAAQ,GAC1B,EAAgB,AAAG,UAAQ,GAEjC,MAAO,CACL,MAAO,EACP,OAAQ,KC1Ed,OAAoB,OCApB,OAAoB,OAKb,YACL,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAY,EAAE,MAAM,GACpB,EAAwB,AAAG,WAC/B,GAAU,EAAG,EAAO,wBACpB,CAAC,EAAW,GAAI,EAAG,IAEf,EAAkB,AAAG,WACzB,GAAU,EAAG,EAAO,iBACpB,CAAC,EAAW,GAAI,IAElB,MAAO,CAAE,wBAAuB,qBDb7B,YACL,EACA,EACA,GAEA,MAAO,AAAG,SAAK,KACb,GAAM,GAAQ,EAAmB,EAAG,EAAO,OAAQ,CAAC,EAAG,IACjD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IACrD,EAAQ,EAAmB,EAAO,EAAO,OAAQ,CAAC,EAAG,IAErD,EAAiB,GAAmB,EAAQ,EAAO,iBACnD,EAAiB,GAAmB,EAAG,EAAO,iBAC9C,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAClD,EAAiB,GAAmB,EAAO,EAAO,iBAElD,EAAiB,AAAG,UAAO,CAC/B,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,sBACf,EAAe,uBACd,GAEG,EAAmB,AAAG,UAAO,CACjC,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,gBACf,EAAe,iBACd,GAEH,MAAO,CACL,iBACA,sBEhDN,YAYE,YAAY,CAAE,gBAAe,cAAuC,IAN1D,WAAgB,wBAUxB,GAHA,KAAK,eAAiB,GAAiB,GACvC,KAAK,YAAc,GAAc,IAE7B,MAAO,MAAK,gBAAmB,UAAY,KAAK,gBAAkB,GAAK,KAAK,gBAAkB,EAChG,KAAM,IAAI,OAAM,GAAG,KAAK,iEAG1B,GAAI,MAAO,MAAK,aAAgB,SAC9B,KAAM,IAAI,OAAM,GAAG,KAAK,iDAIxB,iBAA0B,MAAO,MAAK,kBAEtC,cAAuB,MAAO,MAAK,cT3BzC,oBAeoC,GAClC,cACE,MAAM,kBAGD,aAAa,GAClB,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,gDAGlB,MAAO,AAAG,SAAK,KACb,GAAM,GAAc,AAAG,QAAK,EAAM,cAAc,IAAK,IAAQ,WACvD,EAAI,AAAG,OAAI,AAAG,OAAI,EAAa,AAAG,UAAO,sBAAwB,AAAG,UAAO,IAC3E,EAAW,GAAY,EAAG,EAAO,aAEjC,CACJ,iBACA,oBACE,GAAgB,EAAS,IAAK,EAAS,OAAQ,EAAO,kBAE1D,MAAO,IAAY,EAAgB,EAAkB,EAAO,qBAInD,SAAQ,GACnB,MAAO,MAAK,aAAa,KAAM,GAAW,SAG/B,aACX,EACA,EAAkC,IAElC,GAAM,CAAE,aAAY,iBAAkB,GAAI,GAAsB,GAE1D,EAAW,KAAM,GAAW,GAE5B,CACJ,MAAO,EACP,OAAQ,GACN,KAAK,aAAa,GAEhB,EAAQ,EAAO,GACf,EAAS,EAAQ,GACvB,OAAS,GAAI,EAAG,EAAI,EAAO,OAAQ,IACjC,EAAO,GAAG,UACV,EAAQ,GAAG,UAGb,GAAM,GAAa,MAAM,KAAK,KAAM,GAAO,QAErC,EAAU,GACd,EACA,EACA,EAJmB,GAMnB,GAGI,EAAe,EAAS,2BAA2B,GACnD,EAAY,EAAS,UACrB,EAAO,EAAY,EAAa,MAChC,EAAO,EAAY,EAAa,OAEhC,EAAY,EAAM,YAClB,EAAU,EACb,IAAI,AAAC,IACJ,GAAM,CAAC,EAAK,GAAU,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACf,CAAC,GAAM,IAAS,CACpB,KAAK,IAAI,EAAG,EAAU,GAAK,IAC3B,KAAK,IAAI,EAAK,EAAU,GAAK,KAC7B,IAAI,AAAC,GAAQ,EAAM,GACrB,MAAO,IAAI,GACT,EAAW,GACX,GAAI,IACF,GACA,EACA,GAAQ,GACR,EAAS,GAEX,CACE,OAAQ,EAAS,eAAe,GAChC,MAAO,EAAS,cAAc,OAKtC,SAAM,UACN,EAAO,UACA,EAGC,sBACR,MAAO,wBAGC,2BAA2B,GACnC,MAAO,IAA2B,GAG1B,cAAc,GACtB,MAAO,IAAc,KUnHlB,YAA8B,GACnC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,EAGF,YAAgC,GACrC,MAAO,IAAqB,GAZ9B,oBAgBsC,MCd/B,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,QAAU,SACpB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,QAAS,SACnB,GAAI,GAAM,OAAQ,SAClB,GAAI,GAAM,QAAS,UAGR,GAAwB,CACnC,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAA+C,CAAC,QAAS,QAAS,QAElE,GAAqB,oBACrB,GAAoC,mCCvBjD,MAAoB,OCapB,GAAM,IAAW,AAAC,GAAa,MAAO,IAAQ,SAEvC,YAAwB,GAC7B,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,mBAAmB,KAGrC,GAAI,MAAO,GAAO,oBAAuB,UACvC,KAAM,IAAI,OAAM,wDAAwD,EAAO,sBAGjF,GAAI,CAAC,GAAS,EAAO,eAAiB,EAAO,aAAe,GAAK,EAAO,aAAe,EACrF,KAAM,IAAI,OAAM,gEAAgE,EAAO,gBAGzF,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,MAAM,AAAC,GAAW,MAAO,IAAM,UAElD,KAAM,IAAI,OAAM,kEAAkE,KAAK,UAAU,EAAO,YAG1G,GACE,CAAC,MAAM,QAAQ,EAAO,UACnB,CAAC,EAAO,QAAQ,QAChB,CAAC,EAAO,QAAQ,IAAI,AAAC,GAAW,GAAK,IAAI,MAAM,AAAC,GAAW,GAAS,EAAE,IAAM,GAAS,EAAE,IAE1F,KAAM,IAAI,OAAM,wEAAwE,KAAK,UAAU,EAAO,YAGhH,GAAI,EAAO,SACT,EAAC,MAAM,QAAQ,EAAO,UACnB,EAAO,QAAQ,SAAW,GAC1B,CAAC,EAAO,QAAQ,MAAM,KAEzB,KAAM,IAAI,OAAM,8EAA8E,KAAK,UAAU,EAAO,YCjDxH,MAAoB,OCApB,MAAoB,OAEb,YAAe,GACpB,MAAO,AAAG,QAAK,KACb,GAAM,GAAM,AAAG,MAAI,EAAG,AAAG,SAAO,qBAChC,MAAO,AAAG,OAAI,AAAG,OAAK,AAAG,MAAI,EAAG,IAAO,KDApC,YAA2B,EAAgB,GAChD,MAAO,AAAG,QAAK,KACb,GAAI,GAAM,AAAG,MAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KACjD,SAAM,AAAG,SAAO,EAAK,EAAO,KAAK,QAAS,CAAC,EAAG,GAAI,SAClD,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,KAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,GAAG,SAC5B,EAAM,AAAG,MAAI,EAAK,EAAO,KAAK,MACvB,GAAM,KEZjB,OAAoB,OAKb,YAAgC,EAAgB,GACrD,MAAO,AAAG,SAAK,KACb,GAAI,GAAM,AAAG,OAAI,EAAG,CAAC,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,CAAC,EAAG,KACjD,SAAM,AAAG,mBAAgB,EAAK,EAAO,iBAAkB,EAAO,iBAAkB,CAAC,EAAG,GAAI,SACxF,EAAM,AAAG,OAAI,EAAK,EAAO,MAClB,GAAM,KCVjB,OAAoB,OASpB,YAA2B,EAAwC,GACjE,GAAM,GAAoB,GAAyB,EAAgB,GAEnE,WAAgC,EAAc,GAC5C,GAAM,GAAM,AAAG,YAAS,EAAe,IACjC,EAAU,AAAG,YAAS,EAAe,IAE3C,SAAc,KACZ,CAAE,UAAW,GAAG,SAChB,CAAE,UAAW,GAAG,cAEX,CAAE,MAAK,WAGhB,WAAwC,EAAoB,EAAqB,GAC/E,GAAM,GAAO,EAAkB,EAAY,EAAa,EAAG,GAAG,UACxD,EAAK,EAAuB,EAAa,GAAG,QAClD,MAAO,CAAE,OAAM,MAEjB,GAAM,GAA6B,GAAkC,EAAgB,GAErF,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,EACA,EACA,GAEA,GAAM,CACJ,iBACA,uBACE,EAAsB,GAEpB,EAAgC,GAChC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAgB,GAClC,EAEJ,GAAI,EAAO,oBACT,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAAO,mBACjB,EAAkB,EAAI,EAAI,EAAG,SAC7B,EAA2B,EAAI,EAAI,SACjC,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,EAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAA2B,EAAI,EAAI,SAC3C,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAK,EAA2B,EAAI,EAAI,SAAW,OAC3D,GAAQ,EAAkB,GAAM,GAAM,EAAI,EAAI,EAAiB,EAAG,SACxE,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,eAG1D,GAAM,CAAC,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,EAAI,GAAM,EACvC,EAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,EAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAA+B,EAAI,EAAI,SAC/C,GAAQ,EAAkB,EAAI,EAAI,EAAiB,EAAG,SAC5D,EAAS,CACP,QAAO,QAAO,SAAO,SAAO,QAAO,SAAO,SAAO,SAAO,UAG5D,GAAI,IAAsB,SAAW,EACnC,KAAM,IAAI,OAAM,kCAAkC,IAAsB,UAE1E,MAAO,CAAE,SAAQ,iBChFnB,YAA2B,EAAgB,GACzC,GAAM,GAAqB,EAA0B,EAAW,GAEhE,WAAgC,GAC9B,GAAM,GAAM,EAAmB,GAAG,QAAc,GAC1C,EAAU,EAAmB,GAAG,YAAkB,GACxD,MAAO,CAAE,MAAK,WAGhB,WAA2B,GACzB,GAAM,GAAU,EAAmB,GAAG,YAAkB,GAClD,EAAO,EAAmB,GAAG,SAAe,GAClD,MAAO,CAAE,UAAS,QAGpB,WAAwC,GACtC,GAAM,GAAO,EAAkB,GAAG,UAC5B,EAAK,EAAuB,GAAG,QACrC,MAAO,CAAE,OAAM,MAGjB,GAAM,GAA6B,GAA+B,GAClE,MAAO,CACL,oBACA,iCACA,8BAIG,YACL,EACA,GAEA,GAAM,GAAgC,GAEhC,CACJ,oBACA,iCACA,8BACE,GAAkB,EAAW,GAE7B,EAEJ,GAAI,EAAO,oBAET,GAAM,GAAc,EAAO,aAAe,EAAO,YAAY,QAAU,EACvE,EAAS,CACP,MAAO,EAAO,mBAAqB,EAAkB,SAAW,EAA2B,SAC3F,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAA2B,SAClC,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAa,EAAI,EAA2B,SAAW,OAC9D,MAAO,EAAkB,cAG3B,GAAS,CACP,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAA+B,SACtC,MAAO,EAAkB,UAI7B,SAA2B,EAAW,GAC/B,CAAE,SAAQ,iBClFnB,aAYE,YAAY,CAAE,YAAW,kBAAuC,IANtD,WAAgB,oBAUxB,GAHA,KAAK,WAAa,GAAa,IAC/B,KAAK,gBAAkB,GAAkB,GAErC,MAAO,MAAK,YAAe,UAAY,KAAK,WAAa,IAAO,EAClE,KAAM,IAAI,OAAM,GAAG,KAAK,6DAG1B,GAAI,MAAO,MAAK,iBAAoB,UAAY,KAAK,iBAAmB,GAAK,KAAK,iBAAmB,EACnG,KAAM,IAAI,OAAM,GAAG,KAAK,qEAIxB,aAAsB,MAAO,MAAK,cAElC,kBAA2B,MAAO,MAAK,kBP3B7C,oBAuBoC,GAKlC,YAAY,GACV,MAAM,cACN,GAAe,GACf,KAAK,QAAU,KAGN,UACT,MAAO,MAAK,WAGH,mBACT,MAAO,MAAK,OAAO,iBAAmB,KAAK,OAAO,QAAQ,OAAS,KAG1D,mBACT,MAAO,GAAK,MAAK,gBAAkB,KAAK,OAAO,QAAQ,OAAS,GAG3D,cAAc,EAAgB,GACnC,GAAI,GAAM,GAAkB,EAAG,EAAO,OACtC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAkB,EAAK,EAAO,OACpC,EAAM,GAAkB,EAAK,EAAO,OAC7B,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAgB,GAClC,GAAI,GAAM,KAAK,OAAO,mBAClB,GAAM,GAAU,EAAG,EAAO,MAAqB,QAAS,KACxD,GAAuB,EAAG,EAAO,OACrC,SAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,GAAuB,EAAK,EAAO,OACzC,EAAM,AAAG,UAAQ,EAAK,CAAC,EAAG,GAAI,CAAC,EAAG,GAAI,QACtC,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EACjE,EAAM,EAAO,MAAQ,GAAuB,EAAK,EAAO,OAAS,EAC1D,GAAU,EAAK,EAAO,MAAO,QAAS,IAGxC,aAAa,EAAiB,GACnC,GAAM,CAAE,UAAW,KAEnB,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,4CAGlB,MAAO,AAAG,QAAK,KACb,GAAI,GAAc,AAAG,OAAK,EAAM,cAAc,EAAW,IAAQ,WACjE,SAAc,KAAK,OAAO,QACtB,GAAU,EAAa,KAAK,OAAO,SACnC,EACJ,EAAc,EAAY,IAAI,AAAG,SAAO,MACjC,KAAK,OAAO,mBACf,KAAK,aAAa,EAAa,GAC/B,KAAK,cAAc,EAAa,UAI3B,SAAQ,EAAkB,GACrC,MAAO,MAAK,aAAa,KAAM,GAAW,GAAQ,QAGvC,QAAO,EAAkB,EAAoC,IACxE,GAAM,CAAE,YAAW,kBAAmB,GAAI,IAAkB,GACtD,EAAW,KAAM,GAAW,GAC5B,EAAM,KAAM,MAAK,aAAa,EAAU,GACxC,EAAO,AAAG,OAAK,IAAM,AAAG,UAAQ,GAAK,GAAG,cACxC,EAAkB,CACtB,MAAO,EAAS,cAAc,GAC9B,OAAQ,EAAS,eAAe,IAG5B,EAAU,KAAM,MAAK,aAAa,EAAM,EAAS,2BAA2B,GAAI,GACtF,EAAI,UACJ,EAAK,UAEL,GAAM,GAAQ,EAAQ,IAAI,AAAC,GAAQ,EAAI,KACjC,EAAS,EAAQ,IAAI,AAAC,GAAQ,EAAI,OAClC,EAAc,EAAQ,IAAI,AAAC,GAAQ,EAAI,YACvC,EAAa,EAAQ,IAAI,AAAC,GAAQ,KAAK,OAAO,QAAQ,EAAI,QAgBhE,MAPmB,AAPH,IACd,EAAM,IAAI,AAAC,GAAQ,EAAI,QAAQ,IAC/B,EACA,KAAK,OAAO,aACZ,IAGyB,IAAI,AAAC,GAAQ,GAAI,IAC1C,EAAO,GACP,EAAY,GACZ,EAAW,GACX,EAAM,GACN,IAKM,sBACR,MAAO,GAGC,2BAA2B,GACnC,MAAO,IAA2B,EAAW,KAAK,QAG1C,cAAc,GACtB,GAAM,GAAc,KAAK,OAAO,aAAe,GAAe,qBAExD,EAAa,EAAc,EAAY,OAAS,OACtD,GAAI,IAAe,GAAK,IAAe,GAAK,IAAe,EACzD,KAAM,IAAI,OAAM,oEAAoE,2BAEtF,MAAO,IAAc,EAAS,KAAK,OAAQ,KAAK,gBAAiB,QAGnD,cACd,EACA,EACA,GAEA,GAAM,CAAE,QAAO,UAAW,EACpB,EAAY,KAAK,IAAI,EAAO,GAC5B,EAAoB,EAAY,EAChC,EAAoB,EAAY,EAEhC,EAAW,EAAa,MAAM,GAC9B,EAAW,KAAK,OAAO,QAAQ,OAE/B,CAAC,EAAa,EAAc,GAAqB,AAAG,OAAK,KAC7D,GAAM,GAAW,EAAa,QAAQ,CAAC,EAAU,EAAU,EAAU,KAAK,kBAEpE,EAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACpE,EAAS,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,IACrE,EAAc,KAAK,gBACrB,AAAG,UAAQ,EAAS,MAAM,CAAC,EAAG,EAAG,EAAG,GAAI,CAAC,EAAU,EAAU,EAAU,KAAK,OAAO,QAAQ,SAAU,GACrG,AAAG,SAAO,GACd,MAAO,CAAC,EAAO,EAAQ,KAGnB,EAAU,GACV,EAAa,KAAM,GAAa,QAChC,EAAY,KAAM,GAAY,QACpC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAM,EAAG,EAAM,EAAU,IAChC,OAAS,GAAS,EAAG,EAAS,EAAU,KACtC,GAAM,GAAQ,GAAQ,EAAW,GAAK,GAAK,GAAQ,IACnD,GAAI,CAAC,GAAkB,EAAQ,GAC7B,GAAM,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAQ,GAAM,GAAQ,EAAU,GAAK,GAAK,GAAQ,KAAO,EAAY,EACrE,GAAe,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACvG,EAAgB,KAAK,IAAI,EAAU,GAAK,GAAK,GAAQ,IAAM,KAAK,OAAO,QAAQ,GAAQ,EAAK,EAAY,EACxG,GAAK,EAAO,GAAa,EACzB,GAAK,GAAO,EAAc,EAC1B,GAAM,CAAE,MAAK,MAAK,UAClB,CAAE,cAAY,UAAU,KAAK,gBAC/B,KAAM,MAAK,sBAAsB,EAAkC,IACnE,CAAE,WAAY,EAAG,MAAO,GAC5B,EAAQ,KAAK,CACX,IAAK,GAAI,IAAY,GAAG,GAAG,GAAI,GAAY,GAAI,GAC/C,QACA,WAAY,EAAQ,GACpB,YACG,MAOb,SAAY,UACZ,EAAa,UACb,EAAkB,UACX,OAGK,uBAAsB,EAA4B,GAC9D,GAAM,CAAE,MAAK,MAAK,UAAW,EACvB,EAAc,KAAM,GAAc,QACxC,MAAO,OAAM,KAAK,OAAO,QAAQ,QAAQ,KAAK,GAC3C,IAAI,CAAC,EAAG,IAAM,EAAY,GAAK,GAAK,GAAQ,IAC5C,IAAI,CAAC,EAAY,IAAW,EAC3B,aACA,WAED,OAAO,CAAC,EAAK,IAAU,EAAI,WAAa,EAAK,WAAa,EAAM,KAtOvE,MAwBgB,AAxBhB,GAwBgB,qBAAuB,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,IAAK,KAAM,MQxB5E,oBAiBgC,IAC9B,YAAY,EAA8B,IACxC,GAAM,GAAS,CACb,qBACA,aAAc,GACd,QAAS,CAAC,WACN,EACA,CACA,QAAS,GACT,QAAS,IAET,CACA,QAAS,GACT,gBAAiB,KAIvB,MAAM,MAGG,sBACT,MAAO,MAAK,OAAO,sBAGV,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,MAAK,mBAAqB,GAAoC,GAG7D,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KChDrC,YAA0B,EAAuB,EAA8B,IACpF,GAAM,GAAM,GAAI,IAAW,GAC3B,SAAI,eAAe,GACZ,ECVT,oBAI6C,IAJ7C,kCAKY,WAAgB,4BCL5B,kBACe,MAEX,GAEA,MAAO,GAAY,KAAM,MAAK,YAGnB,OACX,KAAM,IAAI,OAAM,6CCRpB,OAAoB,OCDpB,OAAoB,OAOpB,kBACE,EACA,EAEA,EACA,EAEA,EAAwF,CAAC,CAAE,iBAAkB,GAE7G,GAAM,GAAY,EAAc,IAAI,AAAC,GAAkB,GAAoB,GACvE,EAAoB,GACpB,EAAa,WACX,EAAgD,GACpD,aAAoB,WAChB,KAAM,IAAmB,EAAO,GAChC,KAAM,IAAa,EAAO,IAG1B,EAAU,KAAM,GAAe,GAErC,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAGT,kBACE,EACA,EAEA,EACA,EAEA,GAEA,MAAO,IACL,CAAC,GACD,EACA,KAAO,IAAU,EAAc,EAAM,IACrC,EACA,GC5CG,GAAM,IAAgB,GAEhB,GAAc,CACzB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,UACpB,GAAI,GAAM,SAAU,WAGT,GAAqC,CAAC,QAAS,QAAS,QCZrE,oBAUsC,IACpC,cACE,GAAM,GAAS,CACb,mBAAoB,GACpB,aAAc,GACd,QAAS,CAAC,QACV,QAAS,GACT,QAAS,GACT,mBAAoB,GACpB,YAAa,CAAC,EAAG,GAAI,GAAI,GAAI,IAAK,IAAK,MAGzC,MAAM,MAGG,WACT,MAAO,MAAK,OAAO,aAGR,aAAY,EAAkB,GAEzC,MAAO,AADkB,MAAM,MAAK,OAAO,EAAO,IAC1B,IAAI,AAAC,GAAQ,GAAI,GAAc,EAAI,MAAO,EAAI,YAAa,CAAE,MAAO,EAAI,WAAY,OAAQ,EAAI,eAGhH,sBACR,MAAO,2BAGC,2BAA2B,GACnC,MAAO,OAAM,2BAA2B,KCvBrC,GAAM,GAAO,CAClB,eAAgB,GAAI,IACpB,iBAAkB,GAAI,IACtB,WAAY,GAAI,IAChB,kBAAmB,GAAI,IACvB,sBAAuB,GAAI,IAC3B,mBAAoB,GAAI,IACxB,kBAAmB,GAAI,IACvB,aAAc,GAAI,KAUP,GAAiB,CAAC,EAAkB,IAA6D,EAAK,eAAe,YAAY,EAAO,GASxI,GAAmB,CAAC,EAAkB,IAA+D,EAAK,iBAAiB,YAAY,EAAO,GAS9I,GAAa,CAAC,EAAkB,IAA0D,EAAK,WAAW,YAAY,EAAO,GAS7H,GAAsB,AAAC,GAAmE,EAAK,kBAAkB,gBAAgB,GAWjI,GAA0B,AAAC,GAAmE,EAAK,sBAAsB,gBAAgB,GAYzI,GAAwB,AAAC,GAA6D,EAAK,mBAAmB,sBAAsB,GASpI,GAA2B,AAAC,GAAmE,EAAK,kBAAkB,mBAAmB,GASzI,GAAsB,AAAC,GAAiF,EAAK,aAAa,oBAAoB,GAE9I,GAA0B,AAAC,GAAgB,EAAK,eAAe,KAAK,GACpE,GAA4B,AAAC,GAAgB,EAAK,iBAAiB,KAAK,GACxE,GAAsB,AAAC,GAAgB,EAAK,WAAW,KAAK,GAC5D,GAAwB,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACrE,GAA4B,AAAC,GAAgB,EAAK,sBAAsB,KAAK,GAC7E,GAA2B,AAAC,GAAgB,EAAK,mBAAmB,KAAK,GACzE,GAA0B,AAAC,GAAgB,EAAK,kBAAkB,KAAK,GACvE,GAAqB,AAAC,GAAgB,EAAK,aAAa,KAAK,GAG7D,GAAyB,GACzB,GAAc,GACd,GAAkB,GCpH/B,oBAmB4E,IAC1E,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA1Bd,gBAkCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAwB,KAAM,IAClC,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,KAEtD,KAAK,gBAGP,MAAO,GAAc,IACnB,CAAC,EAAc,IAAM,GAAmC,EAAc,EAAsB,KAIhG,mBACE,MAAO,IAAI,IAA2B,KAAM,KAAK,SArDrD,gBA2DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,GAAkB,KAAM,IAC5B,EACA,KAAK,MACL,AAAC,GAAS,EAAK,kBAAkB,mBAAmB,GACpD,KAAK,gBAGP,MAAO,IAA0B,EAAc,GAGjD,mBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA7ExD,gBAmFU,IACR,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAzFxD,gBA+FU,IACR,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCrG1D,oBAoByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,wBA3Bd,gBAmCU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAE3B,EAAqB,KAAM,IAC/B,EACA,KAAK,MACL,KAAO,IAAU,QAAQ,IAAI,EAAM,IACjC,AAAC,GAAS,EAAK,aAAa,oBAAoB,KAElD,KAAK,gBAGP,MAAO,GAAc,IAAI,CAAC,EAAc,KACtC,GAAM,CAAE,MAAK,SAAQ,qBAAsB,EAAmB,GAC9D,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,KAIpF,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SAvDxD,gBA6DU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,MAAK,SAAQ,qBAAsB,KAAM,IAC/C,EACA,KAAK,MACL,AAAC,GAAS,EAAK,aAAa,oBAAoB,GAChD,KAAK,gBAGP,MAAO,IAAc,GAAiB,EAAc,EAAQ,GAAoB,GAGlF,sBACE,MAAO,IAAI,IAAiC,KAAM,KAAK,SA/E3D,gBAqFU,IACR,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SA3FxD,gBAiGU,IACR,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SCvG1D,oBAiB4E,IAC1E,YAEY,EAEA,GAEV,QAJU,kBAEA,eAtBd,gBA8BU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAUjC,MAAO,AARa,MAAM,IACxB,EACA,KAAK,MACL,AAAC,GAAU,QAAQ,IAAI,EAAM,IAAI,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,KACzF,KACA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,OAGxD,IAAI,CAAC,EAAY,IAAM,GAAkC,EAAc,GAAI,IAGhG,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,SAlDtE,gBAwDU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAEF,GAAM,GAAa,KAAM,IACvB,EACA,KAAK,MACL,AAAC,GAAS,EAAK,mBAAmB,sBAAsB,GACxD,KAEA,AAAC,GAAiB,EAAa,UAAU,MAAM,KAAM,CAAE,iBAAkB,MAG3E,MAAO,IAAyB,EAAc,GAGhD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,SP/EzE,oBAqByE,IACvE,YAEY,EAEA,EAEA,GAEV,QANU,kBAEA,aAEA,6BAKE,eACZ,MAAO,MAAK,mBACR,EAAK,sBACL,EAAK,oBApCb,gBA0CU,SACK,OACX,GAAM,GAAgB,KAAM,MAAK,WAC3B,EAAa,EAAc,IAAI,AAAC,GAAQ,EAAI,WAE5C,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,GACrC,KAAM,IAAa,KAAK,MAAO,GAE7B,EAAsB,KAAM,SAAQ,IAAI,EAAM,IAClD,AAAC,GAAS,KAAK,YAAY,gBAAgB,KAG7C,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,EAAc,IAAI,CAAC,EAAc,IAAM,GAAiC,EAAc,EAAoB,KAGnH,sBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,mBACE,MAAO,IAAI,IAA4C,KAAM,KAAK,OAGpE,sBACE,MAAO,IAAI,IAA8B,KAAM,KAAK,SArExD,gBA2EU,SACK,OACX,GAAM,GAAe,KAAM,MAAK,WAChC,GAAI,CAAC,EACH,OAGF,GAAM,CAAE,aAAc,EAChB,EAAgD,KAAK,gBAAoB,WAC3E,KAAM,IAAmB,KAAK,MAAO,CAAC,IACtC,KAAM,IAAa,KAAK,MAAO,CAAC,IAE9B,EAAY,KAAM,MAAK,YAAY,gBAAgB,EAAM,IAE/D,SAAM,QAAQ,AAAC,GAAM,YAAgB,YAAU,EAAE,WAE1C,GAAiC,EAAc,GAGxD,sBACE,MAAO,IAAI,IAAkD,KAAM,KAAK,OAG1E,mBACE,MAAO,IAAI,IAA+C,KAAM,KAAK,OAGvE,qBACE,MAAO,IAAI,IAAgC,KAAM,KAAK,SQvG1D,oBAckD,IAChD,YAEY,EAEA,EAAgC,GAAI,IAE9C,QAJU,aAEA,iBAnBd,gBAyBwC,SACzB,OACX,GAAM,CAAE,QAAO,WAAY,KAGrB,EAAwB,YAAmB,IAE7C,AAAC,GAAqB,EAAK,iBAAiB,YAAY,EAAO,GAG/D,YAAmB,GAEf,AAAC,GAAqB,EAAK,eAAe,YAAY,EAAO,GAE7D,YAAmB,IAEf,AAAC,GAAqB,EAAK,WAAW,YAAY,EAAO,GACzD,KAIZ,GAAI,CAAC,EACH,KAAM,IAAI,OAAM,uIAGlB,MAAO,GAAsB,GAGvB,iCAEN,MAAO,IAAI,SAAiC,KAAO,KACjD,GAAM,GAAa,KAAM,MAAK,MAC9B,EAAQ,EAAW,IAAI,AAAC,GAAc,GAAwB,GAAI,OAItE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,iCACL,KAAK,SA/EX,gBAoF0C,SAC3B,OACX,GAAM,GAAiB,KAAM,IAAI,IAAmB,KAAK,MAAO,KAAK,SACjE,EAAgC,EAAe,GACnD,SAAe,QAAQ,AAAC,IACtB,AAAI,EAAc,MAAQ,EAA8B,OACtD,GAAgC,KAG7B,EAGD,gCAEN,MAAO,IAAI,SAA2C,KAAO,KAC3D,GAAM,GAAY,KAAM,MAAK,MAC7B,EAAQ,EAAY,GAA4B,GAAI,GAAa,UAIrE,kBAAkB,EAA8B,IAC9C,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,MACL,GAIJ,sBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,OAIT,mBACE,MAAO,IAAI,IACT,KAAK,gCACL,KAAK,SCrHJ,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAqB,EAAO,GAGlC,YACL,EACA,EAAgC,GAAI,IAEpC,MAAO,IAAI,IAAmB,EAAO,GCRvC,kBACE,EACA,GAEA,MAAO,IAAe,EAAO,GAAI,GAAsB,EAAgB,CAAE,iBAAkB,KACxF,oBACA,sBAGL,kBACE,EACA,EAAoC,IAEpC,MAAO,IAAe,EAAO,GAAI,IAAkB,IAChD,oBACA,sBAGE,GAAM,IAAW,GC1BjB,YAA2B,EAA+B,GAC/D,GAAI,EAAK,SAAW,EAAK,OAAQ,KAAM,IAAI,OAAM,kDAEjD,GAAM,GAAQ,MAAM,KAAK,GACnB,EAAQ,MAAM,KAAK,GAEzB,MAAO,MAAK,KACV,EACG,IAAI,CAAC,EAAK,IAAM,EAAM,EAAM,IAC5B,OAAO,CAAC,EAAK,IAAS,EAAO,GAAQ,EAAI,ICThD,aAUE,YACE,EACA,EAA4B,IAE5B,KAAK,mBAAqB,EAE1B,GAAM,GAAa,MAAM,QAAQ,GAAU,EAAS,CAAC,GAErD,GAAI,CAAC,EAAW,OACd,KAAM,IAAI,OAAM,2DAGlB,GAAI,GAAQ,EACN,EAAoB,IAAM,UAAU,MAE1C,KAAK,oBAAsB,EAAW,IAAI,AAAC,IACzC,GAAI,YAAgB,IAClB,MAAO,GAGT,GAAI,YAAgB,cAClB,MAAO,IAAI,IAAuB,IAAqB,CAAC,IAG1D,GAAI,EAAK,YAAc,EAAK,qBAAsB,cAChD,MAAO,IAAI,IAAuB,IAAqB,CAAC,EAAK,aAG/D,KAAM,IAAI,OAAM,4MAIT,sBAAiD,MAAO,MAAK,uBAE7D,qBAA8B,MAAO,MAAK,mBAE9C,oBAAoB,EAA+B,GACxD,MAAO,GACJ,IAAI,AAAC,GAAM,GAAkB,EAAG,IAChC,OAAO,CAAC,EAAI,IAAO,EAAK,EAAI,GACxB,GAAY,QAAU,GAGxB,gBAAgB,GACrB,MAAO,MAAK,mBACT,IAAI,CAAC,CAAE,cAAa,WAAY,GAAI,IACnC,EACA,KAAK,oBAAoB,EAAiB,KAE3C,OAAO,CAAC,EAAM,IAAU,EAAK,SAAW,EAAK,SAAW,EAAO,GAG7D,cAAc,GACnB,GAAM,GAAY,KAAK,gBAAgB,GACvC,MAAO,GAAU,SAAW,KAAK,kBAC7B,EACA,GAAI,IAAU,UAAW,EAAU,UAGlC,SACL,MAAO,CACL,kBAAmB,KAAK,kBACxB,mBAAoB,KAAK,mBAAmB,IAAI,AAAC,GAAO,EAAG,iBAIjD,UAAS,GACrB,GAAM,GAAqB,EAAK,mBAC7B,IAAI,AAAC,GAAY,GAAuB,SAAS,IACpD,MAAO,IAAI,IAAY,EAAoB,EAAK,qBC1E7C,YAAgC,GACrC,GAAM,GAAM,GAAI,IAChB,SAAI,eAAe,GACZ,ECFF,YAA0B,EAAY,GAC3C,GAAM,CAAE,QAAO,UAAW,GAAI,GAAW,EAAW,MAAO,EAAW,QAEtE,GAAI,GAAS,GAAK,GAAU,EAC1B,KAAM,IAAI,OAAM,uCAAuC,KAAK,UAAU,CAAE,QAAO,cAGjF,GAAI,MAAM,QAAQ,GAEhB,MAAQ,GAAuB,IAAI,AAAC,GAAQ,GAAc,EAAK,CAAE,QAAO,YAG1E,GAAI,GAAoB,IACtB,GAAM,GAAmB,EAAQ,UAAU,QAAQ,EAAO,GACpD,EAAmB,EAAQ,mBAAmB,QAAQ,EAAiB,IAAI,MAAO,EAAiB,IAAI,QAC7G,MAAO,IAAwB,GAAwB,EAAS,GAAmB,GAGrF,MAAI,IAAoB,GACf,GAAwB,EAAS,EAAQ,UAAU,QAAQ,EAAO,IAGvE,YAAmB,IAAiB,YAAmB,GACjD,EAAgB,QAAQ,EAAO,GAGlC,EjJRT,GAAM,IAAQ,MAAO,UAAY,YAC3B,GAAW,MAAO,YAAc,aAAiB,MAAO,WAAU,WAAc,YACzE,GAAU,CAAE,QAAa,GAAmB,QAAM", "names": [] } diff --git a/dist/face-api.node.json b/dist/face-api.node.json index b4d329d..caaecc7 100644 --- a/dist/face-api.node.json +++ b/dist/face-api.node.json @@ -18,7 +18,7 @@ ] }, "src/utils/index.ts": { - "bytes": 1842, + "bytes": 1793, "imports": [ { "path": "dist/tfjs.esm.js", @@ -843,7 +843,7 @@ ] }, "src/NeuralNetwork.ts": { - "bytes": 5289, + "bytes": 5291, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1326,7 +1326,7 @@ ] }, "src/xception/TinyXception.ts": { - "bytes": 3148, + "bytes": 3143, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1553,7 +1553,7 @@ ] }, "src/faceLandmarkNet/index.ts": { - "bytes": 195, + "bytes": 194, "imports": [ { "path": "src/faceLandmarkNet/FaceLandmark68Net.ts", @@ -1609,7 +1609,7 @@ ] }, "src/faceRecognitionNet/extractParamsFromWeightMap.ts": { - "bytes": 3101, + "bytes": 3098, "imports": [ { "path": "src/common/index.ts", @@ -1635,7 +1635,7 @@ ] }, "src/faceRecognitionNet/FaceRecognitionNet.ts": { - "bytes": 2981, + "bytes": 2959, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1735,7 +1735,7 @@ ] }, "src/ssdMobilenetv1/extractParams.ts": { - "bytes": 8339, + "bytes": 8330, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1748,7 +1748,7 @@ ] }, "src/ssdMobilenetv1/extractParamsFromWeightMap.ts": { - "bytes": 5782, + "bytes": 5775, "imports": [ { "path": "src/common/index.ts", @@ -1783,11 +1783,11 @@ ] }, "src/ssdMobilenetv1/nonMaxSuppression.ts": { - "bytes": 2187, + "bytes": 2170, "imports": [] }, "src/ssdMobilenetv1/outputLayer.ts": { - "bytes": 2187, + "bytes": 2183, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1796,7 +1796,7 @@ ] }, "src/ssdMobilenetv1/boxPredictionLayer.ts": { - "bytes": 617, + "bytes": 598, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1830,7 +1830,7 @@ "imports": [] }, "src/ssdMobilenetv1/SsdMobilenetv1.ts": { - "bytes": 3826, + "bytes": 3675, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1913,7 +1913,7 @@ "imports": [] }, "src/tinyYolov2/leaky.ts": { - "bytes": 271, + "bytes": 238, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1922,7 +1922,7 @@ ] }, "src/tinyYolov2/convWithBatchNorm.ts": { - "bytes": 532, + "bytes": 530, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1935,7 +1935,7 @@ ] }, "src/tinyYolov2/depthwiseSeparableConv.ts": { - "bytes": 502, + "bytes": 500, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1948,7 +1948,7 @@ ] }, "src/tinyYolov2/extractParams.ts": { - "bytes": 3918, + "bytes": 3911, "imports": [ { "path": "dist/tfjs.esm.js", @@ -1969,7 +1969,7 @@ ] }, "src/tinyYolov2/extractParamsFromWeightMap.ts": { - "bytes": 3284, + "bytes": 3282, "imports": [ { "path": "src/common/disposeUnusedWeightTensors.ts", @@ -1990,7 +1990,7 @@ "imports": [] }, "src/tinyYolov2/TinyYolov2Base.ts": { - "bytes": 9700, + "bytes": 9606, "imports": [ { "path": "dist/tfjs.esm.js", @@ -2080,7 +2080,7 @@ "imports": [] }, "src/tinyYolov2/index.ts": { - "bytes": 349, + "bytes": 347, "imports": [ { "path": "src/tinyYolov2/TinyYolov2.ts", @@ -2501,7 +2501,7 @@ ] }, "src/index.ts": { - "bytes": 1024, + "bytes": 987, "imports": [ { "path": "dist/tfjs.esm.js", @@ -2590,7 +2590,7 @@ "dist/face-api.node.js.map": { "imports": [], "inputs": {}, - "bytes": 310104 + "bytes": 309641 }, "dist/face-api.node.js": { "imports": [], @@ -2780,7 +2780,7 @@ "bytesInOutput": 621 }, "src/NeuralNetwork.ts": { - "bytesInOutput": 2640 + "bytesInOutput": 2654 }, "src/faceFeatureExtractor/denseBlock.ts": { "bytesInOutput": 568 @@ -2912,7 +2912,7 @@ "bytesInOutput": 176 }, "src/faceRecognitionNet/FaceRecognitionNet.ts": { - "bytesInOutput": 1062 + "bytesInOutput": 1156 }, "src/faceRecognitionNet/convLayer.ts": { "bytesInOutput": 277 @@ -3065,7 +3065,7 @@ "bytesInOutput": 443 } }, - "bytes": 82575 + "bytes": 82683 } } }