ambiser
/
human
mirror of https://github.com/vladmandic/human
9
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

pure tensor pipeline without image converts

pull/50/head
Vladimir Mandic 2020-10-18 09:21:53 -04:00
parent 5e90ab0d51
commit b146a0a64e
24 changed files with 721 additions and 868 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -268,7 +268,6 @@ config = {
inputSize: 64, // fixed value inputSize: 64, // fixed value
minConfidence: 0.5, // threshold for discarding a prediction minConfidence: 0.5, // threshold for discarding a prediction
skipFrames: 10, // how many frames to go without re-running the detector, only used for video inputs skipFrames: 10, // how many frames to go without re-running the detector, only used for video inputs
useGrayscale: true, // convert image to grayscale before prediction or use highest channel
modelPath: '../models/emotion/model.json', modelPath: '../models/emotion/model.json',
}, },
}, },

1
config.js
View File

@ -51,7 +51,6 @@ export default {
inputSize: 64, // fixed value inputSize: 64, // fixed value
minConfidence: 0.5, // threshold for discarding a prediction minConfidence: 0.5, // threshold for discarding a prediction
skipFrames: 10, // how many frames to go without re-running the detector skipFrames: 10, // how many frames to go without re-running the detector
useGrayscale: true, // convert image to grayscale before prediction or use highest channel
modelPath: '../models/emotion/model.json', modelPath: '../models/emotion/model.json',
}, },
}, },

195
dist/human.cjs vendored
View File

@ -144,13 +144,7 @@ var require_blazeface = __commonJS((exports2) => {
}; };
} }
async estimateFaces(input) { async estimateFaces(input) {
const imageRaw = !(input instanceof tf2.Tensor) ? tf2.browser.fromPixels(input) : input; const {boxes, scaleFactor} = await this.getBoundingBoxes(input);
const imageCast = imageRaw.toFloat();
const image = imageCast.expandDims(0);
imageRaw.dispose();
imageCast.dispose();
const {boxes, scaleFactor} = await this.getBoundingBoxes(image);
image.dispose();
return Promise.all(boxes.map(async (face) => { return Promise.all(boxes.map(async (face) => {
const scaledBox = scaleBoxFromPrediction(face, scaleFactor); const scaledBox = scaleBoxFromPrediction(face, scaleFactor);
const [landmarkData, boxData, probabilityData] = await Promise.all([face.landmarks, scaledBox, face.probability].map(async (d) => d.array())); const [landmarkData, boxData, probabilityData] = await Promise.all([face.landmarks, scaledBox, face.probability].map(async (d) => d.array()));
@ -3818,13 +3812,7 @@ var require_facemesh = __commonJS((exports2) => {
async estimateFaces(input, config2) { async estimateFaces(input, config2) {
if (config2) if (config2)
this.config = config2; this.config = config2;
const imageRaw = !(input instanceof tf2.Tensor) ? tf2.browser.fromPixels(input) : input; const predictions = await this.pipeline.predict(input, config2);
const imageCast = imageRaw.toFloat();
const image = imageCast.expandDims(0);
imageRaw.dispose();
imageCast.dispose();
const predictions = await this.pipeline.predict(image, config2);
tf2.dispose(image);
const results = []; const results = [];
for (const prediction of predictions || []) { for (const prediction of predictions || []) {
if (prediction.isDisposedInternal) if (prediction.isDisposedInternal)
@ -3879,12 +3867,6 @@ var require_ssrnet = __commonJS((exports2) => {
const models2 = {}; const models2 = {};
let last = {age: 0, gender: ""}; let last = {age: 0, gender: ""};
let frame = 0; let frame = 0;
async function getImage(image, size) {
const buffer = tf2.browser.fromPixels(image);
const resize = tf2.image.resizeBilinear(buffer, [size, size]);
const expand = tf2.cast(tf2.expandDims(resize, 0), "float32");
return expand;
}
async function loadAge(config2) { async function loadAge(config2) {
if (!models2.age) if (!models2.age)
models2.age = await tf2.loadGraphModel(config2.face.age.modelPath); models2.age = await tf2.loadGraphModel(config2.face.age.modelPath);
@ -3901,14 +3883,9 @@ var require_ssrnet = __commonJS((exports2) => {
return last; return last;
} }
frame = 0; frame = 0;
let enhance;
if (image instanceof tf2.Tensor) {
const resize = tf2.image.resizeBilinear(image, [config2.face.age.inputSize, config2.face.age.inputSize], false); const resize = tf2.image.resizeBilinear(image, [config2.face.age.inputSize, config2.face.age.inputSize], false);
enhance = tf2.mul(resize, [255]); const enhance = tf2.mul(resize, [255]);
tf2.dispose(resize); tf2.dispose(resize);
} else {
enhance = await getImage(image, config2.face.age.inputSize);
}
const promises = []; const promises = [];
let ageT; let ageT;
let genderT; let genderT;
@ -3949,15 +3926,6 @@ var require_emotion = __commonJS((exports2) => {
let last = []; let last = [];
let frame = 0; let frame = 0;
const multiplier = 1.5; const multiplier = 1.5;
function getImage(image, size) {
const tensor = tf2.tidy(() => {
const buffer = tf2.browser.fromPixels(image, 1);
const resize = tf2.image.resizeBilinear(buffer, [size, size]);
const expand = tf2.cast(tf2.expandDims(resize, 0), "float32");
return expand;
});
return tensor;
}
async function load2(config2) { async function load2(config2) {
if (!models2.emotion) if (!models2.emotion)
models2.emotion = await tf2.loadGraphModel(config2.face.emotion.modelPath); models2.emotion = await tf2.loadGraphModel(config2.face.emotion.modelPath);
@ -3969,24 +3937,22 @@ var require_emotion = __commonJS((exports2) => {
return last; return last;
} }
frame = 0; frame = 0;
const enhance = tf2.tidy(() => {
if (image instanceof tf2.Tensor) {
const resize = tf2.image.resizeBilinear(image, [config2.face.emotion.inputSize, config2.face.emotion.inputSize], false); const resize = tf2.image.resizeBilinear(image, [config2.face.emotion.inputSize, config2.face.emotion.inputSize], false);
const [r, g, b] = tf2.split(resize, 3, 3); const [red, green, blue] = tf2.split(resize, 3, 3);
if (config2.face.emotion.useGrayscale) { resize.dispose();
const r1 = tf2.mul(r, [0.2989]); const redNorm = tf2.mul(red, [0.2989]);
const g1 = tf2.mul(g, [0.587]); const greenNorm = tf2.mul(green, [0.587]);
const b1 = tf2.mul(b, [0.114]); const blueNorm = tf2.mul(blue, [0.114]);
const grayscale = tf2.addN([r1, g1, b1]); red.dispose();
return grayscale; green.dispose();
} blue.dispose();
return g; const grayscale = tf2.addN([redNorm, greenNorm, blueNorm]);
} redNorm.dispose();
return getImage(image, config2.face.emotion.inputSize); greenNorm.dispose();
}); blueNorm.dispose();
const obj = []; const obj = [];
if (config2.face.emotion.enabled) { if (config2.face.emotion.enabled) {
const emotionT = await models2.emotion.predict(enhance); const emotionT = await models2.emotion.predict(grayscale);
const data = await emotionT.data(); const data = await emotionT.data();
for (let i = 0; i < data.length; i++) { for (let i = 0; i < data.length; i++) {
if (multiplier * data[i] > config2.face.emotion.minConfidence) if (multiplier * data[i] > config2.face.emotion.minConfidence)
@ -3995,7 +3961,7 @@ var require_emotion = __commonJS((exports2) => {
obj.sort((a, b) => b.score - a.score); obj.sort((a, b) => b.score - a.score);
tf2.dispose(emotionT); tf2.dispose(emotionT);
} }
tf2.dispose(enhance); tf2.dispose(grayscale);
last = obj; last = obj;
return obj; return obj;
} }
@ -4407,7 +4373,6 @@ var require_decodeMultiple = __commonJS((exports2) => {
// src/posenet/util.js // src/posenet/util.js
var require_util2 = __commonJS((exports2) => { var require_util2 = __commonJS((exports2) => {
const tf2 = require("@tensorflow/tfjs");
const kpt = require_keypoints2(); const kpt = require_keypoints2();
function eitherPointDoesntMeetConfidence(a, b, minConfidence) { function eitherPointDoesntMeetConfidence(a, b, minConfidence) {
return a < minConfidence || b < minConfidence; return a < minConfidence || b < minConfidence;
@ -4446,70 +4411,26 @@ var require_util2 = __commonJS((exports2) => {
return Promise.all(tensors.map((tensor) => tensor.buffer())); return Promise.all(tensors.map((tensor) => tensor.buffer()));
} }
exports2.toTensorBuffers3D = toTensorBuffers3D; exports2.toTensorBuffers3D = toTensorBuffers3D;
function scalePose(pose, scaleY, scaleX, offsetY = 0, offsetX = 0) { function scalePose(pose, scaleY, scaleX) {
return { return {
score: pose.score, score: pose.score,
keypoints: pose.keypoints.map(({score, part, position}) => ({ keypoints: pose.keypoints.map(({score, part, position}) => ({
score, score,
part, part,
position: { position: {x: position.x * scaleX, y: position.y * scaleY}
x: position.x * scaleX + offsetX,
y: position.y * scaleY + offsetY
}
})) }))
}; };
} }
exports2.scalePose = scalePose; exports2.scalePose = scalePose;
function scalePoses(poses, scaleY, scaleX, offsetY = 0, offsetX = 0) { function resizeTo(image, [targetH, targetW]) {
if (scaleX === 1 && scaleY === 1 && offsetY === 0 && offsetX === 0) { const input = image.squeeze(0);
return poses; const resized = input.resizeBilinear([targetH, targetW]);
input.dispose();
return resized;
} }
return poses.map((pose) => scalePose(pose, scaleY, scaleX, offsetY, offsetX)); exports2.resizeTo = resizeTo;
} function scaleAndFlipPoses(poses, [height, width], [inputResolutionHeight, inputResolutionWidth]) {
exports2.scalePoses = scalePoses; const scaledPoses = poses.map((pose) => scalePose(pose, height / inputResolutionHeight, width / inputResolutionWidth));
function getInputTensorDimensions(input) {
return input instanceof tf2.Tensor ? [input.shape[0], input.shape[1]] : [input.height, input.width];
}
exports2.getInputTensorDimensions = getInputTensorDimensions;
function toInputTensor(input) {
return input instanceof tf2.Tensor ? input : tf2.browser.fromPixels(input);
}
exports2.toInputTensor = toInputTensor;
function toResizedInputTensor(input, resizeHeight, resizeWidth) {
return tf2.tidy(() => {
const imageTensor = toInputTensor(input);
return imageTensor.resizeBilinear([resizeHeight, resizeWidth]);
});
}
exports2.toResizedInputTensor = toResizedInputTensor;
function padAndResizeTo(input, [targetH, targetW]) {
const [height, width] = getInputTensorDimensions(input);
const targetAspect = targetW / targetH;
const aspect = width / height;
let [padT, padB, padL, padR] = [0, 0, 0, 0];
if (aspect < targetAspect) {
padT = 0;
padB = 0;
padL = Math.round(0.5 * (targetAspect * height - width));
padR = Math.round(0.5 * (targetAspect * height - width));
} else {
padT = Math.round(0.5 * (1 / targetAspect * width - height));
padB = Math.round(0.5 * (1 / targetAspect * width - height));
padL = 0;
padR = 0;
}
const resized = tf2.tidy(() => {
let imageTensor = toInputTensor(input);
imageTensor = tf2.pad3d(imageTensor, [[padT, padB], [padL, padR], [0, 0]]);
return imageTensor.resizeBilinear([targetH, targetW]);
});
return {resized, padding: {top: padT, left: padL, right: padR, bottom: padB}};
}
exports2.padAndResizeTo = padAndResizeTo;
function scaleAndFlipPoses(poses, [height, width], [inputResolutionHeight, inputResolutionWidth], padding) {
const scaleY = (height + padding.top + padding.bottom) / inputResolutionHeight;
const scaleX = (width + padding.left + padding.right) / inputResolutionWidth;
const scaledPoses = scalePoses(poses, scaleY, scaleX, -padding.top, -padding.left);
return scaledPoses; return scaledPoses;
} }
exports2.scaleAndFlipPoses = scaleAndFlipPoses; exports2.scaleAndFlipPoses = scaleAndFlipPoses;
@ -4527,8 +4448,9 @@ var require_modelPoseNet = __commonJS((exports2) => {
} }
async estimatePoses(input, config2) { async estimatePoses(input, config2) {
const outputStride = config2.outputStride; const outputStride = config2.outputStride;
const [height, width] = util.getInputTensorDimensions(input); const height = input.shape[1];
const {resized, padding} = util.padAndResizeTo(input, [config2.inputResolution, config2.inputResolution]); const width = input.shape[2];
const resized = util.resizeTo(input, [config2.inputResolution, config2.inputResolution]);
const {heatmapScores, offsets, displacementFwd, displacementBwd} = this.baseModel.predict(resized); const {heatmapScores, offsets, displacementFwd, displacementBwd} = this.baseModel.predict(resized);
const allTensorBuffers = await util.toTensorBuffers3D([heatmapScores, offsets, displacementFwd, displacementBwd]); const allTensorBuffers = await util.toTensorBuffers3D([heatmapScores, offsets, displacementFwd, displacementBwd]);
const scoresBuffer = allTensorBuffers[0]; const scoresBuffer = allTensorBuffers[0];
@ -4536,7 +4458,7 @@ var require_modelPoseNet = __commonJS((exports2) => {
const displacementsFwdBuffer = allTensorBuffers[2]; const displacementsFwdBuffer = allTensorBuffers[2];
const displacementsBwdBuffer = allTensorBuffers[3]; const displacementsBwdBuffer = allTensorBuffers[3];
const poses = await decodeMultiple.decodeMultiplePoses(scoresBuffer, offsetsBuffer, displacementsFwdBuffer, displacementsBwdBuffer, outputStride, config2.maxDetections, config2.scoreThreshold, config2.nmsRadius); const poses = await decodeMultiple.decodeMultiplePoses(scoresBuffer, offsetsBuffer, displacementsFwdBuffer, displacementsBwdBuffer, outputStride, config2.maxDetections, config2.scoreThreshold, config2.nmsRadius);
const resultPoses = util.scaleAndFlipPoses(poses, [height, width], [config2.inputResolution, config2.inputResolution], padding); const resultPoses = util.scaleAndFlipPoses(poses, [height, width], [config2.inputResolution, config2.inputResolution]);
heatmapScores.dispose(); heatmapScores.dispose();
offsets.dispose(); offsets.dispose();
displacementFwd.dispose(); displacementFwd.dispose();
@ -4685,15 +4607,15 @@ var require_handdetector = __commonJS((exports2) => {
}); });
} }
async getBoundingBoxes(input) { async getBoundingBoxes(input) {
const normalizedInput = tf2.tidy(() => tf2.mul(tf2.sub(input, 0.5), 2)); const batchedPrediction = this.model.predict(input);
const batchedPrediction = this.model.predict(normalizedInput);
const prediction = batchedPrediction.squeeze(); const prediction = batchedPrediction.squeeze();
console.log(prediction);
const scores = tf2.tidy(() => tf2.sigmoid(tf2.slice(prediction, [0, 0], [-1, 1])).squeeze()); const scores = tf2.tidy(() => tf2.sigmoid(tf2.slice(prediction, [0, 0], [-1, 1])).squeeze());
const rawBoxes = tf2.slice(prediction, [0, 1], [-1, 4]); const rawBoxes = tf2.slice(prediction, [0, 1], [-1, 4]);
const boxes = this.normalizeBoxes(rawBoxes); const boxes = this.normalizeBoxes(rawBoxes);
const boxesWithHandsTensor = await tf2.image.nonMaxSuppressionAsync(boxes, scores, this.maxHands, this.iouThreshold, this.scoreThreshold); const boxesWithHandsTensor = await tf2.image.nonMaxSuppressionAsync(boxes, scores, this.maxHands, this.iouThreshold, this.scoreThreshold);
const boxesWithHands = await boxesWithHandsTensor.array(); const boxesWithHands = await boxesWithHandsTensor.array();
const toDispose = [normalizedInput, batchedPrediction, boxesWithHandsTensor, prediction, boxes, rawBoxes, scores]; const toDispose = [batchedPrediction, boxesWithHandsTensor, prediction, boxes, rawBoxes, scores];
const detectedHands = tf2.tidy(() => { const detectedHands = tf2.tidy(() => {
const detectedBoxes = []; const detectedBoxes = [];
for (const i in boxesWithHands) { for (const i in boxesWithHands) {
@ -4709,12 +4631,16 @@ var require_handdetector = __commonJS((exports2) => {
return detectedHands; return detectedHands;
} }
async estimateHandBounds(input, config2) { async estimateHandBounds(input, config2) {
const inputHeight = input.shape[1];
const inputWidth = input.shape[2];
this.iouThreshold = config2.iouThreshold; this.iouThreshold = config2.iouThreshold;
this.scoreThreshold = config2.scoreThreshold; this.scoreThreshold = config2.scoreThreshold;
this.maxHands = config2.maxHands; this.maxHands = config2.maxHands;
const image = tf2.tidy(() => input.resizeBilinear([this.width, this.height]).div(255)); const resized = input.resizeBilinear([this.width, this.height]);
const divided = resized.div(255);
const normalized = divided.sub(0.5);
const image = normalized.mul(2);
resized.dispose();
divided.dispose();
normalized.dispose();
const predictions = await this.getBoundingBoxes(image); const predictions = await this.getBoundingBoxes(image);
image.dispose(); image.dispose();
if (!predictions || predictions.length === 0) if (!predictions || predictions.length === 0)
@ -4728,7 +4654,7 @@ var require_handdetector = __commonJS((exports2) => {
const palmLandmarks = await prediction.palmLandmarks.array(); const palmLandmarks = await prediction.palmLandmarks.array();
prediction.boxes.dispose(); prediction.boxes.dispose();
prediction.palmLandmarks.dispose(); prediction.palmLandmarks.dispose();
hands.push(bounding.scaleBoxCoordinates({startPoint, endPoint, palmLandmarks}, [inputWidth / this.width, inputHeight / this.height])); hands.push(bounding.scaleBoxCoordinates({startPoint, endPoint, palmLandmarks}, [input.shape[2] / this.width, input.shape[1] / this.height]));
} }
return hands; return hands;
} }
@ -4886,7 +4812,7 @@ var require_pipeline2 = __commonJS((exports2) => {
]); ]);
} }
async estimateHands(image, config2) { async estimateHands(image, config2) {
this.maxContinuousChecks = config2.skipFrames; this.skipFrames = config2.skipFrames;
this.detectionConfidence = config2.minConfidence; this.detectionConfidence = config2.minConfidence;
this.maxHands = config2.maxHands; this.maxHands = config2.maxHands;
this.runsWithoutHandDetector++; this.runsWithoutHandDetector++;
@ -4996,14 +4922,7 @@ var require_handpose = __commonJS((exports2) => {
this.skipFrames = config2.skipFrames; this.skipFrames = config2.skipFrames;
this.detectionConfidence = config2.minConfidence; this.detectionConfidence = config2.minConfidence;
this.maxHands = config2.maxHands; this.maxHands = config2.maxHands;
const image = tf2.tidy(() => { const predictions = await this.pipeline.estimateHands(input, config2);
if (!(input instanceof tf2.Tensor)) {
input = tf2.browser.fromPixels(input);
}
return input.toFloat().expandDims(0);
});
const predictions = await this.pipeline.estimateHands(image, config2);
image.dispose();
const hands = []; const hands = [];
if (!predictions) if (!predictions)
return hands; return hands;
@ -5094,7 +5013,6 @@ var require_config = __commonJS((exports2) => {
inputSize: 64, inputSize: 64,
minConfidence: 0.5, minConfidence: 0.5,
skipFrames: 10, skipFrames: 10,
useGrayscale: true,
modelPath: "../models/emotion/model.json" modelPath: "../models/emotion/model.json"
} }
}, },
@ -5258,7 +5176,7 @@ function mergeDeep(...objects) {
function sanity(input) { function sanity(input) {
if (!input) if (!input)
return "input is not defined"; return "input is not defined";
if (tf.ENV.flags.IS_BROWSER && (input instanceof ImageData || input instanceof HTMLImageElement || input instanceof HTMLCanvasElement || input instanceof HTMLVideoElement || input instanceof HTMLMediaElement)) { if (!(input instanceof tf.Tensor) || tf.ENV.flags.IS_BROWSER && (input instanceof ImageData || input instanceof HTMLImageElement || input instanceof HTMLCanvasElement || input instanceof HTMLVideoElement || input instanceof HTMLMediaElement)) {
const width = input.naturalWidth || input.videoWidth || input.width || input.shape && input.shape[1] > 0; const width = input.naturalWidth || input.videoWidth || input.width || input.shape && input.shape[1] > 0;
if (!width || width === 0) if (!width || width === 0)
return "input is empty"; return "input is empty";
@ -5293,6 +5211,19 @@ async function load(userConfig) {
if (config.face.enabled && config.face.emotion.enabled && !models.emotion) if (config.face.enabled && config.face.emotion.enabled && !models.emotion)
models.emotion = await emotion.load(config); models.emotion = await emotion.load(config);
} }
function tfImage(input) {
let image;
if (input instanceof tf.Tensor) {
image = tf.clone(input);
} else {
const pixels = tf.browser.fromPixels(input);
const casted = pixels.toFloat();
image = casted.expandDims(0);
pixels.dispose();
casted.dispose();
}
return image;
}
async function detect(input, userConfig = {}) { async function detect(input, userConfig = {}) {
state = "config"; state = "config";
const perf = {}; const perf = {};
@ -5332,16 +5263,17 @@ async function detect(input, userConfig = {}) {
if (config.scoped) if (config.scoped)
tf.engine().startScope(); tf.engine().startScope();
analyze("Start Detect:"); analyze("Start Detect:");
const imageTensor = tfImage(input);
state = "run:body"; state = "run:body";
timeStamp = now(); timeStamp = now();
analyze("Start PoseNet"); analyze("Start PoseNet");
const poseRes = config.body.enabled ? await models.posenet.estimatePoses(input, config.body) : []; const poseRes = config.body.enabled ? await models.posenet.estimatePoses(imageTensor, config.body) : [];
analyze("End PoseNet:"); analyze("End PoseNet:");
perf.body = Math.trunc(now() - timeStamp); perf.body = Math.trunc(now() - timeStamp);
state = "run:hand"; state = "run:hand";
timeStamp = now(); timeStamp = now();
analyze("Start HandPose:"); analyze("Start HandPose:");
const handRes = config.hand.enabled ? await models.handpose.estimateHands(input, config.hand) : []; const handRes = config.hand.enabled ? await models.handpose.estimateHands(imageTensor, config.hand) : [];
analyze("End HandPose:"); analyze("End HandPose:");
perf.hand = Math.trunc(now() - timeStamp); perf.hand = Math.trunc(now() - timeStamp);
const faceRes = []; const faceRes = [];
@ -5349,7 +5281,7 @@ async function detect(input, userConfig = {}) {
state = "run:face"; state = "run:face";
timeStamp = now(); timeStamp = now();
analyze("Start FaceMesh:"); analyze("Start FaceMesh:");
const faces = await models.facemesh.estimateFaces(input, config.face); const faces = await models.facemesh.estimateFaces(imageTensor, config.face);
perf.face = Math.trunc(now() - timeStamp); perf.face = Math.trunc(now() - timeStamp);
for (const face of faces) { for (const face of faces) {
if (!face.image || face.image.isDisposedInternal) { if (!face.image || face.image.isDisposedInternal) {
@ -5377,9 +5309,10 @@ async function detect(input, userConfig = {}) {
emotion: emotionData, emotion: emotionData,
iris: iris !== 0 ? Math.trunc(100 * 11.7 / iris) / 100 : 0 iris: iris !== 0 ? Math.trunc(100 * 11.7 / iris) / 100 : 0
}); });
}
analyze("End FaceMesh:"); analyze("End FaceMesh:");
} }
}
imageTensor.dispose();
state = "idle"; state = "idle";
if (config.scoped) if (config.scoped)
tf.engine().endScope(); tf.engine().endScope();

48
dist/human.cjs.json vendored
View File

@ -1,7 +1,7 @@
{ {
"inputs": { "inputs": {
"config.js": { "config.js": {
"bytes": 4862, "bytes": 4762,
"imports": [] "imports": []
}, },
"package.json": { "package.json": {
@ -9,11 +9,11 @@
"imports": [] "imports": []
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytes": 2019, "bytes": 1646,
"imports": [] "imports": []
}, },
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytes": 7407, "bytes": 7161,
"imports": [] "imports": []
}, },
"src/facemesh/box.js": { "src/facemesh/box.js": {
@ -21,7 +21,7 @@
"imports": [] "imports": []
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytes": 2816, "bytes": 2568,
"imports": [ "imports": [
{ {
"path": "src/facemesh/blazeface.js" "path": "src/facemesh/blazeface.js"
@ -75,7 +75,7 @@
"imports": [] "imports": []
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytes": 4296, "bytes": 4277,
"imports": [ "imports": [
{ {
"path": "src/handpose/box.js" "path": "src/handpose/box.js"
@ -83,7 +83,7 @@
] ]
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytes": 2356, "bytes": 2152,
"imports": [ "imports": [
{ {
"path": "src/handpose/handdetector.js" "path": "src/handpose/handdetector.js"
@ -101,7 +101,7 @@
"imports": [] "imports": []
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytes": 8178, "bytes": 8169,
"imports": [ "imports": [
{ {
"path": "src/handpose/box.js" "path": "src/handpose/box.js"
@ -116,7 +116,7 @@
"imports": [] "imports": []
}, },
"src/human.js": { "src/human.js": {
"bytes": 8299, "bytes": 8784,
"imports": [ "imports": [
{ {
"path": "src/facemesh/facemesh.js" "path": "src/facemesh/facemesh.js"
@ -195,7 +195,7 @@
] ]
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytes": 3472, "bytes": 3447,
"imports": [ "imports": [
{ {
"path": "src/posenet/modelMobileNet.js" "path": "src/posenet/modelMobileNet.js"
@ -229,7 +229,7 @@
] ]
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytes": 4202, "bytes": 2260,
"imports": [ "imports": [
{ {
"path": "src/posenet/keypoints.js" "path": "src/posenet/keypoints.js"
@ -245,7 +245,7 @@
] ]
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytes": 1937, "bytes": 1574,
"imports": [] "imports": []
} }
}, },
@ -253,13 +253,13 @@
"dist/human.cjs.map": { "dist/human.cjs.map": {
"imports": [], "imports": [],
"inputs": {}, "inputs": {},
"bytes": 220934 "bytes": 215962
}, },
"dist/human.cjs": { "dist/human.cjs": {
"imports": [], "imports": [],
"inputs": { "inputs": {
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytesInOutput": 7398 "bytesInOutput": 7138
}, },
"src/facemesh/keypoints.js": { "src/facemesh/keypoints.js": {
"bytesInOutput": 2771 "bytesInOutput": 2771
@ -280,13 +280,13 @@
"bytesInOutput": 23311 "bytesInOutput": 23311
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytesInOutput": 2950 "bytesInOutput": 2687
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytesInOutput": 2158 "bytesInOutput": 1768
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytesInOutput": 2133 "bytesInOutput": 1736
}, },
"src/posenet/modelBase.js": { "src/posenet/modelBase.js": {
"bytesInOutput": 1120 "bytesInOutput": 1120
@ -313,10 +313,10 @@
"bytesInOutput": 1992 "bytesInOutput": 1992
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytesInOutput": 4383 "bytesInOutput": 2404
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytesInOutput": 1976 "bytesInOutput": 1955
}, },
"src/posenet/posenet.js": { "src/posenet/posenet.js": {
"bytesInOutput": 917 "bytesInOutput": 917
@ -325,7 +325,7 @@
"bytesInOutput": 2813 "bytesInOutput": 2813
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytesInOutput": 4135 "bytesInOutput": 4161
}, },
"src/handpose/keypoints.js": { "src/handpose/keypoints.js": {
"bytesInOutput": 265 "bytesInOutput": 265
@ -334,22 +334,22 @@
"bytesInOutput": 2671 "bytesInOutput": 2671
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytesInOutput": 7625 "bytesInOutput": 7616
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytesInOutput": 2509 "bytesInOutput": 2288
}, },
"config.js": { "config.js": {
"bytesInOutput": 1872 "bytesInOutput": 1844
}, },
"package.json": { "package.json": {
"bytesInOutput": 2778 "bytesInOutput": 2778
}, },
"src/human.js": { "src/human.js": {
"bytesInOutput": 7273 "bytesInOutput": 7694
} }
}, },
"bytes": 134728 "bytes": 131607
} }
} }
} }

4
dist/human.cjs.map vendored
View File

File diff suppressed because one or more lines are too long

2
dist/human.esm-nobundle.js vendored
View File

File diff suppressed because one or more lines are too long

4
dist/human.esm-nobundle.js.map vendored
View File

File diff suppressed because one or more lines are too long

50
dist/human.esm-nobundle.json vendored
View File

@ -1,7 +1,7 @@
{ {
"inputs": { "inputs": {
"config.js": { "config.js": {
"bytes": 4862, "bytes": 4762,
"imports": [] "imports": []
}, },
"package.json": { "package.json": {
@ -9,11 +9,11 @@
"imports": [] "imports": []
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytes": 2019, "bytes": 1646,
"imports": [] "imports": []
}, },
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytes": 7407, "bytes": 7161,
"imports": [] "imports": []
}, },
"src/facemesh/box.js": { "src/facemesh/box.js": {
@ -21,7 +21,7 @@
"imports": [] "imports": []
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytes": 2816, "bytes": 2568,
"imports": [ "imports": [
{ {
"path": "src/facemesh/blazeface.js" "path": "src/facemesh/blazeface.js"
@ -75,7 +75,7 @@
"imports": [] "imports": []
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytes": 4296, "bytes": 4277,
"imports": [ "imports": [
{ {
"path": "src/handpose/box.js" "path": "src/handpose/box.js"
@ -83,7 +83,7 @@
] ]
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytes": 2356, "bytes": 2152,
"imports": [ "imports": [
{ {
"path": "src/handpose/handdetector.js" "path": "src/handpose/handdetector.js"
@ -101,7 +101,7 @@
"imports": [] "imports": []
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytes": 8178, "bytes": 8169,
"imports": [ "imports": [
{ {
"path": "src/handpose/box.js" "path": "src/handpose/box.js"
@ -116,7 +116,7 @@
"imports": [] "imports": []
}, },
"src/human.js": { "src/human.js": {
"bytes": 8299, "bytes": 8784,
"imports": [ "imports": [
{ {
"path": "src/facemesh/facemesh.js" "path": "src/facemesh/facemesh.js"
@ -195,7 +195,7 @@
] ]
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytes": 3472, "bytes": 3447,
"imports": [ "imports": [
{ {
"path": "src/posenet/modelMobileNet.js" "path": "src/posenet/modelMobileNet.js"
@ -229,7 +229,7 @@
] ]
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytes": 4202, "bytes": 2260,
"imports": [ "imports": [
{ {
"path": "src/posenet/keypoints.js" "path": "src/posenet/keypoints.js"
@ -245,7 +245,7 @@
] ]
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytes": 1937, "bytes": 1574,
"imports": [] "imports": []
} }
}, },
@ -253,13 +253,13 @@
"dist/human.esm-nobundle.js.map": { "dist/human.esm-nobundle.js.map": {
"imports": [], "imports": [],
"inputs": {}, "inputs": {},
"bytes": 199199 "bytes": 194427
}, },
"dist/human.esm-nobundle.js": { "dist/human.esm-nobundle.js": {
"imports": [], "imports": [],
"inputs": { "inputs": {
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytesInOutput": 3255 "bytesInOutput": 3131
}, },
"src/facemesh/keypoints.js": { "src/facemesh/keypoints.js": {
"bytesInOutput": 1950 "bytesInOutput": 1950
@ -280,13 +280,13 @@
"bytesInOutput": 9995 "bytesInOutput": 9995
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytesInOutput": 1391 "bytesInOutput": 1259
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytesInOutput": 1142 "bytesInOutput": 934
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytesInOutput": 1147 "bytesInOutput": 944
}, },
"src/posenet/modelBase.js": { "src/posenet/modelBase.js": {
"bytesInOutput": 597 "bytesInOutput": 597
@ -313,10 +313,10 @@
"bytesInOutput": 608 "bytesInOutput": 608
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytesInOutput": 1850 "bytesInOutput": 1058
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytesInOutput": 885 "bytesInOutput": 846
}, },
"src/posenet/posenet.js": { "src/posenet/posenet.js": {
"bytesInOutput": 464 "bytesInOutput": 464
@ -325,31 +325,31 @@
"bytesInOutput": 1400 "bytesInOutput": 1400
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytesInOutput": 2040 "bytesInOutput": 2067
}, },
"src/handpose/keypoints.js": { "src/handpose/keypoints.js": {
"bytesInOutput": 160 "bytesInOutput": 160
}, },
"src/handpose/util.js": { "src/handpose/util.js": {
"bytesInOutput": 984 "bytesInOutput": 977
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytesInOutput": 3218 "bytesInOutput": 3209
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytesInOutput": 1317 "bytesInOutput": 1211
}, },
"config.js": { "config.js": {
"bytesInOutput": 1146 "bytesInOutput": 1130
}, },
"package.json": { "package.json": {
"bytesInOutput": 2305 "bytesInOutput": 2305
}, },
"src/human.js": { "src/human.js": {
"bytesInOutput": 4135 "bytesInOutput": 4349
} }
}, },
"bytes": 69965 "bytes": 68570
} }
} }
} }

474
dist/human.esm.js vendored
View File

File diff suppressed because one or more lines are too long

4
dist/human.esm.js.map vendored
View File

File diff suppressed because one or more lines are too long

51
dist/human.esm.json vendored
View File

@ -1,7 +1,7 @@
{ {
"inputs": { "inputs": {
"config.js": { "config.js": {
"bytes": 4862, "bytes": 4762,
"imports": [] "imports": []
}, },
"node_modules/@tensorflow/tfjs-backend-cpu/dist/tf-backend-cpu.node.js": { "node_modules/@tensorflow/tfjs-backend-cpu/dist/tf-backend-cpu.node.js": {
@ -153,7 +153,7 @@
"imports": [] "imports": []
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytes": 2019, "bytes": 1646,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -161,7 +161,7 @@
] ]
}, },
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytes": 7407, "bytes": 7161,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -177,7 +177,7 @@
] ]
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytes": 2816, "bytes": 2568,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -241,7 +241,7 @@
] ]
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytes": 4296, "bytes": 4277,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -252,7 +252,7 @@
] ]
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytes": 2356, "bytes": 2152,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -273,7 +273,7 @@
"imports": [] "imports": []
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytes": 8178, "bytes": 8169,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -291,7 +291,7 @@
"imports": [] "imports": []
}, },
"src/human.js": { "src/human.js": {
"bytes": 8299, "bytes": 8784,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -380,7 +380,7 @@
] ]
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytes": 3472, "bytes": 3447,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -417,11 +417,8 @@
] ]
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytes": 4202, "bytes": 2260,
"imports": [ "imports": [
{
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
},
{ {
"path": "src/posenet/keypoints.js" "path": "src/posenet/keypoints.js"
} }
@ -436,7 +433,7 @@
] ]
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytes": 1937, "bytes": 1574,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -464,7 +461,7 @@
"dist/human.esm.js.map": { "dist/human.esm.js.map": {
"imports": [], "imports": [],
"inputs": {}, "inputs": {},
"bytes": 4960250 "bytes": 4955479
}, },
"dist/human.esm.js": { "dist/human.esm.js": {
"imports": [], "imports": [],
@ -527,7 +524,7 @@
"bytesInOutput": 765 "bytesInOutput": 765
}, },
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytesInOutput": 3268 "bytesInOutput": 3142
}, },
"src/facemesh/keypoints.js": { "src/facemesh/keypoints.js": {
"bytesInOutput": 1951 "bytesInOutput": 1951
@ -548,13 +545,13 @@
"bytesInOutput": 9996 "bytesInOutput": 9996
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytesInOutput": 1376 "bytesInOutput": 1242
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytesInOutput": 1143 "bytesInOutput": 930
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytesInOutput": 1142 "bytesInOutput": 932
}, },
"src/posenet/modelBase.js": { "src/posenet/modelBase.js": {
"bytesInOutput": 575 "bytesInOutput": 575
@ -581,10 +578,10 @@
"bytesInOutput": 609 "bytesInOutput": 609
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytesInOutput": 1840 "bytesInOutput": 1067
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytesInOutput": 863 "bytesInOutput": 824
}, },
"src/posenet/posenet.js": { "src/posenet/posenet.js": {
"bytesInOutput": 479 "bytesInOutput": 479
@ -593,7 +590,7 @@
"bytesInOutput": 1386 "bytesInOutput": 1386
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytesInOutput": 2050 "bytesInOutput": 2073
}, },
"src/handpose/keypoints.js": { "src/handpose/keypoints.js": {
"bytesInOutput": 161 "bytesInOutput": 161
@ -602,22 +599,22 @@
"bytesInOutput": 993 "bytesInOutput": 993
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytesInOutput": 3214 "bytesInOutput": 3205
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytesInOutput": 1303 "bytesInOutput": 1189
}, },
"config.js": { "config.js": {
"bytesInOutput": 1147 "bytesInOutput": 1131
}, },
"package.json": { "package.json": {
"bytesInOutput": 2306 "bytesInOutput": 2306
}, },
"src/human.js": { "src/human.js": {
"bytesInOutput": 4246 "bytesInOutput": 4464
} }
}, },
"bytes": 1106891 "bytes": 1105498
} }
} }
} }

474
dist/human.js vendored
View File

File diff suppressed because one or more lines are too long

4
dist/human.js.map vendored
View File

File diff suppressed because one or more lines are too long

51
dist/human.json vendored
View File

@ -1,7 +1,7 @@
{ {
"inputs": { "inputs": {
"config.js": { "config.js": {
"bytes": 4862, "bytes": 4762,
"imports": [] "imports": []
}, },
"node_modules/@tensorflow/tfjs-backend-cpu/dist/tf-backend-cpu.node.js": { "node_modules/@tensorflow/tfjs-backend-cpu/dist/tf-backend-cpu.node.js": {
@ -153,7 +153,7 @@
"imports": [] "imports": []
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytes": 2019, "bytes": 1646,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -161,7 +161,7 @@
] ]
}, },
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytes": 7407, "bytes": 7161,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -177,7 +177,7 @@
] ]
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytes": 2816, "bytes": 2568,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -241,7 +241,7 @@
] ]
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytes": 4296, "bytes": 4277,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -252,7 +252,7 @@
] ]
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytes": 2356, "bytes": 2152,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -273,7 +273,7 @@
"imports": [] "imports": []
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytes": 8178, "bytes": 8169,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -291,7 +291,7 @@
"imports": [] "imports": []
}, },
"src/human.js": { "src/human.js": {
"bytes": 8299, "bytes": 8784,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -380,7 +380,7 @@
] ]
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytes": 3472, "bytes": 3447,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -417,11 +417,8 @@
] ]
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytes": 4202, "bytes": 2260,
"imports": [ "imports": [
{
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
},
{ {
"path": "src/posenet/keypoints.js" "path": "src/posenet/keypoints.js"
} }
@ -436,7 +433,7 @@
] ]
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytes": 1937, "bytes": 1574,
"imports": [ "imports": [
{ {
"path": "node_modules/@tensorflow/tfjs/dist/tf.node.js" "path": "node_modules/@tensorflow/tfjs/dist/tf.node.js"
@ -464,7 +461,7 @@
"dist/human.js.map": { "dist/human.js.map": {
"imports": [], "imports": [],
"inputs": {}, "inputs": {},
"bytes": 4960250 "bytes": 4955479
}, },
"dist/human.js": { "dist/human.js": {
"imports": [], "imports": [],
@ -527,7 +524,7 @@
"bytesInOutput": 765 "bytesInOutput": 765
}, },
"src/facemesh/blazeface.js": { "src/facemesh/blazeface.js": {
"bytesInOutput": 3268 "bytesInOutput": 3142
}, },
"src/facemesh/keypoints.js": { "src/facemesh/keypoints.js": {
"bytesInOutput": 1951 "bytesInOutput": 1951
@ -548,13 +545,13 @@
"bytesInOutput": 9996 "bytesInOutput": 9996
}, },
"src/facemesh/facemesh.js": { "src/facemesh/facemesh.js": {
"bytesInOutput": 1376 "bytesInOutput": 1242
}, },
"src/ssrnet/ssrnet.js": { "src/ssrnet/ssrnet.js": {
"bytesInOutput": 1143 "bytesInOutput": 930
}, },
"src/emotion/emotion.js": { "src/emotion/emotion.js": {
"bytesInOutput": 1142 "bytesInOutput": 932
}, },
"src/posenet/modelBase.js": { "src/posenet/modelBase.js": {
"bytesInOutput": 575 "bytesInOutput": 575
@ -581,10 +578,10 @@
"bytesInOutput": 609 "bytesInOutput": 609
}, },
"src/posenet/util.js": { "src/posenet/util.js": {
"bytesInOutput": 1840 "bytesInOutput": 1067
}, },
"src/posenet/modelPoseNet.js": { "src/posenet/modelPoseNet.js": {
"bytesInOutput": 863 "bytesInOutput": 824
}, },
"src/posenet/posenet.js": { "src/posenet/posenet.js": {
"bytesInOutput": 479 "bytesInOutput": 479
@ -593,7 +590,7 @@
"bytesInOutput": 1386 "bytesInOutput": 1386
}, },
"src/handpose/handdetector.js": { "src/handpose/handdetector.js": {
"bytesInOutput": 2050 "bytesInOutput": 2073
}, },
"src/handpose/keypoints.js": { "src/handpose/keypoints.js": {
"bytesInOutput": 161 "bytesInOutput": 161
@ -602,22 +599,22 @@
"bytesInOutput": 993 "bytesInOutput": 993
}, },
"src/handpose/pipeline.js": { "src/handpose/pipeline.js": {
"bytesInOutput": 3214 "bytesInOutput": 3205
}, },
"src/handpose/handpose.js": { "src/handpose/handpose.js": {
"bytesInOutput": 1303 "bytesInOutput": 1189
}, },
"config.js": { "config.js": {
"bytesInOutput": 1147 "bytesInOutput": 1131
}, },
"package.json": { "package.json": {
"bytesInOutput": 2306 "bytesInOutput": 2306
}, },
"src/human.js": { "src/human.js": {
"bytesInOutput": 4246 "bytesInOutput": 4464
} }
}, },
"bytes": 1106900 "bytes": 1105507
} }
} }
} }

40
src/emotion/emotion.js
View File

@ -6,16 +6,6 @@ let last = [];
let frame = 0; let frame = 0;
const multiplier = 1.5; const multiplier = 1.5;
function getImage(image, size) {
const tensor = tf.tidy(() => {
const buffer = tf.browser.fromPixels(image, 1);
const resize = tf.image.resizeBilinear(buffer, [size, size]);
const expand = tf.cast(tf.expandDims(resize, 0), 'float32');
return expand;
});
return tensor;
}
async function load(config) { async function load(config) {
if (!models.emotion) models.emotion = await tf.loadGraphModel(config.face.emotion.modelPath); if (!models.emotion) models.emotion = await tf.loadGraphModel(config.face.emotion.modelPath);
return models.emotion; return models.emotion;
@ -27,25 +17,23 @@ async function predict(image, config) {
return last; return last;
} }
frame = 0; frame = 0;
const enhance = tf.tidy(() => {
if (image instanceof tf.Tensor) {
const resize = tf.image.resizeBilinear(image, [config.face.emotion.inputSize, config.face.emotion.inputSize], false); const resize = tf.image.resizeBilinear(image, [config.face.emotion.inputSize, config.face.emotion.inputSize], false);
const [r, g, b] = tf.split(resize, 3, 3); const [red, green, blue] = tf.split(resize, 3, 3);
if (config.face.emotion.useGrayscale) { resize.dispose();
// weighted rgb to grayscale: https://www.mathworks.com/help/matlab/ref/rgb2gray.html // weighted rgb to grayscale: https://www.mathworks.com/help/matlab/ref/rgb2gray.html
const r1 = tf.mul(r, [0.2989]); const redNorm = tf.mul(red, [0.2989]);
const g1 = tf.mul(g, [0.5870]); const greenNorm = tf.mul(green, [0.5870]);
const b1 = tf.mul(b, [0.1140]); const blueNorm = tf.mul(blue, [0.1140]);
const grayscale = tf.addN([r1, g1, b1]); red.dispose();
return grayscale; green.dispose();
} blue.dispose();
return g; const grayscale = tf.addN([redNorm, greenNorm, blueNorm]);
} redNorm.dispose();
return getImage(image, config.face.emotion.inputSize); greenNorm.dispose();
}); blueNorm.dispose();
const obj = []; const obj = [];
if (config.face.emotion.enabled) { if (config.face.emotion.enabled) {
const emotionT = await models.emotion.predict(enhance); const emotionT = await models.emotion.predict(grayscale);
const data = await emotionT.data(); const data = await emotionT.data();
for (let i = 0; i < data.length; i++) { for (let i = 0; i < data.length; i++) {
if (multiplier * data[i] > config.face.emotion.minConfidence) obj.push({ score: Math.min(0.99, Math.trunc(100 * multiplier * data[i]) / 100), emotion: annotations[i] }); if (multiplier * data[i] > config.face.emotion.minConfidence) obj.push({ score: Math.min(0.99, Math.trunc(100 * multiplier * data[i]) / 100), emotion: annotations[i] });
@ -53,7 +41,7 @@ async function predict(image, config) {
obj.sort((a, b) => b.score - a.score); obj.sort((a, b) => b.score - a.score);
tf.dispose(emotionT); tf.dispose(emotionT);
} }
tf.dispose(enhance); tf.dispose(grayscale);
last = obj; last = obj;
return obj; return obj;
} }

8
src/facemesh/blazeface.js
View File

@ -144,13 +144,7 @@ class BlazeFaceModel {
} }
async estimateFaces(input) { async estimateFaces(input) {
const imageRaw = !(input instanceof tf.Tensor) ? tf.browser.fromPixels(input) : input; const { boxes, scaleFactor } = await this.getBoundingBoxes(input);
const imageCast = imageRaw.toFloat();
const image = imageCast.expandDims(0);
imageRaw.dispose();
imageCast.dispose();
const { boxes, scaleFactor } = await this.getBoundingBoxes(image);
image.dispose();
return Promise.all(boxes.map(async (face) => { return Promise.all(boxes.map(async (face) => {
const scaledBox = scaleBoxFromPrediction(face, scaleFactor); const scaledBox = scaleBoxFromPrediction(face, scaleFactor);
const [landmarkData, boxData, probabilityData] = await Promise.all([face.landmarks, scaledBox, face.probability].map(async (d) => d.array())); const [landmarkData, boxData, probabilityData] = await Promise.all([face.landmarks, scaledBox, face.probability].map(async (d) => d.array()));

8
src/facemesh/facemesh.js
View File

@ -13,13 +13,7 @@ class MediaPipeFaceMesh {
async estimateFaces(input, config) { async estimateFaces(input, config) {
if (config) this.config = config; if (config) this.config = config;
const imageRaw = !(input instanceof tf.Tensor) ? tf.browser.fromPixels(input) : input; const predictions = await this.pipeline.predict(input, config);
const imageCast = imageRaw.toFloat();
const image = imageCast.expandDims(0);
imageRaw.dispose();
imageCast.dispose();
const predictions = await this.pipeline.predict(image, config);
tf.dispose(image);
const results = []; const results = [];
for (const prediction of (predictions || [])) { for (const prediction of (predictions || [])) {
// guard against disposed tensors on long running operations such as pause in middle of processing // guard against disposed tensors on long running operations such as pause in middle of processing

24
src/handpose/handdetector.js
View File

@ -32,9 +32,9 @@ class HandDetector {
} }
async getBoundingBoxes(input) { async getBoundingBoxes(input) {
const normalizedInput = tf.tidy(() => tf.mul(tf.sub(input, 0.5), 2)); const batchedPrediction = this.model.predict(input);
const batchedPrediction = this.model.predict(normalizedInput);
const prediction = batchedPrediction.squeeze(); const prediction = batchedPrediction.squeeze();
console.log(prediction);
// Regression score for each anchor point. // Regression score for each anchor point.
const scores = tf.tidy(() => tf.sigmoid(tf.slice(prediction, [0, 0], [-1, 1])).squeeze()); const scores = tf.tidy(() => tf.sigmoid(tf.slice(prediction, [0, 0], [-1, 1])).squeeze());
// Bounding box for each anchor point. // Bounding box for each anchor point.
@ -42,11 +42,7 @@ class HandDetector {
const boxes = this.normalizeBoxes(rawBoxes); const boxes = this.normalizeBoxes(rawBoxes);
const boxesWithHandsTensor = await tf.image.nonMaxSuppressionAsync(boxes, scores, this.maxHands, this.iouThreshold, this.scoreThreshold); const boxesWithHandsTensor = await tf.image.nonMaxSuppressionAsync(boxes, scores, this.maxHands, this.iouThreshold, this.scoreThreshold);
const boxesWithHands = await boxesWithHandsTensor.array(); const boxesWithHands = await boxesWithHandsTensor.array();
const toDispose = [normalizedInput, batchedPrediction, boxesWithHandsTensor, prediction, boxes, rawBoxes, scores]; const toDispose = [batchedPrediction, boxesWithHandsTensor, prediction, boxes, rawBoxes, scores];
// if (boxesWithHands.length === 0) {
// toDispose.forEach((tensor) => tensor.dispose());
// return null;
// }
const detectedHands = tf.tidy(() => { const detectedHands = tf.tidy(() => {
const detectedBoxes = []; const detectedBoxes = [];
for (const i in boxesWithHands) { for (const i in boxesWithHands) {
@ -69,12 +65,18 @@ class HandDetector {
* @param input The image to classify. * @param input The image to classify.
*/ */
async estimateHandBounds(input, config) { async estimateHandBounds(input, config) {
const inputHeight = input.shape[1]; // const inputHeight = input.shape[2];
const inputWidth = input.shape[2]; // const inputWidth = input.shape[1];
this.iouThreshold = config.iouThreshold; this.iouThreshold = config.iouThreshold;
this.scoreThreshold = config.scoreThreshold; this.scoreThreshold = config.scoreThreshold;
this.maxHands = config.maxHands; this.maxHands = config.maxHands;
const image = tf.tidy(() => input.resizeBilinear([this.width, this.height]).div(255)); const resized = input.resizeBilinear([this.width, this.height]);
const divided = resized.div(255);
const normalized = divided.sub(0.5);
const image = normalized.mul(2.0);
resized.dispose();
divided.dispose();
normalized.dispose();
const predictions = await this.getBoundingBoxes(image); const predictions = await this.getBoundingBoxes(image);
image.dispose(); image.dispose();
if (!predictions || (predictions.length === 0)) return null; if (!predictions || (predictions.length === 0)) return null;
@ -87,7 +89,7 @@ class HandDetector {
const palmLandmarks = await prediction.palmLandmarks.array(); const palmLandmarks = await prediction.palmLandmarks.array();
prediction.boxes.dispose(); prediction.boxes.dispose();
prediction.palmLandmarks.dispose(); prediction.palmLandmarks.dispose();
hands.push(bounding.scaleBoxCoordinates({ startPoint, endPoint, palmLandmarks }, [inputWidth / this.width, inputHeight / this.height])); hands.push(bounding.scaleBoxCoordinates({ startPoint, endPoint, palmLandmarks }, [input.shape[2] / this.width, input.shape[1] / this.height]));
} }
return hands; return hands;
} }

9
src/handpose/handpose.js
View File

@ -12,14 +12,7 @@ class HandPose {
this.skipFrames = config.skipFrames; this.skipFrames = config.skipFrames;
this.detectionConfidence = config.minConfidence; this.detectionConfidence = config.minConfidence;
this.maxHands = config.maxHands; this.maxHands = config.maxHands;
const image = tf.tidy(() => { const predictions = await this.pipeline.estimateHands(input, config);
if (!(input instanceof tf.Tensor)) {
input = tf.browser.fromPixels(input);
}
return input.toFloat().expandDims(0);
});
const predictions = await this.pipeline.estimateHands(image, config);
image.dispose();
const hands = []; const hands = [];
if (!predictions) return hands; if (!predictions) return hands;
for (const prediction of predictions) { for (const prediction of predictions) {

2
src/handpose/pipeline.js
View File

@ -76,7 +76,7 @@ class HandPipeline {
} }
async estimateHands(image, config) { async estimateHands(image, config) {
this.maxContinuousChecks = config.skipFrames; this.skipFrames = config.skipFrames;
this.detectionConfidence = config.minConfidence; this.detectionConfidence = config.minConfidence;
this.maxHands = config.maxHands; this.maxHands = config.maxHands;
this.runsWithoutHandDetector++; this.runsWithoutHandDetector++;

29
src/human.js
View File

@ -71,7 +71,9 @@ function mergeDeep(...objects) {
function sanity(input) { function sanity(input) {
if (!input) return 'input is not defined'; if (!input) return 'input is not defined';
if (tf.ENV.flags.IS_BROWSER && (input instanceof ImageData || input instanceof HTMLImageElement || input instanceof HTMLCanvasElement || input instanceof HTMLVideoElement || input instanceof HTMLMediaElement)) { if (!(input instanceof tf.Tensor)
|| (tf.ENV.flags.IS_BROWSER
&& (input instanceof ImageData || input instanceof HTMLImageElement || input instanceof HTMLCanvasElement || input instanceof HTMLVideoElement || input instanceof HTMLMediaElement))) {
const width = input.naturalWidth || input.videoWidth || input.width || (input.shape && (input.shape[1] > 0)); const width = input.naturalWidth || input.videoWidth || input.width || (input.shape && (input.shape[1] > 0));
if (!width || (width === 0)) return 'input is empty'; if (!width || (width === 0)) return 'input is empty';
} }
@ -99,6 +101,20 @@ async function load(userConfig) {
if (config.face.enabled && config.face.emotion.enabled && !models.emotion) models.emotion = await emotion.load(config); if (config.face.enabled && config.face.emotion.enabled && !models.emotion) models.emotion = await emotion.load(config);
} }
function tfImage(input) {
let image;
if (input instanceof tf.Tensor) {
image = tf.clone(input);
} else {
const pixels = tf.browser.fromPixels(input);
const casted = pixels.toFloat();
image = casted.expandDims(0);
pixels.dispose();
casted.dispose();
}
return image;
}
async function detect(input, userConfig = {}) { async function detect(input, userConfig = {}) {
state = 'config'; state = 'config';
const perf = {}; const perf = {};
@ -151,11 +167,13 @@ async function detect(input, userConfig = {}) {
analyze('Start Detect:'); analyze('Start Detect:');
const imageTensor = tfImage(input);
// run posenet // run posenet
state = 'run:body'; state = 'run:body';
timeStamp = now(); timeStamp = now();
analyze('Start PoseNet'); analyze('Start PoseNet');
const poseRes = config.body.enabled ? await models.posenet.estimatePoses(input, config.body) : []; const poseRes = config.body.enabled ? await models.posenet.estimatePoses(imageTensor, config.body) : [];
analyze('End PoseNet:'); analyze('End PoseNet:');
perf.body = Math.trunc(now() - timeStamp); perf.body = Math.trunc(now() - timeStamp);
@ -163,7 +181,7 @@ async function detect(input, userConfig = {}) {
state = 'run:hand'; state = 'run:hand';
timeStamp = now(); timeStamp = now();
analyze('Start HandPose:'); analyze('Start HandPose:');
const handRes = config.hand.enabled ? await models.handpose.estimateHands(input, config.hand) : []; const handRes = config.hand.enabled ? await models.handpose.estimateHands(imageTensor, config.hand) : [];
analyze('End HandPose:'); analyze('End HandPose:');
perf.hand = Math.trunc(now() - timeStamp); perf.hand = Math.trunc(now() - timeStamp);
@ -173,7 +191,7 @@ async function detect(input, userConfig = {}) {
state = 'run:face'; state = 'run:face';
timeStamp = now(); timeStamp = now();
analyze('Start FaceMesh:'); analyze('Start FaceMesh:');
const faces = await models.facemesh.estimateFaces(input, config.face); const faces = await models.facemesh.estimateFaces(imageTensor, config.face);
perf.face = Math.trunc(now() - timeStamp); perf.face = Math.trunc(now() - timeStamp);
for (const face of faces) { for (const face of faces) {
// is something went wrong, skip the face // is something went wrong, skip the face
@ -210,10 +228,11 @@ async function detect(input, userConfig = {}) {
emotion: emotionData, emotion: emotionData,
iris: (iris !== 0) ? Math.trunc(100 * 11.7 /* human iris size in mm */ / iris) / 100 : 0, iris: (iris !== 0) ? Math.trunc(100 * 11.7 /* human iris size in mm */ / iris) / 100 : 0,
}); });
}
analyze('End FaceMesh:'); analyze('End FaceMesh:');
} }
}
imageTensor.dispose();
state = 'idle'; state = 'idle';
if (config.scoped) tf.engine().endScope(); if (config.scoped) tf.engine().endScope();

7
src/posenet/modelPoseNet.js
View File

@ -31,8 +31,9 @@ class PoseNet {
async estimatePoses(input, config) { async estimatePoses(input, config) {
const outputStride = config.outputStride; const outputStride = config.outputStride;
// const inputResolution = config.inputResolution; // const inputResolution = config.inputResolution;
const [height, width] = util.getInputTensorDimensions(input); const height = input.shape[1];
const { resized, padding } = util.padAndResizeTo(input, [config.inputResolution, config.inputResolution]); const width = input.shape[2];
const resized = util.resizeTo(input, [config.inputResolution, config.inputResolution]);
const { heatmapScores, offsets, displacementFwd, displacementBwd } = this.baseModel.predict(resized); const { heatmapScores, offsets, displacementFwd, displacementBwd } = this.baseModel.predict(resized);
const allTensorBuffers = await util.toTensorBuffers3D([heatmapScores, offsets, displacementFwd, displacementBwd]); const allTensorBuffers = await util.toTensorBuffers3D([heatmapScores, offsets, displacementFwd, displacementBwd]);
const scoresBuffer = allTensorBuffers[0]; const scoresBuffer = allTensorBuffers[0];
@ -40,7 +41,7 @@ class PoseNet {
const displacementsFwdBuffer = allTensorBuffers[2]; const displacementsFwdBuffer = allTensorBuffers[2];
const displacementsBwdBuffer = allTensorBuffers[3]; const displacementsBwdBuffer = allTensorBuffers[3];
const poses = await decodeMultiple.decodeMultiplePoses(scoresBuffer, offsetsBuffer, displacementsFwdBuffer, displacementsBwdBuffer, outputStride, config.maxDetections, config.scoreThreshold, config.nmsRadius); const poses = await decodeMultiple.decodeMultiplePoses(scoresBuffer, offsetsBuffer, displacementsFwdBuffer, displacementsBwdBuffer, outputStride, config.maxDetections, config.scoreThreshold, config.nmsRadius);
const resultPoses = util.scaleAndFlipPoses(poses, [height, width], [config.inputResolution, config.inputResolution], padding); const resultPoses = util.scaleAndFlipPoses(poses, [height, width], [config.inputResolution, config.inputResolution]);
heatmapScores.dispose(); heatmapScores.dispose();
offsets.dispose(); offsets.dispose();
displacementFwd.dispose(); displacementFwd.dispose();

71
src/posenet/util.js
View File

@ -1,4 +1,3 @@
const tf = require('@tensorflow/tfjs');
const kpt = require('./keypoints'); const kpt = require('./keypoints');
function eitherPointDoesntMeetConfidence(a, b, minConfidence) { function eitherPointDoesntMeetConfidence(a, b, minConfidence) {
@ -41,78 +40,28 @@ async function toTensorBuffers3D(tensors) {
} }
exports.toTensorBuffers3D = toTensorBuffers3D; exports.toTensorBuffers3D = toTensorBuffers3D;
function scalePose(pose, scaleY, scaleX, offsetY = 0, offsetX = 0) { function scalePose(pose, scaleY, scaleX) {
return { return {
score: pose.score, score: pose.score,
keypoints: pose.keypoints.map(({ score, part, position }) => ({ keypoints: pose.keypoints.map(({ score, part, position }) => ({
score, score,
part, part,
position: { position: { x: position.x * scaleX, y: position.y * scaleY },
x: position.x * scaleX + offsetX,
y: position.y * scaleY + offsetY,
},
})), })),
}; };
} }
exports.scalePose = scalePose; exports.scalePose = scalePose;
function scalePoses(poses, scaleY, scaleX, offsetY = 0, offsetX = 0) { function resizeTo(image, [targetH, targetW]) {
if (scaleX === 1 && scaleY === 1 && offsetY === 0 && offsetX === 0) { const input = image.squeeze(0);
return poses; const resized = input.resizeBilinear([targetH, targetW]);
input.dispose();
return resized;
} }
return poses.map((pose) => scalePose(pose, scaleY, scaleX, offsetY, offsetX)); exports.resizeTo = resizeTo;
}
exports.scalePoses = scalePoses;
function getInputTensorDimensions(input) { function scaleAndFlipPoses(poses, [height, width], [inputResolutionHeight, inputResolutionWidth]) {
return input instanceof tf.Tensor ? [input.shape[0], input.shape[1]] : [input.height, input.width]; const scaledPoses = poses.map((pose) => scalePose(pose, height / inputResolutionHeight, width / inputResolutionWidth));
}
exports.getInputTensorDimensions = getInputTensorDimensions;
function toInputTensor(input) {
return input instanceof tf.Tensor ? input : tf.browser.fromPixels(input);
}
exports.toInputTensor = toInputTensor;
function toResizedInputTensor(input, resizeHeight, resizeWidth) {
return tf.tidy(() => {
const imageTensor = toInputTensor(input);
return imageTensor.resizeBilinear([resizeHeight, resizeWidth]);
});
}
exports.toResizedInputTensor = toResizedInputTensor;
function padAndResizeTo(input, [targetH, targetW]) {
const [height, width] = getInputTensorDimensions(input);
const targetAspect = targetW / targetH;
const aspect = width / height;
let [padT, padB, padL, padR] = [0, 0, 0, 0];
if (aspect < targetAspect) {
// pads the width
padT = 0;
padB = 0;
padL = Math.round(0.5 * (targetAspect * height - width));
padR = Math.round(0.5 * (targetAspect * height - width));
} else {
// pads the height
padT = Math.round(0.5 * ((1.0 / targetAspect) * width - height));
padB = Math.round(0.5 * ((1.0 / targetAspect) * width - height));
padL = 0;
padR = 0;
}
const resized = tf.tidy(() => {
let imageTensor = toInputTensor(input);
imageTensor = tf.pad3d(imageTensor, [[padT, padB], [padL, padR], [0, 0]]);
return imageTensor.resizeBilinear([targetH, targetW]);
});
return { resized, padding: { top: padT, left: padL, right: padR, bottom: padB } };
}
exports.padAndResizeTo = padAndResizeTo;
function scaleAndFlipPoses(poses, [height, width], [inputResolutionHeight, inputResolutionWidth], padding) {
const scaleY = (height + padding.top + padding.bottom) / (inputResolutionHeight);
const scaleX = (width + padding.left + padding.right) / (inputResolutionWidth);
const scaledPoses = scalePoses(poses, scaleY, scaleX, -padding.top, -padding.left);
return scaledPoses; return scaledPoses;
} }
exports.scaleAndFlipPoses = scaleAndFlipPoses; exports.scaleAndFlipPoses = scaleAndFlipPoses;

14
src/ssrnet/ssrnet.js
View File

@ -4,13 +4,6 @@ const models = {};
let last = { age: 0, gender: '' }; let last = { age: 0, gender: '' };
let frame = 0; let frame = 0;
async function getImage(image, size) {
const buffer = tf.browser.fromPixels(image);
const resize = tf.image.resizeBilinear(buffer, [size, size]);
const expand = tf.cast(tf.expandDims(resize, 0), 'float32');
return expand;
}
async function loadAge(config) { async function loadAge(config) {
if (!models.age) models.age = await tf.loadGraphModel(config.face.age.modelPath); if (!models.age) models.age = await tf.loadGraphModel(config.face.age.modelPath);
return models.age; return models.age;
@ -27,14 +20,9 @@ async function predict(image, config) {
return last; return last;
} }
frame = 0; frame = 0;
let enhance;
if (image instanceof tf.Tensor) {
const resize = tf.image.resizeBilinear(image, [config.face.age.inputSize, config.face.age.inputSize], false); const resize = tf.image.resizeBilinear(image, [config.face.age.inputSize, config.face.age.inputSize], false);
enhance = tf.mul(resize, [255.0]); const enhance = tf.mul(resize, [255.0]);
tf.dispose(resize); tf.dispose(resize);
} else {
enhance = await getImage(image, config.face.age.inputSize);
}
const promises = []; const promises = [];
let ageT; let ageT;