update node demos

CHANGELOG.md

@@ -1,7 +1,7 @@
 # @vladmandic/face-api  
 
-Version: **1.1.4**  
-Description: **FaceAPI: AI-powered Face Detection, Face Embedding & Recognition Using Tensorflow/JS**  
+Version: **1.1.5**  
+Description: **FaceAPI: AI-powered Face Detection, Description & Recognition using Tensorflow/JS**  
 
 Author: **Vladimir Mandic <mandic00@live.com>**  
 License: **MIT** </LICENSE>  
@@ -9,8 +9,12 @@ Repository: **<git+https://github.com/vladmandic/face-api.git>**
 
 ## Changelog
 
-### **HEAD -> master** 2021/03/19 mandic00@live.com
+### **HEAD -> master** 2021/03/25 mandic00@live.com
 
+
+### **1.1.5** 2021/03/23 mandic00@live.com
+
+- add node-canvas demo
 - refactoring
 
 ### **1.1.4** 2021/03/18 mandic00@live.com

README.md

@@ -54,9 +54,7 @@ Example can be accessed directly using Git pages using URL:
 
 Three NodeJS examples are:
 
-- `/demo/node-singleprocess.js`:  
-  Regular usage of `FaceAPI` from `NodeJS`  
-- `/demo/node-singleprocess.js`:  
+- `/demo/node.js`:  
   Regular usage of `FaceAPI` from `NodeJS`  
   Using `TFJS` native methods to load images
 - `/demo/node-canvas.js`:  

demo/node-canvas.js

@@ -5,24 +5,24 @@ const process = require('process');
 const path = require('path');
 // eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require
 const log = require('@vladmandic/pilogger');
-// eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require
+// eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require, no-unused-vars
 const tf = require('@tensorflow/tfjs-node');
+// eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require
+const canvas = require('canvas');
 const faceapi = require('../dist/face-api.node.js'); // this is equivalent to '@vladmandic/faceapi'
 
 const modelPathRoot = '../model';
 const imgPathRoot = './demo'; // modify to include your sample images
-const minScore = 0.1;
+const minConfidence = 0.15;
 const maxResults = 5;
 let optionsSSDMobileNet;
 
-async function image(img) {
-  const buffer = fs.readFileSync(img);
-  const decoded = tf.node.decodeImage(buffer);
-  const casted = decoded.toFloat();
-  const result = casted.expandDims(0);
-  decoded.dispose();
-  casted.dispose();
-  return result;
+async function image(input) {
+  const img = await canvas.loadImage(input);
+  const c = canvas.createCanvas(img.width, img.height);
+  const ctx = c.getContext('2d');
+  ctx.drawImage(img, 0, 0, img.width, img.height);
+  return c;
 }
 
 async function detect(tensor) {
@@ -35,10 +35,19 @@ async function detect(tensor) {
   return result;
 }
 
+function print(face) {
+  const expression = Object.entries(face.expressions).reduce((acc, val) => ((val[1] > acc[1]) ? val : acc), ['', 0]);
+  const box = [face.alignedRect._box._x, face.alignedRect._box._y, face.alignedRect._box._width, face.alignedRect._box._height];
+  const gender = `Gender: ${Math.round(100 * face.genderProbability)}% ${face.gender}`;
+  log.data(`Detection confidence: ${Math.round(100 * face.detection._score)}% ${gender} Age: ${Math.round(10 * face.age) / 10} Expression: ${Math.round(100 * expression[1])}% ${expression[0]} Box: ${box.map((a) => Math.round(a))}`);
+}
+
 async function main() {
   log.header();
   log.info('FaceAPI single-process test');
 
+  faceapi.env.monkeyPatch({ Canvas: canvas.Canvas, Image: canvas.Image, ImageData: canvas.ImageData });
+
   await faceapi.tf.setBackend('tensorflow');
   await faceapi.tf.enableProdMode();
   await faceapi.tf.ENV.set('DEBUG', false);
@@ -53,33 +62,27 @@ async function main() {
   await faceapi.nets.faceLandmark68Net.loadFromDisk(modelPath);
   await faceapi.nets.faceRecognitionNet.loadFromDisk(modelPath);
   await faceapi.nets.faceExpressionNet.loadFromDisk(modelPath);
-  optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options({ minConfidence: minScore, maxResults });
+  optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options({ minConfidence, maxResults });
 
   if (process.argv.length !== 3) {
     const t0 = process.hrtime.bigint();
     const dir = fs.readdirSync(imgPathRoot);
     for (const img of dir) {
       if (!img.toLocaleLowerCase().endsWith('.jpg')) continue;
-      const tensor = await image(path.join(imgPathRoot, img));
-      const result = await detect(tensor);
+      const c = await image(path.join(imgPathRoot, img));
+      const result = await detect(c);
       log.data('Image:', img, 'Detected faces:', result.length);
-      for (const i of result) {
-        log.data('Gender:', Math.round(100 * i.genderProbability), 'probability', i.gender, 'with age', Math.round(10 * i.age) / 10);
-      }
-      tensor.dispose();
+      for (const face of result) print(face);
     }
     const t1 = process.hrtime.bigint();
     log.info('Processed', dir.length, 'images in', Math.trunc(parseInt(t1 - t0) / 1000 / 1000), 'ms');
   } else {
     const param = process.argv[2];
     if (fs.existsSync(param)) {
-      const tensor = await image(param);
-      const result = await detect(tensor);
+      const c = await image(param);
+      const result = await detect(c);
       log.data('Image:', param, 'Detected faces:', result.length);
-      for (const i of result) {
-        log.data('Gender:', Math.round(100 * i.genderProbability), 'probability', i.gender, 'with age', Math.round(10 * i.age) / 10);
-      }
-      tensor.dispose();
+      for (const face of result) print(face);
     }
   }
 }

demo/node-multiprocess-worker.js

@@ -12,7 +12,7 @@ const faceapi = require('../dist/face-api.node.js'); // this is equivalent to '@
 
 // options used by faceapi
 const modelPathRoot = '../model';
-const minScore = 0.1;
+const minConfidence = 0.15;
 const maxResults = 5;
 let optionsSSDMobileNet;
 
@@ -62,7 +62,7 @@ async function main() {
   await faceapi.nets.faceLandmark68Net.loadFromDisk(modelPath);
   await faceapi.nets.faceRecognitionNet.loadFromDisk(modelPath);
   await faceapi.nets.faceExpressionNet.loadFromDisk(modelPath);
-  optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options({ minConfidence: minScore, maxResults });
+  optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options({ minConfidence, maxResults });
 
   // now we're ready, so send message back to main that it knows it can use this worker
   process.send({ ready: true });

demo/node.js

@@ -5,24 +5,24 @@ const process = require('process');
 const path = require('path');
 // eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require
 const log = require('@vladmandic/pilogger');
-// eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require, no-unused-vars
-const tf = require('@tensorflow/tfjs-node');
 // eslint-disable-next-line import/no-extraneous-dependencies, node/no-unpublished-require
-const canvas = require('canvas');
+const tf = require('@tensorflow/tfjs-node');
 const faceapi = require('../dist/face-api.node.js'); // this is equivalent to '@vladmandic/faceapi'
 
 const modelPathRoot = '../model';
 const imgPathRoot = './demo'; // modify to include your sample images
-const minScore = 0.1;
+const minConfidence = 0.15;
 const maxResults = 5;
 let optionsSSDMobileNet;
 
-async function image(input) {
-  const img = canvas.loadImage(input);
-  const c = canvas.createCanvas(img.width, img.height);
-  const ctx = c.getContext('2d');
-  ctx.drawImage(img, 0, 0, img.width, img.height);
-  return c;
+async function image(img) {
+  const buffer = fs.readFileSync(img);
+  const decoded = tf.node.decodeImage(buffer);
+  const casted = decoded.toFloat();
+  const result = casted.expandDims(0);
+  decoded.dispose();
+  casted.dispose();
+  return result;
 }
 
 async function detect(tensor) {
@@ -35,12 +35,17 @@ async function detect(tensor) {
   return result;
 }
 
+function print(face) {
+  const expression = Object.entries(face.expressions).reduce((acc, val) => ((val[1] > acc[1]) ? val : acc), ['', 0]);
+  const box = [face.alignedRect._box._x, face.alignedRect._box._y, face.alignedRect._box._width, face.alignedRect._box._height];
+  const gender = `Gender: ${Math.round(100 * face.genderProbability)}% ${face.gender}`;
+  log.data(`Detection confidence: ${Math.round(100 * face.detection._score)}% ${gender} Age: ${Math.round(10 * face.age) / 10} Expression: ${Math.round(100 * expression[1])}% ${expression[0]} Box: ${box.map((a) => Math.round(a))}`);
+}
+
 async function main() {
   log.header();
   log.info('FaceAPI single-process test');
 
-  faceapi.env.monkeyPatch({ Canvas: canvas.Canvas, Image: canvas.Image, ImageData: canvas.ImageData });
-
   await faceapi.tf.setBackend('tensorflow');
   await faceapi.tf.enableProdMode();
   await faceapi.tf.ENV.set('DEBUG', false);
@@ -55,7 +60,7 @@ async function main() {
   await faceapi.nets.faceLandmark68Net.loadFromDisk(modelPath);
   await faceapi.nets.faceRecognitionNet.loadFromDisk(modelPath);
   await faceapi.nets.faceExpressionNet.loadFromDisk(modelPath);
-  optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options({ minConfidence: minScore, maxResults });
+  optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options({ minConfidence, maxResults });
 
   if (process.argv.length !== 3) {
     const t0 = process.hrtime.bigint();
@@ -65,9 +70,7 @@ async function main() {
       const tensor = await image(path.join(imgPathRoot, img));
       const result = await detect(tensor);
       log.data('Image:', img, 'Detected faces:', result.length);
-      for (const i of result) {
-        log.data('Gender:', Math.round(100 * i.genderProbability), 'probability', i.gender, 'with age', Math.round(10 * i.age) / 10);
-      }
+      for (const face of result) print(face);
       tensor.dispose();
     }
     const t1 = process.hrtime.bigint();
@@ -78,9 +81,7 @@ async function main() {
       const tensor = await image(param);
       const result = await detect(tensor);
       log.data('Image:', param, 'Detected faces:', result.length);
-      for (const i of result) {
-        log.data('Gender:', Math.round(100 * i.genderProbability), 'probability', i.gender, 'with age', Math.round(10 * i.age) / 10);
-      }
+      for (const face of result) print(face);
       tensor.dispose();
     }
   }

package.json

@@ -21,7 +21,7 @@
     "url": "git+https://github.com/vladmandic/face-api.git"
   },
   "scripts": {
-    "start": "node --trace-warnings demo/node-singleprocess.js",
+    "start": "node --trace-warnings demo/node.js",
     "dev": "node --trace-warnings server/serve.js",
     "build": "rimraf dist/* types/* typedoc/* && node server/build.js",
     "lint": "eslint src/**/* demo/*.js server/*.js",
@@ -43,14 +43,14 @@
     "@tensorflow/tfjs-backend-wasm": "^3.3.0",
     "@tensorflow/tfjs-node": "^3.3.0",
     "@tensorflow/tfjs-node-gpu": "^3.3.0",
-    "@types/node": "^14.14.35",
+    "@types/node": "^14.14.36",
     "@typescript-eslint/eslint-plugin": "^4.19.0",
     "@typescript-eslint/parser": "^4.19.0",
     "@vladmandic/pilogger": "^0.2.15",
     "canvas": "^2.7.0",
     "chokidar": "^3.5.1",
     "dayjs": "^1.10.4",
-    "esbuild": "^0.9.6",
+    "esbuild": "^0.10.1",
     "eslint": "^7.22.0",
     "eslint-config-airbnb-base": "^14.2.1",
     "eslint-plugin-import": "^2.22.1",
@@ -61,7 +61,7 @@
     "seedrandom": "^3.0.5",
     "simple-git": "^2.37.0",
     "tslib": "^2.1.0",
-    "typedoc": "^0.20.33",
+    "typedoc": "^0.20.34",
     "typescript": "^4.2.3"
   }
 }

server/build.js

@@ -42,9 +42,9 @@ const tsconfig = {
 // common configuration
 const common = {
   banner,
-  minifyWhitespace: true,
-  minifyIdentifiers: true,
-  minifySyntax: true,
+  minifyWhitespace: false,
+  minifyIdentifiers: false,
+  minifySyntax: false,
   bundle: true,
   sourcemap: true,
   metafile: true,

src/dom/awaitMediaLoaded.ts

@@ -4,9 +4,7 @@ import { isMediaLoaded } from './isMediaLoaded';
 export function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {
   // eslint-disable-next-line consistent-return
   return new Promise((resolve, reject) => {
-    if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {
-      return resolve(null);
-    }
+    if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) return resolve(null);
 
     function onError(e: Event) {
       if (!e.currentTarget) return;

src/dom/extractFaces.ts

@@ -16,29 +16,17 @@ import { TNetInput } from './types';
  */
 export async function extractFaces(input: TNetInput, detections: Array<FaceDetection | Rect>): Promise<HTMLCanvasElement[]> {
   const { Canvas } = env.getEnv();
-
   let canvas = input as HTMLCanvasElement;
-
   if (!(input instanceof Canvas)) {
     const netInput = await toNetInput(input);
-
-    if (netInput.batchSize > 1) {
-      throw new Error('extractFaces - batchSize > 1 not supported');
-    }
-
+    if (netInput.batchSize > 1) throw new Error('extractFaces - batchSize > 1 not supported');
     const tensorOrCanvas = netInput.getInput(0);
-    canvas = tensorOrCanvas instanceof Canvas
-      ? tensorOrCanvas
-      : await imageTensorToCanvas(tensorOrCanvas);
+    canvas = tensorOrCanvas instanceof Canvas ? tensorOrCanvas : await imageTensorToCanvas(tensorOrCanvas);
   }
-
   const ctx = getContext2dOrThrow(canvas);
   const boxes = detections
-    .map((det) => (det instanceof FaceDetection
-      ? det.forSize(canvas.width, canvas.height).box.floor()
-      : det))
+    .map((det) => (det instanceof FaceDetection ? det.forSize(canvas.width, canvas.height).box.floor() : det))
     .map((box) => box.clipAtImageBorders(canvas.width, canvas.height));
-
   return boxes.map(({ x, y, width, height }) => {
     const faceImg = createCanvas({ width, height });
     if (width > 0 && height > 0) getContext2dOrThrow(faceImg).putImageData(ctx.getImageData(x, y, width, height), 0, 0);

src/dom/toNetInput.ts

@@ -13,44 +13,23 @@ import { TNetInput } from './types';
  * @returns A NetInput instance, which can be passed into one of the neural networks.
  */
 export async function toNetInput(inputs: TNetInput): Promise<NetInput> {
-  if (inputs instanceof NetInput) {
-    return inputs;
-  }
-
-  const inputArgArray = Array.isArray(inputs)
-    ? inputs
-    : [inputs];
-
-  if (!inputArgArray.length) {
-    throw new Error('toNetInput - empty array passed as input');
-  }
-
+  if (inputs instanceof NetInput) return inputs;
+  const inputArgArray = Array.isArray(inputs) ? inputs : [inputs];
+  if (!inputArgArray.length) throw new Error('toNetInput - empty array passed as input');
   const getIdxHint = (idx: number) => (Array.isArray(inputs) ? ` at input index ${idx}:` : '');
-
   const inputArray = inputArgArray.map(resolveInput);
-
   inputArray.forEach((input, i) => {
     if (!isMediaElement(input) && !isTensor3D(input) && !isTensor4D(input)) {
-      if (typeof inputArgArray[i] === 'string') {
-        throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);
-      }
-
+      if (typeof inputArgArray[i] === 'string') throw new Error(`toNetInput -${getIdxHint(i)} string passed, but could not resolve HTMLElement for element id ${inputArgArray[i]}`);
       throw new Error(`toNetInput -${getIdxHint(i)} expected media to be of type HTMLImageElement | HTMLVideoElement | HTMLCanvasElement | tf.Tensor3D, or to be an element id`);
     }
-
     if (isTensor4D(input)) {
       // if tf.Tensor4D is passed in the input array, the batch size has to be 1
       const batchSize = input.shape[0];
-      if (batchSize !== 1) {
-        throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);
-      }
+      if (batchSize !== 1) throw new Error(`toNetInput -${getIdxHint(i)} tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`);
     }
   });
-
   // wait for all media elements being loaded
-  await Promise.all(
-    inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)),
-  );
-
+  await Promise.all(inputArray.map((input) => isMediaElement(input) && awaitMediaLoaded(input)));
   return new NetInput(inputArray, Array.isArray(inputs));
 }

src/globalApi/DetectFacesTasks.ts

@@ -13,12 +13,8 @@ import { PredictAllFaceExpressionsTask, PredictSingleFaceExpressionsTask } from
 import { FaceDetectionOptions } from './types';
 
 export class DetectFacesTaskBase<TReturn> extends ComposableTask<TReturn> {
-  constructor(
-    // eslint-disable-next-line no-unused-vars
-    protected input: TNetInput,
-    // eslint-disable-next-line no-unused-vars
-    protected options: FaceDetectionOptions = new SsdMobilenetv1Options(),
-  ) {
+  // eslint-disable-next-line no-unused-vars
+  constructor(protected input: TNetInput, protected options: FaceDetectionOptions = new SsdMobilenetv1Options()) {
     super();
   }
 }

src/globalApi/allFaces.ts

@@ -4,21 +4,13 @@ import { SsdMobilenetv1Options } from '../ssdMobilenetv1/index';
 import { ITinyYolov2Options, TinyYolov2Options } from '../tinyYolov2/index';
 import { detectAllFaces } from './detectFaces';
 
-// export allFaces API for backward compatibility
-
-export async function allFacesSsdMobilenetv1(
-  input: TNetInput,
-  minConfidence?: number,
-): Promise<WithFaceDescriptor<WithFaceLandmarks<WithFaceDetection<{}>>>[]> {
+export async function allFacesSsdMobilenetv1(input: TNetInput, minConfidence?: number): Promise<WithFaceDescriptor<WithFaceLandmarks<WithFaceDetection<{}>>>[]> {
   return detectAllFaces(input, new SsdMobilenetv1Options(minConfidence ? { minConfidence } : {}))
     .withFaceLandmarks()
     .withFaceDescriptors();
 }
 
-export async function allFacesTinyYolov2(
-  input: TNetInput,
-  forwardParams: ITinyYolov2Options = {},
-): Promise<WithFaceDescriptor<WithFaceLandmarks<WithFaceDetection<{}>>>[]> {
+export async function allFacesTinyYolov2(input: TNetInput, forwardParams: ITinyYolov2Options = {}): Promise<WithFaceDescriptor<WithFaceLandmarks<WithFaceDetection<{}>>>[]> {
   return detectAllFaces(input, new TinyYolov2Options(forwardParams))
     .withFaceLandmarks()
     .withFaceDescriptors();

src/ssdMobilenetv1/SsdMobilenetv1.ts

@@ -43,10 +43,7 @@ export class SsdMobilenetv1 extends NeuralNetwork<NetParams> {
     const { maxResults, minConfidence } = new SsdMobilenetv1Options(options);
     const netInput = await toNetInput(input);
 
-    const {
-      boxes: _boxes,
-      scores: _scores,
-    } = this.forwardInput(netInput);
+    const { boxes: _boxes, scores: _scores } = this.forwardInput(netInput);
 
     const boxes = _boxes[0];
     const scores = _scores[0];
@@ -57,13 +54,7 @@ export class SsdMobilenetv1 extends NeuralNetwork<NetParams> {
 
     const scoresData = Array.from(scores.dataSync());
     const iouThreshold = 0.5;
-    const indices = nonMaxSuppression(
-      boxes,
-      scoresData as number[],
-      maxResults,
-      iouThreshold,
-      minConfidence,
-    );
+    const indices = nonMaxSuppression(boxes, scoresData as number[], maxResults, iouThreshold, minConfidence);
 
     const reshapedDims = netInput.getReshapedInputDimensions(0);
     const inputSize = netInput.inputSize as number;
@@ -83,16 +74,8 @@ export class SsdMobilenetv1 extends NeuralNetwork<NetParams> {
         ].map((val) => val * padX);
         return new FaceDetection(
           scoresData[idx] as number,
-          new Rect(
-            left,
-            top,
-            right - left,
-            bottom - top,
-          ),
-          {
-            height: netInput.getInputHeight(0),
-            width: netInput.getInputWidth(0),
-          },
+          new Rect(left, top, right - left, bottom - top),
+          { height: netInput.getInputHeight(0), width: netInput.getInputWidth(0) },
         );
       });