Remove unused face-api files
This commit is contained in:
Shailesh Pandit
parent
bce97ce579
commit
868d19b3d0
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
|
|
@ -1 +0,0 @@
|
|||
[{"weights":[{"name":"dense0/conv0/filters","shape":[3,3,3,32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.008194216092427571,"min":-0.9423348506291708}},{"name":"dense0/conv0/bias","shape":[32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.006839508168837603,"min":-0.8412595047670252}},{"name":"dense0/conv1/depthwise_filter","shape":[3,3,32,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.009194007106855804,"min":-1.2779669878529567}},{"name":"dense0/conv1/pointwise_filter","shape":[1,1,32,32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0036026100317637128,"min":-0.3170296827952067}},{"name":"dense0/conv1/bias","shape":[32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.000740380117706224,"min":-0.06367269012273527}},{"name":"dense0/conv2/depthwise_filter","shape":[3,3,32,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":1,"min":0}},{"name":"dense0/conv2/pointwise_filter","shape":[1,1,32,32],"dtype":"float32","quantization":{"dtype":"uint8","scale":1,"min":0}},{"name":"dense0/conv2/bias","shape":[32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0037702228508743585,"min":-0.6220867703942692}},{"name":"dense1/conv0/depthwise_filter","shape":[3,3,32,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0033707996209462483,"min":-0.421349952618281}},{"name":"dense1/conv0/pointwise_filter","shape":[1,1,32,64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.014611541991140328,"min":-1.8556658328748217}},{"name":"dense1/conv0/bias","shape":[64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.002832523046755323,"min":-0.30307996600281956}},{"name":"dense1/conv1/depthwise_filter","shape":[3,3,64,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.006593170586754294,"min":-0.6329443763284123}},{"name":"dense1/conv1/pointwise_filter","shape":[1,1,64,64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.012215249211180444,"min":-1.6001976466646382}},{"name":"dense1/conv1/bias","shape":[64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.002384825547536214,"min":-0.3028728445370992}},{"name":"dense1/conv2/depthwise_filter","shape":[3,3,64,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.005859645441466687,"min":-0.7617539073906693}},{"name":"dense1/conv2/pointwise_filter","shape":[1,1,64,64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.013121426806730382,"min":-1.7845140457153321}},{"name":"dense1/conv2/bias","shape":[64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0032247188044529336,"min":-0.46435950784122243}},{"name":"dense2/conv0/depthwise_filter","shape":[3,3,64,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.002659512618008782,"min":-0.32977956463308894}},{"name":"dense2/conv0/pointwise_filter","shape":[1,1,64,128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.015499923743453681,"min":-1.9839902391620712}},{"name":"dense2/conv0/bias","shape":[128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0032450980999890497,"min":-0.522460794098237}},{"name":"dense2/conv1/depthwise_filter","shape":[3,3,128,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.005911862382701799,"min":-0.792189559282041}},{"name":"dense2/conv1/pointwise_filter","shape":[1,1,128,128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.021025861478319356,"min":-2.2077154552235325}},{"name":"dense2/conv1/bias","shape":[128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.00349616945958605,"min":-0.46149436866535865}},{"name":"dense2/conv2/depthwise_filter","shape":[3,3,128,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.008104994250278847,"min":-1.013124281284856}},{"name":"dense2/conv2/pointwise_filter","shape":[1,1,128,128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.029337059282789044,"min":-3.5791212325002633}},{"name":"dense2/conv2/bias","shape":[128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0038808938334969913,"min":-0.4230174278511721}},{"name":"fc/weights","shape":[128,136],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.014016061670639936,"min":-1.8921683255363912}},{"name":"fc/bias","shape":[136],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0029505149698724935,"min":0.088760145008564}}],"paths":["face_landmark_68_tiny_model-shard1"]}]
|
||||
Binary file not shown.
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Binary file not shown.
|
|
@ -1 +0,0 @@
|
|||
[{"paths":["mtcnn_model-shard1"],"weights":[{"dtype":"float32","name":"pnet/conv1/weights","shape":[3,3,3,10]},{"dtype":"float32","name":"pnet/conv1/bias","shape":[10]},{"dtype":"float32","name":"pnet/prelu1_alpha","shape":[10]},{"dtype":"float32","name":"pnet/conv2/weights","shape":[3,3,10,16]},{"dtype":"float32","name":"pnet/conv2/bias","shape":[16]},{"dtype":"float32","name":"pnet/prelu2_alpha","shape":[16]},{"dtype":"float32","name":"pnet/conv3/weights","shape":[3,3,16,32]},{"dtype":"float32","name":"pnet/conv3/bias","shape":[32]},{"dtype":"float32","name":"pnet/prelu3_alpha","shape":[32]},{"dtype":"float32","name":"pnet/conv4_1/weights","shape":[1,1,32,2]},{"dtype":"float32","name":"pnet/conv4_1/bias","shape":[2]},{"dtype":"float32","name":"pnet/conv4_2/weights","shape":[1,1,32,4]},{"dtype":"float32","name":"pnet/conv4_2/bias","shape":[4]},{"dtype":"float32","name":"rnet/conv1/weights","shape":[3,3,3,28]},{"dtype":"float32","name":"rnet/conv1/bias","shape":[28]},{"dtype":"float32","name":"rnet/prelu1_alpha","shape":[28]},{"dtype":"float32","name":"rnet/conv2/weights","shape":[3,3,28,48]},{"dtype":"float32","name":"rnet/conv2/bias","shape":[48]},{"dtype":"float32","name":"rnet/prelu2_alpha","shape":[48]},{"dtype":"float32","name":"rnet/conv3/weights","shape":[2,2,48,64]},{"dtype":"float32","name":"rnet/conv3/bias","shape":[64]},{"dtype":"float32","name":"rnet/prelu3_alpha","shape":[64]},{"dtype":"float32","name":"rnet/fc1/weights","shape":[576,128]},{"dtype":"float32","name":"rnet/fc1/bias","shape":[128]},{"dtype":"float32","name":"rnet/prelu4_alpha","shape":[128]},{"dtype":"float32","name":"rnet/fc2_1/weights","shape":[128,2]},{"dtype":"float32","name":"rnet/fc2_1/bias","shape":[2]},{"dtype":"float32","name":"rnet/fc2_2/weights","shape":[128,4]},{"dtype":"float32","name":"rnet/fc2_2/bias","shape":[4]},{"dtype":"float32","name":"onet/conv1/weights","shape":[3,3,3,32]},{"dtype":"float32","name":"onet/conv1/bias","shape":[32]},{"dtype":"float32","name":"onet/prelu1_alpha","shape":[32]},{"dtype":"float32","name":"onet/conv2/weights","shape":[3,3,32,64]},{"dtype":"float32","name":"onet/conv2/bias","shape":[64]},{"dtype":"float32","name":"onet/prelu2_alpha","shape":[64]},{"dtype":"float32","name":"onet/conv3/weights","shape":[3,3,64,64]},{"dtype":"float32","name":"onet/conv3/bias","shape":[64]},{"dtype":"float32","name":"onet/prelu3_alpha","shape":[64]},{"dtype":"float32","name":"onet/conv4/weights","shape":[2,2,64,128]},{"dtype":"float32","name":"onet/conv4/bias","shape":[128]},{"dtype":"float32","name":"onet/prelu4_alpha","shape":[128]},{"dtype":"float32","name":"onet/fc1/weights","shape":[1152,256]},{"dtype":"float32","name":"onet/fc1/bias","shape":[256]},{"dtype":"float32","name":"onet/prelu5_alpha","shape":[256]},{"dtype":"float32","name":"onet/fc2_1/weights","shape":[256,2]},{"dtype":"float32","name":"onet/fc2_1/bias","shape":[2]},{"dtype":"float32","name":"onet/fc2_2/weights","shape":[256,4]},{"dtype":"float32","name":"onet/fc2_2/bias","shape":[4]},{"dtype":"float32","name":"onet/fc2_3/weights","shape":[256,10]},{"dtype":"float32","name":"onet/fc2_3/bias","shape":[10]}]}]
|
||||
Binary file not shown.
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Binary file not shown.
|
|
@ -1 +0,0 @@
|
|||
[{"weights":[{"name":"conv0/filters","shape":[3,3,3,16],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.009007044399485869,"min":-1.2069439495311063}},{"name":"conv0/bias","shape":[16],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.005263455241334205,"min":-0.9211046672334858}},{"name":"conv1/depthwise_filter","shape":[3,3,16,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.004001977630690033,"min":-0.5042491814669441}},{"name":"conv1/pointwise_filter","shape":[1,1,16,32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.013836609615999109,"min":-1.411334180831909}},{"name":"conv1/bias","shape":[32],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0015159862590771096,"min":-0.30926119685173037}},{"name":"conv2/depthwise_filter","shape":[3,3,32,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.002666276225856706,"min":-0.317286870876948}},{"name":"conv2/pointwise_filter","shape":[1,1,32,64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.015265831292844286,"min":-1.6792414422128714}},{"name":"conv2/bias","shape":[64],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0020280554598453,"min":-0.37113414915168985}},{"name":"conv3/depthwise_filter","shape":[3,3,64,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.006100742489683862,"min":-0.8907084034938438}},{"name":"conv3/pointwise_filter","shape":[1,1,64,128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.016276211832083907,"min":-2.0508026908425725}},{"name":"conv3/bias","shape":[128],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.003394414279975143,"min":-0.7637432129944072}},{"name":"conv4/depthwise_filter","shape":[3,3,128,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.006716050119961009,"min":-0.8059260143953211}},{"name":"conv4/pointwise_filter","shape":[1,1,128,256],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.021875603993733724,"min":-2.8875797271728514}},{"name":"conv4/bias","shape":[256],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.0041141652009066415,"min":-0.8187188749804216}},{"name":"conv5/depthwise_filter","shape":[3,3,256,1],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.008423839597141042,"min":-0.9013508368940915}},{"name":"conv5/pointwise_filter","shape":[1,1,256,512],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.030007277283014035,"min":-3.8709387695088107}},{"name":"conv5/bias","shape":[512],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.008402082966823203,"min":-1.4871686851277068}},{"name":"conv8/filters","shape":[1,1,512,25],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.028336129469030042,"min":-4.675461362389957}},{"name":"conv8/bias","shape":[25],"dtype":"float32","quantization":{"dtype":"uint8","scale":0.002268134028303857,"min":-0.41053225912299807}}],"paths":["tiny_face_detector_model-shard1"]}]
|
||||
|
|
@ -1,101 +0,0 @@
|
|||
/* eslint no-prototype-builtins: "off", no-case-declarations: "off", no-undef: "off", no-constant-condition: "off", eqeqeq: "off" */
|
||||
// From: https://github.com/justadudewhohacks/face-api.js/issues/47
|
||||
// This is needed because face-api.js does not support working in a WebWorker natively
|
||||
// Updated Dec 1 2020 to work on latest Chrome (tested in WebWorkers on Chrome Mobile on Android / Google Pixel 3 as well)
|
||||
|
||||
self.Canvas = self.HTMLCanvasElement = OffscreenCanvas;
|
||||
// self.HTMLCanvasElement.name = 'HTMLCanvasElement';
|
||||
// self.Canvas.name = 'Canvas';
|
||||
|
||||
self.CanvasRenderingContext2D = OffscreenCanvasRenderingContext2D;
|
||||
|
||||
function HTMLImageElement() {}
|
||||
function HTMLVideoElement() {}
|
||||
|
||||
self.Image = HTMLImageElement;
|
||||
self.Video = HTMLVideoElement;
|
||||
|
||||
function Storage() {
|
||||
let _data = {};
|
||||
this.clear = function () {
|
||||
return (_data = {});
|
||||
};
|
||||
this.getItem = function (id) {
|
||||
return _data.hasOwnProperty(id) ? _data[id] : undefined;
|
||||
};
|
||||
this.removeItem = function (id) {
|
||||
return delete _data[id];
|
||||
};
|
||||
this.setItem = function (id, val) {
|
||||
return (_data[id] = String(val));
|
||||
};
|
||||
}
|
||||
class Document extends EventTarget {}
|
||||
|
||||
self.document = new Document();
|
||||
|
||||
self.window = self.Window = self;
|
||||
self.localStorage = new Storage();
|
||||
|
||||
function createElement(element) {
|
||||
switch (element) {
|
||||
case 'canvas':
|
||||
const canvas = new Canvas(1, 1);
|
||||
canvas.localName = 'canvas';
|
||||
canvas.nodeName = 'CANVAS';
|
||||
canvas.tagName = 'CANVAS';
|
||||
canvas.nodeType = 1;
|
||||
canvas.innerHTML = '';
|
||||
canvas.remove = () => {
|
||||
console.log('nope');
|
||||
};
|
||||
return canvas;
|
||||
default:
|
||||
console.log('arg', element);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
document.createElement = createElement;
|
||||
document.location = self.location;
|
||||
|
||||
// These are the same checks face-api.js/isBrowser does
|
||||
if (!typeof window == 'object') {
|
||||
console.warn('Check failed: window');
|
||||
}
|
||||
if (typeof document === 'undefined') {
|
||||
console.warn('Check failed: document');
|
||||
}
|
||||
if (typeof HTMLImageElement === 'undefined') {
|
||||
console.warn('Check failed: HTMLImageElement');
|
||||
}
|
||||
if (typeof HTMLCanvasElement === 'undefined') {
|
||||
console.warn('Check failed: HTMLCanvasElement');
|
||||
}
|
||||
if (typeof HTMLVideoElement === 'undefined') {
|
||||
console.warn('Check failed: HTMLVideoElement');
|
||||
}
|
||||
if (typeof ImageData === 'undefined') {
|
||||
console.warn('Check failed: ImageData');
|
||||
}
|
||||
if (typeof CanvasRenderingContext2D === 'undefined') {
|
||||
console.warn('Check failed: CanvasRenderingContext2D');
|
||||
}
|
||||
|
||||
self.window = window;
|
||||
self.document = document;
|
||||
self.HTMLImageElement = HTMLImageElement;
|
||||
self.HTMLVideoElement = HTMLVideoElement;
|
||||
|
||||
// These are the same checks face-api.js/isBrowser does
|
||||
const isBrowserCheck =
|
||||
typeof window === 'object' &&
|
||||
typeof document !== 'undefined' &&
|
||||
typeof HTMLImageElement !== 'undefined' &&
|
||||
typeof HTMLCanvasElement !== 'undefined' &&
|
||||
typeof HTMLVideoElement !== 'undefined' &&
|
||||
typeof ImageData !== 'undefined' &&
|
||||
typeof CanvasRenderingContext2D !== 'undefined';
|
||||
if (!isBrowserCheck) {
|
||||
throw new Error('Failed to monkey patch for face-api, face-api will fail');
|
||||
}
|
||||
|
|
@ -1,70 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
import { gather } from '@tensorflow/tfjs';
|
||||
import { extractFaces } from 'utils/machineLearning';
|
||||
import { AlignedFace, FaceEmbedding } from 'types/machineLearning';
|
||||
import { FaceRecognitionNet } from '../../../thirdparty/face-api/faceRecognitionNet';
|
||||
|
||||
class FAPIFaceEmbeddingService {
|
||||
private faceRecognitionNet: FaceRecognitionNet;
|
||||
private faceSize: number;
|
||||
|
||||
public constructor(faceSize: number = 112) {
|
||||
this.faceRecognitionNet = new FaceRecognitionNet();
|
||||
this.faceSize = faceSize;
|
||||
}
|
||||
|
||||
public async init() {
|
||||
await this.faceRecognitionNet.loadFromUri('/models/face-api/');
|
||||
|
||||
console.log(
|
||||
'loaded faceRecognitionNet: ',
|
||||
this.faceRecognitionNet,
|
||||
await tf.getBackend()
|
||||
);
|
||||
}
|
||||
|
||||
public async getEmbeddingsBatch(faceImagesTensor) {
|
||||
const embeddings = [];
|
||||
for (let i = 0; i < faceImagesTensor.shape[0]; i++) {
|
||||
const face = tf.tidy(() =>
|
||||
gather(faceImagesTensor, i).expandDims()
|
||||
);
|
||||
const embedding =
|
||||
await this.faceRecognitionNet.computeFaceDescriptor(face);
|
||||
tf.dispose(face);
|
||||
embeddings[i] = embedding;
|
||||
}
|
||||
|
||||
return embeddings;
|
||||
}
|
||||
|
||||
public async getEmbeddings(image: tf.Tensor3D, faces: AlignedFace[]) {
|
||||
if (!faces || faces.length < 1) {
|
||||
return {
|
||||
embeddings: [],
|
||||
faceImages: [],
|
||||
};
|
||||
}
|
||||
|
||||
const boxes = faces.map((f) => f.detection.box);
|
||||
const faceImagesTensor = extractFaces(image, boxes, this.faceSize);
|
||||
// const embeddingsTensor = await this.mobileFaceNetModel.predict(faceImagesTensor);
|
||||
const f32embeddings = await this.getEmbeddingsBatch(faceImagesTensor);
|
||||
const embeddings = f32embeddings;
|
||||
// const embeddings = await embeddingsTensor.array();
|
||||
// const faceImages = await faceImagesTensor.array();
|
||||
tf.dispose(faceImagesTensor);
|
||||
// tf.dispose(embeddingsTensor);
|
||||
// console.log('embeddings: ', embeddings[0]);
|
||||
return {
|
||||
embeddings: embeddings as FaceEmbedding[],
|
||||
// faceImages: faceImages as FaceImage[],
|
||||
};
|
||||
}
|
||||
|
||||
public async dispose() {
|
||||
return this.faceRecognitionNet.dispose();
|
||||
}
|
||||
}
|
||||
|
||||
export default FAPIFaceEmbeddingService;
|
||||
|
|
@ -1,99 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
import { gather } from '@tensorflow/tfjs';
|
||||
import { extractFaces } from 'utils/machineLearning';
|
||||
import { DetectedFace, FaceDetection } from 'types/machineLearning';
|
||||
import { FaceLandmarks68 } from '../../../thirdparty/face-api/classes';
|
||||
import { FaceLandmark68Net } from '../../../thirdparty/face-api/faceLandmarkNet';
|
||||
import { getRotatedFaceImage } from 'utils/machineLearning/faceAlign';
|
||||
|
||||
class FAPIFaceLandmarksService {
|
||||
private faceLandmarkNet: FaceLandmark68Net;
|
||||
private faceSize;
|
||||
|
||||
public constructor(faceSize: number = 112) {
|
||||
this.faceLandmarkNet = new FaceLandmark68Net();
|
||||
this.faceSize = faceSize;
|
||||
}
|
||||
|
||||
public async init() {
|
||||
await this.faceLandmarkNet.loadFromUri('/models/face-api/');
|
||||
|
||||
console.log(
|
||||
'loaded faceLandmarkNet: ',
|
||||
this.faceLandmarkNet,
|
||||
await tf.getBackend()
|
||||
);
|
||||
}
|
||||
|
||||
private async getLandmarksBatch(faceImagesTensor) {
|
||||
const landmarks = [];
|
||||
for (let i = 0; i < faceImagesTensor.shape[0]; i++) {
|
||||
const face = tf.tidy(() =>
|
||||
gather(faceImagesTensor, i).expandDims()
|
||||
);
|
||||
const landmark = await this.faceLandmarkNet.detectLandmarks(face);
|
||||
tf.dispose(face);
|
||||
landmarks[i] = landmark;
|
||||
}
|
||||
|
||||
return landmarks;
|
||||
}
|
||||
|
||||
public async getAlignedFaces(
|
||||
image: tf.Tensor3D,
|
||||
faceDetections: Array<FaceDetection>
|
||||
): Promise<tf.Tensor4D> {
|
||||
if (!faceDetections || faceDetections.length < 1) {
|
||||
return null as tf.Tensor4D;
|
||||
}
|
||||
|
||||
const alignedFaceImages = new Array<tf.Tensor3D>(faceDetections.length);
|
||||
for (let i = 0; i < faceDetections.length; i++) {
|
||||
const rotFaceImageTensor = getRotatedFaceImage(
|
||||
image,
|
||||
faceDetections[i]
|
||||
);
|
||||
|
||||
const landmarks = await this.faceLandmarkNet.detectLandmarks(
|
||||
rotFaceImageTensor
|
||||
);
|
||||
Array.isArray(landmarks) &&
|
||||
console.log('multiple landmarks for single face');
|
||||
const landmark = Array.isArray(landmarks)
|
||||
? landmarks[0]
|
||||
: landmarks;
|
||||
const alignedBox = landmark.align();
|
||||
const face = extractFaces(
|
||||
rotFaceImageTensor,
|
||||
[alignedBox],
|
||||
this.faceSize
|
||||
);
|
||||
alignedFaceImages[i] = tf.tidy(() => tf.squeeze(face, [0]));
|
||||
|
||||
tf.dispose(rotFaceImageTensor);
|
||||
}
|
||||
|
||||
return tf.stack(alignedFaceImages) as tf.Tensor4D;
|
||||
}
|
||||
|
||||
public async detectLandmarks(image: tf.Tensor3D, faces: DetectedFace[]) {
|
||||
if (!faces || faces.length < 1) {
|
||||
return [] as Array<FaceLandmarks68>;
|
||||
}
|
||||
|
||||
const boxes = faces.map((f) => f.detection.box);
|
||||
const faceImagesTensor = extractFaces(image, boxes, this.faceSize);
|
||||
|
||||
const landmarks = await this.getLandmarksBatch(faceImagesTensor);
|
||||
|
||||
tf.dispose(faceImagesTensor);
|
||||
|
||||
return landmarks as Array<FaceLandmarks68>;
|
||||
}
|
||||
|
||||
public async dispose() {
|
||||
return this.faceLandmarkNet.dispose();
|
||||
}
|
||||
}
|
||||
|
||||
export default FAPIFaceLandmarksService;
|
||||
|
|
@ -1,7 +1,6 @@
|
|||
import { TreeNode } from 'hdbscan';
|
||||
import { euclidean, TreeNode } from 'hdbscan';
|
||||
import { RawNodeDatum } from 'react-d3-tree/lib/types/common';
|
||||
import { f32Average, getAllFacesFromMap } from '.';
|
||||
import { euclideanDistance } from '../../../thirdparty/face-api/euclideanDistance';
|
||||
import {
|
||||
FacesCluster,
|
||||
Cluster,
|
||||
|
|
@ -50,7 +49,10 @@ export function getNearestCluster(
|
|||
let nearest: FacesCluster = null;
|
||||
let nearestDist = 100000;
|
||||
syncContext.mlLibraryData.faceClustersWithNoise.clusters.forEach((c) => {
|
||||
const dist = euclideanDistance(noise.embedding, c.summary);
|
||||
const dist = euclidean(
|
||||
Array.from(noise.embedding),
|
||||
Array.from(c.summary)
|
||||
);
|
||||
if (dist < nearestDist) {
|
||||
nearestDist = dist;
|
||||
nearest = c;
|
||||
|
|
|
|||
159
thirdparty/face-api/NeuralNetwork.ts
vendored
159
thirdparty/face-api/NeuralNetwork.ts
vendored
|
|
@ -1,159 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ParamMapping } from './common';
|
||||
import { getModelUris } from './common/getModelUris';
|
||||
import { loadWeightMap } from './dom';
|
||||
import { env } from './env';
|
||||
|
||||
export abstract class NeuralNetwork<TNetParams> {
|
||||
|
||||
protected _params: TNetParams | undefined = undefined
|
||||
protected _paramMappings: ParamMapping[] = []
|
||||
|
||||
constructor(protected _name: string) {}
|
||||
|
||||
public get params(): TNetParams | undefined { return this._params }
|
||||
public get paramMappings(): ParamMapping[] { return this._paramMappings }
|
||||
public get isLoaded(): boolean { return !!this.params }
|
||||
|
||||
public getParamFromPath(paramPath: string): tf.Tensor {
|
||||
const { obj, objProp } = this.traversePropertyPath(paramPath)
|
||||
return obj[objProp]
|
||||
}
|
||||
|
||||
public reassignParamFromPath(paramPath: string, tensor: tf.Tensor) {
|
||||
const { obj, objProp } = this.traversePropertyPath(paramPath)
|
||||
obj[objProp].dispose()
|
||||
obj[objProp] = tensor
|
||||
}
|
||||
|
||||
public getParamList() {
|
||||
return this._paramMappings.map(({ paramPath }) => ({
|
||||
path: paramPath,
|
||||
tensor: this.getParamFromPath(paramPath)
|
||||
}))
|
||||
}
|
||||
|
||||
public getTrainableParams() {
|
||||
return this.getParamList().filter(param => param.tensor instanceof tf.Variable)
|
||||
}
|
||||
|
||||
public getFrozenParams() {
|
||||
return this.getParamList().filter(param => !(param.tensor instanceof tf.Variable))
|
||||
}
|
||||
|
||||
public variable() {
|
||||
this.getFrozenParams().forEach(({ path, tensor }) => {
|
||||
this.reassignParamFromPath(path, tensor.variable())
|
||||
})
|
||||
}
|
||||
|
||||
public freeze() {
|
||||
this.getTrainableParams().forEach(({ path, tensor: variable }) => {
|
||||
const tensor = tf.tensor(variable.dataSync())
|
||||
variable.dispose()
|
||||
this.reassignParamFromPath(path, tensor)
|
||||
})
|
||||
}
|
||||
|
||||
public dispose(throwOnRedispose: boolean = true) {
|
||||
this.getParamList().forEach(param => {
|
||||
if (throwOnRedispose && param.tensor.isDisposed) {
|
||||
throw new Error(`param tensor has already been disposed for path ${param.path}`)
|
||||
}
|
||||
param.tensor.dispose()
|
||||
})
|
||||
this._params = undefined
|
||||
}
|
||||
|
||||
public serializeParams(): Float32Array {
|
||||
return new Float32Array(
|
||||
this.getParamList()
|
||||
.map(({ tensor }) => Array.from(tensor.dataSync()) as number[])
|
||||
.reduce((flat, arr) => flat.concat(arr))
|
||||
)
|
||||
}
|
||||
|
||||
public async load(weightsOrUrl: Float32Array | string | undefined): Promise<void> {
|
||||
if (weightsOrUrl instanceof Float32Array) {
|
||||
this.extractWeights(weightsOrUrl)
|
||||
return
|
||||
}
|
||||
|
||||
await this.loadFromUri(weightsOrUrl)
|
||||
}
|
||||
|
||||
public async loadFromUri(uri: string | undefined) {
|
||||
if (uri && typeof uri !== 'string') {
|
||||
throw new Error(`${this._name}.loadFromUri - expected model uri`)
|
||||
}
|
||||
|
||||
const weightMap = await loadWeightMap(uri, this.getDefaultModelName())
|
||||
this.loadFromWeightMap(weightMap)
|
||||
}
|
||||
|
||||
public async loadFromDisk(filePath: string | undefined) {
|
||||
if (filePath && typeof filePath !== 'string') {
|
||||
throw new Error(`${this._name}.loadFromDisk - expected model file path`)
|
||||
}
|
||||
|
||||
const { readFile } = env.getEnv()
|
||||
|
||||
const { manifestUri, modelBaseUri } = getModelUris(filePath, this.getDefaultModelName())
|
||||
|
||||
const fetchWeightsFromDisk = (filePaths: string[]) => Promise.all(
|
||||
filePaths.map(filePath => readFile(filePath).then(buf => buf.buffer))
|
||||
)
|
||||
const loadWeights = tf.io.weightsLoaderFactory(fetchWeightsFromDisk)
|
||||
|
||||
const manifest = JSON.parse((await readFile(manifestUri)).toString())
|
||||
const weightMap = await loadWeights(manifest, modelBaseUri)
|
||||
|
||||
this.loadFromWeightMap(weightMap)
|
||||
}
|
||||
|
||||
public loadFromWeightMap(weightMap: tf.NamedTensorMap) {
|
||||
const {
|
||||
paramMappings,
|
||||
params
|
||||
} = this.extractParamsFromWeigthMap(weightMap)
|
||||
|
||||
this._paramMappings = paramMappings
|
||||
this._params = params
|
||||
}
|
||||
|
||||
public extractWeights(weights: Float32Array) {
|
||||
const {
|
||||
paramMappings,
|
||||
params
|
||||
} = this.extractParams(weights)
|
||||
|
||||
this._paramMappings = paramMappings
|
||||
this._params = params
|
||||
}
|
||||
|
||||
private traversePropertyPath(paramPath: string) {
|
||||
if (!this.params) {
|
||||
throw new Error(`traversePropertyPath - model has no loaded params`)
|
||||
}
|
||||
|
||||
const result = paramPath.split('/').reduce((res: { nextObj: any, obj?: any, objProp?: string }, objProp) => {
|
||||
if (!res.nextObj.hasOwnProperty(objProp)) {
|
||||
throw new Error(`traversePropertyPath - object does not have property ${objProp}, for path ${paramPath}`)
|
||||
}
|
||||
|
||||
return { obj: res.nextObj, objProp, nextObj: res.nextObj[objProp] }
|
||||
}, { nextObj: this.params })
|
||||
|
||||
const { obj, objProp } = result
|
||||
if (!obj || !objProp || !(obj[objProp] instanceof tf.Tensor)) {
|
||||
throw new Error(`traversePropertyPath - parameter is not a tensor, for path ${paramPath}`)
|
||||
}
|
||||
|
||||
return { obj, objProp }
|
||||
}
|
||||
|
||||
protected abstract getDefaultModelName(): string
|
||||
protected abstract extractParamsFromWeigthMap(weightMap: tf.NamedTensorMap): { params: TNetParams, paramMappings: ParamMapping[] }
|
||||
protected abstract extractParams(weights: Float32Array): { params: TNetParams, paramMappings: ParamMapping[] }
|
||||
}
|
||||
24
thirdparty/face-api/classes/FaceDetection.ts
vendored
24
thirdparty/face-api/classes/FaceDetection.ts
vendored
|
|
@ -1,24 +0,0 @@
|
|||
import { Box } from './Box';
|
||||
import { IDimensions } from './Dimensions';
|
||||
import { ObjectDetection } from './ObjectDetection';
|
||||
import { Rect } from './Rect';
|
||||
|
||||
export interface IFaceDetecion {
|
||||
score: number
|
||||
box: Box
|
||||
}
|
||||
|
||||
export class FaceDetection extends ObjectDetection implements IFaceDetecion {
|
||||
constructor(
|
||||
score: number,
|
||||
relativeBox: Rect,
|
||||
imageDims: IDimensions
|
||||
) {
|
||||
super(score, score, '', relativeBox, imageDims)
|
||||
}
|
||||
|
||||
public forSize(width: number, height: number): FaceDetection {
|
||||
const { score, relativeBox, imageDims } = super.forSize(width, height)
|
||||
return new FaceDetection(score, relativeBox, imageDims)
|
||||
}
|
||||
}
|
||||
125
thirdparty/face-api/classes/FaceLandmarks.ts
vendored
125
thirdparty/face-api/classes/FaceLandmarks.ts
vendored
|
|
@ -1,125 +0,0 @@
|
|||
import { minBbox } from '../ops';
|
||||
import { getCenterPoint } from '../utils';
|
||||
import { IBoundingBox } from './BoundingBox';
|
||||
import { Box } from './Box';
|
||||
import { Dimensions, IDimensions } from './Dimensions';
|
||||
import { FaceDetection } from './FaceDetection';
|
||||
import { Point } from './Point';
|
||||
import { IRect, Rect } from './Rect';
|
||||
|
||||
// face alignment constants
|
||||
const relX = 0.5
|
||||
const relY = 0.43
|
||||
const relScale = 0.45
|
||||
|
||||
export interface IFaceLandmarks {
|
||||
positions: Point[]
|
||||
shift: Point
|
||||
}
|
||||
|
||||
export class FaceLandmarks implements IFaceLandmarks {
|
||||
protected _shift: Point
|
||||
protected _positions: Point[]
|
||||
protected _imgDims: Dimensions
|
||||
|
||||
constructor(
|
||||
relativeFaceLandmarkPositions: Point[],
|
||||
imgDims: IDimensions,
|
||||
shift: Point = new Point(0, 0)
|
||||
) {
|
||||
const { width, height } = imgDims
|
||||
this._imgDims = new Dimensions(width, height)
|
||||
this._shift = shift
|
||||
this._positions = relativeFaceLandmarkPositions.map(
|
||||
pt => pt.mul(new Point(width, height)).add(shift)
|
||||
)
|
||||
}
|
||||
|
||||
public get shift(): Point { return new Point(this._shift.x, this._shift.y) }
|
||||
public get imageWidth(): number { return this._imgDims.width }
|
||||
public get imageHeight(): number { return this._imgDims.height }
|
||||
public get positions(): Point[] { return this._positions }
|
||||
public get relativePositions(): Point[] {
|
||||
return this._positions.map(
|
||||
pt => pt.sub(this._shift).div(new Point(this.imageWidth, this.imageHeight))
|
||||
)
|
||||
}
|
||||
|
||||
public forSize<T extends FaceLandmarks>(width: number, height: number): T {
|
||||
return new (this.constructor as any)(
|
||||
this.relativePositions,
|
||||
{ width, height }
|
||||
)
|
||||
}
|
||||
|
||||
public shiftBy<T extends FaceLandmarks>(x: number, y: number): T {
|
||||
return new (this.constructor as any)(
|
||||
this.relativePositions,
|
||||
this._imgDims,
|
||||
new Point(x, y)
|
||||
)
|
||||
}
|
||||
|
||||
public shiftByPoint<T extends FaceLandmarks>(pt: Point): T {
|
||||
return this.shiftBy(pt.x, pt.y)
|
||||
}
|
||||
|
||||
/**
|
||||
* Aligns the face landmarks after face detection from the relative positions of the faces
|
||||
* bounding box, or it's current shift. This function should be used to align the face images
|
||||
* after face detection has been performed, before they are passed to the face recognition net.
|
||||
* This will make the computed face descriptor more accurate.
|
||||
*
|
||||
* @param detection (optional) The bounding box of the face or the face detection result. If
|
||||
* no argument was passed the position of the face landmarks are assumed to be relative to
|
||||
* it's current shift.
|
||||
* @returns The bounding box of the aligned face.
|
||||
*/
|
||||
public align(
|
||||
detection?: FaceDetection | IRect | IBoundingBox | null,
|
||||
options: { useDlibAlignment?: boolean, minBoxPadding?: number } = { }
|
||||
): Box {
|
||||
if (detection) {
|
||||
const box = detection instanceof FaceDetection
|
||||
? detection.box.floor()
|
||||
: new Box(detection)
|
||||
|
||||
return this.shiftBy(box.x, box.y).align(null, options)
|
||||
}
|
||||
|
||||
const { useDlibAlignment, minBoxPadding } = Object.assign({}, { useDlibAlignment: false, minBoxPadding: 0.2 }, options)
|
||||
|
||||
if (useDlibAlignment) {
|
||||
return this.alignDlib()
|
||||
}
|
||||
|
||||
return this.alignMinBbox(minBoxPadding)
|
||||
}
|
||||
|
||||
private alignDlib(): Box {
|
||||
|
||||
const centers = this.getRefPointsForAlignment()
|
||||
|
||||
const [leftEyeCenter, rightEyeCenter, mouthCenter] = centers
|
||||
const distToMouth = (pt: Point) => mouthCenter.sub(pt).magnitude()
|
||||
const eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2
|
||||
|
||||
const size = Math.floor(eyeToMouthDist / relScale)
|
||||
|
||||
const refPoint = getCenterPoint(centers)
|
||||
// TODO: pad in case rectangle is out of image bounds
|
||||
const x = Math.floor(Math.max(0, refPoint.x - (relX * size)))
|
||||
const y = Math.floor(Math.max(0, refPoint.y - (relY * size)))
|
||||
|
||||
return new Rect(x, y, Math.min(size, this.imageWidth + x), Math.min(size, this.imageHeight + y))
|
||||
}
|
||||
|
||||
private alignMinBbox(padding: number): Box {
|
||||
const box = minBbox(this.positions)
|
||||
return box.pad(box.width * padding, box.height * padding)
|
||||
}
|
||||
|
||||
protected getRefPointsForAlignment(): Point[] {
|
||||
throw new Error('getRefPointsForAlignment not implemented by base class')
|
||||
}
|
||||
}
|
||||
16
thirdparty/face-api/classes/FaceLandmarks5.ts
vendored
16
thirdparty/face-api/classes/FaceLandmarks5.ts
vendored
|
|
@ -1,16 +0,0 @@
|
|||
import { getCenterPoint } from '../utils';
|
||||
import { FaceLandmarks } from './FaceLandmarks';
|
||||
import { Point } from './Point';
|
||||
|
||||
|
||||
export class FaceLandmarks5 extends FaceLandmarks {
|
||||
|
||||
protected getRefPointsForAlignment(): Point[] {
|
||||
const pts = this.positions
|
||||
return [
|
||||
pts[0],
|
||||
pts[1],
|
||||
getCenterPoint([pts[3], pts[4]])
|
||||
]
|
||||
}
|
||||
}
|
||||
41
thirdparty/face-api/classes/FaceLandmarks68.ts
vendored
41
thirdparty/face-api/classes/FaceLandmarks68.ts
vendored
|
|
@ -1,41 +0,0 @@
|
|||
import { getCenterPoint } from '../utils';
|
||||
import { FaceLandmarks } from './FaceLandmarks';
|
||||
import { Point } from './Point';
|
||||
|
||||
export class FaceLandmarks68 extends FaceLandmarks {
|
||||
public getJawOutline(): Point[] {
|
||||
return this.positions.slice(0, 17)
|
||||
}
|
||||
|
||||
public getLeftEyeBrow(): Point[] {
|
||||
return this.positions.slice(17, 22)
|
||||
}
|
||||
|
||||
public getRightEyeBrow(): Point[] {
|
||||
return this.positions.slice(22, 27)
|
||||
}
|
||||
|
||||
public getNose(): Point[] {
|
||||
return this.positions.slice(27, 36)
|
||||
}
|
||||
|
||||
public getLeftEye(): Point[] {
|
||||
return this.positions.slice(36, 42)
|
||||
}
|
||||
|
||||
public getRightEye(): Point[] {
|
||||
return this.positions.slice(42, 48)
|
||||
}
|
||||
|
||||
public getMouth(): Point[] {
|
||||
return this.positions.slice(48, 68)
|
||||
}
|
||||
|
||||
protected getRefPointsForAlignment(): Point[] {
|
||||
return [
|
||||
this.getLeftEye(),
|
||||
this.getRightEye(),
|
||||
this.getMouth()
|
||||
].map(getCenterPoint)
|
||||
}
|
||||
}
|
||||
23
thirdparty/face-api/classes/FaceMatch.ts
vendored
23
thirdparty/face-api/classes/FaceMatch.ts
vendored
|
|
@ -1,23 +0,0 @@
|
|||
import { round } from '../utils';
|
||||
|
||||
export interface IFaceMatch {
|
||||
label: string
|
||||
distance: number
|
||||
}
|
||||
|
||||
export class FaceMatch implements IFaceMatch {
|
||||
private _label: string
|
||||
private _distance: number
|
||||
|
||||
constructor(label: string, distance: number) {
|
||||
this._label = label
|
||||
this._distance = distance
|
||||
}
|
||||
|
||||
public get label(): string { return this._label }
|
||||
public get distance(): number { return this._distance }
|
||||
|
||||
public toString(withDistance: boolean = true): string {
|
||||
return `${this.label}${withDistance ? ` (${round(this.distance)})` : ''}`
|
||||
}
|
||||
}
|
||||
25
thirdparty/face-api/classes/LabeledBox.ts
vendored
25
thirdparty/face-api/classes/LabeledBox.ts
vendored
|
|
@ -1,25 +0,0 @@
|
|||
import { isValidNumber } from '../utils';
|
||||
import { IBoundingBox } from './BoundingBox';
|
||||
import { Box } from './Box';
|
||||
import { IRect } from './Rect';
|
||||
|
||||
export class LabeledBox extends Box<LabeledBox> {
|
||||
|
||||
public static assertIsValidLabeledBox(box: any, callee: string) {
|
||||
Box.assertIsValidBox(box, callee)
|
||||
|
||||
if (!isValidNumber(box.label)) {
|
||||
throw new Error(`${callee} - expected property label (${box.label}) to be a number`)
|
||||
}
|
||||
}
|
||||
|
||||
private _label: number
|
||||
|
||||
constructor(box: IBoundingBox | IRect | any, label: number) {
|
||||
super(box)
|
||||
this._label = label
|
||||
}
|
||||
|
||||
public get label(): number { return this._label }
|
||||
|
||||
}
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
export class LabeledFaceDescriptors {
|
||||
private _label: string
|
||||
private _descriptors: Float32Array[]
|
||||
|
||||
constructor(label: string, descriptors: Float32Array[]) {
|
||||
if (!(typeof label === 'string')) {
|
||||
throw new Error('LabeledFaceDescriptors - constructor expected label to be a string')
|
||||
}
|
||||
|
||||
if (!Array.isArray(descriptors) || descriptors.some(desc => !(desc instanceof Float32Array))) {
|
||||
throw new Error('LabeledFaceDescriptors - constructor expected descriptors to be an array of Float32Array')
|
||||
}
|
||||
|
||||
this._label = label
|
||||
this._descriptors = descriptors
|
||||
}
|
||||
|
||||
public get label(): string { return this._label }
|
||||
public get descriptors(): Float32Array[] { return this._descriptors }
|
||||
|
||||
public toJSON(): any {
|
||||
return {
|
||||
label: this.label,
|
||||
descriptors: this.descriptors.map((d) => Array.from(d))
|
||||
};
|
||||
}
|
||||
|
||||
public static fromJSON(json: any): LabeledFaceDescriptors {
|
||||
const descriptors = json.descriptors.map((d: any) => {
|
||||
return new Float32Array(d);
|
||||
});
|
||||
return new LabeledFaceDescriptors(json.label, descriptors);
|
||||
}
|
||||
|
||||
}
|
||||
44
thirdparty/face-api/classes/ObjectDetection.ts
vendored
44
thirdparty/face-api/classes/ObjectDetection.ts
vendored
|
|
@ -1,44 +0,0 @@
|
|||
import { Box } from './Box';
|
||||
import { Dimensions, IDimensions } from './Dimensions';
|
||||
import { IRect, Rect } from './Rect';
|
||||
|
||||
export class ObjectDetection {
|
||||
private _score: number
|
||||
private _classScore: number
|
||||
private _className: string
|
||||
private _box: Rect
|
||||
private _imageDims: Dimensions
|
||||
|
||||
constructor(
|
||||
score: number,
|
||||
classScore: number,
|
||||
className: string,
|
||||
relativeBox: IRect,
|
||||
imageDims: IDimensions
|
||||
) {
|
||||
this._imageDims = new Dimensions(imageDims.width, imageDims.height)
|
||||
this._score = score
|
||||
this._classScore = classScore
|
||||
this._className = className
|
||||
this._box = new Box(relativeBox).rescale(this._imageDims)
|
||||
}
|
||||
|
||||
public get score(): number { return this._score }
|
||||
public get classScore(): number { return this._classScore }
|
||||
public get className(): string { return this._className }
|
||||
public get box(): Box { return this._box }
|
||||
public get imageDims(): Dimensions { return this._imageDims }
|
||||
public get imageWidth(): number { return this.imageDims.width }
|
||||
public get imageHeight(): number { return this.imageDims.height }
|
||||
public get relativeBox(): Box { return new Box(this._box).rescale(this.imageDims.reverse()) }
|
||||
|
||||
public forSize(width: number, height: number): ObjectDetection {
|
||||
return new ObjectDetection(
|
||||
this.score,
|
||||
this.classScore,
|
||||
this.className,
|
||||
this.relativeBox,
|
||||
{ width, height}
|
||||
)
|
||||
}
|
||||
}
|
||||
31
thirdparty/face-api/classes/PredictedBox.ts
vendored
31
thirdparty/face-api/classes/PredictedBox.ts
vendored
|
|
@ -1,31 +0,0 @@
|
|||
import { isValidProbablitiy } from '../utils';
|
||||
import { IBoundingBox } from './BoundingBox';
|
||||
import { LabeledBox } from './LabeledBox';
|
||||
import { IRect } from './Rect';
|
||||
|
||||
export class PredictedBox extends LabeledBox {
|
||||
|
||||
public static assertIsValidPredictedBox(box: any, callee: string) {
|
||||
LabeledBox.assertIsValidLabeledBox(box, callee)
|
||||
|
||||
if (
|
||||
!isValidProbablitiy(box.score)
|
||||
|| !isValidProbablitiy(box.classScore)
|
||||
) {
|
||||
throw new Error(`${callee} - expected properties score (${box.score}) and (${box.classScore}) to be a number between [0, 1]`)
|
||||
}
|
||||
}
|
||||
|
||||
private _score: number
|
||||
private _classScore: number
|
||||
|
||||
constructor(box: IBoundingBox | IRect | any, label: number, score: number, classScore: number) {
|
||||
super(box, label)
|
||||
this._score = score
|
||||
this._classScore = classScore
|
||||
}
|
||||
|
||||
public get score(): number { return this._score }
|
||||
public get classScore(): number { return this._classScore }
|
||||
|
||||
}
|
||||
9
thirdparty/face-api/classes/index.ts
vendored
9
thirdparty/face-api/classes/index.ts
vendored
|
|
@ -1,14 +1,5 @@
|
|||
export * from './BoundingBox'
|
||||
export * from './Box'
|
||||
export * from './Dimensions'
|
||||
export * from './FaceDetection';
|
||||
export * from './FaceLandmarks';
|
||||
export * from './FaceLandmarks5';
|
||||
export * from './FaceLandmarks68';
|
||||
export * from './FaceMatch';
|
||||
export * from './LabeledBox'
|
||||
export * from './LabeledFaceDescriptors';
|
||||
export * from './ObjectDetection'
|
||||
export * from './Point'
|
||||
export * from './PredictedBox'
|
||||
export * from './Rect'
|
||||
19
thirdparty/face-api/common/convLayer.ts
vendored
19
thirdparty/face-api/common/convLayer.ts
vendored
|
|
@ -1,19 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ConvParams } from './types';
|
||||
|
||||
export function convLayer(
|
||||
x: tf.Tensor4D,
|
||||
params: ConvParams,
|
||||
padding: 'valid' | 'same' = 'same',
|
||||
withRelu: boolean = false
|
||||
): tf.Tensor4D {
|
||||
return tf.tidy(() => {
|
||||
const out = tf.add(
|
||||
tf.conv2d(x, params.filters, [1, 1], padding),
|
||||
params.bias
|
||||
) as tf.Tensor4D
|
||||
|
||||
return withRelu ? tf.relu(out) : out
|
||||
})
|
||||
}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { SeparableConvParams } from './types';
|
||||
|
||||
export function depthwiseSeparableConv(
|
||||
x: tf.Tensor4D,
|
||||
params: SeparableConvParams,
|
||||
stride: [number, number]
|
||||
): tf.Tensor4D {
|
||||
return tf.tidy(() => {
|
||||
let out = tf.separableConv2d(x, params.depthwise_filter, params.pointwise_filter, stride, 'same')
|
||||
out = tf.add(out, params.bias)
|
||||
return out
|
||||
})
|
||||
}
|
||||
|
|
@ -1,9 +0,0 @@
|
|||
import { ParamMapping } from './types';
|
||||
|
||||
export function disposeUnusedWeightTensors(weightMap: any, paramMappings: ParamMapping[]) {
|
||||
Object.keys(weightMap).forEach(path => {
|
||||
if (!paramMappings.some(pm => pm.originalPath === path)) {
|
||||
weightMap[path].dispose()
|
||||
}
|
||||
})
|
||||
}
|
||||
|
|
@ -1,31 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ConvParams, ExtractWeightsFunction, ParamMapping } from './types';
|
||||
|
||||
export function extractConvParamsFactory(
|
||||
extractWeights: ExtractWeightsFunction,
|
||||
paramMappings: ParamMapping[]
|
||||
) {
|
||||
|
||||
return function(
|
||||
channelsIn: number,
|
||||
channelsOut: number,
|
||||
filterSize: number,
|
||||
mappedPrefix: string
|
||||
): ConvParams {
|
||||
|
||||
const filters = tf.tensor4d(
|
||||
extractWeights(channelsIn * channelsOut * filterSize * filterSize),
|
||||
[filterSize, filterSize, channelsIn, channelsOut]
|
||||
)
|
||||
const bias = tf.tensor1d(extractWeights(channelsOut))
|
||||
|
||||
paramMappings.push(
|
||||
{ paramPath: `${mappedPrefix}/filters` },
|
||||
{ paramPath: `${mappedPrefix}/bias` }
|
||||
)
|
||||
|
||||
return { filters, bias }
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -1,31 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ExtractWeightsFunction, FCParams, ParamMapping } from './types';
|
||||
|
||||
|
||||
export function extractFCParamsFactory(
|
||||
extractWeights: ExtractWeightsFunction,
|
||||
paramMappings: ParamMapping[]
|
||||
) {
|
||||
|
||||
return function(
|
||||
channelsIn: number,
|
||||
channelsOut: number,
|
||||
mappedPrefix: string
|
||||
): FCParams {
|
||||
|
||||
const fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut])
|
||||
const fc_bias = tf.tensor1d(extractWeights(channelsOut))
|
||||
|
||||
paramMappings.push(
|
||||
{ paramPath: `${mappedPrefix}/weights` },
|
||||
{ paramPath: `${mappedPrefix}/bias` }
|
||||
)
|
||||
|
||||
return {
|
||||
weights: fc_weights,
|
||||
bias: fc_bias
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -1,46 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ExtractWeightsFunction, ParamMapping, SeparableConvParams } from './types';
|
||||
|
||||
export function extractSeparableConvParamsFactory(
|
||||
extractWeights: ExtractWeightsFunction,
|
||||
paramMappings: ParamMapping[]
|
||||
) {
|
||||
|
||||
return function(channelsIn: number, channelsOut: number, mappedPrefix: string): SeparableConvParams {
|
||||
const depthwise_filter = tf.tensor4d(extractWeights(3 * 3 * channelsIn), [3, 3, channelsIn, 1])
|
||||
const pointwise_filter = tf.tensor4d(extractWeights(channelsIn * channelsOut), [1, 1, channelsIn, channelsOut])
|
||||
const bias = tf.tensor1d(extractWeights(channelsOut))
|
||||
|
||||
paramMappings.push(
|
||||
{ paramPath: `${mappedPrefix}/depthwise_filter` },
|
||||
{ paramPath: `${mappedPrefix}/pointwise_filter` },
|
||||
{ paramPath: `${mappedPrefix}/bias` }
|
||||
)
|
||||
|
||||
return new SeparableConvParams(
|
||||
depthwise_filter,
|
||||
pointwise_filter,
|
||||
bias
|
||||
)
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
export function loadSeparableConvParamsFactory(
|
||||
extractWeightEntry: <T>(originalPath: string, paramRank: number) => T
|
||||
) {
|
||||
|
||||
return function (prefix: string): SeparableConvParams {
|
||||
const depthwise_filter = extractWeightEntry<tf.Tensor4D>(`${prefix}/depthwise_filter`, 4)
|
||||
const pointwise_filter = extractWeightEntry<tf.Tensor4D>(`${prefix}/pointwise_filter`, 4)
|
||||
const bias = extractWeightEntry<tf.Tensor1D>(`${prefix}/bias`, 1)
|
||||
|
||||
return new SeparableConvParams(
|
||||
depthwise_filter,
|
||||
pointwise_filter,
|
||||
bias
|
||||
)
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
import { isTensor } from '../utils';
|
||||
import { ParamMapping } from './types';
|
||||
|
||||
export function extractWeightEntryFactory(weightMap: any, paramMappings: ParamMapping[]) {
|
||||
|
||||
return function<T> (originalPath: string, paramRank: number, mappedPath?: string): T {
|
||||
const tensor = weightMap[originalPath]
|
||||
|
||||
if (!isTensor(tensor, paramRank)) {
|
||||
throw new Error(`expected weightMap[${originalPath}] to be a Tensor${paramRank}D, instead have ${tensor}`)
|
||||
}
|
||||
|
||||
paramMappings.push(
|
||||
{ originalPath, paramPath: mappedPath || originalPath }
|
||||
)
|
||||
|
||||
return tensor
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
export function extractWeightsFactory(weights: Float32Array) {
|
||||
let remainingWeights = weights
|
||||
|
||||
function extractWeights(numWeights: number): Float32Array {
|
||||
const ret = remainingWeights.slice(0, numWeights)
|
||||
remainingWeights = remainingWeights.slice(numWeights)
|
||||
return ret
|
||||
}
|
||||
|
||||
function getRemainingWeights(): Float32Array {
|
||||
return remainingWeights
|
||||
}
|
||||
|
||||
return {
|
||||
extractWeights,
|
||||
getRemainingWeights
|
||||
}
|
||||
}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { FCParams } from './types';
|
||||
|
||||
export function fullyConnectedLayer(
|
||||
x: tf.Tensor2D,
|
||||
params: FCParams
|
||||
): tf.Tensor2D {
|
||||
return tf.tidy(() =>
|
||||
tf.add(
|
||||
tf.matMul(x, params.weights),
|
||||
params.bias
|
||||
)
|
||||
)
|
||||
}
|
||||
33
thirdparty/face-api/common/getModelUris.ts
vendored
33
thirdparty/face-api/common/getModelUris.ts
vendored
|
|
@ -1,33 +0,0 @@
|
|||
export function getModelUris(uri: string | undefined, defaultModelName: string) {
|
||||
const defaultManifestFilename = `${defaultModelName}-weights_manifest.json`
|
||||
|
||||
if (!uri) {
|
||||
return {
|
||||
modelBaseUri: '',
|
||||
manifestUri: defaultManifestFilename
|
||||
}
|
||||
}
|
||||
|
||||
if (uri === '/') {
|
||||
return {
|
||||
modelBaseUri: '/',
|
||||
manifestUri: `/${defaultManifestFilename}`
|
||||
}
|
||||
}
|
||||
const protocol = uri.startsWith('http://') ? 'http://' : uri.startsWith('https://') ? 'https://' : '';
|
||||
uri = uri.replace(protocol, '');
|
||||
|
||||
const parts = uri.split('/').filter(s => s)
|
||||
|
||||
const manifestFile = uri.endsWith('.json')
|
||||
? parts[parts.length - 1]
|
||||
: defaultManifestFilename
|
||||
|
||||
let modelBaseUri = protocol + (uri.endsWith('.json') ? parts.slice(0, parts.length - 1) : parts).join('/')
|
||||
modelBaseUri = uri.startsWith('/') ? `/${modelBaseUri}` : modelBaseUri
|
||||
|
||||
return {
|
||||
modelBaseUri,
|
||||
manifestUri: modelBaseUri === '/' ? `/${manifestFile}` : `${modelBaseUri}/${manifestFile}`
|
||||
}
|
||||
}
|
||||
10
thirdparty/face-api/common/index.ts
vendored
10
thirdparty/face-api/common/index.ts
vendored
|
|
@ -1,10 +0,0 @@
|
|||
export * from './convLayer'
|
||||
export * from './depthwiseSeparableConv'
|
||||
export * from './disposeUnusedWeightTensors'
|
||||
export * from './extractConvParamsFactory'
|
||||
export * from './extractFCParamsFactory'
|
||||
export * from './extractSeparableConvParamsFactory'
|
||||
export * from './extractWeightEntryFactory'
|
||||
export * from './extractWeightsFactory'
|
||||
export * from './getModelUris'
|
||||
export * from './types'
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ConvParams } from './types';
|
||||
|
||||
export function loadConvParamsFactory(extractWeightEntry: <T>(originalPath: string, paramRank: number) => T) {
|
||||
return function(prefix: string): ConvParams {
|
||||
const filters = extractWeightEntry<tf.Tensor4D>(`${prefix}/filters`, 4)
|
||||
const bias = extractWeightEntry<tf.Tensor1D>(`${prefix}/bias`, 1)
|
||||
|
||||
return { filters, bias }
|
||||
}
|
||||
}
|
||||
26
thirdparty/face-api/common/types.ts
vendored
26
thirdparty/face-api/common/types.ts
vendored
|
|
@ -1,26 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
export type ExtractWeightsFunction = (numWeights: number) => Float32Array
|
||||
|
||||
export type ParamMapping = {
|
||||
originalPath?: string
|
||||
paramPath: string
|
||||
}
|
||||
|
||||
export type ConvParams = {
|
||||
filters: tf.Tensor4D
|
||||
bias: tf.Tensor1D
|
||||
}
|
||||
|
||||
export type FCParams = {
|
||||
weights: tf.Tensor2D
|
||||
bias: tf.Tensor1D
|
||||
}
|
||||
|
||||
export class SeparableConvParams {
|
||||
constructor(
|
||||
public depthwise_filter: tf.Tensor4D,
|
||||
public pointwise_filter: tf.Tensor4D,
|
||||
public bias: tf.Tensor1D
|
||||
) {}
|
||||
}
|
||||
153
thirdparty/face-api/dom/NetInput.ts
vendored
153
thirdparty/face-api/dom/NetInput.ts
vendored
|
|
@ -1,153 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { Dimensions } from '../classes/Dimensions';
|
||||
import { env } from '../env';
|
||||
import { padToSquare } from '../ops/padToSquare';
|
||||
import { computeReshapedDimensions, isTensor3D, isTensor4D, range } from '../utils';
|
||||
import { createCanvasFromMedia } from './createCanvas';
|
||||
import { imageToSquare } from './imageToSquare';
|
||||
import { TResolvedNetInput } from './types';
|
||||
|
||||
export class NetInput {
|
||||
private _imageTensors: Array<tf.Tensor3D | tf.Tensor4D> = []
|
||||
private _canvases: HTMLCanvasElement[] = []
|
||||
private _batchSize: number
|
||||
private _treatAsBatchInput: boolean = false
|
||||
|
||||
private _inputDimensions: number[][] = []
|
||||
private _inputSize: number
|
||||
|
||||
constructor(
|
||||
inputs: Array<TResolvedNetInput>,
|
||||
treatAsBatchInput: boolean = false
|
||||
) {
|
||||
if (!Array.isArray(inputs)) {
|
||||
throw new Error(`NetInput.constructor - expected inputs to be an Array of TResolvedNetInput or to be instanceof tf.Tensor4D, instead have ${inputs}`)
|
||||
}
|
||||
|
||||
this._treatAsBatchInput = treatAsBatchInput
|
||||
this._batchSize = inputs.length
|
||||
|
||||
inputs.forEach((input, idx) => {
|
||||
|
||||
if (isTensor3D(input)) {
|
||||
this._imageTensors[idx] = input
|
||||
this._inputDimensions[idx] = input.shape
|
||||
return
|
||||
}
|
||||
|
||||
if (isTensor4D(input)) {
|
||||
const batchSize = input.shape[0]
|
||||
if (batchSize !== 1) {
|
||||
throw new Error(`NetInput - tf.Tensor4D with batchSize ${batchSize} passed, but not supported in input array`)
|
||||
}
|
||||
|
||||
this._imageTensors[idx] = input
|
||||
this._inputDimensions[idx] = input.shape.slice(1)
|
||||
return
|
||||
}
|
||||
|
||||
const canvas = input instanceof env.getEnv().Canvas ? input : createCanvasFromMedia(input)
|
||||
this._canvases[idx] = canvas
|
||||
this._inputDimensions[idx] = [canvas.height, canvas.width, 3]
|
||||
})
|
||||
}
|
||||
|
||||
public get imageTensors(): Array<tf.Tensor3D | tf.Tensor4D> {
|
||||
return this._imageTensors
|
||||
}
|
||||
|
||||
public get canvases(): HTMLCanvasElement[] {
|
||||
return this._canvases
|
||||
}
|
||||
|
||||
public get isBatchInput(): boolean {
|
||||
return this.batchSize > 1 || this._treatAsBatchInput
|
||||
}
|
||||
|
||||
public get batchSize(): number {
|
||||
return this._batchSize
|
||||
}
|
||||
|
||||
public get inputDimensions(): number[][] {
|
||||
return this._inputDimensions
|
||||
}
|
||||
|
||||
public get inputSize(): number | undefined {
|
||||
return this._inputSize
|
||||
}
|
||||
|
||||
public get reshapedInputDimensions(): Dimensions[] {
|
||||
return range(this.batchSize, 0, 1).map(
|
||||
(_, batchIdx) => this.getReshapedInputDimensions(batchIdx)
|
||||
)
|
||||
}
|
||||
|
||||
public getInput(batchIdx: number): tf.Tensor3D | tf.Tensor4D | HTMLCanvasElement {
|
||||
return this.canvases[batchIdx] || this.imageTensors[batchIdx]
|
||||
}
|
||||
|
||||
public getInputDimensions(batchIdx: number): number[] {
|
||||
return this._inputDimensions[batchIdx]
|
||||
}
|
||||
|
||||
public getInputHeight(batchIdx: number): number {
|
||||
return this._inputDimensions[batchIdx][0]
|
||||
}
|
||||
|
||||
public getInputWidth(batchIdx: number): number {
|
||||
return this._inputDimensions[batchIdx][1]
|
||||
}
|
||||
|
||||
public getReshapedInputDimensions(batchIdx: number): Dimensions {
|
||||
if (typeof this.inputSize !== 'number') {
|
||||
throw new Error('getReshapedInputDimensions - inputSize not set, toBatchTensor has not been called yet')
|
||||
}
|
||||
|
||||
const width = this.getInputWidth(batchIdx)
|
||||
const height = this.getInputHeight(batchIdx)
|
||||
return computeReshapedDimensions({ width, height }, this.inputSize)
|
||||
}
|
||||
|
||||
/**
|
||||
* Create a batch tensor from all input canvases and tensors
|
||||
* with size [batchSize, inputSize, inputSize, 3].
|
||||
*
|
||||
* @param inputSize Height and width of the tensor.
|
||||
* @param isCenterImage (optional, default: false) If true, add an equal amount of padding on
|
||||
* both sides of the minor dimension oof the image.
|
||||
* @returns The batch tensor.
|
||||
*/
|
||||
public toBatchTensor(inputSize: number, isCenterInputs: boolean = true): tf.Tensor4D {
|
||||
|
||||
this._inputSize = inputSize
|
||||
|
||||
return tf.tidy(() => {
|
||||
|
||||
const inputTensors = range(this.batchSize, 0, 1).map(batchIdx => {
|
||||
const input = this.getInput(batchIdx)
|
||||
|
||||
if (input instanceof tf.Tensor) {
|
||||
let imgTensor = isTensor4D(input) ? input : input.expandDims<tf.Tensor4D>()
|
||||
imgTensor = padToSquare(imgTensor, isCenterInputs)
|
||||
|
||||
if (imgTensor.shape[1] !== inputSize || imgTensor.shape[2] !== inputSize) {
|
||||
imgTensor = tf.image.resizeBilinear(imgTensor, [inputSize, inputSize])
|
||||
}
|
||||
|
||||
return imgTensor.as3D(inputSize, inputSize, 3)
|
||||
}
|
||||
|
||||
if (input instanceof env.getEnv().Canvas) {
|
||||
return tf.browser.fromPixels(imageToSquare(input, inputSize, isCenterInputs))
|
||||
}
|
||||
|
||||
throw new Error(`toBatchTensor - at batchIdx ${batchIdx}, expected input to be instanceof tf.Tensor or instanceof HTMLCanvasElement, instead have ${input}`)
|
||||
})
|
||||
|
||||
const batchTensor = tf.stack(inputTensors.map(t => t.toFloat())).as4D(this.batchSize, inputSize, inputSize, 3)
|
||||
|
||||
return batchTensor
|
||||
})
|
||||
}
|
||||
}
|
||||
28
thirdparty/face-api/dom/awaitMediaLoaded.ts
vendored
28
thirdparty/face-api/dom/awaitMediaLoaded.ts
vendored
|
|
@ -1,28 +0,0 @@
|
|||
import { env } from '../env';
|
||||
import { isMediaLoaded } from './isMediaLoaded';
|
||||
|
||||
export function awaitMediaLoaded(media: HTMLImageElement | HTMLVideoElement | HTMLCanvasElement) {
|
||||
|
||||
return new Promise((resolve, reject) => {
|
||||
if (media instanceof env.getEnv().Canvas || isMediaLoaded(media)) {
|
||||
return resolve(null)
|
||||
}
|
||||
|
||||
function onLoad(e: Event) {
|
||||
if (!e.currentTarget) return
|
||||
e.currentTarget.removeEventListener('load', onLoad)
|
||||
e.currentTarget.removeEventListener('error', onError)
|
||||
resolve(e)
|
||||
}
|
||||
|
||||
function onError(e: Event) {
|
||||
if (!e.currentTarget) return
|
||||
e.currentTarget.removeEventListener('load', onLoad)
|
||||
e.currentTarget.removeEventListener('error', onError)
|
||||
reject(e)
|
||||
}
|
||||
|
||||
media.addEventListener('load', onLoad)
|
||||
media.addEventListener('error', onError)
|
||||
})
|
||||
}
|
||||
23
thirdparty/face-api/dom/bufferToImage.ts
vendored
23
thirdparty/face-api/dom/bufferToImage.ts
vendored
|
|
@ -1,23 +0,0 @@
|
|||
import { env } from '../env';
|
||||
|
||||
export function bufferToImage(buf: Blob): Promise<HTMLImageElement> {
|
||||
return new Promise((resolve, reject) => {
|
||||
if (!(buf instanceof Blob)) {
|
||||
return reject('bufferToImage - expected buf to be of type: Blob')
|
||||
}
|
||||
|
||||
const reader = new FileReader()
|
||||
reader.onload = () => {
|
||||
if (typeof reader.result !== 'string') {
|
||||
return reject('bufferToImage - expected reader.result to be a string, in onload')
|
||||
}
|
||||
|
||||
const img = env.getEnv().createImageElement()
|
||||
img.onload = () => resolve(img)
|
||||
img.onerror = reject
|
||||
img.src = reader.result
|
||||
}
|
||||
reader.onerror = reject
|
||||
reader.readAsDataURL(buf)
|
||||
})
|
||||
}
|
||||
33
thirdparty/face-api/dom/createCanvas.ts
vendored
33
thirdparty/face-api/dom/createCanvas.ts
vendored
|
|
@ -1,33 +0,0 @@
|
|||
import { IDimensions } from '../classes/Dimensions';
|
||||
import { env } from '../env';
|
||||
import { getContext2dOrThrow } from './getContext2dOrThrow';
|
||||
import { getMediaDimensions } from './getMediaDimensions';
|
||||
import { isMediaLoaded } from './isMediaLoaded';
|
||||
|
||||
export function createCanvas({ width, height }: IDimensions): HTMLCanvasElement {
|
||||
|
||||
const { createCanvasElement } = env.getEnv()
|
||||
const canvas = createCanvasElement()
|
||||
canvas.width = width
|
||||
canvas.height = height
|
||||
return canvas
|
||||
}
|
||||
|
||||
export function createCanvasFromMedia(media: HTMLImageElement | HTMLVideoElement | ImageData, dims?: IDimensions): HTMLCanvasElement {
|
||||
|
||||
const { ImageData } = env.getEnv()
|
||||
|
||||
if (!(media instanceof ImageData) && !isMediaLoaded(media)) {
|
||||
throw new Error('createCanvasFromMedia - media has not finished loading yet')
|
||||
}
|
||||
|
||||
const { width, height } = dims || getMediaDimensions(media)
|
||||
const canvas = createCanvas({ width, height })
|
||||
|
||||
if (media instanceof ImageData) {
|
||||
getContext2dOrThrow(canvas).putImageData(media, 0, 0)
|
||||
} else {
|
||||
getContext2dOrThrow(canvas).drawImage(media, 0, 0, width, height)
|
||||
}
|
||||
return canvas
|
||||
}
|
||||
46
thirdparty/face-api/dom/extractFaceTensors.ts
vendored
46
thirdparty/face-api/dom/extractFaceTensors.ts
vendored
|
|
@ -1,46 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { Rect } from '../classes';
|
||||
import { FaceDetection } from '../classes/FaceDetection';
|
||||
import { isTensor3D, isTensor4D } from '../utils';
|
||||
|
||||
/**
|
||||
* Extracts the tensors of the image regions containing the detected faces.
|
||||
* Useful if you want to compute the face descriptors for the face images.
|
||||
* Using this method is faster then extracting a canvas for each face and
|
||||
* converting them to tensors individually.
|
||||
*
|
||||
* @param imageTensor The image tensor that face detection has been performed on.
|
||||
* @param detections The face detection results or face bounding boxes for that image.
|
||||
* @returns Tensors of the corresponding image region for each detected face.
|
||||
*/
|
||||
export async function extractFaceTensors(
|
||||
imageTensor: tf.Tensor3D | tf.Tensor4D,
|
||||
detections: Array<FaceDetection | Rect>
|
||||
): Promise<tf.Tensor3D[]> {
|
||||
|
||||
if (!isTensor3D(imageTensor) && !isTensor4D(imageTensor)) {
|
||||
throw new Error('extractFaceTensors - expected image tensor to be 3D or 4D')
|
||||
}
|
||||
|
||||
if (isTensor4D(imageTensor) && imageTensor.shape[0] > 1) {
|
||||
throw new Error('extractFaceTensors - batchSize > 1 not supported')
|
||||
}
|
||||
|
||||
return tf.tidy(() => {
|
||||
const [imgHeight, imgWidth, numChannels] = imageTensor.shape.slice(isTensor4D(imageTensor) ? 1 : 0)
|
||||
|
||||
const boxes = detections.map(
|
||||
det => det instanceof FaceDetection
|
||||
? det.forSize(imgWidth, imgHeight).box
|
||||
: det
|
||||
)
|
||||
.map(box => box.clipAtImageBorders(imgWidth, imgHeight))
|
||||
|
||||
const faceTensors = boxes.map(({ x, y, width, height }) =>
|
||||
tf.slice3d(imageTensor.as3D(imgHeight, imgWidth, numChannels), [y, x, 0], [height, width, numChannels])
|
||||
)
|
||||
|
||||
return faceTensors
|
||||
})
|
||||
}
|
||||
53
thirdparty/face-api/dom/extractFaces.ts
vendored
53
thirdparty/face-api/dom/extractFaces.ts
vendored
|
|
@ -1,53 +0,0 @@
|
|||
import { FaceDetection } from '../classes/FaceDetection';
|
||||
import { Rect } from '../classes/Rect';
|
||||
import { env } from '../env';
|
||||
import { createCanvas } from './createCanvas';
|
||||
import { getContext2dOrThrow } from './getContext2dOrThrow';
|
||||
import { imageTensorToCanvas } from './imageTensorToCanvas';
|
||||
import { toNetInput } from './toNetInput';
|
||||
import { TNetInput } from './types';
|
||||
|
||||
/**
|
||||
* Extracts the image regions containing the detected faces.
|
||||
*
|
||||
* @param input The image that face detection has been performed on.
|
||||
* @param detections The face detection results or face bounding boxes for that image.
|
||||
* @returns The Canvases of the corresponding image region for each detected face.
|
||||
*/
|
||||
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')
|
||||
}
|
||||
|
||||
const tensorOrCanvas = netInput.getInput(0)
|
||||
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(box => box.clipAtImageBorders(canvas.width, canvas.height))
|
||||
|
||||
return boxes.map(({ x, y, width, height }) => {
|
||||
const faceImg = createCanvas({ width, height })
|
||||
getContext2dOrThrow(faceImg)
|
||||
.putImageData(ctx.getImageData(x, y, width, height), 0, 0)
|
||||
return faceImg
|
||||
})
|
||||
}
|
||||
12
thirdparty/face-api/dom/fetchImage.ts
vendored
12
thirdparty/face-api/dom/fetchImage.ts
vendored
|
|
@ -1,12 +0,0 @@
|
|||
import { bufferToImage } from './bufferToImage';
|
||||
import { fetchOrThrow } from './fetchOrThrow';
|
||||
|
||||
export async function fetchImage(uri: string): Promise<HTMLImageElement> {
|
||||
const res = await fetchOrThrow(uri)
|
||||
const blob = await (res).blob()
|
||||
|
||||
if (!blob.type.startsWith('image/')) {
|
||||
throw new Error(`fetchImage - expected blob type to be of type image/*, instead have: ${blob.type}, for url: ${res.url}`)
|
||||
}
|
||||
return bufferToImage(blob)
|
||||
}
|
||||
5
thirdparty/face-api/dom/fetchJson.ts
vendored
5
thirdparty/face-api/dom/fetchJson.ts
vendored
|
|
@ -1,5 +0,0 @@
|
|||
import { fetchOrThrow } from './fetchOrThrow';
|
||||
|
||||
export async function fetchJson<T>(uri: string): Promise<T> {
|
||||
return (await fetchOrThrow(uri)).json()
|
||||
}
|
||||
5
thirdparty/face-api/dom/fetchNetWeights.ts
vendored
5
thirdparty/face-api/dom/fetchNetWeights.ts
vendored
|
|
@ -1,5 +0,0 @@
|
|||
import { fetchOrThrow } from './fetchOrThrow';
|
||||
|
||||
export async function fetchNetWeights(uri: string): Promise<Float32Array> {
|
||||
return new Float32Array(await (await fetchOrThrow(uri)).arrayBuffer())
|
||||
}
|
||||
14
thirdparty/face-api/dom/fetchOrThrow.ts
vendored
14
thirdparty/face-api/dom/fetchOrThrow.ts
vendored
|
|
@ -1,14 +0,0 @@
|
|||
import { env } from '../env';
|
||||
|
||||
export async function fetchOrThrow(
|
||||
url: string,
|
||||
init?: RequestInit
|
||||
): Promise<Response> {
|
||||
|
||||
const fetch = env.getEnv().fetch
|
||||
const res = await fetch(url, init)
|
||||
if (!(res.status < 400)) {
|
||||
throw new Error(`failed to fetch: (${res.status}) ${res.statusText}, from url: ${res.url}`)
|
||||
}
|
||||
return res
|
||||
}
|
||||
24
thirdparty/face-api/dom/getContext2dOrThrow.ts
vendored
24
thirdparty/face-api/dom/getContext2dOrThrow.ts
vendored
|
|
@ -1,24 +0,0 @@
|
|||
import { env } from '../env';
|
||||
import { resolveInput } from './resolveInput';
|
||||
|
||||
export function getContext2dOrThrow(canvasArg: string | HTMLCanvasElement | CanvasRenderingContext2D): CanvasRenderingContext2D {
|
||||
|
||||
const { Canvas, CanvasRenderingContext2D } = env.getEnv()
|
||||
|
||||
if (canvasArg instanceof CanvasRenderingContext2D) {
|
||||
return canvasArg
|
||||
}
|
||||
|
||||
const canvas = resolveInput(canvasArg)
|
||||
|
||||
if (!(canvas instanceof Canvas)) {
|
||||
throw new Error('resolveContext2d - expected canvas to be of instance of Canvas')
|
||||
}
|
||||
|
||||
const ctx = canvas.getContext('2d')
|
||||
if (!ctx) {
|
||||
throw new Error('resolveContext2d - canvas 2d context is null')
|
||||
}
|
||||
|
||||
return ctx
|
||||
}
|
||||
15
thirdparty/face-api/dom/getMediaDimensions.ts
vendored
15
thirdparty/face-api/dom/getMediaDimensions.ts
vendored
|
|
@ -1,15 +0,0 @@
|
|||
import { Dimensions, IDimensions } from '../classes/Dimensions';
|
||||
import { env } from '../env';
|
||||
|
||||
export function getMediaDimensions(input: HTMLImageElement | HTMLCanvasElement | HTMLVideoElement | IDimensions): Dimensions {
|
||||
|
||||
const { Image, Video } = env.getEnv()
|
||||
|
||||
if (input instanceof Image) {
|
||||
return new Dimensions(input.naturalWidth, input.naturalHeight)
|
||||
}
|
||||
if (input instanceof Video) {
|
||||
return new Dimensions(input.videoWidth, input.videoHeight)
|
||||
}
|
||||
return new Dimensions(input.width, input.height)
|
||||
}
|
||||
20
thirdparty/face-api/dom/imageTensorToCanvas.ts
vendored
20
thirdparty/face-api/dom/imageTensorToCanvas.ts
vendored
|
|
@ -1,20 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { env } from '../env';
|
||||
import { isTensor4D } from '../utils';
|
||||
|
||||
export async function imageTensorToCanvas(
|
||||
imgTensor: tf.Tensor,
|
||||
canvas?: HTMLCanvasElement
|
||||
): Promise<HTMLCanvasElement> {
|
||||
|
||||
const targetCanvas = canvas || env.getEnv().createCanvasElement()
|
||||
|
||||
const [height, width, numChannels] = imgTensor.shape.slice(isTensor4D(imgTensor) ? 1 : 0)
|
||||
const imgTensor3D = tf.tidy(() => imgTensor.as3D(height, width, numChannels).toInt())
|
||||
await tf.browser.toPixels(imgTensor3D, targetCanvas)
|
||||
|
||||
imgTensor3D.dispose()
|
||||
|
||||
return targetCanvas
|
||||
}
|
||||
28
thirdparty/face-api/dom/imageToSquare.ts
vendored
28
thirdparty/face-api/dom/imageToSquare.ts
vendored
|
|
@ -1,28 +0,0 @@
|
|||
import { env } from '../env';
|
||||
import { createCanvas, createCanvasFromMedia } from './createCanvas';
|
||||
import { getContext2dOrThrow } from './getContext2dOrThrow';
|
||||
import { getMediaDimensions } from './getMediaDimensions';
|
||||
|
||||
export function imageToSquare(input: HTMLImageElement | HTMLCanvasElement, inputSize: number, centerImage: boolean = false) {
|
||||
|
||||
const { Image, Canvas } = env.getEnv()
|
||||
|
||||
if (!(input instanceof Image || input instanceof Canvas)) {
|
||||
throw new Error('imageToSquare - expected arg0 to be HTMLImageElement | HTMLCanvasElement')
|
||||
}
|
||||
|
||||
const dims = getMediaDimensions(input)
|
||||
const scale = inputSize / Math.max(dims.height, dims.width)
|
||||
const width = scale * dims.width
|
||||
const height = scale * dims.height
|
||||
|
||||
const targetCanvas = createCanvas({ width: inputSize, height: inputSize })
|
||||
const inputCanvas = input instanceof Canvas ? input : createCanvasFromMedia(input)
|
||||
|
||||
const offset = Math.abs(width - height) / 2
|
||||
const dx = centerImage && width < height ? offset : 0
|
||||
const dy = centerImage && height < width ? offset : 0
|
||||
getContext2dOrThrow(targetCanvas).drawImage(inputCanvas, dx, dy, width, height)
|
||||
|
||||
return targetCanvas
|
||||
}
|
||||
21
thirdparty/face-api/dom/index.ts
vendored
21
thirdparty/face-api/dom/index.ts
vendored
|
|
@ -1,21 +0,0 @@
|
|||
export * from './awaitMediaLoaded'
|
||||
export * from './bufferToImage'
|
||||
export * from './createCanvas'
|
||||
export * from './extractFaces'
|
||||
export * from './extractFaceTensors'
|
||||
export * from './fetchImage'
|
||||
export * from './fetchJson'
|
||||
export * from './fetchNetWeights'
|
||||
export * from './fetchOrThrow'
|
||||
export * from './getContext2dOrThrow'
|
||||
export * from './getMediaDimensions'
|
||||
export * from './imageTensorToCanvas'
|
||||
export * from './imageToSquare'
|
||||
export * from './isMediaElement'
|
||||
export * from './isMediaLoaded'
|
||||
export * from './loadWeightMap'
|
||||
export * from './matchDimensions'
|
||||
export * from './NetInput'
|
||||
export * from './resolveInput'
|
||||
export * from './toNetInput'
|
||||
export * from './types'
|
||||
10
thirdparty/face-api/dom/isMediaElement.ts
vendored
10
thirdparty/face-api/dom/isMediaElement.ts
vendored
|
|
@ -1,10 +0,0 @@
|
|||
import { env } from '../env';
|
||||
|
||||
export function isMediaElement(input: any) {
|
||||
|
||||
const { Image, Canvas, Video } = env.getEnv()
|
||||
|
||||
return input instanceof Image
|
||||
|| input instanceof Canvas
|
||||
|| input instanceof Video
|
||||
}
|
||||
9
thirdparty/face-api/dom/isMediaLoaded.ts
vendored
9
thirdparty/face-api/dom/isMediaLoaded.ts
vendored
|
|
@ -1,9 +0,0 @@
|
|||
import { env } from '../env';
|
||||
|
||||
export function isMediaLoaded(media: HTMLImageElement | HTMLVideoElement) : boolean {
|
||||
|
||||
const { Image, Video } = env.getEnv()
|
||||
|
||||
return (media instanceof Image && media.complete)
|
||||
|| (media instanceof Video && media.readyState >= 3)
|
||||
}
|
||||
15
thirdparty/face-api/dom/loadWeightMap.ts
vendored
15
thirdparty/face-api/dom/loadWeightMap.ts
vendored
|
|
@ -1,15 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { getModelUris } from '../common/getModelUris';
|
||||
import { fetchJson } from './fetchJson';
|
||||
|
||||
export async function loadWeightMap(
|
||||
uri: string | undefined,
|
||||
defaultModelName: string,
|
||||
): Promise<tf.NamedTensorMap> {
|
||||
const { manifestUri, modelBaseUri } = getModelUris(uri, defaultModelName)
|
||||
|
||||
const manifest = await fetchJson<tf.io.WeightsManifestConfig>(manifestUri)
|
||||
|
||||
return tf.io.loadWeights(manifest, modelBaseUri)
|
||||
}
|
||||
11
thirdparty/face-api/dom/matchDimensions.ts
vendored
11
thirdparty/face-api/dom/matchDimensions.ts
vendored
|
|
@ -1,11 +0,0 @@
|
|||
import { IDimensions } from '../classes';
|
||||
import { getMediaDimensions } from './getMediaDimensions';
|
||||
|
||||
export function matchDimensions(input: IDimensions, reference: IDimensions, useMediaDimensions: boolean = false) {
|
||||
const { width, height } = useMediaDimensions
|
||||
? getMediaDimensions(reference)
|
||||
: reference
|
||||
input.width = width
|
||||
input.height = height
|
||||
return { width, height }
|
||||
}
|
||||
8
thirdparty/face-api/dom/resolveInput.ts
vendored
8
thirdparty/face-api/dom/resolveInput.ts
vendored
|
|
@ -1,8 +0,0 @@
|
|||
import { env } from '../env';
|
||||
|
||||
export function resolveInput(arg: string | any) {
|
||||
if (!env.isNodejs() && typeof arg === 'string') {
|
||||
return document.getElementById(arg)
|
||||
}
|
||||
return arg
|
||||
}
|
||||
57
thirdparty/face-api/dom/toNetInput.ts
vendored
57
thirdparty/face-api/dom/toNetInput.ts
vendored
|
|
@ -1,57 +0,0 @@
|
|||
import { isTensor3D, isTensor4D } from '../utils';
|
||||
import { awaitMediaLoaded } from './awaitMediaLoaded';
|
||||
import { isMediaElement } from './isMediaElement';
|
||||
import { NetInput } from './NetInput';
|
||||
import { resolveInput } from './resolveInput';
|
||||
import { TNetInput } from './types';
|
||||
|
||||
/**
|
||||
* Validates the input to make sure, they are valid net inputs and awaits all media elements
|
||||
* to be finished loading.
|
||||
*
|
||||
* @param input The input, which can be a media element or an array of different media elements.
|
||||
* @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
|
||||
}
|
||||
|
||||
let 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 ${inputArgArray[i]}`)
|
||||
}
|
||||
|
||||
throw new Error(`toNetInput -${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`)
|
||||
}
|
||||
}
|
||||
})
|
||||
|
||||
// wait for all media elements being loaded
|
||||
await Promise.all(
|
||||
inputArray.map(input => isMediaElement(input) && awaitMediaLoaded(input))
|
||||
)
|
||||
|
||||
return new NetInput(inputArray, Array.isArray(inputs))
|
||||
}
|
||||
11
thirdparty/face-api/dom/types.ts
vendored
11
thirdparty/face-api/dom/types.ts
vendored
|
|
@ -1,11 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { NetInput } from './NetInput';
|
||||
|
||||
export type TMediaElement = HTMLImageElement | HTMLVideoElement | HTMLCanvasElement
|
||||
|
||||
export type TResolvedNetInput = TMediaElement | tf.Tensor3D | tf.Tensor4D
|
||||
|
||||
export type TNetInputArg = string | TResolvedNetInput
|
||||
|
||||
export type TNetInput = TNetInputArg | Array<TNetInputArg> | NetInput | tf.Tensor4D
|
||||
24
thirdparty/face-api/env/createBrowserEnv.ts
vendored
24
thirdparty/face-api/env/createBrowserEnv.ts
vendored
|
|
@ -1,24 +0,0 @@
|
|||
import { Environment } from './types';
|
||||
|
||||
export function createBrowserEnv(): Environment {
|
||||
|
||||
const fetch = window['fetch'] || function() {
|
||||
throw new Error('fetch - missing fetch implementation for browser environment')
|
||||
}
|
||||
|
||||
const readFile = function() {
|
||||
throw new Error('readFile - filesystem not available for browser environment')
|
||||
}
|
||||
|
||||
return {
|
||||
Canvas: HTMLCanvasElement,
|
||||
CanvasRenderingContext2D: CanvasRenderingContext2D,
|
||||
Image: HTMLImageElement,
|
||||
ImageData: ImageData,
|
||||
Video: HTMLVideoElement,
|
||||
createCanvasElement: () => document.createElement('canvas'),
|
||||
createImageElement: () => document.createElement('img'),
|
||||
fetch,
|
||||
readFile
|
||||
}
|
||||
}
|
||||
30
thirdparty/face-api/env/createFileSystem.ts
vendored
30
thirdparty/face-api/env/createFileSystem.ts
vendored
|
|
@ -1,30 +0,0 @@
|
|||
import { FileSystem } from './types';
|
||||
|
||||
export function createFileSystem(fs?: any): FileSystem {
|
||||
|
||||
let requireFsError = ''
|
||||
|
||||
if (!fs) {
|
||||
try {
|
||||
fs = require('fs')
|
||||
} catch (err) {
|
||||
requireFsError = err.toString()
|
||||
}
|
||||
}
|
||||
|
||||
const readFile = fs
|
||||
? function(filePath: string) {
|
||||
return new Promise<Buffer>((res, rej) => {
|
||||
fs.readFile(filePath, function(err: any, buffer: Buffer) {
|
||||
return err ? rej(err) : res(buffer)
|
||||
})
|
||||
})
|
||||
}
|
||||
: function() {
|
||||
throw new Error(`readFile - failed to require fs in nodejs environment with error: ${requireFsError}`)
|
||||
}
|
||||
|
||||
return {
|
||||
readFile
|
||||
}
|
||||
}
|
||||
41
thirdparty/face-api/env/createWorkerEnv.ts
vendored
41
thirdparty/face-api/env/createWorkerEnv.ts
vendored
|
|
@ -1,41 +0,0 @@
|
|||
import { fetch as tfFetch } from '@tensorflow/tfjs-core/dist/util';
|
||||
import { Environment } from './types';
|
||||
|
||||
export function createWorkerEnv(): Environment {
|
||||
|
||||
const fetch = tfFetch || function() {
|
||||
throw new Error('fetch - missing fetch implementation for browser environment')
|
||||
}
|
||||
|
||||
const readFile = function() {
|
||||
throw new Error('readFile - filesystem not available for browser environment')
|
||||
}
|
||||
|
||||
const createCanvasElement = function() {
|
||||
const canvas = new OffscreenCanvas(1, 1) as any;
|
||||
canvas.localName = 'canvas';
|
||||
canvas.nodeName = 'CANVAS';
|
||||
canvas.tagName = 'CANVAS';
|
||||
canvas.nodeType = 1;
|
||||
canvas.innerHTML = '';
|
||||
canvas.remove = () => {
|
||||
console.log('nope');
|
||||
};
|
||||
return canvas;
|
||||
}
|
||||
|
||||
const HTMLImageElement = function() {}
|
||||
const HTMLVideoElement = function() {}
|
||||
|
||||
return {
|
||||
Canvas: OffscreenCanvas as any,
|
||||
CanvasRenderingContext2D: OffscreenCanvasRenderingContext2D as any,
|
||||
Image: HTMLImageElement as any,
|
||||
ImageData: ImageData,
|
||||
Video: HTMLVideoElement as any,
|
||||
createCanvasElement: createCanvasElement,
|
||||
createImageElement: () => document.createElement('img'),
|
||||
fetch,
|
||||
readFile
|
||||
}
|
||||
}
|
||||
69
thirdparty/face-api/env/index.ts
vendored
69
thirdparty/face-api/env/index.ts
vendored
|
|
@ -1,69 +0,0 @@
|
|||
import { createBrowserEnv } from './createBrowserEnv';
|
||||
import { createFileSystem } from './createFileSystem';
|
||||
import { createWorkerEnv } from './createWorkerEnv';
|
||||
import { isBrowser } from './isBrowser';
|
||||
import { isNodejs } from './isNodejs';
|
||||
import { Environment } from './types';
|
||||
|
||||
let environment: Environment | null
|
||||
|
||||
function getEnv(): Environment {
|
||||
if (!environment) {
|
||||
throw new Error('getEnv - environment is not defined, check isNodejs() and isBrowser()')
|
||||
}
|
||||
return environment
|
||||
}
|
||||
|
||||
function setEnv(env: Environment) {
|
||||
environment = env
|
||||
}
|
||||
|
||||
function isWorker() {
|
||||
return typeof importScripts === 'function'
|
||||
}
|
||||
|
||||
function initialize() {
|
||||
// check for isBrowser() first to prevent electron renderer process
|
||||
// to be initialized with wrong environment due to isNodejs() returning true
|
||||
if (isWorker()) {
|
||||
setEnv(createWorkerEnv())
|
||||
} else if (isBrowser()) {
|
||||
setEnv(createBrowserEnv())
|
||||
}
|
||||
}
|
||||
|
||||
function monkeyPatch(env: Partial<Environment>) {
|
||||
if (!environment) {
|
||||
initialize()
|
||||
}
|
||||
|
||||
if (!environment) {
|
||||
throw new Error('monkeyPatch - environment is not defined, check isNodejs() and isBrowser()')
|
||||
}
|
||||
|
||||
const { Canvas = environment.Canvas, Image = environment.Image } = env
|
||||
environment.Canvas = Canvas
|
||||
environment.Image = Image
|
||||
environment.createCanvasElement = env.createCanvasElement || (() => new Canvas())
|
||||
environment.createImageElement = env.createImageElement || (() => new Image())
|
||||
|
||||
environment.ImageData = env.ImageData || environment.ImageData
|
||||
environment.Video = env.Video || environment.Video
|
||||
environment.fetch = env.fetch || environment.fetch
|
||||
environment.readFile = env.readFile || environment.readFile
|
||||
}
|
||||
|
||||
export const env = {
|
||||
getEnv,
|
||||
setEnv,
|
||||
initialize,
|
||||
createBrowserEnv,
|
||||
createFileSystem,
|
||||
monkeyPatch,
|
||||
isBrowser,
|
||||
isNodejs
|
||||
}
|
||||
|
||||
initialize()
|
||||
|
||||
export * from './types'
|
||||
9
thirdparty/face-api/env/isBrowser.ts
vendored
9
thirdparty/face-api/env/isBrowser.ts
vendored
|
|
@ -1,9 +0,0 @@
|
|||
export function isBrowser(): boolean {
|
||||
return typeof window === 'object'
|
||||
&& typeof document !== 'undefined'
|
||||
&& typeof HTMLImageElement !== 'undefined'
|
||||
&& typeof HTMLCanvasElement !== 'undefined'
|
||||
&& typeof HTMLVideoElement !== 'undefined'
|
||||
&& typeof ImageData !== 'undefined'
|
||||
&& typeof CanvasRenderingContext2D !== 'undefined'
|
||||
}
|
||||
8
thirdparty/face-api/env/isNodejs.ts
vendored
8
thirdparty/face-api/env/isNodejs.ts
vendored
|
|
@ -1,8 +0,0 @@
|
|||
export function isNodejs(): boolean {
|
||||
return typeof global === 'object'
|
||||
&& typeof require === 'function'
|
||||
&& typeof module !== 'undefined'
|
||||
// issues with gatsby.js: module.exports is undefined
|
||||
// && !!module.exports
|
||||
&& typeof process !== 'undefined' && !!process.version
|
||||
}
|
||||
14
thirdparty/face-api/env/types.ts
vendored
14
thirdparty/face-api/env/types.ts
vendored
|
|
@ -1,14 +0,0 @@
|
|||
export type FileSystem = {
|
||||
readFile: (filePath: string) => Promise<Buffer>
|
||||
}
|
||||
|
||||
export type Environment = FileSystem & {
|
||||
Canvas: typeof HTMLCanvasElement
|
||||
CanvasRenderingContext2D: typeof CanvasRenderingContext2D
|
||||
Image: typeof HTMLImageElement
|
||||
ImageData: typeof ImageData
|
||||
Video: typeof HTMLVideoElement
|
||||
createCanvasElement: () => HTMLCanvasElement
|
||||
createImageElement: () => HTMLImageElement
|
||||
fetch: (url: string, init?: RequestInit) => Promise<Response>
|
||||
}
|
||||
13
thirdparty/face-api/euclideanDistance.ts
vendored
13
thirdparty/face-api/euclideanDistance.ts
vendored
|
|
@ -1,13 +0,0 @@
|
|||
export function euclideanDistance(arr1: number[] | Float32Array, arr2: number[] | Float32Array) {
|
||||
if (arr1.length !== arr2.length)
|
||||
throw new Error('euclideanDistance: arr1.length !== arr2.length')
|
||||
|
||||
const desc1 = Array.from(arr1)
|
||||
const desc2 = Array.from(arr2)
|
||||
|
||||
return Math.sqrt(
|
||||
desc1
|
||||
.map((val, i) => val - desc2[i])
|
||||
.reduce((res, diff) => res + Math.pow(diff, 2), 0)
|
||||
)
|
||||
}
|
||||
|
|
@ -1,55 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { NetInput, TNetInput, toNetInput } from '../dom';
|
||||
import { NeuralNetwork } from '../NeuralNetwork';
|
||||
import { normalize } from '../ops';
|
||||
import { denseBlock4 } from './denseBlock';
|
||||
import { extractParams } from './extractParams';
|
||||
import { extractParamsFromWeigthMap } from './extractParamsFromWeigthMap';
|
||||
import { FaceFeatureExtractorParams, IFaceFeatureExtractor } from './types';
|
||||
|
||||
export class FaceFeatureExtractor extends NeuralNetwork<FaceFeatureExtractorParams> implements IFaceFeatureExtractor<FaceFeatureExtractorParams> {
|
||||
|
||||
constructor() {
|
||||
super('FaceFeatureExtractor')
|
||||
}
|
||||
|
||||
public forwardInput(input: NetInput): tf.Tensor4D {
|
||||
|
||||
const { params } = this
|
||||
|
||||
if (!params) {
|
||||
throw new Error('FaceFeatureExtractor - load model before inference')
|
||||
}
|
||||
|
||||
return tf.tidy(() => {
|
||||
const batchTensor = input.toBatchTensor(112, true)
|
||||
const meanRgb = [122.782, 117.001, 104.298]
|
||||
const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D
|
||||
|
||||
let out = denseBlock4(normalized, params.dense0, true)
|
||||
out = denseBlock4(out, params.dense1)
|
||||
out = denseBlock4(out, params.dense2)
|
||||
out = denseBlock4(out, params.dense3)
|
||||
out = tf.avgPool(out, [7, 7], [2, 2], 'valid')
|
||||
|
||||
return out
|
||||
})
|
||||
}
|
||||
|
||||
public async forward(input: TNetInput): Promise<tf.Tensor4D> {
|
||||
return this.forwardInput(await toNetInput(input))
|
||||
}
|
||||
|
||||
protected getDefaultModelName(): string {
|
||||
return 'face_feature_extractor_model'
|
||||
}
|
||||
|
||||
protected extractParamsFromWeigthMap(weightMap: tf.NamedTensorMap) {
|
||||
return extractParamsFromWeigthMap(weightMap)
|
||||
}
|
||||
|
||||
protected extractParams(weights: Float32Array) {
|
||||
return extractParams(weights)
|
||||
}
|
||||
}
|
||||
|
|
@ -1,54 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { NetInput, TNetInput, toNetInput } from '../dom';
|
||||
import { NeuralNetwork } from '../NeuralNetwork';
|
||||
import { normalize } from '../ops';
|
||||
import { denseBlock3 } from './denseBlock';
|
||||
import { extractParamsFromWeigthMapTiny } from './extractParamsFromWeigthMapTiny';
|
||||
import { extractParamsTiny } from './extractParamsTiny';
|
||||
import { IFaceFeatureExtractor, TinyFaceFeatureExtractorParams } from './types';
|
||||
|
||||
export class TinyFaceFeatureExtractor extends NeuralNetwork<TinyFaceFeatureExtractorParams> implements IFaceFeatureExtractor<TinyFaceFeatureExtractorParams> {
|
||||
|
||||
constructor() {
|
||||
super('TinyFaceFeatureExtractor')
|
||||
}
|
||||
|
||||
public forwardInput(input: NetInput): tf.Tensor4D {
|
||||
|
||||
const { params } = this
|
||||
|
||||
if (!params) {
|
||||
throw new Error('TinyFaceFeatureExtractor - load model before inference')
|
||||
}
|
||||
|
||||
return tf.tidy(() => {
|
||||
const batchTensor = input.toBatchTensor(112, true)
|
||||
const meanRgb = [122.782, 117.001, 104.298]
|
||||
const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(255)) as tf.Tensor4D
|
||||
|
||||
let out = denseBlock3(normalized, params.dense0, true)
|
||||
out = denseBlock3(out, params.dense1)
|
||||
out = denseBlock3(out, params.dense2)
|
||||
out = tf.avgPool(out, [14, 14], [2, 2], 'valid')
|
||||
|
||||
return out
|
||||
})
|
||||
}
|
||||
|
||||
public async forward(input: TNetInput): Promise<tf.Tensor4D> {
|
||||
return this.forwardInput(await toNetInput(input))
|
||||
}
|
||||
|
||||
protected getDefaultModelName(): string {
|
||||
return 'face_feature_extractor_tiny_model'
|
||||
}
|
||||
|
||||
protected extractParamsFromWeigthMap(weightMap: tf.NamedTensorMap) {
|
||||
return extractParamsFromWeigthMapTiny(weightMap)
|
||||
}
|
||||
|
||||
protected extractParams(weights: Float32Array) {
|
||||
return extractParamsTiny(weights)
|
||||
}
|
||||
}
|
||||
|
|
@ -1,55 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ConvParams, SeparableConvParams } from '../common';
|
||||
import { depthwiseSeparableConv } from '../common/depthwiseSeparableConv';
|
||||
import { DenseBlock3Params, DenseBlock4Params } from './types';
|
||||
|
||||
export function denseBlock3(
|
||||
x: tf.Tensor4D,
|
||||
denseBlockParams: DenseBlock3Params,
|
||||
isFirstLayer: boolean = false
|
||||
): tf.Tensor4D {
|
||||
return tf.tidy(() => {
|
||||
const out1 = tf.relu(
|
||||
isFirstLayer
|
||||
? tf.add(
|
||||
tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, [2, 2], 'same'),
|
||||
denseBlockParams.conv0.bias
|
||||
)
|
||||
: depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, [2, 2])
|
||||
) as tf.Tensor4D
|
||||
const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1])
|
||||
|
||||
const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D
|
||||
const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1])
|
||||
|
||||
return tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D
|
||||
})
|
||||
}
|
||||
|
||||
export function denseBlock4(
|
||||
x: tf.Tensor4D,
|
||||
denseBlockParams: DenseBlock4Params,
|
||||
isFirstLayer: boolean = false,
|
||||
isScaleDown: boolean = true
|
||||
): tf.Tensor4D {
|
||||
return tf.tidy(() => {
|
||||
const out1 = tf.relu(
|
||||
isFirstLayer
|
||||
? tf.add(
|
||||
tf.conv2d(x, (denseBlockParams.conv0 as ConvParams).filters, isScaleDown ? [2, 2] : [1, 1], 'same'),
|
||||
denseBlockParams.conv0.bias
|
||||
)
|
||||
: depthwiseSeparableConv(x, denseBlockParams.conv0 as SeparableConvParams, isScaleDown ? [2, 2] : [1, 1])
|
||||
) as tf.Tensor4D
|
||||
const out2 = depthwiseSeparableConv(out1, denseBlockParams.conv1, [1, 1])
|
||||
|
||||
const in3 = tf.relu(tf.add(out1, out2)) as tf.Tensor4D
|
||||
const out3 = depthwiseSeparableConv(in3, denseBlockParams.conv2, [1, 1])
|
||||
|
||||
const in4 = tf.relu(tf.add(out1, tf.add(out2, out3))) as tf.Tensor4D
|
||||
const out4 = depthwiseSeparableConv(in4, denseBlockParams.conv3, [1, 1])
|
||||
|
||||
return tf.relu(tf.add(out1, tf.add(out2, tf.add(out3, out4)))) as tf.Tensor4D
|
||||
})
|
||||
}
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
import { extractWeightsFactory, ParamMapping } from '../common';
|
||||
import { extractorsFactory } from './extractorsFactory';
|
||||
import { FaceFeatureExtractorParams } from './types';
|
||||
|
||||
|
||||
export function extractParams(weights: Float32Array): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractWeights,
|
||||
getRemainingWeights
|
||||
} = extractWeightsFactory(weights)
|
||||
|
||||
const {
|
||||
extractDenseBlock4Params
|
||||
} = extractorsFactory(extractWeights, paramMappings)
|
||||
|
||||
const dense0 = extractDenseBlock4Params(3, 32, 'dense0', true)
|
||||
const dense1 = extractDenseBlock4Params(32, 64, 'dense1')
|
||||
const dense2 = extractDenseBlock4Params(64, 128, 'dense2')
|
||||
const dense3 = extractDenseBlock4Params(128, 256, 'dense3')
|
||||
|
||||
if (getRemainingWeights().length !== 0) {
|
||||
throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`)
|
||||
}
|
||||
|
||||
return {
|
||||
paramMappings,
|
||||
params: { dense0, dense1, dense2, dense3 }
|
||||
}
|
||||
}
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { disposeUnusedWeightTensors, ParamMapping } from '../common';
|
||||
import { loadParamsFactory } from './loadParamsFactory';
|
||||
import { FaceFeatureExtractorParams } from './types';
|
||||
|
||||
export function extractParamsFromWeigthMap(
|
||||
weightMap: tf.NamedTensorMap
|
||||
): { params: FaceFeatureExtractorParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractDenseBlock4Params
|
||||
} = loadParamsFactory(weightMap, paramMappings)
|
||||
|
||||
const params = {
|
||||
dense0: extractDenseBlock4Params('dense0', true),
|
||||
dense1: extractDenseBlock4Params('dense1'),
|
||||
dense2: extractDenseBlock4Params('dense2'),
|
||||
dense3: extractDenseBlock4Params('dense3')
|
||||
}
|
||||
|
||||
disposeUnusedWeightTensors(weightMap, paramMappings)
|
||||
|
||||
return { params, paramMappings }
|
||||
}
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { disposeUnusedWeightTensors, ParamMapping } from '../common';
|
||||
import { loadParamsFactory } from './loadParamsFactory';
|
||||
import { TinyFaceFeatureExtractorParams } from './types';
|
||||
|
||||
export function extractParamsFromWeigthMapTiny(
|
||||
weightMap: tf.NamedTensorMap
|
||||
): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractDenseBlock3Params
|
||||
} = loadParamsFactory(weightMap, paramMappings)
|
||||
|
||||
const params = {
|
||||
dense0: extractDenseBlock3Params('dense0', true),
|
||||
dense1: extractDenseBlock3Params('dense1'),
|
||||
dense2: extractDenseBlock3Params('dense2')
|
||||
}
|
||||
|
||||
disposeUnusedWeightTensors(weightMap, paramMappings)
|
||||
|
||||
return { params, paramMappings }
|
||||
}
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
import { extractWeightsFactory, ParamMapping } from '../common';
|
||||
import { extractorsFactory } from './extractorsFactory';
|
||||
import { TinyFaceFeatureExtractorParams } from './types';
|
||||
|
||||
|
||||
|
||||
export function extractParamsTiny(weights: Float32Array): { params: TinyFaceFeatureExtractorParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractWeights,
|
||||
getRemainingWeights
|
||||
} = extractWeightsFactory(weights)
|
||||
|
||||
const {
|
||||
extractDenseBlock3Params
|
||||
} = extractorsFactory(extractWeights, paramMappings)
|
||||
|
||||
const dense0 = extractDenseBlock3Params(3, 32, 'dense0', true)
|
||||
const dense1 = extractDenseBlock3Params(32, 64, 'dense1')
|
||||
const dense2 = extractDenseBlock3Params(64, 128, 'dense2')
|
||||
|
||||
if (getRemainingWeights().length !== 0) {
|
||||
throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`)
|
||||
}
|
||||
|
||||
return {
|
||||
paramMappings,
|
||||
params: { dense0, dense1, dense2 }
|
||||
}
|
||||
}
|
||||
|
|
@ -1,38 +0,0 @@
|
|||
import {
|
||||
extractConvParamsFactory,
|
||||
extractSeparableConvParamsFactory,
|
||||
ExtractWeightsFunction,
|
||||
ParamMapping,
|
||||
} from '../common';
|
||||
import { DenseBlock3Params, DenseBlock4Params } from './types';
|
||||
|
||||
export function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {
|
||||
|
||||
const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings)
|
||||
const extractSeparableConvParams = extractSeparableConvParamsFactory(extractWeights, paramMappings)
|
||||
|
||||
function extractDenseBlock3Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock3Params {
|
||||
|
||||
const conv0 = isFirstLayer
|
||||
? extractConvParams(channelsIn, channelsOut, 3, `${mappedPrefix}/conv0`)
|
||||
: extractSeparableConvParams(channelsIn, channelsOut, `${mappedPrefix}/conv0`)
|
||||
const conv1 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv1`)
|
||||
const conv2 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv2`)
|
||||
|
||||
return { conv0, conv1, conv2 }
|
||||
}
|
||||
|
||||
function extractDenseBlock4Params(channelsIn: number, channelsOut: number, mappedPrefix: string, isFirstLayer: boolean = false): DenseBlock4Params {
|
||||
|
||||
const { conv0, conv1, conv2 } = extractDenseBlock3Params(channelsIn, channelsOut, mappedPrefix, isFirstLayer)
|
||||
const conv3 = extractSeparableConvParams(channelsOut, channelsOut, `${mappedPrefix}/conv3`)
|
||||
|
||||
return { conv0, conv1, conv2, conv3 }
|
||||
}
|
||||
|
||||
return {
|
||||
extractDenseBlock3Params,
|
||||
extractDenseBlock4Params
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -1,2 +0,0 @@
|
|||
export * from './FaceFeatureExtractor';
|
||||
export * from './TinyFaceFeatureExtractor';
|
||||
|
|
@ -1,37 +0,0 @@
|
|||
import { extractWeightEntryFactory, loadSeparableConvParamsFactory, ParamMapping } from '../common';
|
||||
import { loadConvParamsFactory } from '../common/loadConvParamsFactory';
|
||||
import { DenseBlock3Params, DenseBlock4Params } from './types';
|
||||
|
||||
export function loadParamsFactory(weightMap: any, paramMappings: ParamMapping[]) {
|
||||
|
||||
const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings)
|
||||
|
||||
const extractConvParams = loadConvParamsFactory(extractWeightEntry)
|
||||
const extractSeparableConvParams = loadSeparableConvParamsFactory(extractWeightEntry)
|
||||
|
||||
function extractDenseBlock3Params(prefix: string, isFirstLayer: boolean = false): DenseBlock3Params {
|
||||
const conv0 = isFirstLayer
|
||||
? extractConvParams(`${prefix}/conv0`)
|
||||
: extractSeparableConvParams(`${prefix}/conv0`)
|
||||
const conv1 = extractSeparableConvParams(`${prefix}/conv1`)
|
||||
const conv2 = extractSeparableConvParams(`${prefix}/conv2`)
|
||||
|
||||
return { conv0, conv1, conv2 }
|
||||
}
|
||||
|
||||
function extractDenseBlock4Params(prefix: string, isFirstLayer: boolean = false): DenseBlock4Params {
|
||||
const conv0 = isFirstLayer
|
||||
? extractConvParams(`${prefix}/conv0`)
|
||||
: extractSeparableConvParams(`${prefix}/conv0`)
|
||||
const conv1 = extractSeparableConvParams(`${prefix}/conv1`)
|
||||
const conv2 = extractSeparableConvParams(`${prefix}/conv2`)
|
||||
const conv3 = extractSeparableConvParams(`${prefix}/conv3`)
|
||||
|
||||
return { conv0, conv1, conv2, conv3 }
|
||||
}
|
||||
|
||||
return {
|
||||
extractDenseBlock3Params,
|
||||
extractDenseBlock4Params
|
||||
}
|
||||
}
|
||||
|
|
@ -1,49 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { NetInput, TNetInput } from '../dom';
|
||||
import { ConvParams, SeparableConvParams } from '../common';
|
||||
import { NeuralNetwork } from '../NeuralNetwork';
|
||||
|
||||
export type ConvWithBatchNormParams = BatchNormParams & {
|
||||
filter: tf.Tensor4D
|
||||
}
|
||||
|
||||
export type BatchNormParams = {
|
||||
mean: tf.Tensor1D
|
||||
variance: tf.Tensor1D
|
||||
scale: tf.Tensor1D
|
||||
offset: tf.Tensor1D
|
||||
}
|
||||
|
||||
export type SeparableConvWithBatchNormParams = {
|
||||
depthwise: ConvWithBatchNormParams
|
||||
pointwise: ConvWithBatchNormParams
|
||||
}
|
||||
|
||||
export type DenseBlock3Params = {
|
||||
conv0: SeparableConvParams | ConvParams
|
||||
conv1: SeparableConvParams
|
||||
conv2: SeparableConvParams
|
||||
}
|
||||
|
||||
export type DenseBlock4Params = DenseBlock3Params & {
|
||||
conv3: SeparableConvParams
|
||||
}
|
||||
|
||||
export type TinyFaceFeatureExtractorParams = {
|
||||
dense0: DenseBlock3Params
|
||||
dense1: DenseBlock3Params
|
||||
dense2: DenseBlock3Params
|
||||
}
|
||||
|
||||
export type FaceFeatureExtractorParams = {
|
||||
dense0: DenseBlock4Params
|
||||
dense1: DenseBlock4Params
|
||||
dense2: DenseBlock4Params
|
||||
dense3: DenseBlock4Params
|
||||
}
|
||||
|
||||
export interface IFaceFeatureExtractor<TNetParams extends TinyFaceFeatureExtractorParams | FaceFeatureExtractorParams> extends NeuralNetwork<TNetParams> {
|
||||
forwardInput(input: NetInput): tf.Tensor4D
|
||||
forward(input: TNetInput): Promise<tf.Tensor4D>
|
||||
}
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
import { FaceFeatureExtractor } from '../faceFeatureExtractor/FaceFeatureExtractor';
|
||||
import { FaceFeatureExtractorParams } from '../faceFeatureExtractor/types';
|
||||
import { FaceLandmark68NetBase } from './FaceLandmark68NetBase';
|
||||
|
||||
export class FaceLandmark68Net extends FaceLandmark68NetBase<FaceFeatureExtractorParams> {
|
||||
|
||||
constructor(faceFeatureExtractor: FaceFeatureExtractor = new FaceFeatureExtractor()) {
|
||||
super('FaceLandmark68Net', faceFeatureExtractor)
|
||||
}
|
||||
|
||||
protected getDefaultModelName(): string {
|
||||
return 'face_landmark_68_model'
|
||||
}
|
||||
|
||||
protected getClassifierChannelsIn(): number {
|
||||
return 256
|
||||
}
|
||||
}
|
||||
|
|
@ -1,107 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { IDimensions, Point } from '../classes';
|
||||
import { FaceLandmarks68 } from '../classes/FaceLandmarks68';
|
||||
import { NetInput, TNetInput, toNetInput } from '../dom';
|
||||
import { FaceFeatureExtractorParams, TinyFaceFeatureExtractorParams } from '../faceFeatureExtractor/types';
|
||||
import { FaceProcessor } from '../faceProcessor/FaceProcessor';
|
||||
import { isEven } from '../utils';
|
||||
|
||||
export abstract class FaceLandmark68NetBase<
|
||||
TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams
|
||||
>
|
||||
extends FaceProcessor<TExtractorParams> {
|
||||
|
||||
public postProcess(output: tf.Tensor2D, inputSize: number, originalDimensions: IDimensions[]): tf.Tensor2D {
|
||||
|
||||
const inputDimensions = originalDimensions.map(({ width, height }) => {
|
||||
const scale = inputSize / Math.max(height, width)
|
||||
return {
|
||||
width: width * scale,
|
||||
height: height * scale
|
||||
}
|
||||
})
|
||||
|
||||
const batchSize = inputDimensions.length
|
||||
|
||||
return tf.tidy(() => {
|
||||
const createInterleavedTensor = (fillX: number, fillY: number) =>
|
||||
tf.stack([
|
||||
tf.fill([68], fillX),
|
||||
tf.fill([68], fillY)
|
||||
], 1).as2D(1, 136).as1D()
|
||||
|
||||
const getPadding = (batchIdx: number, cond: (w: number, h: number) => boolean): number => {
|
||||
const { width, height } = inputDimensions[batchIdx]
|
||||
return cond(width, height) ? Math.abs(width - height) / 2 : 0
|
||||
}
|
||||
const getPaddingX = (batchIdx: number) => getPadding(batchIdx, (w, h) => w < h)
|
||||
const getPaddingY = (batchIdx: number) => getPadding(batchIdx, (w, h) => h < w)
|
||||
|
||||
const landmarkTensors = output
|
||||
.mul(tf.fill([batchSize, 136], inputSize))
|
||||
.sub(tf.stack(Array.from(Array(batchSize), (_, batchIdx) =>
|
||||
createInterleavedTensor(
|
||||
getPaddingX(batchIdx),
|
||||
getPaddingY(batchIdx)
|
||||
)
|
||||
)))
|
||||
.div(tf.stack(Array.from(Array(batchSize), (_, batchIdx) =>
|
||||
createInterleavedTensor(
|
||||
inputDimensions[batchIdx].width,
|
||||
inputDimensions[batchIdx].height
|
||||
)
|
||||
)))
|
||||
|
||||
return landmarkTensors as tf.Tensor2D
|
||||
})
|
||||
}
|
||||
|
||||
public forwardInput(input: NetInput): tf.Tensor2D {
|
||||
return tf.tidy(() => {
|
||||
const out = this.runNet(input)
|
||||
return this.postProcess(
|
||||
out,
|
||||
input.inputSize as number,
|
||||
input.inputDimensions.map(([height, width]) => ({ height, width }))
|
||||
)
|
||||
})
|
||||
}
|
||||
|
||||
public async forward(input: TNetInput): Promise<tf.Tensor2D> {
|
||||
return this.forwardInput(await toNetInput(input))
|
||||
}
|
||||
|
||||
public async detectLandmarks(input: TNetInput): Promise<FaceLandmarks68 | FaceLandmarks68[]> {
|
||||
const netInput = await toNetInput(input)
|
||||
const landmarkTensors = tf.tidy(
|
||||
() => tf.unstack(this.forwardInput(netInput))
|
||||
)
|
||||
|
||||
const landmarksForBatch = await Promise.all(landmarkTensors.map(
|
||||
async (landmarkTensor, batchIdx) => {
|
||||
const landmarksArray = Array.from(await landmarkTensor.data())
|
||||
const xCoords = landmarksArray.filter((_, i) => isEven(i))
|
||||
const yCoords = landmarksArray.filter((_, i) => !isEven(i))
|
||||
|
||||
return new FaceLandmarks68(
|
||||
Array(68).fill(0).map((_, i) => new Point(xCoords[i], yCoords[i])),
|
||||
{
|
||||
height: netInput.getInputHeight(batchIdx),
|
||||
width : netInput.getInputWidth(batchIdx),
|
||||
}
|
||||
)
|
||||
}
|
||||
))
|
||||
|
||||
landmarkTensors.forEach(t => t.dispose())
|
||||
|
||||
return netInput.isBatchInput
|
||||
? landmarksForBatch
|
||||
: landmarksForBatch[0]
|
||||
}
|
||||
|
||||
protected getClassifierChannelsOut(): number {
|
||||
return 136
|
||||
}
|
||||
}
|
||||
5
thirdparty/face-api/faceLandmarkNet/index.ts
vendored
5
thirdparty/face-api/faceLandmarkNet/index.ts
vendored
|
|
@ -1,5 +0,0 @@
|
|||
import { FaceLandmark68Net } from './FaceLandmark68Net';
|
||||
|
||||
export * from './FaceLandmark68Net';
|
||||
|
||||
export class FaceLandmarkNet extends FaceLandmark68Net {}
|
||||
|
|
@ -1,88 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { fullyConnectedLayer } from '../common/fullyConnectedLayer';
|
||||
import { NetInput } from '../dom';
|
||||
import {
|
||||
FaceFeatureExtractorParams,
|
||||
IFaceFeatureExtractor,
|
||||
TinyFaceFeatureExtractorParams,
|
||||
} from '../faceFeatureExtractor/types';
|
||||
import { NeuralNetwork } from '../NeuralNetwork';
|
||||
import { extractParams } from './extractParams';
|
||||
import { extractParamsFromWeigthMap } from './extractParamsFromWeigthMap';
|
||||
import { NetParams } from './types';
|
||||
import { seperateWeightMaps } from './util';
|
||||
|
||||
export abstract class FaceProcessor<
|
||||
TExtractorParams extends FaceFeatureExtractorParams | TinyFaceFeatureExtractorParams
|
||||
>
|
||||
extends NeuralNetwork<NetParams> {
|
||||
|
||||
protected _faceFeatureExtractor: IFaceFeatureExtractor<TExtractorParams>
|
||||
|
||||
constructor(_name: string, faceFeatureExtractor: IFaceFeatureExtractor<TExtractorParams>) {
|
||||
super(_name)
|
||||
this._faceFeatureExtractor = faceFeatureExtractor
|
||||
}
|
||||
|
||||
public get faceFeatureExtractor(): IFaceFeatureExtractor<TExtractorParams> {
|
||||
return this._faceFeatureExtractor
|
||||
}
|
||||
|
||||
protected abstract getDefaultModelName(): string
|
||||
protected abstract getClassifierChannelsIn(): number
|
||||
protected abstract getClassifierChannelsOut(): number
|
||||
|
||||
public runNet(input: NetInput | tf.Tensor4D): tf.Tensor2D {
|
||||
|
||||
const { params } = this
|
||||
|
||||
if (!params) {
|
||||
throw new Error(`${this._name} - load model before inference`)
|
||||
}
|
||||
|
||||
return tf.tidy(() => {
|
||||
const bottleneckFeatures = input instanceof NetInput
|
||||
? this.faceFeatureExtractor.forwardInput(input)
|
||||
: input
|
||||
return fullyConnectedLayer(bottleneckFeatures.as2D(bottleneckFeatures.shape[0], -1), params.fc)
|
||||
})
|
||||
}
|
||||
|
||||
public dispose(throwOnRedispose: boolean = true) {
|
||||
this.faceFeatureExtractor.dispose(throwOnRedispose)
|
||||
super.dispose(throwOnRedispose)
|
||||
}
|
||||
|
||||
public loadClassifierParams(weights: Float32Array) {
|
||||
const { params, paramMappings } = this.extractClassifierParams(weights)
|
||||
this._params = params
|
||||
this._paramMappings = paramMappings
|
||||
}
|
||||
|
||||
public extractClassifierParams(weights: Float32Array) {
|
||||
return extractParams(weights, this.getClassifierChannelsIn(), this.getClassifierChannelsOut())
|
||||
}
|
||||
|
||||
protected extractParamsFromWeigthMap(weightMap: tf.NamedTensorMap) {
|
||||
|
||||
const { featureExtractorMap, classifierMap } = seperateWeightMaps(weightMap)
|
||||
|
||||
this.faceFeatureExtractor.loadFromWeightMap(featureExtractorMap)
|
||||
|
||||
return extractParamsFromWeigthMap(classifierMap)
|
||||
}
|
||||
|
||||
protected extractParams(weights: Float32Array) {
|
||||
|
||||
const cIn = this.getClassifierChannelsIn()
|
||||
const cOut = this.getClassifierChannelsOut()
|
||||
const classifierWeightSize = (cOut * cIn ) + cOut
|
||||
|
||||
const featureExtractorWeights = weights.slice(0, weights.length - classifierWeightSize)
|
||||
const classifierWeights = weights.slice(weights.length - classifierWeightSize)
|
||||
|
||||
this.faceFeatureExtractor.extractWeights(featureExtractorWeights)
|
||||
return this.extractClassifierParams(classifierWeights)
|
||||
}
|
||||
}
|
||||
|
|
@ -1,25 +0,0 @@
|
|||
import { extractFCParamsFactory, extractWeightsFactory, ParamMapping } from '../common';
|
||||
import { NetParams } from './types';
|
||||
|
||||
export function extractParams(weights: Float32Array, channelsIn: number, channelsOut: number): { params: NetParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractWeights,
|
||||
getRemainingWeights
|
||||
} = extractWeightsFactory(weights)
|
||||
|
||||
const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings)
|
||||
|
||||
const fc = extractFCParams(channelsIn, channelsOut, 'fc')
|
||||
|
||||
if (getRemainingWeights().length !== 0) {
|
||||
throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`)
|
||||
}
|
||||
|
||||
return {
|
||||
paramMappings,
|
||||
params: { fc }
|
||||
}
|
||||
}
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { disposeUnusedWeightTensors, extractWeightEntryFactory, FCParams, ParamMapping } from '../common';
|
||||
import { NetParams } from './types';
|
||||
|
||||
export function extractParamsFromWeigthMap(
|
||||
weightMap: tf.NamedTensorMap
|
||||
): { params: NetParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings)
|
||||
|
||||
function extractFcParams(prefix: string): FCParams {
|
||||
const weights = extractWeightEntry<tf.Tensor2D>(`${prefix}/weights`, 2)
|
||||
const bias = extractWeightEntry<tf.Tensor1D>(`${prefix}/bias`, 1)
|
||||
return { weights, bias }
|
||||
}
|
||||
|
||||
const params = {
|
||||
fc: extractFcParams('fc')
|
||||
}
|
||||
|
||||
disposeUnusedWeightTensors(weightMap, paramMappings)
|
||||
|
||||
return { params, paramMappings }
|
||||
}
|
||||
1
thirdparty/face-api/faceProcessor/index.ts
vendored
1
thirdparty/face-api/faceProcessor/index.ts
vendored
|
|
@ -1 +0,0 @@
|
|||
export * from './FaceProcessor';
|
||||
6
thirdparty/face-api/faceProcessor/types.ts
vendored
6
thirdparty/face-api/faceProcessor/types.ts
vendored
|
|
@ -1,6 +0,0 @@
|
|||
import { FCParams } from '../common';
|
||||
|
||||
export type NetParams = {
|
||||
fc: FCParams
|
||||
}
|
||||
|
||||
15
thirdparty/face-api/faceProcessor/util.ts
vendored
15
thirdparty/face-api/faceProcessor/util.ts
vendored
|
|
@ -1,15 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
export function seperateWeightMaps(weightMap: tf.NamedTensorMap) {
|
||||
|
||||
const featureExtractorMap: tf.NamedTensorMap = {}
|
||||
const classifierMap: tf.NamedTensorMap = {}
|
||||
|
||||
Object.keys(weightMap).forEach(key => {
|
||||
const map = key.startsWith('fc') ? classifierMap : featureExtractorMap
|
||||
map[key] = weightMap[key]
|
||||
})
|
||||
|
||||
return { featureExtractorMap, classifierMap }
|
||||
|
||||
}
|
||||
|
|
@ -1,94 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { NetInput, TNetInput, toNetInput } from '../dom';
|
||||
import { NeuralNetwork } from '../NeuralNetwork';
|
||||
import { normalize } from '../ops';
|
||||
import { convDown } from './convLayer';
|
||||
import { extractParams } from './extractParams';
|
||||
import { extractParamsFromWeigthMap } from './extractParamsFromWeigthMap';
|
||||
import { residual, residualDown } from './residualLayer';
|
||||
import { NetParams } from './types';
|
||||
|
||||
|
||||
export class FaceRecognitionNet extends NeuralNetwork<NetParams> {
|
||||
|
||||
constructor() {
|
||||
super('FaceRecognitionNet')
|
||||
}
|
||||
|
||||
public forwardInput(input: NetInput): tf.Tensor2D {
|
||||
|
||||
const { params } = this
|
||||
|
||||
if (!params) {
|
||||
throw new Error('FaceRecognitionNet - load model before inference')
|
||||
}
|
||||
|
||||
return tf.tidy(() => {
|
||||
const batchTensor = input.toBatchTensor(150, true).toFloat()
|
||||
|
||||
const meanRgb = [122.782, 117.001, 104.298]
|
||||
const normalized = normalize(batchTensor, meanRgb).div(tf.scalar(256)) as tf.Tensor4D
|
||||
|
||||
let out = convDown(normalized, params.conv32_down)
|
||||
out = tf.maxPool(out, 3, 2, 'valid')
|
||||
|
||||
out = residual(out, params.conv32_1)
|
||||
out = residual(out, params.conv32_2)
|
||||
out = residual(out, params.conv32_3)
|
||||
|
||||
out = residualDown(out, params.conv64_down)
|
||||
out = residual(out, params.conv64_1)
|
||||
out = residual(out, params.conv64_2)
|
||||
out = residual(out, params.conv64_3)
|
||||
|
||||
out = residualDown(out, params.conv128_down)
|
||||
out = residual(out, params.conv128_1)
|
||||
out = residual(out, params.conv128_2)
|
||||
|
||||
out = residualDown(out, params.conv256_down)
|
||||
out = residual(out, params.conv256_1)
|
||||
out = residual(out, params.conv256_2)
|
||||
out = residualDown(out, params.conv256_down_out)
|
||||
|
||||
const globalAvg = out.mean([1, 2]) as tf.Tensor2D
|
||||
const fullyConnected = tf.matMul(globalAvg, params.fc)
|
||||
|
||||
return fullyConnected as tf.Tensor2D
|
||||
})
|
||||
}
|
||||
|
||||
public async forward(input: TNetInput): Promise<tf.Tensor2D> {
|
||||
return this.forwardInput(await toNetInput(input))
|
||||
}
|
||||
|
||||
public async computeFaceDescriptor(input: TNetInput): Promise<Float32Array|Float32Array[]> {
|
||||
const netInput = await toNetInput(input)
|
||||
|
||||
const faceDescriptorTensors = tf.tidy(
|
||||
() => tf.unstack(this.forwardInput(netInput))
|
||||
)
|
||||
|
||||
const faceDescriptorsForBatch = await Promise.all(faceDescriptorTensors.map(
|
||||
t => t.data()
|
||||
)) as Float32Array[]
|
||||
|
||||
faceDescriptorTensors.forEach(t => t.dispose())
|
||||
|
||||
return netInput.isBatchInput
|
||||
? faceDescriptorsForBatch
|
||||
: faceDescriptorsForBatch[0]
|
||||
}
|
||||
|
||||
protected getDefaultModelName(): string {
|
||||
return 'face_recognition_model'
|
||||
}
|
||||
|
||||
protected extractParamsFromWeigthMap(weightMap: tf.NamedTensorMap) {
|
||||
return extractParamsFromWeigthMap(weightMap)
|
||||
}
|
||||
|
||||
protected extractParams(weights: Float32Array) {
|
||||
return extractParams(weights)
|
||||
}
|
||||
}
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { scale } from './scaleLayer';
|
||||
import { ConvLayerParams } from './types';
|
||||
|
||||
|
||||
function convLayer(
|
||||
x: tf.Tensor4D,
|
||||
params: ConvLayerParams,
|
||||
strides: [number, number],
|
||||
withRelu: boolean,
|
||||
padding: 'valid' | 'same' = 'same'
|
||||
): tf.Tensor4D {
|
||||
const { filters, bias } = params.conv
|
||||
|
||||
let out = tf.conv2d(x, filters, strides, padding)
|
||||
out = tf.add(out, bias)
|
||||
out = scale(out, params.scale)
|
||||
return withRelu ? tf.relu(out) : out
|
||||
}
|
||||
|
||||
export function conv(x: tf.Tensor4D, params: ConvLayerParams) {
|
||||
return convLayer(x, params, [1, 1], true)
|
||||
}
|
||||
|
||||
export function convNoRelu(x: tf.Tensor4D, params: ConvLayerParams) {
|
||||
return convLayer(x, params, [1, 1], false)
|
||||
}
|
||||
|
||||
export function convDown(x: tf.Tensor4D, params: ConvLayerParams) {
|
||||
return convLayer(x, params, [2, 2], true, 'valid')
|
||||
}
|
||||
|
|
@ -1,155 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { ConvParams, extractWeightsFactory, ExtractWeightsFunction, ParamMapping } from '../common';
|
||||
import { isFloat } from '../utils';
|
||||
import { ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams } from './types';
|
||||
|
||||
function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {
|
||||
|
||||
function extractFilterValues(numFilterValues: number, numFilters: number, filterSize: number): tf.Tensor4D {
|
||||
const weights = extractWeights(numFilterValues)
|
||||
const depth = weights.length / (numFilters * filterSize * filterSize)
|
||||
|
||||
if (isFloat(depth)) {
|
||||
throw new Error(`depth has to be an integer: ${depth}, weights.length: ${weights.length}, numFilters: ${numFilters}, filterSize: ${filterSize}`)
|
||||
}
|
||||
|
||||
return tf.tidy(
|
||||
() => tf.transpose(
|
||||
tf.tensor4d(weights, [numFilters, depth, filterSize, filterSize]),
|
||||
[2, 3, 1, 0]
|
||||
)
|
||||
)
|
||||
}
|
||||
|
||||
function extractConvParams(
|
||||
numFilterValues: number,
|
||||
numFilters: number,
|
||||
filterSize: number,
|
||||
mappedPrefix: string
|
||||
): ConvParams {
|
||||
|
||||
const filters = extractFilterValues(numFilterValues, numFilters, filterSize)
|
||||
const bias = tf.tensor1d(extractWeights(numFilters))
|
||||
|
||||
paramMappings.push(
|
||||
{ paramPath: `${mappedPrefix}/filters` },
|
||||
{ paramPath: `${mappedPrefix}/bias` }
|
||||
)
|
||||
|
||||
return { filters, bias }
|
||||
}
|
||||
|
||||
function extractScaleLayerParams(numWeights: number, mappedPrefix: string): ScaleLayerParams {
|
||||
|
||||
const weights = tf.tensor1d(extractWeights(numWeights))
|
||||
const biases = tf.tensor1d(extractWeights(numWeights))
|
||||
|
||||
paramMappings.push(
|
||||
{ paramPath: `${mappedPrefix}/weights` },
|
||||
{ paramPath: `${mappedPrefix}/biases` }
|
||||
)
|
||||
|
||||
return {
|
||||
weights,
|
||||
biases
|
||||
}
|
||||
}
|
||||
|
||||
function extractConvLayerParams(
|
||||
numFilterValues: number,
|
||||
numFilters: number,
|
||||
filterSize: number,
|
||||
mappedPrefix: string
|
||||
): ConvLayerParams {
|
||||
|
||||
const conv = extractConvParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv`)
|
||||
const scale = extractScaleLayerParams(numFilters, `${mappedPrefix}/scale`)
|
||||
|
||||
return { conv, scale }
|
||||
}
|
||||
|
||||
function extractResidualLayerParams(
|
||||
numFilterValues: number,
|
||||
numFilters: number,
|
||||
filterSize: number,
|
||||
mappedPrefix: string,
|
||||
isDown: boolean = false
|
||||
): ResidualLayerParams {
|
||||
|
||||
const conv1 = extractConvLayerParams((isDown ? 0.5 : 1) * numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv1`)
|
||||
const conv2 = extractConvLayerParams(numFilterValues, numFilters, filterSize, `${mappedPrefix}/conv2`)
|
||||
|
||||
return { conv1, conv2 }
|
||||
}
|
||||
|
||||
return {
|
||||
extractConvLayerParams,
|
||||
extractResidualLayerParams
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
export function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const {
|
||||
extractWeights,
|
||||
getRemainingWeights
|
||||
} = extractWeightsFactory(weights)
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractConvLayerParams,
|
||||
extractResidualLayerParams
|
||||
} = extractorsFactory(extractWeights, paramMappings)
|
||||
|
||||
const conv32_down = extractConvLayerParams(4704, 32, 7, 'conv32_down')
|
||||
const conv32_1 = extractResidualLayerParams(9216, 32, 3, 'conv32_1')
|
||||
const conv32_2 = extractResidualLayerParams(9216, 32, 3, 'conv32_2')
|
||||
const conv32_3 = extractResidualLayerParams(9216, 32, 3, 'conv32_3')
|
||||
|
||||
const conv64_down = extractResidualLayerParams(36864, 64, 3, 'conv64_down', true)
|
||||
const conv64_1 = extractResidualLayerParams(36864, 64, 3, 'conv64_1')
|
||||
const conv64_2 = extractResidualLayerParams(36864, 64, 3, 'conv64_2')
|
||||
const conv64_3 = extractResidualLayerParams(36864, 64, 3, 'conv64_3')
|
||||
|
||||
const conv128_down = extractResidualLayerParams(147456, 128, 3, 'conv128_down', true)
|
||||
const conv128_1 = extractResidualLayerParams(147456, 128, 3, 'conv128_1')
|
||||
const conv128_2 = extractResidualLayerParams(147456, 128, 3, 'conv128_2')
|
||||
|
||||
const conv256_down = extractResidualLayerParams(589824, 256, 3, 'conv256_down', true)
|
||||
const conv256_1 = extractResidualLayerParams(589824, 256, 3, 'conv256_1')
|
||||
const conv256_2 = extractResidualLayerParams(589824, 256, 3, 'conv256_2')
|
||||
const conv256_down_out = extractResidualLayerParams(589824, 256, 3, 'conv256_down_out')
|
||||
|
||||
const fc = tf.tidy(
|
||||
() => tf.transpose(tf.tensor2d(extractWeights(256 * 128), [128, 256]), [1, 0])
|
||||
)
|
||||
paramMappings.push({ paramPath: `fc` })
|
||||
|
||||
if (getRemainingWeights().length !== 0) {
|
||||
throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`)
|
||||
}
|
||||
|
||||
const params = {
|
||||
conv32_down,
|
||||
conv32_1,
|
||||
conv32_2,
|
||||
conv32_3,
|
||||
conv64_down,
|
||||
conv64_1,
|
||||
conv64_2,
|
||||
conv64_3,
|
||||
conv128_down,
|
||||
conv128_1,
|
||||
conv128_2,
|
||||
conv256_down,
|
||||
conv256_1,
|
||||
conv256_2,
|
||||
conv256_down_out,
|
||||
fc
|
||||
}
|
||||
|
||||
return { params, paramMappings }
|
||||
}
|
||||
|
|
@ -1,101 +0,0 @@
|
|||
import * as tf from '@tensorflow/tfjs-core';
|
||||
|
||||
import { disposeUnusedWeightTensors, extractWeightEntryFactory, ParamMapping } from '../common';
|
||||
import { isTensor2D } from '../utils';
|
||||
import { ConvLayerParams, NetParams, ResidualLayerParams, ScaleLayerParams } from './types';
|
||||
|
||||
function extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {
|
||||
|
||||
const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings)
|
||||
|
||||
function extractScaleLayerParams(prefix: string): ScaleLayerParams {
|
||||
|
||||
const weights = extractWeightEntry<tf.Tensor1D>(`${prefix}/scale/weights`, 1)
|
||||
const biases = extractWeightEntry<tf.Tensor1D>(`${prefix}/scale/biases`, 1)
|
||||
|
||||
return { weights, biases }
|
||||
}
|
||||
|
||||
function extractConvLayerParams(prefix: string): ConvLayerParams {
|
||||
|
||||
const filters = extractWeightEntry<tf.Tensor4D>(`${prefix}/conv/filters`, 4)
|
||||
const bias = extractWeightEntry<tf.Tensor1D>(`${prefix}/conv/bias`, 1)
|
||||
const scale = extractScaleLayerParams(prefix)
|
||||
|
||||
return { conv: { filters, bias }, scale }
|
||||
}
|
||||
|
||||
function extractResidualLayerParams(prefix: string): ResidualLayerParams {
|
||||
return {
|
||||
conv1: extractConvLayerParams(`${prefix}/conv1`),
|
||||
conv2: extractConvLayerParams(`${prefix}/conv2`)
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
extractConvLayerParams,
|
||||
extractResidualLayerParams
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
export function extractParamsFromWeigthMap(
|
||||
weightMap: tf.NamedTensorMap
|
||||
): { params: NetParams, paramMappings: ParamMapping[] } {
|
||||
|
||||
const paramMappings: ParamMapping[] = []
|
||||
|
||||
const {
|
||||
extractConvLayerParams,
|
||||
extractResidualLayerParams
|
||||
} = extractorsFactory(weightMap, paramMappings)
|
||||
|
||||
const conv32_down = extractConvLayerParams('conv32_down')
|
||||
const conv32_1 = extractResidualLayerParams('conv32_1')
|
||||
const conv32_2 = extractResidualLayerParams('conv32_2')
|
||||
const conv32_3 = extractResidualLayerParams('conv32_3')
|
||||
|
||||
const conv64_down = extractResidualLayerParams('conv64_down')
|
||||
const conv64_1 = extractResidualLayerParams('conv64_1')
|
||||
const conv64_2 = extractResidualLayerParams('conv64_2')
|
||||
const conv64_3 = extractResidualLayerParams('conv64_3')
|
||||
|
||||
const conv128_down = extractResidualLayerParams('conv128_down')
|
||||
const conv128_1 = extractResidualLayerParams('conv128_1')
|
||||
const conv128_2 = extractResidualLayerParams('conv128_2')
|
||||
|
||||
const conv256_down = extractResidualLayerParams('conv256_down')
|
||||
const conv256_1 = extractResidualLayerParams('conv256_1')
|
||||
const conv256_2 = extractResidualLayerParams('conv256_2')
|
||||
const conv256_down_out = extractResidualLayerParams('conv256_down_out')
|
||||
|
||||
const fc = weightMap['fc']
|
||||
paramMappings.push({ originalPath: 'fc', paramPath: 'fc' })
|
||||
|
||||
if (!isTensor2D(fc)) {
|
||||
throw new Error(`expected weightMap[fc] to be a Tensor2D, instead have ${fc}`)
|
||||
}
|
||||
|
||||
const params = {
|
||||
conv32_down,
|
||||
conv32_1,
|
||||
conv32_2,
|
||||
conv32_3,
|
||||
conv64_down,
|
||||
conv64_1,
|
||||
conv64_2,
|
||||
conv64_3,
|
||||
conv128_down,
|
||||
conv128_1,
|
||||
conv128_2,
|
||||
conv256_down,
|
||||
conv256_1,
|
||||
conv256_2,
|
||||
conv256_down_out,
|
||||
fc
|
||||
}
|
||||
|
||||
disposeUnusedWeightTensors(weightMap, paramMappings)
|
||||
|
||||
return { params, paramMappings }
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Reference in a new issue