Merge pull request #51 from justadudewhohacks/mtcnn

README.md

@@ -8,14 +8,16 @@ Check out my article **[face-api.js — JavaScript API for Face Recognition
 
 * **[Running the Examples](#running-the-examples)**
 * **[About the Package](#about-the-package)**
-  * **[Face Detection](#about-face-detection)**
+  * **[Face Detection - SSD Mobilenet v1](#about-face-detection-ssd)**
+  * **[Face Detection & 5 Point Face Landmarks - MTCNN](#about-face-detection-mtcnn)**
   * **[Face Recognition](#about-face-recognition)**
-  * **[Face Landmark Detection](#about-face-landmark-detection)**
+  * **[68 Point Face Landmark Detection](#about-face-landmark-detection)**
 * **[Usage](#usage)**
   * **[Loading the Models](#usage-load-models)**
-  * **[Face Detection](#usage-face-detection)**
+  * **[Face Detection - SSD Mobilenet v1](#usage-face-detection-ssd)**
+  * **[Face Detection & 5 Point Face Landmarks - MTCNN](#usage-face-detection-mtcnn)**
   * **[Face Recognition](#usage-face-recognition)**
-  * **[Face Landmark Detection](#usage-face-landmark-detection)**
+  * **[68 Point Face Landmark Detection](#usage-face-landmark-detection)**
   * **[Full Face Detection and Recognition Pipeline](#usage-full-face-detection-and-recognition-pipeline)**
 
 ## Examples
@@ -38,8 +40,14 @@ Check out my article **[face-api.js — JavaScript API for Face Recognition
 
 ### Live Video Face Detection
 
+**SSD Mobilenet v1**
+
 ![preview_video-facedetection](https://user-images.githubusercontent.com/31125521/41238649-bbf10046-6d96-11e8-9041-1de46c6adccd.jpg)
 
+**MTCNN**
+
+![preview_mtcnn_video](https://user-images.githubusercontent.com/31125521/42725487-857adfd4-8784-11e8-8de2-4faae81e7ea2.jpg)
+
 ### Face Alignment
 
 ![preview_face_alignment](https://user-images.githubusercontent.com/31125521/41526994-1a690818-72e6-11e8-8f3c-d2cf31fe517b.jpg)
@@ -60,14 +68,22 @@ Browse to http://localhost:3000/.
 
 ## About the Package
 
-<a name="about-face-detection"></a>
+<a name="about-face-detection-ssd"></a>
 
-### Face Detection
+### Face Detection - SSD Mobilenet v1
 
-For face detection, this project implements a SSD (Single Shot Multibox Detector) based on MobileNetV1. The neural net will compute the locations of each face in an image and will return the bounding boxes together with it's probability for each face.
+For face detection, this project implements a SSD (Single Shot Multibox Detector) based on MobileNetV1. The neural net will compute the locations of each face in an image and will return the bounding boxes together with it's probability for each face. This face detector is aiming towards obtaining high accuracy in detecting face bounding boxes instead of low inference time.
 
 The face detection model has been trained on the [WIDERFACE dataset](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/) and the weights are provided by [yeephycho](https://github.com/yeephycho) in [this](https://github.com/yeephycho/tensorflow-face-detection) repo.
 
+<a name="about-face-detection-mtcnn"></a>
+
+### Face Detection & 5 Point Face Landmarks - MTCNN
+
+MTCNN (Multi-task Cascaded Convolutional Neural Networks) represents an alternative to SSD Mobilenet v1, which offers much more room for configuration and is able to achieve much lower processing times. MTCNN is a 3 stage cascaded CNN, which simultanously returns 5 face landmark points along with the bounding boxes and scores for each face. By limiting the minimum size of faces expected in an image, MTCNN allows you to process frames from your webcam in realtime. Additionally with 2MB, the size of the weights file is only a third of the size of the quantized SSD Mobilenet v1 model (~6MB).
+
+MTCNN has been presented in the paper [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://kpzhang93.github.io/MTCNN_face_detection_alignment/paper/spl.pdf) by Zhang et al. and the model weights are provided in the official [repo](https://github.com/kpzhang93/MTCNN_face_detection_alignment) of the MTCNN implementation.
+
 <a name="about-face-recognition"></a>
 
 ### Face Recognition
@@ -78,7 +94,7 @@ The neural net is equivalent to the **FaceRecognizerNet** used in [face-recognit
 
 <a name="about-face-landmark-detection"></a>
 
-### Face Landmark Detection
+### 68 Point Face Landmark Detection
 
 This package implements a CNN to detect the 68 point face landmarks for a given face image.
 
@@ -113,6 +129,7 @@ await faceapi.loadFaceDetectionModel('/models')
 // accordingly for the other models:
 // await faceapi.loadFaceLandmarkModel('/models')
 // await faceapi.loadFaceRecognitionModel('/models')
+// await faceapi.loadMtcnnModel('/models')
 ```
 
 As an alternative, you can also create instance of the neural nets:
@@ -122,12 +139,14 @@ const net = new faceapi.FaceDetectionNet()
 // accordingly for the other models:
 // const net = new faceapi.FaceLandmarkNet()
 // const net = new faceapi.FaceRecognitionNet()
+// const net = new faceapi.Mtcnn()
 
 await net.load('/models/face_detection_model-weights_manifest.json')
 // await net.load('/models/face_landmark_68_model-weights_manifest.json')
 // await net.load('/models/face_recognition_model-weights_manifest.json')
+// await net.load('/models/mtcnn_model-weights_manifest.json')
 
-// or simply
+// or simply load all models
 await net.load('/models')
 ```
 
@@ -145,9 +164,9 @@ const weights = new Float32Array(res.data)
 net.load(weights)
 ```
 
-<a name="usage-face-detection"></a>
+<a name="usage-face-detection-ssd"></a>
 
-### Face Detection
+### Face Detection - SSD Mobilenet v1
 
 Detect faces and get the bounding boxes and scores:
 
@@ -178,6 +197,62 @@ You can also obtain the tensors of the unfiltered bounding boxes and scores for
 const { boxes, scores } = await net.forward('myImg')
 ```
 
+<a name="usage-face-detection-mtcnn"></a>
+
+### Face Detection & 5 Point Face Landmarks - MTCNN
+
+Detect faces and get the bounding boxes and scores:
+
+``` javascript
+// defaults parameters shown:
+const forwardParams = {
+  // number of scaled versions of the input image passed through the CNN
+  // of the first stage, lower numbers will result in lower inference time,
+  // but will also be less accurate
+  maxNumScales: 10,
+  // scale factor used to calculate the scale steps of the image
+  // pyramid used in stage 1
+  scaleFactor: 0.709,
+  // the score threshold values used to filter the bounding
+  // boxes of stage 1, 2 and 3
+  scoreThresholds: [0.6, 0.7, 0.7],
+  // mininum face size to expect, the higher the faster processing will be,
+  // but smaller faces won't be detected
+  minFaceSize: 20
+}
+
+const results = await faceapi.mtcnn(document.getElementById('myImg'), forwardParams)
+```
+
+Alternatively you can also specify the scale steps manually:
+
+``` javascript
+const forwardParams = {
+  scaleSteps: [0.4, 0.2, 0.1, 0.05]
+}
+
+const results = await faceapi.mtcnn(document.getElementById('myImg'), forwardParams)
+```
+
+Finally you can draw the returned bounding boxes and 5 Point Face Landmarks into a canvas:
+
+``` javascript
+const minConfidence = 0.9
+
+if (results) {
+  results.forEach(({ faceDetection, faceLandmarks }) => {
+
+    // ignore results with low confidence score
+    if (faceDetection.score < minConfidence) {
+      return
+    }
+
+    faceapi.drawDetection('overlay', faceDetection)
+    faceapi.drawLandmarks('overlay', faceLandmarks)
+  })
+}
+```
+
 <a name="usage-face-recognition"></a>
 
 ### Face Recognition
@@ -265,7 +340,7 @@ const fullFaceDescriptions = await faceapi.allFaces(input, minConfidence)
 const fullFaceDescription0 = fullFaceDescriptions[0]
 console.log(fullFaceDescription0.detection) // bounding box & score
 console.log(fullFaceDescription0.landmarks) // 68 point face landmarks
-console.log(fullFaceDescription0.descriptor) // face descriptors
+console.log(fullFaceDescription0.descriptor) // face descriptor
 
 ```
 

build/FaceDetection.d.ts

+import { Rect } from './Rect';
+import { Dimensions } from './types';
+export declare class FaceDetection {
+    private _score;
+    private _box;
+    private _imageWidth;
+    private _imageHeight;
+    constructor(score: number, relativeBox: Rect, imageDims: Dimensions);
+    readonly score: number;
+    readonly box: Rect;
+    readonly imageWidth: number;
+    readonly imageHeight: number;
+    readonly relativeBox: Rect;
+    getScore(): number;
+    getBox(): Rect;
+    getImageWidth(): number;
+    getImageHeight(): number;
+    getRelativeBox(): Rect;
+    forSize(width: number, height: number): FaceDetection;
+}

build/FaceDetection.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var Rect_1 = require("./Rect");
+var FaceDetection = /** @class */ (function () {
+    function FaceDetection(score, relativeBox, imageDims) {
+        var width = imageDims.width, height = imageDims.height;
+        this._imageWidth = width;
+        this._imageHeight = height;
+        this._score = score;
+        this._box = new Rect_1.Rect(relativeBox.x * width, relativeBox.y * height, relativeBox.width * width, relativeBox.height * height);
+    }
+    Object.defineProperty(FaceDetection.prototype, "score", {
+        get: function () {
+            return this._score;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(FaceDetection.prototype, "box", {
+        get: function () {
+            return this._box;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(FaceDetection.prototype, "imageWidth", {
+        get: function () {
+            return this._imageWidth;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(FaceDetection.prototype, "imageHeight", {
+        get: function () {
+            return this._imageHeight;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(FaceDetection.prototype, "relativeBox", {
+        get: function () {
+            return new Rect_1.Rect(this._box.x / this._imageWidth, this._box.y / this._imageHeight, this._box.width / this._imageWidth, this._box.height / this._imageHeight);
+        },
+        enumerable: true,
+        configurable: true
+    });
+    FaceDetection.prototype.getScore = function () {
+        return this.score;
+    };
+    FaceDetection.prototype.getBox = function () {
+        return this.box;
+    };
+    FaceDetection.prototype.getImageWidth = function () {
+        return this.imageWidth;
+    };
+    FaceDetection.prototype.getImageHeight = function () {
+        return this.imageHeight;
+    };
+    FaceDetection.prototype.getRelativeBox = function () {
+        return this.relativeBox;
+    };
+    FaceDetection.prototype.forSize = function (width, height) {
+        return new FaceDetection(this._score, this.getRelativeBox(), { width: width, height: height });
+    };
+    return FaceDetection;
+}());
+exports.FaceDetection = FaceDetection;
+//# sourceMappingURL=FaceDetection.js.map
\ No newline at end of file

build/FaceDetection.js.map

+{"version":3,"file":"FaceDetection.js","sourceRoot":"","sources":["../src/FaceDetection.ts"],"names":[],"mappings":";;AAAA,+BAA8B;AAG9B;IAME,uBACE,KAAa,EACb,WAAiB,EACjB,SAAqB;QAEb,IAAA,uBAAK,EAAE,yBAAM,CAAc;QACnC,IAAI,CAAC,WAAW,GAAG,KAAK,CAAA;QACxB,IAAI,CAAC,YAAY,GAAG,MAAM,CAAA;QAC1B,IAAI,CAAC,MAAM,GAAG,KAAK,CAAA;QACnB,IAAI,CAAC,IAAI,GAAG,IAAI,WAAI,CAClB,WAAW,CAAC,CAAC,GAAG,KAAK,EACrB,WAAW,CAAC,CAAC,GAAG,MAAM,EACtB,WAAW,CAAC,KAAK,GAAG,KAAK,EACzB,WAAW,CAAC,MAAM,GAAG,MAAM,CAC5B,CAAA;IACH,CAAC;IAED,sBAAW,gCAAK;aAAhB;YACE,OAAO,IAAI,CAAC,MAAM,CAAA;QACpB,CAAC;;;OAAA;IAED,sBAAW,8BAAG;aAAd;YACE,OAAO,IAAI,CAAC,IAAI,CAAA;QAClB,CAAC;;;OAAA;IAED,sBAAW,qCAAU;aAArB;YACE,OAAO,IAAI,CAAC,WAAW,CAAA;QACzB,CAAC;;;OAAA;IAED,sBAAW,sCAAW;aAAtB;YACE,OAAO,IAAI,CAAC,YAAY,CAAA;QAC1B,CAAC;;;OAAA;IAED,sBAAW,sCAAW;aAAtB;YACE,OAAO,IAAI,WAAI,CACb,IAAI,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,WAAW,EAC9B,IAAI,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,YAAY,EAC/B,IAAI,CAAC,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,WAAW,EAClC,IAAI,CAAC,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,YAAY,CACrC,CAAA;QACH,CAAC;;;OAAA;IAEM,gCAAQ,GAAf;QACE,OAAO,IAAI,CAAC,KAAK,CAAA;IACnB,CAAC;IAEM,8BAAM,GAAb;QACE,OAAO,IAAI,CAAC,GAAG,CAAA;IACjB,CAAC;IAEM,qCAAa,GAApB;QACE,OAAO,IAAI,CAAC,UAAU,CAAA;IACxB,CAAC;IAEM,sCAAc,GAArB;QACE,OAAO,IAAI,CAAC,WAAW,CAAA;IACzB,CAAC;IAEM,sCAAc,GAArB;QACE,OAAO,IAAI,CAAC,WAAW,CAAA;IACzB,CAAC;IAEM,+BAAO,GAAd,UAAe,KAAa,EAAE,MAAc;QAC1C,OAAO,IAAI,aAAa,CACtB,IAAI,CAAC,MAAM,EACX,IAAI,CAAC,cAAc,EAAE,EACrB,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAC,CACjB,CAAA;IACH,CAAC;IACH,oBAAC;AAAD,CAAC,AA3ED,IA2EC;AA3EY,sCAAa"}
\ No newline at end of file

build/FaceLandmarks.d.ts

+import { Point } from './Point';
+import { Dimensions } from './types';
+export declare class FaceLandmarks {
+    protected _imageWidth: number;
+    protected _imageHeight: number;
+    protected _shift: Point;
+    protected _faceLandmarks: Point[];
+    constructor(relativeFaceLandmarkPositions: Point[], imageDims: Dimensions, shift?: Point);
+    getShift(): Point;
+    getImageWidth(): number;
+    getImageHeight(): number;
+    getPositions(): Point[];
+    getRelativePositions(): Point[];
+}

build/FaceLandmarks.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var Point_1 = require("./Point");
+var FaceLandmarks = /** @class */ (function () {
+    function FaceLandmarks(relativeFaceLandmarkPositions, imageDims, shift) {
+        if (shift === void 0) { shift = new Point_1.Point(0, 0); }
+        var width = imageDims.width, height = imageDims.height;
+        this._imageWidth = width;
+        this._imageHeight = height;
+        this._shift = shift;
+        this._faceLandmarks = relativeFaceLandmarkPositions.map(function (pt) { return pt.mul(new Point_1.Point(width, height)).add(shift); });
+    }
+    FaceLandmarks.prototype.getShift = function () {
+        return new Point_1.Point(this._shift.x, this._shift.y);
+    };
+    FaceLandmarks.prototype.getImageWidth = function () {
+        return this._imageWidth;
+    };
+    FaceLandmarks.prototype.getImageHeight = function () {
+        return this._imageHeight;
+    };
+    FaceLandmarks.prototype.getPositions = function () {
+        return this._faceLandmarks;
+    };
+    FaceLandmarks.prototype.getRelativePositions = function () {
+        var _this = this;
+        return this._faceLandmarks.map(function (pt) { return pt.sub(_this._shift).div(new Point_1.Point(_this._imageWidth, _this._imageHeight)); });
+    };
+    return FaceLandmarks;
+}());
+exports.FaceLandmarks = FaceLandmarks;
+//# sourceMappingURL=FaceLandmarks.js.map
\ No newline at end of file

build/FaceLandmarks.js.map

+{"version":3,"file":"FaceLandmarks.js","sourceRoot":"","sources":["../src/FaceLandmarks.ts"],"names":[],"mappings":";;AAAA,iCAAgC;AAGhC;IAME,uBACE,6BAAsC,EACtC,SAAqB,EACrB,KAA8B;QAA9B,sBAAA,EAAA,YAAmB,aAAK,CAAC,CAAC,EAAE,CAAC,CAAC;QAEtB,IAAA,uBAAK,EAAE,yBAAM,CAAc;QACnC,IAAI,CAAC,WAAW,GAAG,KAAK,CAAA;QACxB,IAAI,CAAC,YAAY,GAAG,MAAM,CAAA;QAC1B,IAAI,CAAC,MAAM,GAAG,KAAK,CAAA;QACnB,IAAI,CAAC,cAAc,GAAG,6BAA6B,CAAC,GAAG,CACrD,UAAA,EAAE,IAAI,OAAA,EAAE,CAAC,GAAG,CAAC,IAAI,aAAK,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,CAAC,EAA3C,CAA2C,CAClD,CAAA;IACH,CAAC;IAEM,gCAAQ,GAAf;QACE,OAAO,IAAI,aAAK,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAA;IAChD,CAAC;IAEM,qCAAa,GAApB;QACE,OAAO,IAAI,CAAC,WAAW,CAAA;IACzB,CAAC;IAEM,sCAAc,GAArB;QACE,OAAO,IAAI,CAAC,YAAY,CAAA;IAC1B,CAAC;IAEM,oCAAY,GAAnB;QACE,OAAO,IAAI,CAAC,cAAc,CAAA;IAC5B,CAAC;IAEM,4CAAoB,GAA3B;QAAA,iBAIC;QAHC,OAAO,IAAI,CAAC,cAAc,CAAC,GAAG,CAC5B,UAAA,EAAE,IAAI,OAAA,EAAE,CAAC,GAAG,CAAC,KAAI,CAAC,MAAM,CAAC,CAAC,GAAG,CAAC,IAAI,aAAK,CAAC,KAAI,CAAC,WAAW,EAAE,KAAI,CAAC,YAAY,CAAC,CAAC,EAAvE,CAAuE,CAC9E,CAAA;IACH,CAAC;IACH,oBAAC;AAAD,CAAC,AAzCD,IAyCC;AAzCY,sCAAa"}
\ No newline at end of file

build/FullFaceDescription.d.ts

-import { FaceDetection } from './faceDetectionNet/FaceDetection';
-import { FaceLandmarks } from './faceLandmarkNet/FaceLandmarks';
+import { FaceDetection } from './FaceDetection';
+import { FaceLandmarks68 } from './faceLandmarkNet/FaceLandmarks68';
 export declare class FullFaceDescription {
     private _detection;
     private _landmarks;
     private _descriptor;
-    constructor(_detection: FaceDetection, _landmarks: FaceLandmarks, _descriptor: Float32Array);
+    constructor(_detection: FaceDetection, _landmarks: FaceLandmarks68, _descriptor: Float32Array);
     readonly detection: FaceDetection;
-    readonly landmarks: FaceLandmarks;
+    readonly landmarks: FaceLandmarks68;
     readonly descriptor: Float32Array;
     forSize(width: number, height: number): FullFaceDescription;
 }

build/FullFaceDescription.js.map

-{"version":3,"file":"FullFaceDescription.js","sourceRoot":"","sources":["../src/FullFaceDescription.ts"],"names":[],"mappings":";;AAGA;IACE,6BACU,UAAyB,EACzB,UAAyB,EACzB,WAAyB;QAFzB,eAAU,GAAV,UAAU,CAAe;QACzB,eAAU,GAAV,UAAU,CAAe;QACzB,gBAAW,GAAX,WAAW,CAAc;IAChC,CAAC;IAEJ,sBAAW,0CAAS;aAApB;YACE,OAAO,IAAI,CAAC,UAAU,CAAA;QACxB,CAAC;;;OAAA;IAED,sBAAW,0CAAS;aAApB;YACE,OAAO,IAAI,CAAC,UAAU,CAAA;QACxB,CAAC;;;OAAA;IAED,sBAAW,2CAAU;aAArB;YACE,OAAO,IAAI,CAAC,WAAW,CAAA;QACzB,CAAC;;;OAAA;IAEM,qCAAO,GAAd,UAAe,KAAa,EAAE,MAAc;QAC1C,OAAO,IAAI,mBAAmB,CAC5B,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,EACtC,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,EACtC,IAAI,CAAC,WAAW,CACjB,CAAA;IACH,CAAC;IACH,0BAAC;AAAD,CAAC,AA1BD,IA0BC;AA1BY,kDAAmB"}
\ No newline at end of file
+{"version":3,"file":"FullFaceDescription.js","sourceRoot":"","sources":["../src/FullFaceDescription.ts"],"names":[],"mappings":";;AAGA;IACE,6BACU,UAAyB,EACzB,UAA2B,EAC3B,WAAyB;QAFzB,eAAU,GAAV,UAAU,CAAe;QACzB,eAAU,GAAV,UAAU,CAAiB;QAC3B,gBAAW,GAAX,WAAW,CAAc;IAChC,CAAC;IAEJ,sBAAW,0CAAS;aAApB;YACE,OAAO,IAAI,CAAC,UAAU,CAAA;QACxB,CAAC;;;OAAA;IAED,sBAAW,0CAAS;aAApB;YACE,OAAO,IAAI,CAAC,UAAU,CAAA;QACxB,CAAC;;;OAAA;IAED,sBAAW,2CAAU;aAArB;YACE,OAAO,IAAI,CAAC,WAAW,CAAA;QACzB,CAAC;;;OAAA;IAEM,qCAAO,GAAd,UAAe,KAAa,EAAE,MAAc;QAC1C,OAAO,IAAI,mBAAmB,CAC5B,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,EACtC,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,EACtC,IAAI,CAAC,WAAW,CACjB,CAAA;IACH,CAAC;IACH,0BAAC;AAAD,CAAC,AA1BD,IA0BC;AA1BY,kDAAmB"}
\ No newline at end of file

build/NetInput.d.ts

@@ -3,12 +3,14 @@ import { Point } from './Point';
 import { TResolvedNetInput } from './types';
 export declare class NetInput {
     private _inputs;
+    private _canvases;
     private _isManaged;
     private _isBatchInput;
     private _inputDimensions;
     private _paddings;
-    constructor(inputs: tf.Tensor4D | Array<TResolvedNetInput>, isBatchInput?: boolean);
+    constructor(inputs: tf.Tensor4D | Array<TResolvedNetInput>, isBatchInput?: boolean, keepCanvases?: boolean);
     readonly inputs: tf.Tensor3D[];
+    readonly canvases: HTMLCanvasElement[];
     readonly isManaged: boolean;
     readonly isBatchInput: boolean;
     readonly batchSize: number;

build/NetInput.js

@@ -6,9 +6,12 @@ var padToSquare_1 = require("./padToSquare");
 var Point_1 = require("./Point");
 var utils_1 = require("./utils");
 var NetInput = /** @class */ (function () {
-    function NetInput(inputs, isBatchInput) {
+    function NetInput(inputs, isBatchInput, keepCanvases) {
         if (isBatchInput === void 0) { isBatchInput = false; }
+        if (keepCanvases === void 0) { keepCanvases = false; }
+        var _this = this;
         this._inputs = [];
+        this._canvases = [];
         this._isManaged = false;
         this._isBatchInput = false;
         this._inputDimensions = [];
@@ -17,7 +20,7 @@ var NetInput = /** @class */ (function () {
             this._inputs = tf.unstack(inputs);
         }
         if (Array.isArray(inputs)) {
-            this._inputs = inputs.map(function (input) {
+            this._inputs = inputs.map(function (input, idx) {
                 if (isTensor_1.isTensor3D(input)) {
                     // TODO: make sure not to dispose original tensors passed in by the user
                     return tf.clone(input);
@@ -30,7 +33,11 @@ var NetInput = /** @class */ (function () {
                     }
                     return input.reshape(shape.slice(1));
                 }
-                return tf.fromPixels(input instanceof HTMLCanvasElement ? input : utils_1.createCanvasFromMedia(input));
+                var canvas = input instanceof HTMLCanvasElement ? input : utils_1.createCanvasFromMedia(input);
+                if (keepCanvases) {
+                    _this._canvases[idx] = canvas;
+                }
+                return tf.fromPixels(canvas);
             });
         }
         this._isBatchInput = this.batchSize > 1 || isBatchInput;
@@ -43,6 +50,13 @@ var NetInput = /** @class */ (function () {
         enumerable: true,
         configurable: true
     });
+    Object.defineProperty(NetInput.prototype, "canvases", {
+        get: function () {
+            return this._canvases;
+        },
+        enumerable: true,
+        configurable: true
+    });
     Object.defineProperty(NetInput.prototype, "isManaged", {
         get: function () {
             return this._isManaged;

build/NetInput.js.map

-{"version":3,"file":"NetInput.js","sourceRoot":"","sources":["../src/NetInput.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,+CAA4D;AAC5D,6CAA4C;AAC5C,iCAAgC;AAEhC,iCAAgD;AAEhD;IAQE,kBACE,MAA8C,EAC9C,YAA6B;QAA7B,6BAAA,EAAA,oBAA6B;QATvB,YAAO,GAAkB,EAAE,CAAA;QAC3B,eAAU,GAAY,KAAK,CAAA;QAC3B,kBAAa,GAAY,KAAK,CAAA;QAE9B,qBAAgB,GAAe,EAAE,CAAA;QACjC,cAAS,GAAY,EAAE,CAAA;QAM7B,IAAI,qBAAU,CAAC,MAAM,CAAC,EAAE;YACtB,IAAI,CAAC,OAAO,GAAG,EAAE,CAAC,OAAO,CAAC,MAAqB,CAAkB,CAAA;SAClE;QAED,IAAI,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE;YACzB,IAAI,CAAC,OAAO,GAAG,MAAM,CAAC,GAAG,CAAC,UAAA,KAAK;gBAC7B,IAAI,qBAAU,CAAC,KAAK,CAAC,EAAE;oBACrB,wEAAwE;oBACxE,OAAO,EAAE,CAAC,KAAK,CAAC,KAAoB,CAAC,CAAA;iBACtC;gBAED,IAAI,qBAAU,CAAC,KAAK,CAAC,EAAE;oBACrB,IAAM,KAAK,GAAI,KAAqB,CAAC,KAAK,CAAA;oBAC1C,IAAM,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;oBAC1B,IAAI,SAAS,KAAK,CAAC,EAAE;wBACnB,MAAM,IAAI,KAAK,CAAC,2CAAyC,SAAS,8CAA2C,CAAC,CAAA;qBAC/G;oBAED,OAAQ,KAAqB,CAAC,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAA6B,CAAgB,CAAA;iBACjG;gBAED,OAAO,EAAE,CAAC,UAAU,CAClB,KAAK,YAAY,iBAAiB,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,6BAAqB,CAAC,KAA4C,CAAC,CACjH,CAAA;YACH,CAAC,CAAC,CAAA;SACH;QAED,IAAI,CAAC,aAAa,GAAG,IAAI,CAAC,SAAS,GAAG,CAAC,IAAI,YAAY,CAAA;QACvD,IAAI,CAAC,gBAAgB,GAAG,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,KAAK,EAAP,CAAO,CAAC,CAAA;IACxD,CAAC;IAED,sBAAW,4BAAM;aAAjB;YACE,OAAO,IAAI,CAAC,OAAO,CAAA;QACrB,CAAC;;;OAAA;IAED,sBAAW,+BAAS;aAApB;YACE,OAAO,IAAI,CAAC,UAAU,CAAA;QACxB,CAAC;;;OAAA;IAED,sBAAW,kCAAY;aAAvB;YACE,OAAO,IAAI,CAAC,aAAa,CAAA;QAC3B,CAAC;;;OAAA;IAED,sBAAW,+BAAS;aAApB;YACE,OAAO,IAAI,CAAC,OAAO,CAAC,MAAM,CAAA;QAC5B,CAAC;;;OAAA;IAED,sBAAW,qCAAe;aAA1B;YACE,OAAO,IAAI,CAAC,gBAAgB,CAAA;QAC9B,CAAC;;;OAAA;IAED,sBAAW,8BAAQ;aAAnB;YACE,OAAO,IAAI,CAAC,SAAS,CAAA;QACvB,CAAC;;;OAAA;IAEM,qCAAkB,GAAzB,UAA0B,QAAgB;QACxC,OAAO,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAA;IACxC,CAAC;IAEM,iCAAc,GAArB,UAAsB,QAAgB;QACpC,OAAO,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAA;IAC3C,CAAC;IAEM,gCAAa,GAApB,UAAqB,QAAgB;QACnC,OAAO,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAA;IAC3C,CAAC;IAEM,8BAAW,GAAlB,UAAmB,QAAgB;QACjC,OAAO,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,CAAA;IACjC,CAAC;IAEM,gCAAa,GAApB,UAAqB,SAAiB,EAAE,cAA8B;QAAtE,iBA+BC;QA/BuC,+BAAA,EAAA,qBAA8B;QAEpE,OAAO,EAAE,CAAC,IAAI,CAAC;YAEb,IAAM,YAAY,GAAG,KAAI,CAAC,OAAO,CAAC,GAAG,CAAC,UAAC,WAAwB;gBACvD,IAAA,sBAAmD,EAAlD,sBAAc,EAAE,qBAAa,CAAqB;gBAEzD,IAAI,SAAS,GAAG,WAAW,CAAC,UAAU,EAAE,CAAC,OAAO,EAAiB,CAAA;gBACjE,SAAS,GAAG,yBAAW,CAAC,SAAS,EAAE,cAAc,CAAC,CAAA;gBAE5C,IAAA,6BAAkE,EAAjE,0BAAkB,EAAE,yBAAiB,CAA4B;gBAExE,IAAI,kBAAkB,KAAK,SAAS,IAAI,iBAAiB,KAAK,SAAS,EAAE;oBACvE,SAAS,GAAG,EAAE,CAAC,KAAK,CAAC,cAAc,CAAC,SAAS,EAAE,CAAC,SAAS,EAAE,SAAS,CAAC,CAAC,CAAA;iBACvE;gBAED,KAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,aAAK,CAC3B,iBAAiB,GAAG,aAAa,EACjC,kBAAkB,GAAG,cAAc,CACpC,CAAC,CAAA;gBACF,OAAO,SAAS,CAAA;YAClB,CAAC,CAAC,CAAA;YAEF,IAAM,WAAW,GAAG,EAAE,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,IAAI,CAAC,KAAI,CAAC,SAAS,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,CAAC,CAAA;YAExF,IAAI,KAAI,CAAC,SAAS,EAAE;gBAClB,KAAI,CAAC,OAAO,EAAE,CAAA;aACf;YAED,OAAO,WAAW,CAAA;QACpB,CAAC,CAAC,CAAA;IACJ,CAAC;IAED;;;OAGG;IACI,0BAAO,GAAd;QACE,IAAI,CAAC,UAAU,GAAG,IAAI,CAAA;QACtB,OAAO,IAAI,CAAA;IACb,CAAC;IAEM,0BAAO,GAAd;QACE,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;IACxC,CAAC;IACH,eAAC;AAAD,CAAC,AAhID,IAgIC;AAhIY,4BAAQ"}
\ No newline at end of file
+{"version":3,"file":"NetInput.js","sourceRoot":"","sources":["../src/NetInput.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,+CAA4D;AAC5D,6CAA4C;AAC5C,iCAAgC;AAEhC,iCAAgD;AAEhD;IASE,kBACE,MAA8C,EAC9C,YAA6B,EAC7B,YAA6B;QAD7B,6BAAA,EAAA,oBAA6B;QAC7B,6BAAA,EAAA,oBAA6B;QAH/B,iBAoCC;QA5CO,YAAO,GAAkB,EAAE,CAAA;QAC3B,cAAS,GAAwB,EAAE,CAAA;QACnC,eAAU,GAAY,KAAK,CAAA;QAC3B,kBAAa,GAAY,KAAK,CAAA;QAE9B,qBAAgB,GAAe,EAAE,CAAA;QACjC,cAAS,GAAY,EAAE,CAAA;QAO7B,IAAI,qBAAU,CAAC,MAAM,CAAC,EAAE;YACtB,IAAI,CAAC,OAAO,GAAG,EAAE,CAAC,OAAO,CAAC,MAAqB,CAAkB,CAAA;SAClE;QAED,IAAI,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE;YACzB,IAAI,CAAC,OAAO,GAAG,MAAM,CAAC,GAAG,CAAC,UAAC,KAAK,EAAE,GAAG;gBACnC,IAAI,qBAAU,CAAC,KAAK,CAAC,EAAE;oBACrB,wEAAwE;oBACxE,OAAO,EAAE,CAAC,KAAK,CAAC,KAAoB,CAAC,CAAA;iBACtC;gBAED,IAAI,qBAAU,CAAC,KAAK,CAAC,EAAE;oBACrB,IAAM,KAAK,GAAI,KAAqB,CAAC,KAAK,CAAA;oBAC1C,IAAM,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;oBAC1B,IAAI,SAAS,KAAK,CAAC,EAAE;wBACnB,MAAM,IAAI,KAAK,CAAC,2CAAyC,SAAS,8CAA2C,CAAC,CAAA;qBAC/G;oBAED,OAAQ,KAAqB,CAAC,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAA6B,CAAgB,CAAA;iBACjG;gBAED,IAAM,MAAM,GAAG,KAAK,YAAY,iBAAiB,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,6BAAqB,CAAC,KAA4C,CAAC,CAAA;gBAC/H,IAAI,YAAY,EAAE;oBAChB,KAAI,CAAC,SAAS,CAAC,GAAG,CAAC,GAAG,MAAM,CAAA;iBAC7B;gBACD,OAAO,EAAE,CAAC,UAAU,CAAC,MAAM,CAAC,CAAA;YAC9B,CAAC,CAAC,CAAA;SACH;QAED,IAAI,CAAC,aAAa,GAAG,IAAI,CAAC,SAAS,GAAG,CAAC,IAAI,YAAY,CAAA;QACvD,IAAI,CAAC,gBAAgB,GAAG,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,KAAK,EAAP,CAAO,CAAC,CAAA;IACxD,CAAC;IAED,sBAAW,4BAAM;aAAjB;YACE,OAAO,IAAI,CAAC,OAAO,CAAA;QACrB,CAAC;;;OAAA;IAED,sBAAW,8BAAQ;aAAnB;YACE,OAAO,IAAI,CAAC,SAAS,CAAA;QACvB,CAAC;;;OAAA;IAED,sBAAW,+BAAS;aAApB;YACE,OAAO,IAAI,CAAC,UAAU,CAAA;QACxB,CAAC;;;OAAA;IAED,sBAAW,kCAAY;aAAvB;YACE,OAAO,IAAI,CAAC,aAAa,CAAA;QAC3B,CAAC;;;OAAA;IAED,sBAAW,+BAAS;aAApB;YACE,OAAO,IAAI,CAAC,OAAO,CAAC,MAAM,CAAA;QAC5B,CAAC;;;OAAA;IAED,sBAAW,qCAAe;aAA1B;YACE,OAAO,IAAI,CAAC,gBAAgB,CAAA;QAC9B,CAAC;;;OAAA;IAED,sBAAW,8BAAQ;aAAnB;YACE,OAAO,IAAI,CAAC,SAAS,CAAA;QACvB,CAAC;;;OAAA;IAEM,qCAAkB,GAAzB,UAA0B,QAAgB;QACxC,OAAO,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAA;IACxC,CAAC;IAEM,iCAAc,GAArB,UAAsB,QAAgB;QACpC,OAAO,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAA;IAC3C,CAAC;IAEM,gCAAa,GAApB,UAAqB,QAAgB;QACnC,OAAO,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAA;IAC3C,CAAC;IAEM,8BAAW,GAAlB,UAAmB,QAAgB;QACjC,OAAO,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,CAAA;IACjC,CAAC;IAEM,gCAAa,GAApB,UAAqB,SAAiB,EAAE,cAA8B;QAAtE,iBA+BC;QA/BuC,+BAAA,EAAA,qBAA8B;QAEpE,OAAO,EAAE,CAAC,IAAI,CAAC;YAEb,IAAM,YAAY,GAAG,KAAI,CAAC,OAAO,CAAC,GAAG,CAAC,UAAC,WAAwB;gBACvD,IAAA,sBAAmD,EAAlD,sBAAc,EAAE,qBAAa,CAAqB;gBAEzD,IAAI,SAAS,GAAG,WAAW,CAAC,UAAU,EAAE,CAAC,OAAO,EAAiB,CAAA;gBACjE,SAAS,GAAG,yBAAW,CAAC,SAAS,EAAE,cAAc,CAAC,CAAA;gBAE5C,IAAA,6BAAkE,EAAjE,0BAAkB,EAAE,yBAAiB,CAA4B;gBAExE,IAAI,kBAAkB,KAAK,SAAS,IAAI,iBAAiB,KAAK,SAAS,EAAE;oBACvE,SAAS,GAAG,EAAE,CAAC,KAAK,CAAC,cAAc,CAAC,SAAS,EAAE,CAAC,SAAS,EAAE,SAAS,CAAC,CAAC,CAAA;iBACvE;gBAED,KAAI,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,aAAK,CAC3B,iBAAiB,GAAG,aAAa,EACjC,kBAAkB,GAAG,cAAc,CACpC,CAAC,CAAA;gBACF,OAAO,SAAS,CAAA;YAClB,CAAC,CAAC,CAAA;YAEF,IAAM,WAAW,GAAG,EAAE,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,IAAI,CAAC,KAAI,CAAC,SAAS,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,CAAC,CAAA;YAExF,IAAI,KAAI,CAAC,SAAS,EAAE;gBAClB,KAAI,CAAC,OAAO,EAAE,CAAA;aACf;YAED,OAAO,WAAW,CAAA;QACpB,CAAC,CAAC,CAAA;IACJ,CAAC;IAED;;;OAGG;IACI,0BAAO,GAAd;QACE,IAAI,CAAC,UAAU,GAAG,IAAI,CAAA;QACtB,OAAO,IAAI,CAAA;IACb,CAAC;IAEM,0BAAO,GAAd;QACE,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;IACxC,CAAC;IACH,eAAC;AAAD,CAAC,AAxID,IAwIC;AAxIY,4BAAQ"}
\ No newline at end of file

build/allFacesFactory.js.map

-{"version":3,"file":"allFacesFactory.js","sourceRoot":"","sources":["../src/allFacesFactory.ts"],"names":[],"mappings":";;;AAAA,2DAA0D;AAK1D,6DAA4D;AAG5D,yBACE,YAA8B,EAC9B,WAA4B,EAC5B,cAAkC;IAElC,OAAO,UACL,KAAgB,EAChB,aAAqB,EACrB,kBAAmC;QAAnC,mCAAA,EAAA,0BAAmC;;;;;4BAGhB,qBAAM,YAAY,CAAC,WAAW,CAAC,KAAK,EAAE,aAAa,CAAC,EAAA;;wBAAjE,UAAU,GAAG,SAAoD;wBAEnD,qBAAM,uCAAkB,CAAC,KAAK,EAAE,UAAU,CAAC,EAAA;;wBAAzD,WAAW,GAAG,SAA2C;6BAEnC,kBAAkB,EAAlB,wBAAkB;wBAC1C,qBAAM,WAAW,CAAC,eAAe,CAAC,WAAW,CAAC,EAAA;;wBAA9C,KAAA,SAAiE,CAAA;;4BACjE,qBAAM,OAAO,CAAC,GAAG,CAAC,WAAW,CAAC,GAAG,CACjC,UAAA,UAAU,IAAI,OAAA,WAAW,CAAC,eAAe,CAAC,UAAU,CAAC,EAAvC,CAAuC,CACtD,CAAC,EAAA;;wBAFA,KAAA,SAEmB,CAAA;;;wBAJjB,mBAAmB,KAIF;wBAEvB,WAAW,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;wBAE/B,gBAAgB,GAAG,mBAAmB,CAAC,GAAG,CAC9C,UAAC,SAAS,EAAE,CAAC,IAAK,OAAA,SAAS,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,EAAvC,CAAuC,CAC1D,CAAA;wBAC0B,qBAAM,uCAAkB,CAAC,KAAK,EAAE,gBAAgB,CAAC,EAAA;;wBAAtE,kBAAkB,GAAG,SAAiD;6BAExD,kBAAkB,EAAlB,wBAAkB;wBAClC,qBAAM,cAAc,CAAC,qBAAqB,CAAC,kBAAkB,CAAC,EAAA;;wBAA9D,KAAA,SAAgF,CAAA;;4BAChF,qBAAM,OAAO,CAAC,GAAG,CAAC,kBAAkB,CAAC,GAAG,CACxC,UAAA,UAAU,IAAI,OAAA,cAAc,CAAC,qBAAqB,CAAC,UAAU,CAAC,EAAhD,CAAgD,CAC/D,CAAC,EAAA;;wBAFA,KAAA,SAEkB,CAAA;;;wBAJhB,WAAW,KAIK;wBAEtB,kBAAkB,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;wBAE5C,sBAAO,UAAU,CAAC,GAAG,CAAC,UAAC,SAAS,EAAE,CAAC;gCACjC,OAAA,IAAI,yCAAmB,CACrB,SAAS,EACT,mBAAmB,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,SAAS,CAAC,MAAM,EAAE,CAAC,EACvD,WAAW,CAAC,CAAC,CAAC,CACf;4BAJD,CAIC,CACF,EAAA;;;;KAEF,CAAA;AACH,CAAC;AA7CD,0CA6CC"}
\ No newline at end of file
+{"version":3,"file":"allFacesFactory.js","sourceRoot":"","sources":["../src/allFacesFactory.ts"],"names":[],"mappings":";;;AAAA,2DAA0D;AAK1D,6DAA4D;AAG5D,yBACE,YAA8B,EAC9B,WAA4B,EAC5B,cAAkC;IAElC,OAAO,UACL,KAAgB,EAChB,aAAqB,EACrB,kBAAmC;QAAnC,mCAAA,EAAA,0BAAmC;;;;;4BAGhB,qBAAM,YAAY,CAAC,WAAW,CAAC,KAAK,EAAE,aAAa,CAAC,EAAA;;wBAAjE,UAAU,GAAG,SAAoD;wBAEnD,qBAAM,uCAAkB,CAAC,KAAK,EAAE,UAAU,CAAC,EAAA;;wBAAzD,WAAW,GAAG,SAA2C;6BAEnC,kBAAkB,EAAlB,wBAAkB;wBAC1C,qBAAM,WAAW,CAAC,eAAe,CAAC,WAAW,CAAC,EAAA;;wBAA9C,KAAA,SAAmE,CAAA;;4BACnE,qBAAM,OAAO,CAAC,GAAG,CAAC,WAAW,CAAC,GAAG,CACjC,UAAA,UAAU,IAAI,OAAA,WAAW,CAAC,eAAe,CAAC,UAAU,CAAC,EAAvC,CAAuC,CACtD,CAAC,EAAA;;wBAFA,KAAA,SAEqB,CAAA;;;wBAJnB,mBAAmB,KAIA;wBAEzB,WAAW,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;wBAE/B,gBAAgB,GAAG,mBAAmB,CAAC,GAAG,CAC9C,UAAC,SAAS,EAAE,CAAC,IAAK,OAAA,SAAS,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,EAAvC,CAAuC,CAC1D,CAAA;wBAC0B,qBAAM,uCAAkB,CAAC,KAAK,EAAE,gBAAgB,CAAC,EAAA;;wBAAtE,kBAAkB,GAAG,SAAiD;6BAExD,kBAAkB,EAAlB,wBAAkB;wBAClC,qBAAM,cAAc,CAAC,qBAAqB,CAAC,kBAAkB,CAAC,EAAA;;wBAA9D,KAAA,SAAgF,CAAA;;4BAChF,qBAAM,OAAO,CAAC,GAAG,CAAC,kBAAkB,CAAC,GAAG,CACxC,UAAA,UAAU,IAAI,OAAA,cAAc,CAAC,qBAAqB,CAAC,UAAU,CAAC,EAAhD,CAAgD,CAC/D,CAAC,EAAA;;wBAFA,KAAA,SAEkB,CAAA;;;wBAJhB,WAAW,KAIK;wBAEtB,kBAAkB,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;wBAE5C,sBAAO,UAAU,CAAC,GAAG,CAAC,UAAC,SAAS,EAAE,CAAC;gCACjC,OAAA,IAAI,yCAAmB,CACrB,SAAS,EACT,mBAAmB,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,SAAS,CAAC,MAAM,EAAE,CAAC,EACvD,WAAW,CAAC,CAAC,CAAC,CACf;4BAJD,CAIC,CACF,EAAA;;;;KAEF,CAAA;AACH,CAAC;AA7CD,0CA6CC"}
\ No newline at end of file

build/commons/extractConvParamsFactory.js

@@ -6,10 +6,7 @@ function extractConvParamsFactory(extractWeights, paramMappings) {
         var filters = tf.tensor4d(extractWeights(channelsIn * channelsOut * filterSize * filterSize), [filterSize, filterSize, channelsIn, channelsOut]);
         var bias = tf.tensor1d(extractWeights(channelsOut));
         paramMappings.push({ paramPath: mappedPrefix + "/filters" }, { paramPath: mappedPrefix + "/bias" });
-        return {
-            filters: filters,
-            bias: bias
-        };
+        return { filters: filters, bias: bias };
     };
 }
 exports.extractConvParamsFactory = extractConvParamsFactory;

build/commons/extractConvParamsFactory.js.map

-{"version":3,"file":"extractConvParamsFactory.js","sourceRoot":"","sources":["../../src/commons/extractConvParamsFactory.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAI5C,kCAAyC,cAAsC,EAAE,aAA6B;IAC5G,OAAO,UACL,UAAkB,EAClB,WAAmB,EACnB,UAAkB,EAClB,YAAoB;QAEpB,IAAM,OAAO,GAAG,EAAE,CAAC,QAAQ,CACzB,cAAc,CAAC,UAAU,GAAG,WAAW,GAAG,UAAU,GAAG,UAAU,CAAC,EAClE,CAAC,UAAU,EAAE,UAAU,EAAE,UAAU,EAAE,WAAW,CAAC,CAClD,CAAA;QACD,IAAM,IAAI,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,WAAW,CAAC,CAAC,CAAA;QAErD,aAAa,CAAC,IAAI,CAChB,EAAE,SAAS,EAAK,YAAY,aAAU,EAAE,EACxC,EAAE,SAAS,EAAK,YAAY,UAAO,EAAE,CACtC,CAAA;QAED,OAAO;YACL,OAAO,SAAA;YACP,IAAI,MAAA;SACL,CAAA;IACH,CAAC,CAAA;AACH,CAAC;AAvBD,4DAuBC"}
\ No newline at end of file
+{"version":3,"file":"extractConvParamsFactory.js","sourceRoot":"","sources":["../../src/commons/extractConvParamsFactory.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAI5C,kCACE,cAAsC,EACtC,aAA6B;IAG7B,OAAO,UACL,UAAkB,EAClB,WAAmB,EACnB,UAAkB,EAClB,YAAoB;QAGpB,IAAM,OAAO,GAAG,EAAE,CAAC,QAAQ,CACzB,cAAc,CAAC,UAAU,GAAG,WAAW,GAAG,UAAU,GAAG,UAAU,CAAC,EAClE,CAAC,UAAU,EAAE,UAAU,EAAE,UAAU,EAAE,WAAW,CAAC,CAClD,CAAA;QACD,IAAM,IAAI,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,WAAW,CAAC,CAAC,CAAA;QAErD,aAAa,CAAC,IAAI,CAChB,EAAE,SAAS,EAAK,YAAY,aAAU,EAAE,EACxC,EAAE,SAAS,EAAK,YAAY,UAAO,EAAE,CACtC,CAAA;QAED,OAAO,EAAE,OAAO,SAAA,EAAE,IAAI,MAAA,EAAE,CAAA;IAC1B,CAAC,CAAA;AAEH,CAAC;AA1BD,4DA0BC"}
\ No newline at end of file

build/commons/extractFCParamsFactory.d.ts

+import { ExtractWeightsFunction, FCParams, ParamMapping } from './types';
+export declare function extractFCParamsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]): (channelsIn: number, channelsOut: number, mappedPrefix: string) => FCParams;

build/commons/extractFCParamsFactory.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+function extractFCParamsFactory(extractWeights, paramMappings) {
+    return function (channelsIn, channelsOut, mappedPrefix) {
+        var fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);
+        var fc_bias = tf.tensor1d(extractWeights(channelsOut));
+        paramMappings.push({ paramPath: mappedPrefix + "/weights" }, { paramPath: mappedPrefix + "/bias" });
+        return {
+            weights: fc_weights,
+            bias: fc_bias
+        };
+    };
+}
+exports.extractFCParamsFactory = extractFCParamsFactory;
+//# sourceMappingURL=extractFCParamsFactory.js.map
\ No newline at end of file

build/commons/extractFCParamsFactory.js.map

+{"version":3,"file":"extractFCParamsFactory.js","sourceRoot":"","sources":["../../src/commons/extractFCParamsFactory.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAI5C,gCACE,cAAsC,EACtC,aAA6B;IAG7B,OAAO,UACL,UAAkB,EAClB,WAAmB,EACnB,YAAoB;QAGpB,IAAM,UAAU,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,UAAU,GAAG,WAAW,CAAC,EAAE,CAAC,UAAU,EAAE,WAAW,CAAC,CAAC,CAAA;QACnG,IAAM,OAAO,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,WAAW,CAAC,CAAC,CAAA;QAExD,aAAa,CAAC,IAAI,CAChB,EAAE,SAAS,EAAK,YAAY,aAAU,EAAE,EACxC,EAAE,SAAS,EAAK,YAAY,UAAO,EAAE,CACtC,CAAA;QAED,OAAO;YACL,OAAO,EAAE,UAAU;YACnB,IAAI,EAAE,OAAO;SACd,CAAA;IACH,CAAC,CAAA;AAEH,CAAC;AAzBD,wDAyBC"}
\ No newline at end of file

build/commons/types.d.ts

@@ -3,6 +3,10 @@ export declare type ConvParams = {
     filters: tf.Tensor4D;
     bias: tf.Tensor1D;
 };
+export declare type FCParams = {
+    weights: tf.Tensor2D;
+    bias: tf.Tensor1D;
+};
 export declare type ExtractWeightsFunction = (numWeights: number) => Float32Array;
 export declare type BatchReshapeInfo = {
     originalWidth: number;

build/drawing/index.d.ts

-import { FaceDetection } from '../faceDetectionNet/FaceDetection';
-import { FaceLandmarks } from '../faceLandmarkNet/FaceLandmarks';
+import { FaceDetection } from '../FaceDetection';
+import { FaceLandmarks } from '../FaceLandmarks';
 import { DrawBoxOptions, DrawLandmarksOptions, DrawOptions, DrawTextOptions } from './types';
 export declare function getDefaultDrawOptions(): DrawOptions;
 export declare function drawBox(ctx: CanvasRenderingContext2D, x: number, y: number, w: number, h: number, options: DrawBoxOptions): void;

build/drawing/index.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
+var faceLandmarkNet_1 = require("../faceLandmarkNet");
 var utils_1 = require("../utils");
 function getDefaultDrawOptions() {
     return {
@@ -76,7 +77,7 @@ function drawLandmarks(canvasArg, faceLandmarks, options) {
     var lineWidth = drawOptions.lineWidth, color = drawOptions.color;
     var faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks];
     faceLandmarksArray.forEach(function (landmarks) {
-        if (drawLines) {
+        if (drawLines && landmarks instanceof faceLandmarkNet_1.FaceLandmarks68) {
             ctx.strokeStyle = color;
             ctx.lineWidth = lineWidth;
             drawContour(ctx, landmarks.getJawOutline());

build/drawing/index.js.map

-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/drawing/index.ts"],"names":[],"mappings":";;AAGA,kCAAoE;AAGpE;IACE,OAAO;QACL,KAAK,EAAE,MAAM;QACb,SAAS,EAAE,CAAC;QACZ,QAAQ,EAAE,EAAE;QACZ,SAAS,EAAE,SAAS;KACrB,CAAA;AACH,CAAC;AAPD,sDAOC;AAED,iBACE,GAA6B,EAC7B,CAAS,EACT,CAAS,EACT,CAAS,EACT,CAAS,EACT,OAAuB;IAEvB,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;IAED,GAAG,CAAC,WAAW,GAAG,WAAW,CAAC,KAAK,CAAA;IACnC,GAAG,CAAC,SAAS,GAAG,WAAW,CAAC,SAAS,CAAA;IACrC,GAAG,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAA;AAC5B,CAAC;AAhBD,0BAgBC;AAED,kBACE,GAA6B,EAC7B,CAAS,EACT,CAAS,EACT,IAAY,EACZ,OAAwB;IAExB,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;IAED,IAAM,OAAO,GAAG,CAAC,GAAG,WAAW,CAAC,SAAS,CAAA;IAEzC,GAAG,CAAC,SAAS,GAAG,WAAW,CAAC,KAAK,CAAA;IACjC,GAAG,CAAC,IAAI,GAAM,WAAW,CAAC,QAAQ,WAAM,WAAW,CAAC,SAAW,CAAA;IAC/D,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,GAAG,OAAO,EAAE,CAAC,GAAG,OAAO,GAAG,CAAC,WAAW,CAAC,QAAQ,GAAG,GAAG,CAAC,CAAC,CAAA;AAC7E,CAAC;AAjBD,4BAiBC;AAED,uBACE,SAAqC,EACrC,SAA0C,EAC1C,OAAmE;IAEnE,IAAM,MAAM,GAAG,oBAAY,CAAC,SAAS,CAAC,CAAA;IACtC,IAAI,CAAC,CAAC,MAAM,YAAY,iBAAiB,CAAC,EAAE;QAC1C,MAAM,IAAI,KAAK,CAAC,4DAA4D,CAAC,CAAA;KAC9E;IAED,IAAM,cAAc,GAAG,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC;QAC7C,CAAC,CAAC,SAAS;QACX,CAAC,CAAC,CAAC,SAAS,CAAC,CAAA;IAEf,cAAc,CAAC,OAAO,CAAC,UAAC,GAAG;QACnB,IAAA,iBAKU,EAJd,QAAC,EACD,QAAC,EACD,gBAAK,EACL,kBAAM,CACQ;QAEhB,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;QAEO,IAAA,yEAAS,CAAwD;QAEzE,IAAM,GAAG,GAAG,2BAAmB,CAAC,MAAM,CAAC,CAAA;QACvC,OAAO,CACL,GAAG,EACH,CAAC,EACD,CAAC,EACD,KAAK,EACL,MAAM,EACN,WAAW,CACZ,CAAA;QACD,IAAI,SAAS,EAAE;YACb,QAAQ,CACN,GAAG,EACH,CAAC,EACD,CAAC,EACD,KAAG,aAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,CAAG,EAC1B,WAAW,CACZ,CAAA;SACF;IACH,CAAC,CAAC,CAAA;AACJ,CAAC;AAhDD,sCAgDC;AAED,qBACE,GAA6B,EAC7B,MAAe,EACf,QAAyB;IAAzB,yBAAA,EAAA,gBAAyB;IAEzB,GAAG,CAAC,SAAS,EAAE,CAAA;IAEf,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,UAAC,EAAQ,EAAE,OAAO;YAAf,QAAC,EAAE,QAAC;QAC7B,IAAM,IAAI,GAAG,MAAM,CAAC,OAAO,CAAC,CAAA;QAC5B,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAA;QAC1B,GAAG,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA;IAClB,CAAC,CAAC,CAAA;IAEF,IAAI,QAAQ,EAAE;QACZ,IAAM,IAAI,GAAG,MAAM,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;QACtC,IAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;QACpB,IAAI,CAAC,IAAI,IAAI,CAAC,EAAE,EAAE;YAChB,OAAM;SACP;QAED,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAA;QAC1B,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAA;KACvB;IAED,GAAG,CAAC,MAAM,EAAE,CAAA;AACd,CAAC;AAED,uBACE,SAAqC,EACrC,aAA8C,EAC9C,OAAuD;IAEvD,IAAM,MAAM,GAAG,oBAAY,CAAC,SAAS,CAAC,CAAA;IACtC,IAAI,CAAC,CAAC,MAAM,YAAY,iBAAiB,CAAC,EAAE;QAC1C,MAAM,IAAI,KAAK,CAAC,kEAAkE,CAAC,CAAA;KACpF;IAED,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;IAEO,IAAA,0EAAS,CAAyD;IAE1E,IAAM,GAAG,GAAG,2BAAmB,CAAC,MAAM,CAAC,CAAA;IAC/B,IAAA,iCAAS,EAAE,yBAAK,CAAgB;IAExC,IAAM,kBAAkB,GAAG,KAAK,CAAC,OAAO,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAA;IAEzF,kBAAkB,CAAC,OAAO,CAAC,UAAA,SAAS;QAClC,IAAI,SAAS,EAAE;YACb,GAAG,CAAC,WAAW,GAAG,KAAK,CAAA;YACvB,GAAG,CAAC,SAAS,GAAG,SAAS,CAAA;YACzB,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,aAAa,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,cAAc,EAAE,CAAC,CAAA;YAC5C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,eAAe,EAAE,CAAC,CAAA;YAC7C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,OAAO,EAAE,CAAC,CAAA;YACrC,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,UAAU,EAAE,EAAE,IAAI,CAAC,CAAA;YAC9C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,WAAW,EAAE,EAAE,IAAI,CAAC,CAAA;YAC/C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,QAAQ,EAAE,EAAE,IAAI,CAAC,CAAA;YAC5C,OAAM;SACP;QAED,mBAAmB;QACnB,IAAM,QAAQ,GAAG,SAAS,GAAG,CAAC,CAAA;QAC9B,GAAG,CAAC,SAAS,GAAG,KAAK,CAAA;QACrB,SAAS,CAAC,YAAY,EAAE,CAAC,OAAO,CAAC,UAAA,EAAE,IAAI,OAAA,GAAG,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,GAAG,QAAQ,EAAE,EAAE,CAAC,CAAC,GAAG,QAAQ,EAAE,SAAS,EAAE,SAAS,CAAC,EAApE,CAAoE,CAAC,CAAA;IAC9G,CAAC,CAAC,CAAA;AACJ,CAAC;AAzCD,sCAyCC"}
\ No newline at end of file
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/drawing/index.ts"],"names":[],"mappings":";;AACA,sDAAqD;AAGrD,kCAAoE;AAGpE;IACE,OAAO;QACL,KAAK,EAAE,MAAM;QACb,SAAS,EAAE,CAAC;QACZ,QAAQ,EAAE,EAAE;QACZ,SAAS,EAAE,SAAS;KACrB,CAAA;AACH,CAAC;AAPD,sDAOC;AAED,iBACE,GAA6B,EAC7B,CAAS,EACT,CAAS,EACT,CAAS,EACT,CAAS,EACT,OAAuB;IAEvB,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;IAED,GAAG,CAAC,WAAW,GAAG,WAAW,CAAC,KAAK,CAAA;IACnC,GAAG,CAAC,SAAS,GAAG,WAAW,CAAC,SAAS,CAAA;IACrC,GAAG,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAA;AAC5B,CAAC;AAhBD,0BAgBC;AAED,kBACE,GAA6B,EAC7B,CAAS,EACT,CAAS,EACT,IAAY,EACZ,OAAwB;IAExB,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;IAED,IAAM,OAAO,GAAG,CAAC,GAAG,WAAW,CAAC,SAAS,CAAA;IAEzC,GAAG,CAAC,SAAS,GAAG,WAAW,CAAC,KAAK,CAAA;IACjC,GAAG,CAAC,IAAI,GAAM,WAAW,CAAC,QAAQ,WAAM,WAAW,CAAC,SAAW,CAAA;IAC/D,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,GAAG,OAAO,EAAE,CAAC,GAAG,OAAO,GAAG,CAAC,WAAW,CAAC,QAAQ,GAAG,GAAG,CAAC,CAAC,CAAA;AAC7E,CAAC;AAjBD,4BAiBC;AAED,uBACE,SAAqC,EACrC,SAA0C,EAC1C,OAAmE;IAEnE,IAAM,MAAM,GAAG,oBAAY,CAAC,SAAS,CAAC,CAAA;IACtC,IAAI,CAAC,CAAC,MAAM,YAAY,iBAAiB,CAAC,EAAE;QAC1C,MAAM,IAAI,KAAK,CAAC,4DAA4D,CAAC,CAAA;KAC9E;IAED,IAAM,cAAc,GAAG,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC;QAC7C,CAAC,CAAC,SAAS;QACX,CAAC,CAAC,CAAC,SAAS,CAAC,CAAA;IAEf,cAAc,CAAC,OAAO,CAAC,UAAC,GAAG;QACnB,IAAA,iBAKU,EAJd,QAAC,EACD,QAAC,EACD,gBAAK,EACL,kBAAM,CACQ;QAEhB,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;QAEO,IAAA,yEAAS,CAAwD;QAEzE,IAAM,GAAG,GAAG,2BAAmB,CAAC,MAAM,CAAC,CAAA;QACvC,OAAO,CACL,GAAG,EACH,CAAC,EACD,CAAC,EACD,KAAK,EACL,MAAM,EACN,WAAW,CACZ,CAAA;QACD,IAAI,SAAS,EAAE;YACb,QAAQ,CACN,GAAG,EACH,CAAC,EACD,CAAC,EACD,KAAG,aAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,CAAG,EAC1B,WAAW,CACZ,CAAA;SACF;IACH,CAAC,CAAC,CAAA;AACJ,CAAC;AAhDD,sCAgDC;AAED,qBACE,GAA6B,EAC7B,MAAe,EACf,QAAyB;IAAzB,yBAAA,EAAA,gBAAyB;IAEzB,GAAG,CAAC,SAAS,EAAE,CAAA;IAEf,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,UAAC,EAAQ,EAAE,OAAO;YAAf,QAAC,EAAE,QAAC;QAC7B,IAAM,IAAI,GAAG,MAAM,CAAC,OAAO,CAAC,CAAA;QAC5B,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAA;QAC1B,GAAG,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA;IAClB,CAAC,CAAC,CAAA;IAEF,IAAI,QAAQ,EAAE;QACZ,IAAM,IAAI,GAAG,MAAM,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;QACtC,IAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;QACpB,IAAI,CAAC,IAAI,IAAI,CAAC,EAAE,EAAE;YAChB,OAAM;SACP;QAED,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAA;QAC1B,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAA;KACvB;IAED,GAAG,CAAC,MAAM,EAAE,CAAA;AACd,CAAC;AAED,uBACE,SAAqC,EACrC,aAA8C,EAC9C,OAAuD;IAEvD,IAAM,MAAM,GAAG,oBAAY,CAAC,SAAS,CAAC,CAAA;IACtC,IAAI,CAAC,CAAC,MAAM,YAAY,iBAAiB,CAAC,EAAE;QAC1C,MAAM,IAAI,KAAK,CAAC,kEAAkE,CAAC,CAAA;KACpF;IAED,IAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAC/B,qBAAqB,EAAE,EACvB,CAAC,OAAO,IAAI,EAAE,CAAC,CAChB,CAAA;IAEO,IAAA,0EAAS,CAAyD;IAE1E,IAAM,GAAG,GAAG,2BAAmB,CAAC,MAAM,CAAC,CAAA;IAC/B,IAAA,iCAAS,EAAE,yBAAK,CAAgB;IAExC,IAAM,kBAAkB,GAAG,KAAK,CAAC,OAAO,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAA;IAEzF,kBAAkB,CAAC,OAAO,CAAC,UAAA,SAAS;QAClC,IAAI,SAAS,IAAI,SAAS,YAAY,iCAAe,EAAE;YACrD,GAAG,CAAC,WAAW,GAAG,KAAK,CAAA;YACvB,GAAG,CAAC,SAAS,GAAG,SAAS,CAAA;YACzB,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,aAAa,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,cAAc,EAAE,CAAC,CAAA;YAC5C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,eAAe,EAAE,CAAC,CAAA;YAC7C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,OAAO,EAAE,CAAC,CAAA;YACrC,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,UAAU,EAAE,EAAE,IAAI,CAAC,CAAA;YAC9C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,WAAW,EAAE,EAAE,IAAI,CAAC,CAAA;YAC/C,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC,QAAQ,EAAE,EAAE,IAAI,CAAC,CAAA;YAC5C,OAAM;SACP;QAED,mBAAmB;QACnB,IAAM,QAAQ,GAAG,SAAS,GAAG,CAAC,CAAA;QAC9B,GAAG,CAAC,SAAS,GAAG,KAAK,CAAA;QACrB,SAAS,CAAC,YAAY,EAAE,CAAC,OAAO,CAAC,UAAA,EAAE,IAAI,OAAA,GAAG,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,GAAG,QAAQ,EAAE,EAAE,CAAC,CAAC,GAAG,QAAQ,EAAE,SAAS,EAAE,SAAS,CAAC,EAApE,CAAoE,CAAC,CAAA;IAC9G,CAAC,CAAC,CAAA;AACJ,CAAC;AAzCD,sCAyCC"}
\ No newline at end of file

build/extractFaceTensors.d.ts

 import * as tf from '@tensorflow/tfjs-core';
-import { FaceDetection } from './faceDetectionNet/FaceDetection';
+import { FaceDetection } from './FaceDetection';
 import { Rect } from './Rect';
 import { TNetInput } from './types';
 /**

build/extractFaceTensors.js

@@ -2,7 +2,7 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
 var tf = require("@tensorflow/tfjs-core");
-var FaceDetection_1 = require("./faceDetectionNet/FaceDetection");
+var FaceDetection_1 = require("./FaceDetection");
 var toNetInput_1 = require("./toNetInput");
 /**
  * Extracts the tensors of the image regions containing the detected faces.

build/extractFaceTensors.js.map

-{"version":3,"file":"extractFaceTensors.js","sourceRoot":"","sources":["../src/extractFaceTensors.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,kEAAiE;AAEjE,2CAA0C;AAG1C;;;;;;;;;GASG;AACH,4BACE,KAAgB,EAChB,UAAuC;;;;;wBAGtB,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;oBAAxC,QAAQ,GAAG,SAA6B;oBAE9C,IAAI,QAAQ,CAAC,SAAS,GAAG,CAAC,EAAE;wBAC1B,IAAI,QAAQ,CAAC,SAAS,EAAE;4BACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;yBACnB;wBACD,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAA;qBACpE;oBAED,sBAAO,EAAE,CAAC,IAAI,CAAC;4BACb,IAAM,SAAS,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,UAAU,EAAE,CAAC,OAAO,EAAiB,CAAA;4BAEpE,IAAA,6BAA6D,EAA5D,iBAAS,EAAE,gBAAQ,EAAE,mBAAW,CAA4B;4BAEnE,IAAM,KAAK,GAAG,UAAU,CAAC,GAAG,CAC1B,UAAA,GAAG,IAAI,OAAA,GAAG,YAAY,6BAAa;gCACjC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE;gCACnD,CAAC,CAAC,GAAG,EAFA,CAEA,CACR,CAAA;4BACD,IAAM,WAAW,GAAG,KAAK,CAAC,GAAG,CAAC,UAAC,EAAuB;oCAArB,QAAC,EAAE,QAAC,EAAE,gBAAK,EAAE,kBAAM;gCAClD,OAAA,EAAE,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,WAAW,CAAC,CAAC;4BAAlE,CAAkE,CACnE,CAAA;4BAED,IAAI,QAAQ,CAAC,SAAS,EAAE;gCACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;6BACnB;4BACD,OAAO,WAAW,CAAA;wBACpB,CAAC,CAAC,EAAA;;;;CACH;AAjCD,gDAiCC"}
\ No newline at end of file
+{"version":3,"file":"extractFaceTensors.js","sourceRoot":"","sources":["../src/extractFaceTensors.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,iDAAgD;AAEhD,2CAA0C;AAG1C;;;;;;;;;GASG;AACH,4BACE,KAAgB,EAChB,UAAuC;;;;;wBAGtB,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;oBAAxC,QAAQ,GAAG,SAA6B;oBAE9C,IAAI,QAAQ,CAAC,SAAS,GAAG,CAAC,EAAE;wBAC1B,IAAI,QAAQ,CAAC,SAAS,EAAE;4BACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;yBACnB;wBACD,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAA;qBACpE;oBAED,sBAAO,EAAE,CAAC,IAAI,CAAC;4BACb,IAAM,SAAS,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,UAAU,EAAE,CAAC,OAAO,EAAiB,CAAA;4BAEpE,IAAA,6BAA6D,EAA5D,iBAAS,EAAE,gBAAQ,EAAE,mBAAW,CAA4B;4BAEnE,IAAM,KAAK,GAAG,UAAU,CAAC,GAAG,CAC1B,UAAA,GAAG,IAAI,OAAA,GAAG,YAAY,6BAAa;gCACjC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,QAAQ,EAAE,SAAS,CAAC,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE;gCACnD,CAAC,CAAC,GAAG,EAFA,CAEA,CACR,CAAA;4BACD,IAAM,WAAW,GAAG,KAAK,CAAC,GAAG,CAAC,UAAC,EAAuB;oCAArB,QAAC,EAAE,QAAC,EAAE,gBAAK,EAAE,kBAAM;gCAClD,OAAA,EAAE,CAAC,KAAK,CAAC,SAAS,EAAE,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,WAAW,CAAC,CAAC;4BAAlE,CAAkE,CACnE,CAAA;4BAED,IAAI,QAAQ,CAAC,SAAS,EAAE;gCACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;6BACnB;4BACD,OAAO,WAAW,CAAA;wBACpB,CAAC,CAAC,EAAA;;;;CACH;AAjCD,gDAiCC"}
\ No newline at end of file

build/extractFaces.d.ts

-import { FaceDetection } from './faceDetectionNet/FaceDetection';
+import { FaceDetection } from './FaceDetection';
 import { Rect } from './Rect';
 import { TNetInput } from './types';
 /**

build/extractFaces.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
-var FaceDetection_1 = require("./faceDetectionNet/FaceDetection");
+var FaceDetection_1 = require("./FaceDetection");
 var toNetInput_1 = require("./toNetInput");
 var utils_1 = require("./utils");
 /**

build/extractFaces.js.map

-{"version":3,"file":"extractFaces.js","sourceRoot":"","sources":["../src/extractFaces.ts"],"names":[],"mappings":";;;AAAA,kEAAiE;AAEjE,2CAA0C;AAE1C,iCAAiF;AAGjF;;;;;;GAMG;AACH,sBACE,KAAgB,EAChB,UAAuC;;;;;;oBAGnC,MAAM,GAAG,KAA0B,CAAA;yBAEnC,CAAC,CAAC,KAAK,YAAY,iBAAiB,CAAC,EAArC,wBAAqC;oBACtB,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;oBAAxC,QAAQ,GAAG,SAA6B;oBAE9C,IAAI,QAAQ,CAAC,SAAS,GAAG,CAAC,EAAE;wBAC1B,IAAI,QAAQ,CAAC,SAAS,EAAE;4BACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;yBACnB;wBACD,MAAM,IAAI,KAAK,CAAC,4CAA4C,CAAC,CAAA;qBAC9D;oBAEQ,qBAAM,2BAAmB,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAA;;oBAAtD,MAAM,GAAG,SAA6C,CAAA;oBAEtD,IAAI,QAAQ,CAAC,SAAS,EAAE;wBACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;qBACnB;;;oBAGG,GAAG,GAAG,2BAAmB,CAAC,MAAM,CAAC,CAAA;oBAEjC,KAAK,GAAG,UAAU,CAAC,GAAG,CAC1B,UAAA,GAAG,IAAI,OAAA,GAAG,YAAY,6BAAa;wBACjC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE;wBAC3D,CAAC,CAAC,GAAG,EAFA,CAEA,CACR,CAAA;oBACD,sBAAO,KAAK,CAAC,GAAG,CAAC,UAAC,EAAuB;gCAArB,QAAC,EAAE,QAAC,EAAE,gBAAK,EAAE,kBAAM;4BACrC,IAAM,OAAO,GAAG,oBAAY,CAAC,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAE,CAAC,CAAA;4BAC/C,2BAAmB,CAAC,OAAO,CAAC;iCACzB,YAAY,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC,EAAE,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAA;4BAC5D,OAAO,OAAO,CAAA;wBAChB,CAAC,CAAC,EAAA;;;;CACH;AArCD,oCAqCC"}
\ No newline at end of file
+{"version":3,"file":"extractFaces.js","sourceRoot":"","sources":["../src/extractFaces.ts"],"names":[],"mappings":";;;AAAA,iDAAgD;AAEhD,2CAA0C;AAE1C,iCAAiF;AAEjF;;;;;;GAMG;AACH,sBACE,KAAgB,EAChB,UAAuC;;;;;;oBAGnC,MAAM,GAAG,KAA0B,CAAA;yBAEnC,CAAC,CAAC,KAAK,YAAY,iBAAiB,CAAC,EAArC,wBAAqC;oBACtB,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;oBAAxC,QAAQ,GAAG,SAA6B;oBAE9C,IAAI,QAAQ,CAAC,SAAS,GAAG,CAAC,EAAE;wBAC1B,IAAI,QAAQ,CAAC,SAAS,EAAE;4BACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;yBACnB;wBACD,MAAM,IAAI,KAAK,CAAC,4CAA4C,CAAC,CAAA;qBAC9D;oBAEQ,qBAAM,2BAAmB,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAA;;oBAAtD,MAAM,GAAG,SAA6C,CAAA;oBAEtD,IAAI,QAAQ,CAAC,SAAS,EAAE;wBACtB,QAAQ,CAAC,OAAO,EAAE,CAAA;qBACnB;;;oBAGG,GAAG,GAAG,2BAAmB,CAAC,MAAM,CAAC,CAAA;oBAEjC,KAAK,GAAG,UAAU,CAAC,GAAG,CAC1B,UAAA,GAAG,IAAI,OAAA,GAAG,YAAY,6BAAa;wBACjC,CAAC,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE;wBAC3D,CAAC,CAAC,GAAG,EAFA,CAEA,CACR,CAAA;oBACD,sBAAO,KAAK,CAAC,GAAG,CAAC,UAAC,EAAuB;gCAArB,QAAC,EAAE,QAAC,EAAE,gBAAK,EAAE,kBAAM;4BACrC,IAAM,OAAO,GAAG,oBAAY,CAAC,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAE,CAAC,CAAA;4BAC/C,2BAAmB,CAAC,OAAO,CAAC;iCACzB,YAAY,CAAC,GAAG,CAAC,YAAY,CAAC,CAAC,EAAE,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAA;4BAC5D,OAAO,OAAO,CAAA;wBAChB,CAAC,CAAC,EAAA;;;;CACH;AArCD,oCAqCC"}
\ No newline at end of file

build/faceDetectionNet/FaceDetectionNet.d.ts

 import * as tf from '@tensorflow/tfjs-core';
 import { NeuralNetwork } from '../commons/NeuralNetwork';
+import { FaceDetection } from '../FaceDetection';
 import { NetInput } from '../NetInput';
 import { TNetInput } from '../types';
-import { FaceDetection } from './FaceDetection';
 import { NetParams } from './types';
 export declare class FaceDetectionNet extends NeuralNetwork<NetParams> {
     constructor();

build/faceDetectionNet/FaceDetectionNet.js

@@ -3,10 +3,10 @@ Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
 var tf = require("@tensorflow/tfjs-core");
 var NeuralNetwork_1 = require("../commons/NeuralNetwork");
+var FaceDetection_1 = require("../FaceDetection");
 var Rect_1 = require("../Rect");
 var toNetInput_1 = require("../toNetInput");
 var extractParams_1 = require("./extractParams");
-var FaceDetection_1 = require("./FaceDetection");
 var loadQuantizedParams_1 = require("./loadQuantizedParams");
 var mobileNetV1_1 = require("./mobileNetV1");
 var nonMaxSuppression_1 = require("./nonMaxSuppression");

build/faceDetectionNet/FaceDetectionNet.js.map

-{"version":3,"file":"FaceDetectionNet.js","sourceRoot":"","sources":["../../src/faceDetectionNet/FaceDetectionNet.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,0DAAyD;AAEzD,gCAA+B;AAC/B,4CAA2C;AAE3C,iDAAgD;AAChD,iDAAgD;AAChD,6DAA4D;AAC5D,6CAA4C;AAC5C,yDAAwD;AACxD,6CAA4C;AAC5C,qDAAoD;AAGpD;IAAsC,4CAAwB;IAE5D;eACE,kBAAM,kBAAkB,CAAC;IAC3B,CAAC;IAEM,uCAAY,GAAnB,UAAoB,KAAe;QAEzB,IAAA,oBAAM,CAAS;QAEvB,IAAI,CAAC,MAAM,EAAE;YACX,MAAM,IAAI,KAAK,CAAC,gDAAgD,CAAC,CAAA;SAClE;QAED,OAAO,EAAE,CAAC,IAAI,CAAC;YACb,IAAM,WAAW,GAAG,KAAK,CAAC,aAAa,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;YAEnD,IAAM,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,WAAW,EAAE,EAAE,CAAC,MAAM,CAAC,oBAAoB,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,CAAgB,CAAA;YACnG,IAAM,QAAQ,GAAG,yBAAW,CAAC,CAAC,EAAE,MAAM,CAAC,WAAW,CAAC,CAAA;YAE7C,IAAA,8FAGqE,EAFzE,kCAAc,EACd,sCAAgB,CACyD;YAE3E,OAAO,yBAAW,CAAC,cAAc,EAAE,gBAAgB,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAC3E,CAAC,CAAC,CAAA;IACJ,CAAC;IAEY,kCAAO,GAApB,UAAqB,KAAgB;;;;;;wBAC5B,KAAA,IAAI,CAAC,YAAY,CAAA;wBAAC,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;4BAAtD,sBAAO,SAAA,IAAI,GAAc,SAA6B,EAAC,EAAA;;;;KACxD;IAEY,sCAAW,GAAxB,UACE,KAAgB,EAChB,aAA2B,EAC3B,UAAwB;QADxB,8BAAA,EAAA,mBAA2B;QAC3B,2BAAA,EAAA,gBAAwB;;;;;4BAGP,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;wBAAxC,QAAQ,GAAG,SAA6B;wBAExC,KAGF,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,EAFtB,MAAM,WAAA,EACL,OAAO,YAAA,CACc;wBAIzB,KAAK,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;wBACjB,MAAM,GAAG,OAAO,CAAC,CAAC,CAAC,CAAA;wBACzB,KAAS,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;4BACtC,MAAM,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAA;4BACnB,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAA;yBACrB;wBAGkB,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;wBAAC,qBAAM,MAAM,CAAC,IAAI,EAAE,EAAA;;wBAA3C,UAAU,GAAG,cAAW,SAAmB,EAAC;wBAE5C,YAAY,GAAG,GAAG,CAAA;wBAClB,OAAO,GAAG,qCAAiB,CAC/B,KAAK,EACL,UAAU,EACV,UAAU,EACV,YAAY,EACZ,aAAa,CACd,CAAA;wBAEK,oBAAoB,GAAG,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,cAAc,CAAC,CAAC,CAAC,CAAA;wBAC5G,mBAAmB,GAAG,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,CAAA;wBAEzG,OAAO,GAAG,OAAO;6BACpB,GAAG,CAAC,UAAA,GAAG;4BACA,IAAA;;;wFAGkC,EAHjC,WAAG,EAAE,cAAM,CAGsB;4BAClC,IAAA;;;uFAGiC,EAHhC,YAAI,EAAE,aAAK,CAGqB;4BACvC,OAAO,IAAI,6BAAa,CACtB,UAAU,CAAC,GAAG,CAAC,EACf,IAAI,WAAI,CACN,IAAI,EACJ,GAAG,EACH,KAAK,GAAG,IAAI,EACZ,MAAM,GAAG,GAAG,CACb,EACD;gCACE,MAAM,EAAE,QAAQ,CAAC,cAAc,CAAC,CAAC,CAAC;gCAClC,KAAK,EAAE,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC;6BACjC,CACF,CAAA;wBACH,CAAC,CAAC,CAAA;wBAEJ,KAAK,CAAC,OAAO,EAAE,CAAA;wBACf,MAAM,CAAC,OAAO,EAAE,CAAA;wBAEhB,sBAAO,OAAO,EAAA;;;;KACf;IAES,8CAAmB,GAA7B,UAA8B,GAAuB;QACnD,OAAO,yCAAmB,CAAC,GAAG,CAAC,CAAA;IACjC,CAAC;IAES,wCAAa,GAAvB,UAAwB,OAAqB;QAC3C,OAAO,6BAAa,CAAC,OAAO,CAAC,CAAA;IAC/B,CAAC;IACH,uBAAC;AAAD,CAAC,AA5GD,CAAsC,6BAAa,GA4GlD;AA5GY,4CAAgB"}
\ No newline at end of file
+{"version":3,"file":"FaceDetectionNet.js","sourceRoot":"","sources":["../../src/faceDetectionNet/FaceDetectionNet.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,0DAAyD;AACzD,kDAAiD;AAEjD,gCAA+B;AAC/B,4CAA2C;AAE3C,iDAAgD;AAChD,6DAA4D;AAC5D,6CAA4C;AAC5C,yDAAwD;AACxD,6CAA4C;AAC5C,qDAAoD;AAGpD;IAAsC,4CAAwB;IAE5D;eACE,kBAAM,kBAAkB,CAAC;IAC3B,CAAC;IAEM,uCAAY,GAAnB,UAAoB,KAAe;QAEzB,IAAA,oBAAM,CAAS;QAEvB,IAAI,CAAC,MAAM,EAAE;YACX,MAAM,IAAI,KAAK,CAAC,gDAAgD,CAAC,CAAA;SAClE;QAED,OAAO,EAAE,CAAC,IAAI,CAAC;YACb,IAAM,WAAW,GAAG,KAAK,CAAC,aAAa,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;YAEnD,IAAM,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,WAAW,EAAE,EAAE,CAAC,MAAM,CAAC,oBAAoB,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,CAAgB,CAAA;YACnG,IAAM,QAAQ,GAAG,yBAAW,CAAC,CAAC,EAAE,MAAM,CAAC,WAAW,CAAC,CAAA;YAE7C,IAAA,8FAGqE,EAFzE,kCAAc,EACd,sCAAgB,CACyD;YAE3E,OAAO,yBAAW,CAAC,cAAc,EAAE,gBAAgB,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAC3E,CAAC,CAAC,CAAA;IACJ,CAAC;IAEY,kCAAO,GAApB,UAAqB,KAAgB;;;;;;wBAC5B,KAAA,IAAI,CAAC,YAAY,CAAA;wBAAC,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;4BAAtD,sBAAO,SAAA,IAAI,GAAc,SAA6B,EAAC,EAAA;;;;KACxD;IAEY,sCAAW,GAAxB,UACE,KAAgB,EAChB,aAA2B,EAC3B,UAAwB;QADxB,8BAAA,EAAA,mBAA2B;QAC3B,2BAAA,EAAA,gBAAwB;;;;;4BAGP,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;wBAAxC,QAAQ,GAAG,SAA6B;wBAExC,KAGF,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,EAFtB,MAAM,WAAA,EACL,OAAO,YAAA,CACc;wBAIzB,KAAK,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;wBACjB,MAAM,GAAG,OAAO,CAAC,CAAC,CAAC,CAAA;wBACzB,KAAS,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;4BACtC,MAAM,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAA;4BACnB,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAA;yBACrB;wBAGkB,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;wBAAC,qBAAM,MAAM,CAAC,IAAI,EAAE,EAAA;;wBAA3C,UAAU,GAAG,cAAW,SAAmB,EAAC;wBAE5C,YAAY,GAAG,GAAG,CAAA;wBAClB,OAAO,GAAG,qCAAiB,CAC/B,KAAK,EACL,UAAU,EACV,UAAU,EACV,YAAY,EACZ,aAAa,CACd,CAAA;wBAEK,oBAAoB,GAAG,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,cAAc,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,cAAc,CAAC,CAAC,CAAC,CAAA;wBAC5G,mBAAmB,GAAG,CAAC,QAAQ,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,CAAA;wBAEzG,OAAO,GAAG,OAAO;6BACpB,GAAG,CAAC,UAAA,GAAG;4BACA,IAAA;;;wFAGkC,EAHjC,WAAG,EAAE,cAAM,CAGsB;4BAClC,IAAA;;;uFAGiC,EAHhC,YAAI,EAAE,aAAK,CAGqB;4BACvC,OAAO,IAAI,6BAAa,CACtB,UAAU,CAAC,GAAG,CAAC,EACf,IAAI,WAAI,CACN,IAAI,EACJ,GAAG,EACH,KAAK,GAAG,IAAI,EACZ,MAAM,GAAG,GAAG,CACb,EACD;gCACE,MAAM,EAAE,QAAQ,CAAC,cAAc,CAAC,CAAC,CAAC;gCAClC,KAAK,EAAE,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC;6BACjC,CACF,CAAA;wBACH,CAAC,CAAC,CAAA;wBAEJ,KAAK,CAAC,OAAO,EAAE,CAAA;wBACf,MAAM,CAAC,OAAO,EAAE,CAAA;wBAEhB,sBAAO,OAAO,EAAA;;;;KACf;IAES,8CAAmB,GAA7B,UAA8B,GAAuB;QACnD,OAAO,yCAAmB,CAAC,GAAG,CAAC,CAAA;IACjC,CAAC;IAES,wCAAa,GAAvB,UAAwB,OAAqB;QAC3C,OAAO,6BAAa,CAAC,OAAO,CAAC,CAAA;IAC/B,CAAC;IACH,uBAAC;AAAD,CAAC,AA5GD,CAAsC,6BAAa,GA4GlD;AA5GY,4CAAgB"}
\ No newline at end of file

build/faceDetectionNet/index.d.ts

 import { FaceDetectionNet } from './FaceDetectionNet';
 export * from './FaceDetectionNet';
-export * from './FaceDetection';
+export declare function createFaceDetectionNet(weights: Float32Array): FaceDetectionNet;
 export declare function faceDetectionNet(weights: Float32Array): FaceDetectionNet;

build/faceDetectionNet/index.js

@@ -3,11 +3,15 @@ Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
 var FaceDetectionNet_1 = require("./FaceDetectionNet");
 tslib_1.__exportStar(require("./FaceDetectionNet"), exports);
-tslib_1.__exportStar(require("./FaceDetection"), exports);
-function faceDetectionNet(weights) {
+function createFaceDetectionNet(weights) {
     var net = new FaceDetectionNet_1.FaceDetectionNet();
     net.extractWeights(weights);
     return net;
 }
+exports.createFaceDetectionNet = createFaceDetectionNet;
+function faceDetectionNet(weights) {
+    console.warn('faceDetectionNet(weights: Float32Array) will be deprecated in future, use createFaceDetectionNet instead');
+    return createFaceDetectionNet(weights);
+}
 exports.faceDetectionNet = faceDetectionNet;
 //# sourceMappingURL=index.js.map
\ No newline at end of file

build/faceDetectionNet/index.js.map

-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/faceDetectionNet/index.ts"],"names":[],"mappings":";;;AAAA,uDAAsD;AAEtD,6DAAmC;AACnC,0DAAgC;AAEhC,0BAAiC,OAAqB;IACpD,IAAM,GAAG,GAAG,IAAI,mCAAgB,EAAE,CAAA;IAClC,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,4CAIC"}
\ No newline at end of file
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/faceDetectionNet/index.ts"],"names":[],"mappings":";;;AAAA,uDAAsD;AAEtD,6DAAmC;AAEnC,gCAAuC,OAAqB;IAC1D,IAAM,GAAG,GAAG,IAAI,mCAAgB,EAAE,CAAA;IAClC,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,wDAIC;AAED,0BAAiC,OAAqB;IACpD,OAAO,CAAC,IAAI,CAAC,0GAA0G,CAAC,CAAA;IACxH,OAAO,sBAAsB,CAAC,OAAO,CAAC,CAAA;AACxC,CAAC;AAHD,4CAGC"}
\ No newline at end of file

build/faceDetectionNet/loadQuantizedParams.js.map

-{"version":3,"file":"loadQuantizedParams.js","sourceRoot":"","sources":["../../src/faceDetectionNet/loadQuantizedParams.ts"],"names":[],"mappings":";;;AACA,oFAAmF;AACnF,kFAAiF;AACjF,gDAAyE;AACzE,0DAAyD;AAIzD,IAAM,kBAAkB,GAAG,sBAAsB,CAAA;AAEjD,2BAA2B,SAAc,EAAE,aAA6B;IAEtE,IAAM,kBAAkB,GAAG,qDAAyB,CAAC,SAAS,EAAE,aAAa,CAAC,CAAA;IAE9E,oCAAoC,MAAc,EAAE,GAAW,EAAE,YAAoB;QAEnF,IAAM,OAAO,GAAG,kBAAkB,CAAiB,MAAM,gBAAW,GAAG,uBAAoB,EAAE,CAAC,EAAK,YAAY,aAAU,CAAC,CAAA;QAC1H,IAAM,iBAAiB,GAAG,kBAAkB,CAAiB,MAAM,gBAAW,GAAG,qCAAkC,EAAE,CAAC,EAAK,YAAY,uBAAoB,CAAC,CAAA;QAE5J,OAAO,EAAE,OAAO,SAAA,EAAE,iBAAiB,mBAAA,EAAE,CAAA;IACvC,CAAC;IAED,+BAA+B,GAAW;QAExC,IAAM,YAAY,GAAG,sBAAoB,GAAK,CAAA;QAC9C,IAAM,mBAAmB,GAAG,wBAAsB,GAAG,eAAY,CAAA;QACjE,IAAM,yBAAyB,GAAM,YAAY,oBAAiB,CAAA;QAClE,IAAM,yBAAyB,GAAM,YAAY,oBAAiB,CAAA;QAElE,IAAM,OAAO,GAAG,kBAAkB,CAAiB,mBAAmB,uBAAoB,EAAE,CAAC,EAAK,yBAAyB,aAAU,CAAC,CAAA;QACtI,IAAM,gBAAgB,GAAG,kBAAkB,CAAiB,mBAAmB,qBAAkB,EAAE,CAAC,EAAK,yBAAyB,sBAAmB,CAAC,CAAA;QACtJ,IAAM,iBAAiB,GAAG,kBAAkB,CAAiB,mBAAmB,oBAAiB,EAAE,CAAC,EAAK,yBAAyB,uBAAoB,CAAC,CAAA;QACvJ,IAAM,eAAe,GAAG,kBAAkB,CAAiB,mBAAmB,2BAAwB,EAAE,CAAC,EAAK,yBAAyB,qBAAkB,CAAC,CAAA;QAC1J,IAAM,mBAAmB,GAAG,kBAAkB,CAAiB,mBAAmB,+BAA4B,EAAE,CAAC,EAAK,yBAAyB,yBAAsB,CAAC,CAAA;QAEtK,OAAO;YACL,cAAc,EAAE;gBACd,OAAO,SAAA;gBACP,gBAAgB,kBAAA;gBAChB,iBAAiB,mBAAA;gBACjB,eAAe,iBAAA;gBACf,mBAAmB,qBAAA;aACpB;YACD,cAAc,EAAE,0BAA0B,CAAC,aAAa,EAAE,GAAG,EAAE,yBAAyB,CAAC;SAC1F,CAAA;IACH,CAAC;IAED;QACE,OAAO;YACL,MAAM,EAAE,0BAA0B,CAAC,aAAa,EAAE,CAAC,EAAE,oBAAoB,CAAC;YAC1E,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;YAClC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;YAClC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;YAClC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;SACnC,CAAA;IACH,CAAC;IAED,2BAA2B,MAAc,EAAE,YAAoB;QAC7D,IAAM,OAAO,GAAG,kBAAkB,CAAiB,MAAM,aAAU,EAAE,CAAC,EAAK,YAAY,aAAU,CAAC,CAAA;QAClG,IAAM,IAAI,GAAG,kBAAkB,CAAiB,MAAM,YAAS,EAAE,CAAC,EAAK,YAAY,UAAO,CAAC,CAAA;QAE3F,OAAO,EAAE,OAAO,SAAA,EAAE,IAAI,MAAA,EAAE,CAAA;IAC1B,CAAC;IAED,mCAAmC,GAAW;QAE5C,IAAM,sBAAsB,GAAG,iBAAiB,CAC9C,6BAA2B,GAAG,0BAAuB,EACrD,oCAAkC,GAAG,4BAAyB,CAC/D,CAAA;QACD,IAAM,eAAe,GAAG,iBAAiB,CACvC,6BAA2B,GAAG,oBAAiB,EAC/C,oCAAkC,GAAG,qBAAkB,CACxD,CAAA;QAED,OAAO,EAAE,sBAAsB,wBAAA,EAAE,eAAe,iBAAA,EAAE,CAAA;IACpD,CAAC;IAED;QACE,OAAO;YACL,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;SAC9C,CAAA;IACH,CAAC;IAED,OAAO;QACL,wBAAwB,0BAAA;QACxB,4BAA4B,8BAAA;KAC7B,CAAA;AACH,CAAC;AAED,6BACE,GAAuB;;;;;wBAGL,qBAAM,6BAAa,CAAC,GAAG,EAAE,kBAAkB,CAAC,EAAA;;oBAAxD,SAAS,GAAG,SAA4C;oBACxD,aAAa,GAAmB,EAAE,CAAA;oBAElC,KAGF,iBAAiB,CAAC,SAAS,EAAE,aAAa,CAAC,EAF7C,wBAAwB,8BAAA,EACxB,4BAA4B,kCAAA,CACiB;oBAEzC,SAAS,GAAG,SAAS,CAAC,kBAAkB,CAAC,CAAA;oBAC/C,aAAa,CAAC,IAAI,CAAC,EAAE,YAAY,EAAE,kBAAkB,EAAE,SAAS,EAAE,wBAAwB,EAAE,CAAC,CAAA;oBAE7F,IAAI,CAAC,qBAAU,CAAC,SAAS,CAAC,EAAE;wBAC1B,MAAM,IAAI,KAAK,CAAC,2EAAyE,SAAW,CAAC,CAAA;qBACtG;oBAEK,MAAM,GAAG;wBACb,WAAW,EAAE,wBAAwB,EAAE;wBACvC,gBAAgB,EAAE,4BAA4B,EAAE;wBAChD,YAAY,EAAE;4BACZ,SAAS,WAAA;yBACV;qBACF,CAAA;oBAED,uDAA0B,CAAC,SAAS,EAAE,aAAa,CAAC,CAAA;oBAEpD,sBAAO,EAAE,MAAM,QAAA,EAAE,aAAa,eAAA,EAAE,EAAA;;;;CACjC;AA9BD,kDA8BC"}
\ No newline at end of file
+{"version":3,"file":"loadQuantizedParams.js","sourceRoot":"","sources":["../../src/faceDetectionNet/loadQuantizedParams.ts"],"names":[],"mappings":";;;AAEA,oFAAmF;AACnF,kFAAiF;AACjF,gDAAiD;AACjD,0DAAyD;AAIzD,IAAM,kBAAkB,GAAG,sBAAsB,CAAA;AAEjD,2BAA2B,SAAc,EAAE,aAA6B;IAEtE,IAAM,kBAAkB,GAAG,qDAAyB,CAAC,SAAS,EAAE,aAAa,CAAC,CAAA;IAE9E,oCAAoC,MAAc,EAAE,GAAW,EAAE,YAAoB;QAEnF,IAAM,OAAO,GAAG,kBAAkB,CAAiB,MAAM,gBAAW,GAAG,uBAAoB,EAAE,CAAC,EAAK,YAAY,aAAU,CAAC,CAAA;QAC1H,IAAM,iBAAiB,GAAG,kBAAkB,CAAiB,MAAM,gBAAW,GAAG,qCAAkC,EAAE,CAAC,EAAK,YAAY,uBAAoB,CAAC,CAAA;QAE5J,OAAO,EAAE,OAAO,SAAA,EAAE,iBAAiB,mBAAA,EAAE,CAAA;IACvC,CAAC;IAED,+BAA+B,GAAW;QAExC,IAAM,YAAY,GAAG,sBAAoB,GAAK,CAAA;QAC9C,IAAM,mBAAmB,GAAG,wBAAsB,GAAG,eAAY,CAAA;QACjE,IAAM,yBAAyB,GAAM,YAAY,oBAAiB,CAAA;QAClE,IAAM,yBAAyB,GAAM,YAAY,oBAAiB,CAAA;QAElE,IAAM,OAAO,GAAG,kBAAkB,CAAiB,mBAAmB,uBAAoB,EAAE,CAAC,EAAK,yBAAyB,aAAU,CAAC,CAAA;QACtI,IAAM,gBAAgB,GAAG,kBAAkB,CAAiB,mBAAmB,qBAAkB,EAAE,CAAC,EAAK,yBAAyB,sBAAmB,CAAC,CAAA;QACtJ,IAAM,iBAAiB,GAAG,kBAAkB,CAAiB,mBAAmB,oBAAiB,EAAE,CAAC,EAAK,yBAAyB,uBAAoB,CAAC,CAAA;QACvJ,IAAM,eAAe,GAAG,kBAAkB,CAAiB,mBAAmB,2BAAwB,EAAE,CAAC,EAAK,yBAAyB,qBAAkB,CAAC,CAAA;QAC1J,IAAM,mBAAmB,GAAG,kBAAkB,CAAiB,mBAAmB,+BAA4B,EAAE,CAAC,EAAK,yBAAyB,yBAAsB,CAAC,CAAA;QAEtK,OAAO;YACL,cAAc,EAAE;gBACd,OAAO,SAAA;gBACP,gBAAgB,kBAAA;gBAChB,iBAAiB,mBAAA;gBACjB,eAAe,iBAAA;gBACf,mBAAmB,qBAAA;aACpB;YACD,cAAc,EAAE,0BAA0B,CAAC,aAAa,EAAE,GAAG,EAAE,yBAAyB,CAAC;SAC1F,CAAA;IACH,CAAC;IAED;QACE,OAAO;YACL,MAAM,EAAE,0BAA0B,CAAC,aAAa,EAAE,CAAC,EAAE,oBAAoB,CAAC;YAC1E,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,MAAM,EAAE,qBAAqB,CAAC,CAAC,CAAC;YAChC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;YAClC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;YAClC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;YAClC,OAAO,EAAE,qBAAqB,CAAC,EAAE,CAAC;SACnC,CAAA;IACH,CAAC;IAED,2BAA2B,MAAc,EAAE,YAAoB;QAC7D,IAAM,OAAO,GAAG,kBAAkB,CAAiB,MAAM,aAAU,EAAE,CAAC,EAAK,YAAY,aAAU,CAAC,CAAA;QAClG,IAAM,IAAI,GAAG,kBAAkB,CAAiB,MAAM,YAAS,EAAE,CAAC,EAAK,YAAY,UAAO,CAAC,CAAA;QAE3F,OAAO,EAAE,OAAO,SAAA,EAAE,IAAI,MAAA,EAAE,CAAA;IAC1B,CAAC;IAED,mCAAmC,GAAW;QAE5C,IAAM,sBAAsB,GAAG,iBAAiB,CAC9C,6BAA2B,GAAG,0BAAuB,EACrD,oCAAkC,GAAG,4BAAyB,CAC/D,CAAA;QACD,IAAM,eAAe,GAAG,iBAAiB,CACvC,6BAA2B,GAAG,oBAAiB,EAC/C,oCAAkC,GAAG,qBAAkB,CACxD,CAAA;QAED,OAAO,EAAE,sBAAsB,wBAAA,EAAE,eAAe,iBAAA,EAAE,CAAA;IACpD,CAAC;IAED;QACE,OAAO;YACL,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,MAAM,EAAE,0BAA0B,CAAC,YAAY,EAAE,CAAC,EAAE,yBAAyB,CAAC;YAC9E,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;YAC7C,eAAe,EAAE,yBAAyB,CAAC,CAAC,CAAC;SAC9C,CAAA;IACH,CAAC;IAED,OAAO;QACL,wBAAwB,0BAAA;QACxB,4BAA4B,8BAAA;KAC7B,CAAA;AACH,CAAC;AAED,6BACE,GAAuB;;;;;wBAGL,qBAAM,6BAAa,CAAC,GAAG,EAAE,kBAAkB,CAAC,EAAA;;oBAAxD,SAAS,GAAG,SAA4C;oBACxD,aAAa,GAAmB,EAAE,CAAA;oBAElC,KAGF,iBAAiB,CAAC,SAAS,EAAE,aAAa,CAAC,EAF7C,wBAAwB,8BAAA,EACxB,4BAA4B,kCAAA,CACiB;oBAEzC,SAAS,GAAG,SAAS,CAAC,kBAAkB,CAAC,CAAA;oBAC/C,aAAa,CAAC,IAAI,CAAC,EAAE,YAAY,EAAE,kBAAkB,EAAE,SAAS,EAAE,wBAAwB,EAAE,CAAC,CAAA;oBAE7F,IAAI,CAAC,qBAAU,CAAC,SAAS,CAAC,EAAE;wBAC1B,MAAM,IAAI,KAAK,CAAC,2EAAyE,SAAW,CAAC,CAAA;qBACtG;oBAEK,MAAM,GAAG;wBACb,WAAW,EAAE,wBAAwB,EAAE;wBACvC,gBAAgB,EAAE,4BAA4B,EAAE;wBAChD,YAAY,EAAE;4BACZ,SAAS,WAAA;yBACV;qBACF,CAAA;oBAED,uDAA0B,CAAC,SAAS,EAAE,aAAa,CAAC,CAAA;oBAEpD,sBAAO,EAAE,MAAM,QAAA,EAAE,aAAa,eAAA,EAAE,EAAA;;;;CACjC;AA9BD,kDA8BC"}
\ No newline at end of file

build/faceLandmarkNet/FaceLandmarkNet.d.ts

@@ -2,13 +2,13 @@ import * as tf from '@tensorflow/tfjs-core';
 import { NeuralNetwork } from '../commons/NeuralNetwork';
 import { NetInput } from '../NetInput';
 import { TNetInput } from '../types';
-import { FaceLandmarks } from './FaceLandmarks';
+import { FaceLandmarks68 } from './FaceLandmarks68';
 import { NetParams } from './types';
 export declare class FaceLandmarkNet extends NeuralNetwork<NetParams> {
     constructor();
     forwardInput(input: NetInput): tf.Tensor2D;
     forward(input: TNetInput): Promise<tf.Tensor2D>;
-    detectLandmarks(input: TNetInput): Promise<FaceLandmarks | FaceLandmarks[]>;
+    detectLandmarks(input: TNetInput): Promise<FaceLandmarks68 | FaceLandmarks68[]>;
     protected loadQuantizedParams(uri: string | undefined): Promise<{
         params: NetParams;
         paramMappings: {

build/faceLandmarkNet/FaceLandmarkNet.js

@@ -8,7 +8,7 @@ var Point_1 = require("../Point");
 var toNetInput_1 = require("../toNetInput");
 var utils_1 = require("../utils");
 var extractParams_1 = require("./extractParams");
-var FaceLandmarks_1 = require("./FaceLandmarks");
+var FaceLandmarks68_1 = require("./FaceLandmarks68");
 var fullyConnectedLayer_1 = require("./fullyConnectedLayer");
 var loadQuantizedParams_1 = require("./loadQuantizedParams");
 function conv(x, params) {
@@ -101,7 +101,7 @@ var FaceLandmarkNet = /** @class */ (function (_super) {
                                             landmarksArray = _b.apply(_a, [_c.sent()]);
                                             xCoords = landmarksArray.filter(function (_, i) { return utils_1.isEven(i); });
                                             yCoords = landmarksArray.filter(function (_, i) { return !utils_1.isEven(i); });
-                                            return [2 /*return*/, new FaceLandmarks_1.FaceLandmarks(Array(68).fill(0).map(function (_, i) { return new Point_1.Point(xCoords[i], yCoords[i]); }), {
+                                            return [2 /*return*/, new FaceLandmarks68_1.FaceLandmarks68(Array(68).fill(0).map(function (_, i) { return new Point_1.Point(xCoords[i], yCoords[i]); }), {
                                                     height: netInput.getInputHeight(batchIdx),
                                                     width: netInput.getInputWidth(batchIdx),
                                                 })];

build/faceLandmarkNet/FaceLandmarkNet.js.map

-{"version":3,"file":"FaceLandmarkNet.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/FaceLandmarkNet.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,kDAAiD;AACjD,0DAAyD;AAGzD,kCAAiC;AACjC,4CAA2C;AAE3C,kCAAkC;AAClC,iDAAgD;AAChD,iDAAgD;AAChD,6DAA4D;AAC5D,6DAA4D;AAG5D,cAAc,CAAc,EAAE,MAAkB;IAC9C,OAAO,qBAAS,CAAC,CAAC,EAAE,MAAM,EAAE,OAAO,EAAE,IAAI,CAAC,CAAA;AAC5C,CAAC;AAED,iBAAiB,CAAc,EAAE,OAAkC;IAAlC,wBAAA,EAAA,WAA6B,CAAC,EAAE,CAAC,CAAC;IACjE,OAAO,EAAE,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;AAChD,CAAC;AAED;IAAqC,2CAAwB;IAE3D;eACE,kBAAM,iBAAiB,CAAC;IAC1B,CAAC;IAEM,sCAAY,GAAnB,UAAoB,KAAe;QAEzB,IAAA,oBAAM,CAAS;QAEvB,IAAI,CAAC,MAAM,EAAE;YACX,MAAM,IAAI,KAAK,CAAC,+CAA+C,CAAC,CAAA;SACjE;QAED,OAAO,EAAE,CAAC,IAAI,CAAC;YACb,IAAM,WAAW,GAAG,KAAK,CAAC,aAAa,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;YAElD,IAAI,GAAG,GAAG,IAAI,CAAC,WAAW,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YACzC,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;YAClB,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;YAClB,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;YAClB,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,OAAO,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;YAC1B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,IAAM,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,yCAAmB,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;YAChF,IAAM,GAAG,GAAG,yCAAmB,CAAC,GAAG,EAAE,MAAM,CAAC,GAAG,CAAC,CAAA;YAEhD,IAAM,uBAAuB,GAAG,UAAC,KAAa,EAAE,KAAa;gBAC3D,OAAA,EAAE,CAAC,KAAK,CAAC;oBACP,EAAE,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,EAAE,KAAK,CAAC;oBACpB,EAAE,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,EAAE,KAAK,CAAC;iBACrB,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE;YAHzB,CAGyB,CAAA;YAE3B;;;cAGE;YAEF,IAAM,eAAe,GAAG,GAAG;iBACxB,GAAG,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,UAAC,CAAC,EAAE,QAAQ;gBAC3D,OAAA,uBAAuB,CACrB,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,aAAa,CAAC,QAAQ,CAAC,EAC7D,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,cAAc,CAAC,QAAQ,CAAC,CAC/D;YAHD,CAGC,CACF,CAAC,CAAC;iBACF,GAAG,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,UAAC,CAAC,EAAE,QAAQ;gBAC3D,OAAA,uBAAuB,CACrB,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,EAC7C,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAC9C;YAHD,CAGC,CACF,CAAC,CAAC;iBACF,GAAG,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,UAAC,CAAC,EAAE,QAAQ;gBAC3D,OAAA,uBAAuB,CACrB,KAAK,CAAC,aAAa,CAAC,QAAQ,CAAC,EAC7B,KAAK,CAAC,cAAc,CAAC,QAAQ,CAAC,CAC/B;YAHD,CAGC,CACF,CAAC,CAAC,CAAA;YAEL,OAAO,eAA8B,CAAA;QACvC,CAAC,CAAC,CAAA;IACJ,CAAC;IAEY,iCAAO,GAApB,UAAqB,KAAgB;;;;;;wBAC5B,KAAA,IAAI,CAAC,YAAY,CAAA;wBAAC,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;4BAAtD,sBAAO,SAAA,IAAI,GAAc,SAA6B,EAAC,EAAA;;;;KACxD;IAEY,yCAAe,GAA5B,UAA6B,KAAgB;;;;;;4BAC1B,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;wBAAxC,QAAQ,GAAG,SAA6B;wBAExC,eAAe,GAAG,EAAE,CAAC,IAAI,CAC7B,cAAM,OAAA,EAAE,CAAC,OAAO,CAAC,KAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC,EAAvC,CAAuC,CAC9C,CAAA;wBAEyB,qBAAM,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,GAAG,CAC7D,UAAO,cAAc,EAAE,QAAQ;;;;;4CACN,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;4CAAC,qBAAM,cAAc,CAAC,IAAI,EAAE,EAAA;;4CAAvD,cAAc,GAAG,cAAW,SAA2B,EAAC;4CACxD,OAAO,GAAG,cAAc,CAAC,MAAM,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,cAAM,CAAC,CAAC,CAAC,EAAT,CAAS,CAAC,CAAA;4CACpD,OAAO,GAAG,cAAc,CAAC,MAAM,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,CAAC,cAAM,CAAC,CAAC,CAAC,EAAV,CAAU,CAAC,CAAA;4CAE3D,sBAAO,IAAI,6BAAa,CACtB,KAAK,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,IAAI,aAAK,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC,EAAjC,CAAiC,CAAC,EAClE;oDACE,MAAM,EAAE,QAAQ,CAAC,cAAc,CAAC,QAAQ,CAAC;oDACzC,KAAK,EAAG,QAAQ,CAAC,aAAa,CAAC,QAAQ,CAAC;iDACzC,CACF,EAAA;;;iCACF,CACF,CAAC,EAAA;;wBAdI,iBAAiB,GAAG,SAcxB;wBAEF,eAAe,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;wBAEzC,sBAAO,QAAQ,CAAC,YAAY;gCAC1B,CAAC,CAAC,iBAAiB;gCACnB,CAAC,CAAC,iBAAiB,CAAC,CAAC,CAAC,EAAA;;;;KACzB;IAES,6CAAmB,GAA7B,UAA8B,GAAuB;QACnD,OAAO,yCAAmB,CAAC,GAAG,CAAC,CAAA;IACjC,CAAC;IAES,uCAAa,GAAvB,UAAwB,OAAqB;QAC3C,OAAO,6BAAa,CAAC,OAAO,CAAC,CAAA;IAC/B,CAAC;IACH,sBAAC;AAAD,CAAC,AA5GD,CAAqC,6BAAa,GA4GjD;AA5GY,0CAAe"}
\ No newline at end of file
+{"version":3,"file":"FaceLandmarkNet.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/FaceLandmarkNet.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,kDAAiD;AACjD,0DAAyD;AAGzD,kCAAiC;AACjC,4CAA2C;AAE3C,kCAAkC;AAClC,iDAAgD;AAChD,qDAAoD;AACpD,6DAA4D;AAC5D,6DAA4D;AAG5D,cAAc,CAAc,EAAE,MAAkB;IAC9C,OAAO,qBAAS,CAAC,CAAC,EAAE,MAAM,EAAE,OAAO,EAAE,IAAI,CAAC,CAAA;AAC5C,CAAC;AAED,iBAAiB,CAAc,EAAE,OAAkC;IAAlC,wBAAA,EAAA,WAA6B,CAAC,EAAE,CAAC,CAAC;IACjE,OAAO,EAAE,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;AAChD,CAAC;AAED;IAAqC,2CAAwB;IAE3D;eACE,kBAAM,iBAAiB,CAAC;IAC1B,CAAC;IAEM,sCAAY,GAAnB,UAAoB,KAAe;QAEzB,IAAA,oBAAM,CAAS;QAEvB,IAAI,CAAC,MAAM,EAAE;YACX,MAAM,IAAI,KAAK,CAAC,+CAA+C,CAAC,CAAA;SACjE;QAED,OAAO,EAAE,CAAC,IAAI,CAAC;YACb,IAAM,WAAW,GAAG,KAAK,CAAC,aAAa,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;YAElD,IAAI,GAAG,GAAG,IAAI,CAAC,WAAW,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YACzC,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;YAClB,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;YAClB,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;YAClB,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,GAAG,GAAG,OAAO,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;YAC1B,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;YAC7B,IAAM,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,yCAAmB,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;YAChF,IAAM,GAAG,GAAG,yCAAmB,CAAC,GAAG,EAAE,MAAM,CAAC,GAAG,CAAC,CAAA;YAEhD,IAAM,uBAAuB,GAAG,UAAC,KAAa,EAAE,KAAa;gBAC3D,OAAA,EAAE,CAAC,KAAK,CAAC;oBACP,EAAE,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,EAAE,KAAK,CAAC;oBACpB,EAAE,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,EAAE,KAAK,CAAC;iBACrB,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE;YAHzB,CAGyB,CAAA;YAE3B;;;cAGE;YAEF,IAAM,eAAe,GAAG,GAAG;iBACxB,GAAG,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,UAAC,CAAC,EAAE,QAAQ;gBAC3D,OAAA,uBAAuB,CACrB,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,aAAa,CAAC,QAAQ,CAAC,EAC7D,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,cAAc,CAAC,QAAQ,CAAC,CAC/D;YAHD,CAGC,CACF,CAAC,CAAC;iBACF,GAAG,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,UAAC,CAAC,EAAE,QAAQ;gBAC3D,OAAA,uBAAuB,CACrB,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,EAC7C,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAC9C;YAHD,CAGC,CACF,CAAC,CAAC;iBACF,GAAG,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,UAAC,CAAC,EAAE,QAAQ;gBAC3D,OAAA,uBAAuB,CACrB,KAAK,CAAC,aAAa,CAAC,QAAQ,CAAC,EAC7B,KAAK,CAAC,cAAc,CAAC,QAAQ,CAAC,CAC/B;YAHD,CAGC,CACF,CAAC,CAAC,CAAA;YAEL,OAAO,eAA8B,CAAA;QACvC,CAAC,CAAC,CAAA;IACJ,CAAC;IAEY,iCAAO,GAApB,UAAqB,KAAgB;;;;;;wBAC5B,KAAA,IAAI,CAAC,YAAY,CAAA;wBAAC,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;4BAAtD,sBAAO,SAAA,IAAI,GAAc,SAA6B,EAAC,EAAA;;;;KACxD;IAEY,yCAAe,GAA5B,UAA6B,KAAgB;;;;;;4BAC1B,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,CAAC,EAAA;;wBAAxC,QAAQ,GAAG,SAA6B;wBAExC,eAAe,GAAG,EAAE,CAAC,IAAI,CAC7B,cAAM,OAAA,EAAE,CAAC,OAAO,CAAC,KAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC,EAAvC,CAAuC,CAC9C,CAAA;wBAEyB,qBAAM,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,GAAG,CAC7D,UAAO,cAAc,EAAE,QAAQ;;;;;4CACN,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;4CAAC,qBAAM,cAAc,CAAC,IAAI,EAAE,EAAA;;4CAAvD,cAAc,GAAG,cAAW,SAA2B,EAAC;4CACxD,OAAO,GAAG,cAAc,CAAC,MAAM,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,cAAM,CAAC,CAAC,CAAC,EAAT,CAAS,CAAC,CAAA;4CACpD,OAAO,GAAG,cAAc,CAAC,MAAM,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,CAAC,cAAM,CAAC,CAAC,CAAC,EAAV,CAAU,CAAC,CAAA;4CAE3D,sBAAO,IAAI,iCAAe,CACxB,KAAK,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,IAAI,aAAK,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC,EAAjC,CAAiC,CAAC,EAClE;oDACE,MAAM,EAAE,QAAQ,CAAC,cAAc,CAAC,QAAQ,CAAC;oDACzC,KAAK,EAAG,QAAQ,CAAC,aAAa,CAAC,QAAQ,CAAC;iDACzC,CACF,EAAA;;;iCACF,CACF,CAAC,EAAA;;wBAdI,iBAAiB,GAAG,SAcxB;wBAEF,eAAe,CAAC,OAAO,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,OAAO,EAAE,EAAX,CAAW,CAAC,CAAA;wBAEzC,sBAAO,QAAQ,CAAC,YAAY;gCAC1B,CAAC,CAAC,iBAAiB;gCACnB,CAAC,CAAC,iBAAiB,CAAC,CAAC,CAAC,EAAA;;;;KACzB;IAES,6CAAmB,GAA7B,UAA8B,GAAuB;QACnD,OAAO,yCAAmB,CAAC,GAAG,CAAC,CAAA;IACjC,CAAC;IAES,uCAAa,GAAvB,UAAwB,OAAqB;QAC3C,OAAO,6BAAa,CAAC,OAAO,CAAC,CAAA;IAC/B,CAAC;IACH,sBAAC;AAAD,CAAC,AA5GD,CAAqC,6BAAa,GA4GjD;AA5GY,0CAAe"}
\ No newline at end of file

build/faceLandmarkNet/FaceLandmarks68.d.ts

+import { FaceDetection } from '../FaceDetection';
+import { FaceLandmarks } from '../FaceLandmarks';
+import { IPoint, Point } from '../Point';
+import { Rect } from '../Rect';
+export declare class FaceLandmarks68 extends FaceLandmarks {
+    getJawOutline(): Point[];
+    getLeftEyeBrow(): Point[];
+    getRightEyeBrow(): Point[];
+    getNose(): Point[];
+    getLeftEye(): Point[];
+    getRightEye(): Point[];
+    getMouth(): Point[];
+    forSize(width: number, height: number): FaceLandmarks68;
+    shift(x: number, y: number): FaceLandmarks68;
+    shiftByPoint(pt: IPoint): FaceLandmarks68;
+    /**
+     * 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.
+     */
+    align(detection?: FaceDetection | Rect): Rect;
+}

build/faceLandmarkNet/FaceLandmarks68.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var getCenterPoint_1 = require("../commons/getCenterPoint");
+var FaceDetection_1 = require("../FaceDetection");
+var FaceLandmarks_1 = require("../FaceLandmarks");
+var Point_1 = require("../Point");
+var Rect_1 = require("../Rect");
+// face alignment constants
+var relX = 0.5;
+var relY = 0.43;
+var relScale = 0.45;
+var FaceLandmarks68 = /** @class */ (function (_super) {
+    tslib_1.__extends(FaceLandmarks68, _super);
+    function FaceLandmarks68() {
+        return _super !== null && _super.apply(this, arguments) || this;
+    }
+    FaceLandmarks68.prototype.getJawOutline = function () {
+        return this._faceLandmarks.slice(0, 17);
+    };
+    FaceLandmarks68.prototype.getLeftEyeBrow = function () {
+        return this._faceLandmarks.slice(17, 22);
+    };
+    FaceLandmarks68.prototype.getRightEyeBrow = function () {
+        return this._faceLandmarks.slice(22, 27);
+    };
+    FaceLandmarks68.prototype.getNose = function () {
+        return this._faceLandmarks.slice(27, 36);
+    };
+    FaceLandmarks68.prototype.getLeftEye = function () {
+        return this._faceLandmarks.slice(36, 42);
+    };
+    FaceLandmarks68.prototype.getRightEye = function () {
+        return this._faceLandmarks.slice(42, 48);
+    };
+    FaceLandmarks68.prototype.getMouth = function () {
+        return this._faceLandmarks.slice(48, 68);
+    };
+    FaceLandmarks68.prototype.forSize = function (width, height) {
+        return new FaceLandmarks68(this.getRelativePositions(), { width: width, height: height });
+    };
+    FaceLandmarks68.prototype.shift = function (x, y) {
+        return new FaceLandmarks68(this.getRelativePositions(), { width: this._imageWidth, height: this._imageHeight }, new Point_1.Point(x, y));
+    };
+    FaceLandmarks68.prototype.shiftByPoint = function (pt) {
+        return this.shift(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.
+     */
+    FaceLandmarks68.prototype.align = function (detection) {
+        if (detection) {
+            var box = detection instanceof FaceDetection_1.FaceDetection
+                ? detection.getBox().floor()
+                : detection;
+            return this.shift(box.x, box.y).align();
+        }
+        var centers = [
+            this.getLeftEye(),
+            this.getRightEye(),
+            this.getMouth()
+        ].map(getCenterPoint_1.getCenterPoint);
+        var leftEyeCenter = centers[0], rightEyeCenter = centers[1], mouthCenter = centers[2];
+        var distToMouth = function (pt) { return mouthCenter.sub(pt).magnitude(); };
+        var eyeToMouthDist = (distToMouth(leftEyeCenter) + distToMouth(rightEyeCenter)) / 2;
+        var size = Math.floor(eyeToMouthDist / relScale);
+        var refPoint = getCenterPoint_1.getCenterPoint(centers);
+        // TODO: pad in case rectangle is out of image bounds
+        var x = Math.floor(Math.max(0, refPoint.x - (relX * size)));
+        var y = Math.floor(Math.max(0, refPoint.y - (relY * size)));
+        return new Rect_1.Rect(x, y, size, size);
+    };
+    return FaceLandmarks68;
+}(FaceLandmarks_1.FaceLandmarks));
+exports.FaceLandmarks68 = FaceLandmarks68;
+//# sourceMappingURL=FaceLandmarks68.js.map
\ No newline at end of file

build/faceLandmarkNet/FaceLandmarks68.js.map

+{"version":3,"file":"FaceLandmarks68.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/FaceLandmarks68.ts"],"names":[],"mappings":";;;AAAA,4DAA2D;AAC3D,kDAAiD;AACjD,kDAAiD;AACjD,kCAAyC;AACzC,gCAA+B;AAE/B,2BAA2B;AAC3B,IAAM,IAAI,GAAG,GAAG,CAAA;AAChB,IAAM,IAAI,GAAG,IAAI,CAAA;AACjB,IAAM,QAAQ,GAAG,IAAI,CAAA;AAErB;IAAqC,2CAAa;IAAlD;;IAyFA,CAAC;IAxFQ,uCAAa,GAApB;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;IACzC,CAAC;IAEM,wCAAc,GAArB;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAA;IAC1C,CAAC;IAEM,yCAAe,GAAtB;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAA;IAC1C,CAAC;IAEM,iCAAO,GAAd;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAA;IAC1C,CAAC;IAEM,oCAAU,GAAjB;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAA;IAC1C,CAAC;IAEM,qCAAW,GAAlB;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAA;IAC1C,CAAC;IAEM,kCAAQ,GAAf;QACE,OAAO,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAA;IAC1C,CAAC;IAEM,iCAAO,GAAd,UAAe,KAAa,EAAE,MAAc;QAC1C,OAAO,IAAI,eAAe,CACxB,IAAI,CAAC,oBAAoB,EAAE,EAC3B,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAE,CAClB,CAAA;IACH,CAAC;IAEM,+BAAK,GAAZ,UAAa,CAAS,EAAE,CAAS;QAC/B,OAAO,IAAI,eAAe,CACxB,IAAI,CAAC,oBAAoB,EAAE,EAC3B,EAAE,KAAK,EAAE,IAAI,CAAC,WAAW,EAAE,MAAM,EAAE,IAAI,CAAC,YAAY,EAAE,EACtD,IAAI,aAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAChB,CAAA;IACH,CAAC;IAEM,sCAAY,GAAnB,UAAoB,EAAU;QAC5B,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAA;IAC/B,CAAC;IAED;;;;;;;;;;OAUG;IACI,+BAAK,GAAZ,UACE,SAAgC;QAEhC,IAAI,SAAS,EAAE;YACb,IAAM,GAAG,GAAG,SAAS,YAAY,6BAAa;gBAC5C,CAAC,CAAC,SAAS,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE;gBAC5B,CAAC,CAAC,SAAS,CAAA;YAEb,OAAO,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,EAAE,CAAA;SACxC;QAED,IAAM,OAAO,GAAG;YACd,IAAI,CAAC,UAAU,EAAE;YACjB,IAAI,CAAC,WAAW,EAAE;YAClB,IAAI,CAAC,QAAQ,EAAE;SAChB,CAAC,GAAG,CAAC,+BAAc,CAAC,CAAA;QAEd,IAAA,0BAAa,EAAE,2BAAc,EAAE,wBAAW,CAAW;QAC5D,IAAM,WAAW,GAAG,UAAC,EAAS,IAAK,OAAA,WAAW,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,SAAS,EAAE,EAA/B,CAA+B,CAAA;QAClE,IAAM,cAAc,GAAG,CAAC,WAAW,CAAC,aAAa,CAAC,GAAG,WAAW,CAAC,cAAc,CAAC,CAAC,GAAG,CAAC,CAAA;QAErF,IAAM,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,cAAc,GAAG,QAAQ,CAAC,CAAA;QAElD,IAAM,QAAQ,GAAG,+BAAc,CAAC,OAAO,CAAC,CAAA;QACxC,qDAAqD;QACrD,IAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,GAAG,CAAC,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7D,IAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,GAAG,CAAC,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC,CAAA;QAE7D,OAAO,IAAI,WAAI,CAAC,CAAC,EAAE,CAAC,EAAE,IAAI,EAAE,IAAI,CAAC,CAAA;IACnC,CAAC;IACH,sBAAC;AAAD,CAAC,AAzFD,CAAqC,6BAAa,GAyFjD;AAzFY,0CAAe"}
\ No newline at end of file

build/faceLandmarkNet/extractParams.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-var tf = require("@tensorflow/tfjs-core");
+var extractConvParamsFactory_1 = require("../commons/extractConvParamsFactory");
+var extractFCParamsFactory_1 = require("../commons/extractFCParamsFactory");
 var extractWeightsFactory_1 = require("../commons/extractWeightsFactory");
 function extractParams(weights) {
     var paramMappings = [];
     var _a = extractWeightsFactory_1.extractWeightsFactory(weights), extractWeights = _a.extractWeights, getRemainingWeights = _a.getRemainingWeights;
-    function extractConvParams(channelsIn, channelsOut, filterSize, mappedPrefix) {
-        var filters = tf.tensor4d(extractWeights(channelsIn * channelsOut * filterSize * filterSize), [filterSize, filterSize, channelsIn, channelsOut]);
-        var bias = tf.tensor1d(extractWeights(channelsOut));
-        paramMappings.push({ paramPath: mappedPrefix + "/filters" }, { paramPath: mappedPrefix + "/bias" });
-        return { filters: filters, bias: bias };
-    }
-    function extractFcParams(channelsIn, channelsOut, mappedPrefix) {
-        var fc_weights = tf.tensor2d(extractWeights(channelsIn * channelsOut), [channelsIn, channelsOut]);
-        var fc_bias = tf.tensor1d(extractWeights(channelsOut));
-        paramMappings.push({ paramPath: mappedPrefix + "/weights" }, { paramPath: mappedPrefix + "/bias" });
-        return {
-            weights: fc_weights,
-            bias: fc_bias
-        };
-    }
+    var extractConvParams = extractConvParamsFactory_1.extractConvParamsFactory(extractWeights, paramMappings);
+    var extractFCParams = extractFCParamsFactory_1.extractFCParamsFactory(extractWeights, paramMappings);
     var conv0 = extractConvParams(3, 32, 3, 'conv0');
     var conv1 = extractConvParams(32, 64, 3, 'conv1');
     var conv2 = extractConvParams(64, 64, 3, 'conv2');
@@ -28,8 +16,8 @@ function extractParams(weights) {
     var conv5 = extractConvParams(64, 128, 3, 'conv5');
     var conv6 = extractConvParams(128, 128, 3, 'conv6');
     var conv7 = extractConvParams(128, 256, 3, 'conv7');
-    var fc0 = extractFcParams(6400, 1024, 'fc0');
-    var fc1 = extractFcParams(1024, 136, 'fc1');
+    var fc0 = extractFCParams(6400, 1024, 'fc0');
+    var fc1 = extractFCParams(1024, 136, 'fc1');
     if (getRemainingWeights().length !== 0) {
         throw new Error("weights remaing after extract: " + getRemainingWeights().length);
     }

build/faceLandmarkNet/extractParams.js.map

-{"version":3,"file":"extractParams.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/extractParams.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,0EAAyE;AAIzE,uBAA8B,OAAqB;IAEjD,IAAM,aAAa,GAAmB,EAAE,CAAA;IAElC,IAAA,2DAG4B,EAFhC,kCAAc,EACd,4CAAmB,CACa;IAElC,2BACE,UAAkB,EAClB,WAAmB,EACnB,UAAkB,EAClB,YAAoB;QAGpB,IAAM,OAAO,GAAG,EAAE,CAAC,QAAQ,CACzB,cAAc,CAAC,UAAU,GAAG,WAAW,GAAG,UAAU,GAAG,UAAU,CAAC,EAClE,CAAC,UAAU,EAAE,UAAU,EAAE,UAAU,EAAE,WAAW,CAAC,CAClD,CAAA;QACD,IAAM,IAAI,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,WAAW,CAAC,CAAC,CAAA;QAErD,aAAa,CAAC,IAAI,CAChB,EAAE,SAAS,EAAK,YAAY,aAAU,EAAE,EACxC,EAAE,SAAS,EAAK,YAAY,UAAO,EAAE,CACtC,CAAA;QAED,OAAO,EAAE,OAAO,SAAA,EAAE,IAAI,MAAA,EAAE,CAAA;IAC1B,CAAC;IAED,yBAAyB,UAAkB,EAAE,WAAmB,EAAE,YAAoB;QAEpF,IAAM,UAAU,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,UAAU,GAAG,WAAW,CAAC,EAAE,CAAC,UAAU,EAAE,WAAW,CAAC,CAAC,CAAA;QACnG,IAAM,OAAO,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,WAAW,CAAC,CAAC,CAAA;QAExD,aAAa,CAAC,IAAI,CAChB,EAAE,SAAS,EAAK,YAAY,aAAU,EAAE,EACxC,EAAE,SAAS,EAAK,YAAY,UAAO,EAAE,CACtC,CAAA;QAED,OAAO;YACL,OAAO,EAAE,UAAU;YACnB,IAAI,EAAE,OAAO;SACd,CAAA;IACH,CAAC;IAED,IAAM,KAAK,GAAG,iBAAiB,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IAClD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACpD,IAAM,KAAK,GAAG,iBAAiB,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACrD,IAAM,KAAK,GAAG,iBAAiB,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACrD,IAAM,GAAG,GAAG,eAAe,CAAC,IAAI,EAAE,IAAI,EAAE,KAAK,CAAC,CAAA;IAC9C,IAAM,GAAG,GAAG,eAAe,CAAC,IAAI,EAAE,GAAG,EAAE,KAAK,CAAC,CAAA;IAE7C,IAAI,mBAAmB,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE;QACtC,MAAM,IAAI,KAAK,CAAC,oCAAkC,mBAAmB,EAAE,CAAC,MAAQ,CAAC,CAAA;KAClF;IAED,OAAO;QACL,aAAa,eAAA;QACb,MAAM,EAAE;YACN,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,GAAG,KAAA;YACH,GAAG,KAAA;SACJ;KACF,CAAA;AACH,CAAC;AA5ED,sCA4EC"}
\ No newline at end of file
+{"version":3,"file":"extractParams.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/extractParams.ts"],"names":[],"mappings":";;AAAA,gFAA+E;AAC/E,4EAA2E;AAC3E,0EAAyE;AAIzE,uBAA8B,OAAqB;IAEjD,IAAM,aAAa,GAAmB,EAAE,CAAA;IAElC,IAAA,2DAG4B,EAFhC,kCAAc,EACd,4CAAmB,CACa;IAElC,IAAM,iBAAiB,GAAG,mDAAwB,CAAC,cAAc,EAAE,aAAa,CAAC,CAAA;IACjF,IAAM,eAAe,GAAG,+CAAsB,CAAC,cAAc,EAAE,aAAa,CAAC,CAAA;IAE7E,IAAM,KAAK,GAAG,iBAAiB,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IAClD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACnD,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACpD,IAAM,KAAK,GAAG,iBAAiB,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACrD,IAAM,KAAK,GAAG,iBAAiB,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;IACrD,IAAM,GAAG,GAAG,eAAe,CAAC,IAAI,EAAE,IAAI,EAAE,KAAK,CAAC,CAAA;IAC9C,IAAM,GAAG,GAAG,eAAe,CAAC,IAAI,EAAE,GAAG,EAAE,KAAK,CAAC,CAAA;IAE7C,IAAI,mBAAmB,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE;QACtC,MAAM,IAAI,KAAK,CAAC,oCAAkC,mBAAmB,EAAE,CAAC,MAAQ,CAAC,CAAA;KAClF;IAED,OAAO;QACL,aAAa,eAAA;QACb,MAAM,EAAE;YACN,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,KAAK,OAAA;YACL,GAAG,KAAA;YACH,GAAG,KAAA;SACJ;KACF,CAAA;AACH,CAAC;AA1CD,sCA0CC"}
\ No newline at end of file

build/faceLandmarkNet/fullyConnectedLayer.d.ts

 import * as tf from '@tensorflow/tfjs-core';
-import { FCParams } from './types';
+import { FCParams } from '../commons/types';
 export declare function fullyConnectedLayer(x: tf.Tensor2D, params: FCParams): tf.Tensor2D;

build/faceLandmarkNet/index.d.ts

 import { FaceLandmarkNet } from './FaceLandmarkNet';
 export * from './FaceLandmarkNet';
-export * from './FaceLandmarks';
+export * from './FaceLandmarks68';
+export declare function createFaceLandmarkNet(weights: Float32Array): FaceLandmarkNet;
 export declare function faceLandmarkNet(weights: Float32Array): FaceLandmarkNet;

build/faceLandmarkNet/index.js

@@ -3,11 +3,16 @@ Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
 var FaceLandmarkNet_1 = require("./FaceLandmarkNet");
 tslib_1.__exportStar(require("./FaceLandmarkNet"), exports);
-tslib_1.__exportStar(require("./FaceLandmarks"), exports);
-function faceLandmarkNet(weights) {
+tslib_1.__exportStar(require("./FaceLandmarks68"), exports);
+function createFaceLandmarkNet(weights) {
     var net = new FaceLandmarkNet_1.FaceLandmarkNet();
     net.extractWeights(weights);
     return net;
 }
+exports.createFaceLandmarkNet = createFaceLandmarkNet;
+function faceLandmarkNet(weights) {
+    console.warn('faceLandmarkNet(weights: Float32Array) will be deprecated in future, use createFaceLandmarkNet instead');
+    return createFaceLandmarkNet(weights);
+}
 exports.faceLandmarkNet = faceLandmarkNet;
 //# sourceMappingURL=index.js.map
\ No newline at end of file

build/faceLandmarkNet/index.js.map

-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/index.ts"],"names":[],"mappings":";;;AAAA,qDAAoD;AAEpD,4DAAkC;AAClC,0DAAgC;AAEhC,yBAAgC,OAAqB;IACnD,IAAM,GAAG,GAAG,IAAI,iCAAe,EAAE,CAAA;IACjC,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,0CAIC"}
\ No newline at end of file
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/faceLandmarkNet/index.ts"],"names":[],"mappings":";;;AAAA,qDAAoD;AAEpD,4DAAkC;AAClC,4DAAkC;AAElC,+BAAsC,OAAqB;IACzD,IAAM,GAAG,GAAG,IAAI,iCAAe,EAAE,CAAA;IACjC,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,sDAIC;AAED,yBAAgC,OAAqB;IACnD,OAAO,CAAC,IAAI,CAAC,wGAAwG,CAAC,CAAA;IACtH,OAAO,qBAAqB,CAAC,OAAO,CAAC,CAAA;AACvC,CAAC;AAHD,0CAGC"}
\ No newline at end of file

build/faceLandmarkNet/types.d.ts

-import * as tf from '@tensorflow/tfjs-core';
-import { ConvParams } from '../commons/types';
-export declare type FCParams = {
-    weights: tf.Tensor2D;
-    bias: tf.Tensor1D;
-};
+import { ConvParams, FCParams } from '../commons/types';
 export declare type NetParams = {
     conv0: ConvParams;
     conv1: ConvParams;

build/faceRecognitionNet/index.d.ts

 import { FaceRecognitionNet } from './FaceRecognitionNet';
 export * from './FaceRecognitionNet';
+export declare function createFaceRecognitionNet(weights: Float32Array): FaceRecognitionNet;
 export declare function faceRecognitionNet(weights: Float32Array): FaceRecognitionNet;

build/faceRecognitionNet/index.js

@@ -3,10 +3,15 @@ Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
 var FaceRecognitionNet_1 = require("./FaceRecognitionNet");
 tslib_1.__exportStar(require("./FaceRecognitionNet"), exports);
-function faceRecognitionNet(weights) {
+function createFaceRecognitionNet(weights) {
     var net = new FaceRecognitionNet_1.FaceRecognitionNet();
     net.extractWeights(weights);
     return net;
 }
+exports.createFaceRecognitionNet = createFaceRecognitionNet;
+function faceRecognitionNet(weights) {
+    console.warn('faceRecognitionNet(weights: Float32Array) will be deprecated in future, use createFaceRecognitionNet instead');
+    return createFaceRecognitionNet(weights);
+}
 exports.faceRecognitionNet = faceRecognitionNet;
 //# sourceMappingURL=index.js.map
\ No newline at end of file

build/faceRecognitionNet/index.js.map

-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/faceRecognitionNet/index.ts"],"names":[],"mappings":";;;AAAA,2DAA0D;AAE1D,+DAAqC;AAErC,4BAAmC,OAAqB;IACtD,IAAM,GAAG,GAAG,IAAI,uCAAkB,EAAE,CAAA;IACpC,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,gDAIC"}
\ No newline at end of file
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/faceRecognitionNet/index.ts"],"names":[],"mappings":";;;AAAA,2DAA0D;AAE1D,+DAAqC;AAErC,kCAAyC,OAAqB;IAC5D,IAAM,GAAG,GAAG,IAAI,uCAAkB,EAAE,CAAA;IACpC,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,4DAIC;AAED,4BAAmC,OAAqB;IACtD,OAAO,CAAC,IAAI,CAAC,8GAA8G,CAAC,CAAA;IAC5H,OAAO,wBAAwB,CAAC,OAAO,CAAC,CAAA;AAC1C,CAAC;AAHD,gDAGC"}
\ No newline at end of file

build/globalApi.d.ts

 import * as tf from '@tensorflow/tfjs-core';
-import { FaceDetection } from './faceDetectionNet/FaceDetection';
+import { FaceDetection } from './FaceDetection';
 import { FaceDetectionNet } from './faceDetectionNet/FaceDetectionNet';
 import { FaceLandmarkNet } from './faceLandmarkNet/FaceLandmarkNet';
-import { FaceLandmarks } from './faceLandmarkNet/FaceLandmarks';
+import { FaceLandmarks68 } from './faceLandmarkNet/FaceLandmarks68';
 import { FaceRecognitionNet } from './faceRecognitionNet/FaceRecognitionNet';
 import { FullFaceDescription } from './FullFaceDescription';
+import { Mtcnn } from './mtcnn/Mtcnn';
+import { MtcnnForwardParams, MtcnnResult } from './mtcnn/types';
 import { NetInput } from './NetInput';
 import { TNetInput } from './types';
 export declare const detectionNet: FaceDetectionNet;
 export declare const landmarkNet: FaceLandmarkNet;
 export declare const recognitionNet: FaceRecognitionNet;
+export declare const nets: {
+    ssdMobilenet: FaceDetectionNet;
+    faceLandmark68Net: FaceLandmarkNet;
+    faceNet: FaceRecognitionNet;
+    mtcnn: Mtcnn;
+};
 export declare function loadFaceDetectionModel(url: string): Promise<void>;
 export declare function loadFaceLandmarkModel(url: string): Promise<void>;
 export declare function loadFaceRecognitionModel(url: string): Promise<void>;
-export declare function loadModels(url: string): Promise<[void, void, void]>;
+export declare function loadMtcnnModel(url: string): Promise<void>;
+export declare function loadModels(url: string): Promise<[void, void, void, void]>;
 export declare function locateFaces(input: TNetInput, minConfidence?: number, maxResults?: number): Promise<FaceDetection[]>;
-export declare function detectLandmarks(input: TNetInput): Promise<FaceLandmarks | FaceLandmarks[]>;
+export declare function detectLandmarks(input: TNetInput): Promise<FaceLandmarks68 | FaceLandmarks68[]>;
 export declare function computeFaceDescriptor(input: TNetInput): Promise<Float32Array | Float32Array[]>;
+export declare function mtcnn(input: TNetInput, forwardParams: MtcnnForwardParams): Promise<MtcnnResult[]>;
 export declare const allFaces: (input: tf.Tensor | NetInput | TNetInput, minConfidence: number, useBatchProcessing?: boolean) => Promise<FullFaceDescription[]>;

build/globalApi.js

@@ -4,40 +4,58 @@ var allFacesFactory_1 = require("./allFacesFactory");
 var FaceDetectionNet_1 = require("./faceDetectionNet/FaceDetectionNet");
 var FaceLandmarkNet_1 = require("./faceLandmarkNet/FaceLandmarkNet");
 var FaceRecognitionNet_1 = require("./faceRecognitionNet/FaceRecognitionNet");
+var Mtcnn_1 = require("./mtcnn/Mtcnn");
 exports.detectionNet = new FaceDetectionNet_1.FaceDetectionNet();
 exports.landmarkNet = new FaceLandmarkNet_1.FaceLandmarkNet();
 exports.recognitionNet = new FaceRecognitionNet_1.FaceRecognitionNet();
+// nets need more specific names, to avoid ambiguity in future
+// when alternative net implementations are provided
+exports.nets = {
+    ssdMobilenet: exports.detectionNet,
+    faceLandmark68Net: exports.landmarkNet,
+    faceNet: exports.recognitionNet,
+    mtcnn: new Mtcnn_1.Mtcnn()
+};
 function loadFaceDetectionModel(url) {
-    return exports.detectionNet.load(url);
+    return exports.nets.ssdMobilenet.load(url);
 }
 exports.loadFaceDetectionModel = loadFaceDetectionModel;
 function loadFaceLandmarkModel(url) {
-    return exports.landmarkNet.load(url);
+    return exports.nets.faceLandmark68Net.load(url);
 }
 exports.loadFaceLandmarkModel = loadFaceLandmarkModel;
 function loadFaceRecognitionModel(url) {
-    return exports.recognitionNet.load(url);
+    return exports.nets.faceNet.load(url);
 }
 exports.loadFaceRecognitionModel = loadFaceRecognitionModel;
+function loadMtcnnModel(url) {
+    return exports.nets.mtcnn.load(url);
+}
+exports.loadMtcnnModel = loadMtcnnModel;
 function loadModels(url) {
     return Promise.all([
         loadFaceDetectionModel(url),
         loadFaceLandmarkModel(url),
-        loadFaceRecognitionModel(url)
+        loadFaceRecognitionModel(url),
+        loadMtcnnModel(url)
     ]);
 }
 exports.loadModels = loadModels;
 function locateFaces(input, minConfidence, maxResults) {
-    return exports.detectionNet.locateFaces(input, minConfidence, maxResults);
+    return exports.nets.ssdMobilenet.locateFaces(input, minConfidence, maxResults);
 }
 exports.locateFaces = locateFaces;
 function detectLandmarks(input) {
-    return exports.landmarkNet.detectLandmarks(input);
+    return exports.nets.faceLandmark68Net.detectLandmarks(input);
 }
 exports.detectLandmarks = detectLandmarks;
 function computeFaceDescriptor(input) {
-    return exports.recognitionNet.computeFaceDescriptor(input);
+    return exports.nets.faceNet.computeFaceDescriptor(input);
 }
 exports.computeFaceDescriptor = computeFaceDescriptor;
+function mtcnn(input, forwardParams) {
+    return exports.nets.mtcnn.forward(input, forwardParams);
+}
+exports.mtcnn = mtcnn;
 exports.allFaces = allFacesFactory_1.allFacesFactory(exports.detectionNet, exports.landmarkNet, exports.recognitionNet);
 //# sourceMappingURL=globalApi.js.map
\ No newline at end of file

build/globalApi.js.map

-{"version":3,"file":"globalApi.js","sourceRoot":"","sources":["../src/globalApi.ts"],"names":[],"mappings":";;AAEA,qDAAoD;AAEpD,wEAAuE;AACvE,qEAAoE;AAEpE,8EAA6E;AAKhE,QAAA,YAAY,GAAG,IAAI,mCAAgB,EAAE,CAAA;AACrC,QAAA,WAAW,GAAG,IAAI,iCAAe,EAAE,CAAA;AACnC,QAAA,cAAc,GAAG,IAAI,uCAAkB,EAAE,CAAA;AAEtD,gCAAuC,GAAW;IAChD,OAAO,oBAAY,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AAC/B,CAAC;AAFD,wDAEC;AAED,+BAAsC,GAAW;IAC/C,OAAO,mBAAW,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AAC9B,CAAC;AAFD,sDAEC;AAED,kCAAyC,GAAW;IAClD,OAAO,sBAAc,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AACjC,CAAC;AAFD,4DAEC;AAED,oBAA2B,GAAW;IACpC,OAAO,OAAO,CAAC,GAAG,CAAC;QACjB,sBAAsB,CAAC,GAAG,CAAC;QAC3B,qBAAqB,CAAC,GAAG,CAAC;QAC1B,wBAAwB,CAAC,GAAG,CAAC;KAC9B,CAAC,CAAA;AACJ,CAAC;AAND,gCAMC;AAED,qBACE,KAAgB,EAChB,aAAsB,EACtB,UAAmB;IAEnB,OAAO,oBAAY,CAAC,WAAW,CAAC,KAAK,EAAE,aAAa,EAAE,UAAU,CAAC,CAAA;AACnE,CAAC;AAND,kCAMC;AAED,yBACE,KAAgB;IAEhB,OAAO,mBAAW,CAAC,eAAe,CAAC,KAAK,CAAC,CAAA;AAC3C,CAAC;AAJD,0CAIC;AAED,+BACE,KAAgB;IAEhB,OAAO,sBAAc,CAAC,qBAAqB,CAAC,KAAK,CAAC,CAAA;AACpD,CAAC;AAJD,sDAIC;AAEY,QAAA,QAAQ,GAIiB,iCAAe,CACnD,oBAAY,EACZ,mBAAW,EACX,sBAAc,CACf,CAAA"}
\ No newline at end of file
+{"version":3,"file":"globalApi.js","sourceRoot":"","sources":["../src/globalApi.ts"],"names":[],"mappings":";;AAEA,qDAAoD;AAEpD,wEAAuE;AACvE,qEAAoE;AAEpE,8EAA6E;AAG7E,uCAAsC;AAKzB,QAAA,YAAY,GAAG,IAAI,mCAAgB,EAAE,CAAA;AACrC,QAAA,WAAW,GAAG,IAAI,iCAAe,EAAE,CAAA;AACnC,QAAA,cAAc,GAAG,IAAI,uCAAkB,EAAE,CAAA;AAEtD,8DAA8D;AAC9D,oDAAoD;AACvC,QAAA,IAAI,GAAG;IAClB,YAAY,EAAE,oBAAY;IAC1B,iBAAiB,EAAE,mBAAW;IAC9B,OAAO,EAAE,sBAAc;IACvB,KAAK,EAAE,IAAI,aAAK,EAAE;CACnB,CAAA;AAED,gCAAuC,GAAW;IAChD,OAAO,YAAI,CAAC,YAAY,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AACpC,CAAC;AAFD,wDAEC;AAED,+BAAsC,GAAW;IAC/C,OAAO,YAAI,CAAC,iBAAiB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AACzC,CAAC;AAFD,sDAEC;AAED,kCAAyC,GAAW;IAClD,OAAO,YAAI,CAAC,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AAC/B,CAAC;AAFD,4DAEC;AAED,wBAA+B,GAAW;IACxC,OAAO,YAAI,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AAC7B,CAAC;AAFD,wCAEC;AAED,oBAA2B,GAAW;IACpC,OAAO,OAAO,CAAC,GAAG,CAAC;QACjB,sBAAsB,CAAC,GAAG,CAAC;QAC3B,qBAAqB,CAAC,GAAG,CAAC;QAC1B,wBAAwB,CAAC,GAAG,CAAC;QAC7B,cAAc,CAAC,GAAG,CAAC;KACpB,CAAC,CAAA;AACJ,CAAC;AAPD,gCAOC;AAED,qBACE,KAAgB,EAChB,aAAsB,EACtB,UAAmB;IAEnB,OAAO,YAAI,CAAC,YAAY,CAAC,WAAW,CAAC,KAAK,EAAE,aAAa,EAAE,UAAU,CAAC,CAAA;AACxE,CAAC;AAND,kCAMC;AAED,yBACE,KAAgB;IAEhB,OAAO,YAAI,CAAC,iBAAiB,CAAC,eAAe,CAAC,KAAK,CAAC,CAAA;AACtD,CAAC;AAJD,0CAIC;AAED,+BACE,KAAgB;IAEhB,OAAO,YAAI,CAAC,OAAO,CAAC,qBAAqB,CAAC,KAAK,CAAC,CAAA;AAClD,CAAC;AAJD,sDAIC;AAED,eACE,KAAgB,EAChB,aAAiC;IAEjC,OAAO,YAAI,CAAC,KAAK,CAAC,OAAO,CAAC,KAAK,EAAE,aAAa,CAAC,CAAA;AACjD,CAAC;AALD,sBAKC;AAEY,QAAA,QAAQ,GAIiB,iCAAe,CACnD,oBAAY,EACZ,mBAAW,EACX,sBAAc,CACf,CAAA"}
\ No newline at end of file

build/index.d.ts

 import * as tf from '@tensorflow/tfjs-core';
 export { tf };
+export * from './FaceDetection';
 export * from './FullFaceDescription';
 export * from './NetInput';
 export * from './Point';
@@ -12,6 +13,7 @@ export * from './faceDetectionNet';
 export * from './faceLandmarkNet';
 export * from './faceRecognitionNet';
 export * from './globalApi';
+export * from './mtcnn';
 export * from './padToSquare';
 export * from './toNetInput';
 export * from './utils';

build/index.js

@@ -3,6 +3,7 @@ Object.defineProperty(exports, "__esModule", { value: true });
 var tslib_1 = require("tslib");
 var tf = require("@tensorflow/tfjs-core");
 exports.tf = tf;
+tslib_1.__exportStar(require("./FaceDetection"), exports);
 tslib_1.__exportStar(require("./FullFaceDescription"), exports);
 tslib_1.__exportStar(require("./NetInput"), exports);
 tslib_1.__exportStar(require("./Point"), exports);
@@ -15,6 +16,7 @@ tslib_1.__exportStar(require("./faceDetectionNet"), exports);
 tslib_1.__exportStar(require("./faceLandmarkNet"), exports);
 tslib_1.__exportStar(require("./faceRecognitionNet"), exports);
 tslib_1.__exportStar(require("./globalApi"), exports);
+tslib_1.__exportStar(require("./mtcnn"), exports);
 tslib_1.__exportStar(require("./padToSquare"), exports);
 tslib_1.__exportStar(require("./toNetInput"), exports);
 tslib_1.__exportStar(require("./utils"), exports);

build/index.js.map

-{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAG1C,gBAAE;AAGJ,gEAAsC;AACtC,qDAA2B;AAC3B,kDAAwB;AACxB,iDAAuB;AAEvB,oDAA0B;AAC1B,8DAAoC;AACpC,yDAA8B;AAC9B,+DAAoC;AACpC,6DAAmC;AACnC,4DAAkC;AAClC,+DAAqC;AACrC,sDAA4B;AAC5B,wDAA8B;AAC9B,uDAA6B;AAC7B,kDAAuB"}
\ No newline at end of file
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAG1C,gBAAE;AAIJ,0DAAgC;AAChC,gEAAsC;AACtC,qDAA2B;AAC3B,kDAAwB;AACxB,iDAAuB;AAEvB,oDAA0B;AAC1B,8DAAoC;AACpC,yDAA8B;AAC9B,+DAAoC;AACpC,6DAAmC;AACnC,4DAAkC;AAClC,+DAAqC;AACrC,sDAA4B;AAC5B,kDAAwB;AACxB,wDAA8B;AAC9B,uDAA6B;AAC7B,kDAAuB"}
\ No newline at end of file

build/mtcnn/BoundingBox.d.ts

+export declare class BoundingBox {
+    private _left;
+    private _top;
+    private _right;
+    private _bottom;
+    constructor(_left: number, _top: number, _right: number, _bottom: number);
+    readonly left: number;
+    readonly top: number;
+    readonly right: number;
+    readonly bottom: number;
+    readonly width: number;
+    readonly height: number;
+    toSquare(): BoundingBox;
+    round(): BoundingBox;
+    padAtBorders(imageHeight: number, imageWidth: number): {
+        dy: number;
+        edy: number;
+        dx: number;
+        edx: number;
+        y: number;
+        ey: number;
+        x: number;
+        ex: number;
+        w: number;
+        h: number;
+    };
+    calibrate(region: BoundingBox): BoundingBox;
+}

build/mtcnn/BoundingBox.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var BoundingBox = /** @class */ (function () {
+    function BoundingBox(_left, _top, _right, _bottom) {
+        this._left = _left;
+        this._top = _top;
+        this._right = _right;
+        this._bottom = _bottom;
+    }
+    Object.defineProperty(BoundingBox.prototype, "left", {
+        get: function () {
+            return this._left;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(BoundingBox.prototype, "top", {
+        get: function () {
+            return this._top;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(BoundingBox.prototype, "right", {
+        get: function () {
+            return this._right;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(BoundingBox.prototype, "bottom", {
+        get: function () {
+            return this._bottom;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(BoundingBox.prototype, "width", {
+        get: function () {
+            return this.right - this.left;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    Object.defineProperty(BoundingBox.prototype, "height", {
+        get: function () {
+            return this.bottom - this.top;
+        },
+        enumerable: true,
+        configurable: true
+    });
+    BoundingBox.prototype.toSquare = function () {
+        var _a = this, left = _a.left, top = _a.top, right = _a.right, bottom = _a.bottom;
+        var off = (Math.abs(this.width - this.height) / 2);
+        if (this.width < this.height) {
+            left -= off;
+            right += off;
+        }
+        if (this.height < this.width) {
+            top -= off;
+            bottom += off;
+        }
+        return new BoundingBox(left, top, right, bottom);
+    };
+    BoundingBox.prototype.round = function () {
+        return new BoundingBox(Math.round(this.left), Math.round(this.top), Math.round(this.right), Math.round(this.bottom));
+    };
+    BoundingBox.prototype.padAtBorders = function (imageHeight, imageWidth) {
+        var w = this.width + 1;
+        var h = this.height + 1;
+        var dx = 1;
+        var dy = 1;
+        var edx = w;
+        var edy = h;
+        var x = this.left;
+        var y = this.top;
+        var ex = this.right;
+        var ey = this.bottom;
+        if (ex > imageWidth) {
+            edx = -ex + imageWidth + w;
+            ex = imageWidth;
+        }
+        if (ey > imageHeight) {
+            edy = -ey + imageHeight + h;
+            ey = imageHeight;
+        }
+        if (x < 1) {
+            edy = 2 - x;
+            x = 1;
+        }
+        if (y < 1) {
+            edy = 2 - y;
+            y = 1;
+        }
+        return { dy: dy, edy: edy, dx: dx, edx: edx, y: y, ey: ey, x: x, ex: ex, w: w, h: h };
+    };
+    BoundingBox.prototype.calibrate = function (region) {
+        return new BoundingBox(this.left + (region.left * this.width), this.top + (region.top * this.height), this.right + (region.right * this.width), this.bottom + (region.bottom * this.height)).toSquare().round();
+    };
+    return BoundingBox;
+}());
+exports.BoundingBox = BoundingBox;
+//# sourceMappingURL=BoundingBox.js.map
\ No newline at end of file

build/mtcnn/BoundingBox.js.map

+{"version":3,"file":"BoundingBox.js","sourceRoot":"","sources":["../../src/mtcnn/BoundingBox.ts"],"names":[],"mappings":";;AAAA;IACE,qBACU,KAAa,EACb,IAAY,EACZ,MAAc,EACd,OAAe;QAHf,UAAK,GAAL,KAAK,CAAQ;QACb,SAAI,GAAJ,IAAI,CAAQ;QACZ,WAAM,GAAN,MAAM,CAAQ;QACd,YAAO,GAAP,OAAO,CAAQ;IACtB,CAAC;IAGJ,sBAAW,6BAAI;aAAf;YACE,OAAO,IAAI,CAAC,KAAK,CAAA;QACnB,CAAC;;;OAAA;IAED,sBAAW,4BAAG;aAAd;YACE,OAAO,IAAI,CAAC,IAAI,CAAA;QAClB,CAAC;;;OAAA;IAED,sBAAW,8BAAK;aAAhB;YACE,OAAO,IAAI,CAAC,MAAM,CAAA;QACpB,CAAC;;;OAAA;IAED,sBAAW,+BAAM;aAAjB;YACE,OAAO,IAAI,CAAC,OAAO,CAAA;QACrB,CAAC;;;OAAA;IAED,sBAAW,8BAAK;aAAhB;YACE,OAAO,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,IAAI,CAAA;QAC/B,CAAC;;;OAAA;IAED,sBAAW,+BAAM;aAAjB;YACE,OAAO,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,GAAG,CAAA;QAC/B,CAAC;;;OAAA;IAGM,8BAAQ,GAAf;QACM,IAAA,SAAmC,EAAjC,cAAI,EAAE,YAAG,EAAE,gBAAK,EAAE,kBAAM,CAAS;QAEvC,IAAM,GAAG,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;QACpD,IAAI,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,MAAM,EAAE;YAC5B,IAAI,IAAI,GAAG,CAAA;YACX,KAAK,IAAI,GAAG,CAAA;SACb;QACD,IAAI,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,KAAK,EAAE;YAC5B,GAAG,IAAI,GAAG,CAAA;YACV,MAAM,IAAI,GAAG,CAAA;SACd;QACD,OAAO,IAAI,WAAW,CAAC,IAAI,EAAE,GAAG,EAAE,KAAK,EAAE,MAAM,CAAC,CAAA;IAClD,CAAC;IAEM,2BAAK,GAAZ;QACE,OAAO,IAAI,WAAW,CACpB,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EACrB,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,EACpB,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,EACtB,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,CACxB,CAAA;IACH,CAAC;IAEM,kCAAY,GAAnB,UAAoB,WAAmB,EAAE,UAAkB;QACzD,IAAM,CAAC,GAAG,IAAI,CAAC,KAAK,GAAG,CAAC,CAAA;QACxB,IAAM,CAAC,GAAG,IAAI,CAAC,MAAM,GAAG,CAAC,CAAA;QAEzB,IAAI,EAAE,GAAG,CAAC,CAAA;QACV,IAAI,EAAE,GAAG,CAAC,CAAA;QACV,IAAI,GAAG,GAAG,CAAC,CAAA;QACX,IAAI,GAAG,GAAG,CAAC,CAAA;QAEX,IAAI,CAAC,GAAG,IAAI,CAAC,IAAI,CAAA;QACjB,IAAI,CAAC,GAAG,IAAI,CAAC,GAAG,CAAA;QAChB,IAAI,EAAE,GAAG,IAAI,CAAC,KAAK,CAAA;QACnB,IAAI,EAAE,GAAG,IAAI,CAAC,MAAM,CAAA;QAEpB,IAAI,EAAE,GAAG,UAAU,EAAE;YACnB,GAAG,GAAG,CAAC,EAAE,GAAG,UAAU,GAAG,CAAC,CAAA;YAC1B,EAAE,GAAG,UAAU,CAAA;SAChB;QACD,IAAI,EAAE,GAAG,WAAW,EAAE;YACpB,GAAG,GAAG,CAAC,EAAE,GAAG,WAAW,GAAG,CAAC,CAAA;YAC3B,EAAE,GAAG,WAAW,CAAA;SACjB;QACD,IAAI,CAAC,GAAG,CAAC,EAAE;YACT,GAAG,GAAG,CAAC,GAAG,CAAC,CAAA;YACX,CAAC,GAAG,CAAC,CAAA;SACN;QACD,IAAI,CAAC,GAAG,CAAC,EAAE;YACT,GAAG,GAAG,CAAC,GAAG,CAAC,CAAA;YACX,CAAC,GAAG,CAAC,CAAA;SACN;QAED,OAAO,EAAE,EAAE,IAAA,EAAE,GAAG,KAAA,EAAE,EAAE,IAAA,EAAE,GAAG,KAAA,EAAE,CAAC,GAAA,EAAE,EAAE,IAAA,EAAE,CAAC,GAAA,EAAE,EAAE,IAAA,EAAE,CAAC,GAAA,EAAE,CAAC,GAAA,EAAE,CAAA;IACjD,CAAC;IAEM,+BAAS,GAAhB,UAAiB,MAAmB;QAClC,OAAO,IAAI,WAAW,CACpB,IAAI,CAAC,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,EACtC,IAAI,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,GAAG,IAAI,CAAC,MAAM,CAAC,EACrC,IAAI,CAAC,KAAK,GAAG,CAAC,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,EACxC,IAAI,CAAC,MAAM,GAAG,CAAC,MAAM,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC,CAC5C,CAAC,QAAQ,EAAE,CAAC,KAAK,EAAE,CAAA;IACtB,CAAC;IACH,kBAAC;AAAD,CAAC,AApGD,IAoGC;AApGY,kCAAW"}
\ No newline at end of file

build/mtcnn/FaceLandmarks5.d.ts

+import { FaceLandmarks } from '../FaceLandmarks';
+import { IPoint } from '../Point';
+export declare class FaceLandmarks5 extends FaceLandmarks {
+    forSize(width: number, height: number): FaceLandmarks5;
+    shift(x: number, y: number): FaceLandmarks5;
+    shiftByPoint(pt: IPoint): FaceLandmarks5;
+}

build/mtcnn/FaceLandmarks5.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var FaceLandmarks_1 = require("../FaceLandmarks");
+var Point_1 = require("../Point");
+var FaceLandmarks5 = /** @class */ (function (_super) {
+    tslib_1.__extends(FaceLandmarks5, _super);
+    function FaceLandmarks5() {
+        return _super !== null && _super.apply(this, arguments) || this;
+    }
+    FaceLandmarks5.prototype.forSize = function (width, height) {
+        return new FaceLandmarks5(this.getRelativePositions(), { width: width, height: height });
+    };
+    FaceLandmarks5.prototype.shift = function (x, y) {
+        return new FaceLandmarks5(this.getRelativePositions(), { width: this._imageWidth, height: this._imageHeight }, new Point_1.Point(x, y));
+    };
+    FaceLandmarks5.prototype.shiftByPoint = function (pt) {
+        return this.shift(pt.x, pt.y);
+    };
+    return FaceLandmarks5;
+}(FaceLandmarks_1.FaceLandmarks));
+exports.FaceLandmarks5 = FaceLandmarks5;
+//# sourceMappingURL=FaceLandmarks5.js.map
\ No newline at end of file

build/mtcnn/FaceLandmarks5.js.map

+{"version":3,"file":"FaceLandmarks5.js","sourceRoot":"","sources":["../../src/mtcnn/FaceLandmarks5.ts"],"names":[],"mappings":";;;AAAA,kDAAiD;AACjD,kCAAyC;AAEzC;IAAoC,0CAAa;IAAjD;;IAoBA,CAAC;IAlBQ,gCAAO,GAAd,UAAe,KAAa,EAAE,MAAc;QAC1C,OAAO,IAAI,cAAc,CACvB,IAAI,CAAC,oBAAoB,EAAE,EAC3B,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAE,CAClB,CAAA;IACH,CAAC;IAEM,8BAAK,GAAZ,UAAa,CAAS,EAAE,CAAS;QAC/B,OAAO,IAAI,cAAc,CACvB,IAAI,CAAC,oBAAoB,EAAE,EAC3B,EAAE,KAAK,EAAE,IAAI,CAAC,WAAW,EAAE,MAAM,EAAE,IAAI,CAAC,YAAY,EAAE,EACtD,IAAI,aAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAChB,CAAA;IACH,CAAC;IAEM,qCAAY,GAAnB,UAAoB,EAAU;QAC5B,OAAO,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAA;IAC/B,CAAC;IACH,qBAAC;AAAD,CAAC,AApBD,CAAoC,6BAAa,GAoBhD;AApBY,wCAAc"}
\ No newline at end of file

build/mtcnn/Mtcnn.d.ts

+import { NeuralNetwork } from '../commons/NeuralNetwork';
+import { NetInput } from '../NetInput';
+import { TNetInput } from '../types';
+import { MtcnnForwardParams, MtcnnResult, NetParams } from './types';
+export declare class Mtcnn extends NeuralNetwork<NetParams> {
+    constructor();
+    forwardInput(input: NetInput, forwardParams: MtcnnForwardParams): Promise<{
+        results: MtcnnResult[];
+        stats: any;
+    }>;
+    forward(input: TNetInput, forwardParams: MtcnnForwardParams): Promise<MtcnnResult[]>;
+    forwardWithStats(input: TNetInput, forwardParams: MtcnnForwardParams): Promise<{
+        results: MtcnnResult[];
+        stats: any;
+    }>;
+    protected loadQuantizedParams(uri: string | undefined): Promise<{
+        params: NetParams;
+        paramMappings: {
+            originalPath?: string | undefined;
+            paramPath: string;
+        }[];
+    }>;
+    protected extractParams(weights: Float32Array): {
+        params: NetParams;
+        paramMappings: {
+            originalPath?: string | undefined;
+            paramPath: string;
+        }[];
+    };
+}

build/mtcnn/Mtcnn.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var tf = require("@tensorflow/tfjs-core");
+var NeuralNetwork_1 = require("../commons/NeuralNetwork");
+var FaceDetection_1 = require("../FaceDetection");
+var Point_1 = require("../Point");
+var Rect_1 = require("../Rect");
+var toNetInput_1 = require("../toNetInput");
+var bgrToRgbTensor_1 = require("./bgrToRgbTensor");
+var config_1 = require("./config");
+var extractParams_1 = require("./extractParams");
+var FaceLandmarks5_1 = require("./FaceLandmarks5");
+var getDefaultMtcnnForwardParams_1 = require("./getDefaultMtcnnForwardParams");
+var getSizesForScale_1 = require("./getSizesForScale");
+var loadQuantizedParams_1 = require("./loadQuantizedParams");
+var pyramidDown_1 = require("./pyramidDown");
+var stage1_1 = require("./stage1");
+var stage2_1 = require("./stage2");
+var stage3_1 = require("./stage3");
+var Mtcnn = /** @class */ (function (_super) {
+    tslib_1.__extends(Mtcnn, _super);
+    function Mtcnn() {
+        return _super.call(this, 'Mtcnn') || this;
+    }
+    Mtcnn.prototype.forwardInput = function (input, forwardParams) {
+        return tslib_1.__awaiter(this, void 0, void 0, function () {
+            var params, inputTensor, inputCanvas, stats, tsTotal, imgTensor, onReturn, _a, height, width, _b, minFaceSize, scaleFactor, maxNumScales, scoreThresholds, scaleSteps, scales, ts, out1, out2, out3, results;
+            return tslib_1.__generator(this, function (_c) {
+                switch (_c.label) {
+                    case 0:
+                        params = this.params;
+                        if (!params) {
+                            throw new Error('Mtcnn - load model before inference');
+                        }
+                        inputTensor = input.inputs[0];
+                        inputCanvas = input.canvases[0];
+                        if (!inputCanvas) {
+                            throw new Error('Mtcnn - inputCanvas is not defined, note that passing tensors into Mtcnn.forwardInput is not supported yet.');
+                        }
+                        stats = {};
+                        tsTotal = Date.now();
+                        imgTensor = tf.tidy(function () {
+                            return bgrToRgbTensor_1.bgrToRgbTensor(tf.expandDims(inputTensor).toFloat());
+                        });
+                        onReturn = function (results) {
+                            // dispose tensors on return
+                            imgTensor.dispose();
+                            input.dispose();
+                            stats.total = Date.now() - tsTotal;
+                            return results;
+                        };
+                        _a = imgTensor.shape.slice(1), height = _a[0], width = _a[1];
+                        _b = Object.assign({}, getDefaultMtcnnForwardParams_1.getDefaultMtcnnForwardParams(), forwardParams), minFaceSize = _b.minFaceSize, scaleFactor = _b.scaleFactor, maxNumScales = _b.maxNumScales, scoreThresholds = _b.scoreThresholds, scaleSteps = _b.scaleSteps;
+                        scales = (scaleSteps || pyramidDown_1.pyramidDown(minFaceSize, scaleFactor, [height, width]))
+                            .filter(function (scale) {
+                            var sizes = getSizesForScale_1.getSizesForScale(scale, [height, width]);
+                            return Math.min(sizes.width, sizes.height) > config_1.CELL_SIZE;
+                        })
+                            .slice(0, maxNumScales);
+                        stats.scales = scales;
+                        stats.pyramid = scales.map(function (scale) { return getSizesForScale_1.getSizesForScale(scale, [height, width]); });
+                        ts = Date.now();
+                        return [4 /*yield*/, stage1_1.stage1(imgTensor, scales, scoreThresholds[0], params.pnet, stats)];
+                    case 1:
+                        out1 = _c.sent();
+                        stats.total_stage1 = Date.now() - ts;
+                        if (!out1.boxes.length) {
+                            return [2 /*return*/, onReturn({ results: [], stats: stats })];
+                        }
+                        stats.stage2_numInputBoxes = out1.boxes.length;
+                        // using the inputCanvas to extract and resize the image patches, since it is faster
+                        // than doing this on the gpu
+                        ts = Date.now();
+                        return [4 /*yield*/, stage2_1.stage2(inputCanvas, out1.boxes, scoreThresholds[1], params.rnet, stats)];
+                    case 2:
+                        out2 = _c.sent();
+                        stats.total_stage2 = Date.now() - ts;
+                        if (!out2.boxes.length) {
+                            return [2 /*return*/, onReturn({ results: [], stats: stats })];
+                        }
+                        stats.stage3_numInputBoxes = out2.boxes.length;
+                        ts = Date.now();
+                        return [4 /*yield*/, stage3_1.stage3(inputCanvas, out2.boxes, scoreThresholds[2], params.onet, stats)];
+                    case 3:
+                        out3 = _c.sent();
+                        stats.total_stage3 = Date.now() - ts;
+                        results = out3.boxes.map(function (box, idx) { return ({
+                            faceDetection: new FaceDetection_1.FaceDetection(out3.scores[idx], new Rect_1.Rect(box.left / width, box.top / height, box.width / width, box.height / height), {
+                                height: height,
+                                width: width
+                            }),
+                            faceLandmarks: new FaceLandmarks5_1.FaceLandmarks5(out3.points[idx].map(function (pt) { return pt.div(new Point_1.Point(width, height)); }), { width: width, height: height })
+                        }); });
+                        return [2 /*return*/, onReturn({ results: results, stats: stats })];
+                }
+            });
+        });
+    };
+    Mtcnn.prototype.forward = function (input, forwardParams) {
+        return tslib_1.__awaiter(this, void 0, void 0, function () {
+            var _a;
+            return tslib_1.__generator(this, function (_b) {
+                switch (_b.label) {
+                    case 0:
+                        _a = this.forwardInput;
+                        return [4 /*yield*/, toNetInput_1.toNetInput(input, true, true)];
+                    case 1: return [4 /*yield*/, _a.apply(this, [_b.sent(),
+                            forwardParams])];
+                    case 2: return [2 /*return*/, (_b.sent()).results];
+                }
+            });
+        });
+    };
+    Mtcnn.prototype.forwardWithStats = function (input, forwardParams) {
+        return tslib_1.__awaiter(this, void 0, void 0, function () {
+            var _a;
+            return tslib_1.__generator(this, function (_b) {
+                switch (_b.label) {
+                    case 0:
+                        _a = this.forwardInput;
+                        return [4 /*yield*/, toNetInput_1.toNetInput(input, true, true)];
+                    case 1: return [2 /*return*/, _a.apply(this, [_b.sent(),
+                            forwardParams])];
+                }
+            });
+        });
+    };
+    // none of the param tensors are quantized yet
+    Mtcnn.prototype.loadQuantizedParams = function (uri) {
+        return loadQuantizedParams_1.loadQuantizedParams(uri);
+    };
+    Mtcnn.prototype.extractParams = function (weights) {
+        return extractParams_1.extractParams(weights);
+    };
+    return Mtcnn;
+}(NeuralNetwork_1.NeuralNetwork));
+exports.Mtcnn = Mtcnn;
+//# sourceMappingURL=Mtcnn.js.map
\ No newline at end of file

build/mtcnn/Mtcnn.js.map

+{"version":3,"file":"Mtcnn.js","sourceRoot":"","sources":["../../src/mtcnn/Mtcnn.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,0DAAyD;AACzD,kDAAiD;AAEjD,kCAAiC;AACjC,gCAA+B;AAC/B,4CAA2C;AAE3C,mDAAkD;AAClD,mCAAqC;AACrC,iDAAgD;AAChD,mDAAkD;AAClD,+EAA8E;AAC9E,uDAAsD;AACtD,6DAA4D;AAC5D,6CAA4C;AAC5C,mCAAkC;AAClC,mCAAkC;AAClC,mCAAkC;AAGlC;IAA2B,iCAAwB;IAEjD;eACE,kBAAM,OAAO,CAAC;IAChB,CAAC;IAEY,4BAAY,GAAzB,UACE,KAAe,EACf,aAAiC;;;;;;wBAGzB,MAAM,GAAK,IAAI,OAAT,CAAS;wBAEvB,IAAI,CAAC,MAAM,EAAE;4BACX,MAAM,IAAI,KAAK,CAAC,qCAAqC,CAAC,CAAA;yBACvD;wBAEK,WAAW,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAA;wBAC7B,WAAW,GAAG,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAA;wBAErC,IAAI,CAAC,WAAW,EAAE;4BAChB,MAAM,IAAI,KAAK,CAAC,6GAA6G,CAAC,CAAA;yBAC/H;wBAEK,KAAK,GAAQ,EAAE,CAAA;wBAEf,OAAO,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBAEpB,SAAS,GAAG,EAAE,CAAC,IAAI,CAAC;4BACxB,OAAA,+BAAc,CACZ,EAAE,CAAC,UAAU,CAAC,WAAW,CAAC,CAAC,OAAO,EAAiB,CACpD;wBAFD,CAEC,CACF,CAAA;wBAEK,QAAQ,GAAG,UAAC,OAAY;4BAC5B,4BAA4B;4BAC5B,SAAS,CAAC,OAAO,EAAE,CAAA;4BACnB,KAAK,CAAC,OAAO,EAAE,CAAA;4BACf,KAAK,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,OAAO,CAAA;4BAClC,OAAO,OAAO,CAAA;wBAChB,CAAC,CAAA;wBAEK,KAAkB,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,EAAzC,MAAM,QAAA,EAAE,KAAK,QAAA,CAA4B;wBAE1C,KAMF,MAAM,CAAC,MAAM,CAAC,EAAE,EAAE,2DAA4B,EAAE,EAAE,aAAa,CAAC,EALlE,WAAW,iBAAA,EACX,WAAW,iBAAA,EACX,YAAY,kBAAA,EACZ,eAAe,qBAAA,EACf,UAAU,gBAAA,CACwD;wBAE9D,MAAM,GAAG,CAAC,UAAU,IAAI,yBAAW,CAAC,WAAW,EAAE,WAAW,EAAE,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,CAAC;6BAClF,MAAM,CAAC,UAAA,KAAK;4BACX,IAAM,KAAK,GAAG,mCAAgB,CAAC,KAAK,EAAE,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,CAAA;4BACtD,OAAO,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,MAAM,CAAC,GAAG,kBAAS,CAAA;wBACxD,CAAC,CAAC;6BACD,KAAK,CAAC,CAAC,EAAE,YAAY,CAAC,CAAA;wBAEzB,KAAK,CAAC,MAAM,GAAG,MAAM,CAAA;wBACrB,KAAK,CAAC,OAAO,GAAG,MAAM,CAAC,GAAG,CAAC,UAAA,KAAK,IAAI,OAAA,mCAAgB,CAAC,KAAK,EAAE,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,EAAxC,CAAwC,CAAC,CAAA;wBAEzE,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBACN,qBAAM,eAAM,CAAC,SAAS,EAAE,MAAM,EAAE,eAAe,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,EAAA;;wBAA9E,IAAI,GAAG,SAAuE;wBACpF,KAAK,CAAC,YAAY,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;wBAEpC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE;4BACtB,sBAAO,QAAQ,CAAC,EAAE,OAAO,EAAE,EAAE,EAAE,KAAK,OAAA,EAAE,CAAC,EAAA;yBACxC;wBAED,KAAK,CAAC,oBAAoB,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,CAAA;wBAC9C,oFAAoF;wBACpF,6BAA6B;wBAC7B,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBACF,qBAAM,eAAM,CAAC,WAAW,EAAE,IAAI,CAAC,KAAK,EAAE,eAAe,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,EAAA;;wBAApF,IAAI,GAAG,SAA6E;wBAC1F,KAAK,CAAC,YAAY,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;wBAEpC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE;4BACtB,sBAAO,QAAQ,CAAC,EAAE,OAAO,EAAE,EAAE,EAAE,KAAK,OAAA,EAAE,CAAC,EAAA;yBACxC;wBAED,KAAK,CAAC,oBAAoB,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,CAAA;wBAE9C,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBACF,qBAAM,eAAM,CAAC,WAAW,EAAE,IAAI,CAAC,KAAK,EAAE,eAAe,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,EAAA;;wBAApF,IAAI,GAAG,SAA6E;wBAC1F,KAAK,CAAC,YAAY,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;wBAE9B,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,UAAC,GAAG,EAAE,GAAG,IAAK,OAAA,CAAC;4BAC5C,aAAa,EAAE,IAAI,6BAAa,CAC9B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAChB,IAAI,WAAI,CACN,GAAG,CAAC,IAAI,GAAG,KAAK,EAChB,GAAG,CAAC,GAAG,GAAG,MAAM,EAChB,GAAG,CAAC,KAAK,GAAG,KAAK,EACjB,GAAG,CAAC,MAAM,GAAG,MAAM,CACpB,EACD;gCACE,MAAM,QAAA;gCACN,KAAK,OAAA;6BACN,CACF;4BACD,aAAa,EAAE,IAAI,+BAAc,CAC/B,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,UAAA,EAAE,IAAI,OAAA,EAAE,CAAC,GAAG,CAAC,IAAI,aAAK,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,EAAhC,CAAgC,CAAC,EAC5D,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAE,CAClB;yBACF,CAAC,EAlB2C,CAkB3C,CAAC,CAAA;wBAEH,sBAAO,QAAQ,CAAC,EAAE,OAAO,SAAA,EAAE,KAAK,OAAA,EAAE,CAAC,EAAA;;;;KACpC;IAEY,uBAAO,GAApB,UACE,KAAgB,EAChB,aAAiC;;;;;;wBAGzB,KAAA,IAAI,CAAC,YAAY,CAAA;wBACrB,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,EAAA;4BADrC,qBAAM,SAAA,IAAI,GACR,SAAmC;4BACnC,aAAa,EACd,EAAA;4BAJH,sBAAO,CACL,SAGC,CACF,CAAC,OAAO,EAAA;;;;KACV;IAEY,gCAAgB,GAA7B,UACE,KAAgB,EAChB,aAAiC;;;;;;wBAE1B,KAAA,IAAI,CAAC,YAAY,CAAA;wBACtB,qBAAM,uBAAU,CAAC,KAAK,EAAE,IAAI,EAAE,IAAI,CAAC,EAAA;4BADrC,sBAAO,SAAA,IAAI,GACT,SAAmC;4BACnC,aAAa,EACd,EAAA;;;;KACF;IAED,8CAA8C;IACpC,mCAAmB,GAA7B,UAA8B,GAAuB;QACnD,OAAO,yCAAmB,CAAC,GAAG,CAAC,CAAA;IACjC,CAAC;IAES,6BAAa,GAAvB,UAAwB,OAAqB;QAC3C,OAAO,6BAAa,CAAC,OAAO,CAAC,CAAA;IAC/B,CAAC;IACH,YAAC;AAAD,CAAC,AA5ID,CAA2B,6BAAa,GA4IvC;AA5IY,sBAAK"}
\ No newline at end of file

build/mtcnn/ONet.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { ONetParams } from './types';
+export declare function ONet(x: tf.Tensor4D, params: ONetParams): {
+    scores: tf.Tensor1D;
+    regions: tf.Tensor2D;
+    points: tf.Tensor2D;
+};

build/mtcnn/ONet.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+var convLayer_1 = require("../commons/convLayer");
+var fullyConnectedLayer_1 = require("../faceLandmarkNet/fullyConnectedLayer");
+var prelu_1 = require("./prelu");
+var sharedLayers_1 = require("./sharedLayers");
+function ONet(x, params) {
+    return tf.tidy(function () {
+        var out = sharedLayers_1.sharedLayer(x, params);
+        out = tf.maxPool(out, [2, 2], [2, 2], 'same');
+        out = convLayer_1.convLayer(out, params.conv4, 'valid');
+        out = prelu_1.prelu(out, params.prelu4_alpha);
+        var vectorized = tf.reshape(out, [out.shape[0], params.fc1.weights.shape[0]]);
+        var fc1 = fullyConnectedLayer_1.fullyConnectedLayer(vectorized, params.fc1);
+        var prelu5 = prelu_1.prelu(fc1, params.prelu5_alpha);
+        var fc2_1 = fullyConnectedLayer_1.fullyConnectedLayer(prelu5, params.fc2_1);
+        var max = tf.expandDims(tf.max(fc2_1, 1), 1);
+        var prob = tf.softmax(tf.sub(fc2_1, max), 1);
+        var regions = fullyConnectedLayer_1.fullyConnectedLayer(prelu5, params.fc2_2);
+        var points = fullyConnectedLayer_1.fullyConnectedLayer(prelu5, params.fc2_3);
+        var scores = tf.unstack(prob, 1)[1];
+        return { scores: scores, regions: regions, points: points };
+    });
+}
+exports.ONet = ONet;
+//# sourceMappingURL=ONet.js.map
\ No newline at end of file

build/mtcnn/ONet.js.map

+{"version":3,"file":"ONet.js","sourceRoot":"","sources":["../../src/mtcnn/ONet.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,kDAAiD;AACjD,8EAA6E;AAC7E,iCAAgC;AAChC,+CAA6C;AAG7C,cAAqB,CAAc,EAAE,MAAkB;IACrD,OAAO,EAAE,CAAC,IAAI,CAAC;QAEb,IAAI,GAAG,GAAG,0BAAW,CAAC,CAAC,EAAE,MAAM,CAAC,CAAA;QAChC,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,MAAM,CAAC,CAAA;QAC7C,GAAG,GAAG,qBAAS,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC3C,GAAG,GAAG,aAAK,CAAc,GAAG,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAElD,IAAM,UAAU,GAAG,EAAE,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAgB,CAAA;QAC9F,IAAM,GAAG,GAAG,yCAAmB,CAAC,UAAU,EAAE,MAAM,CAAC,GAAG,CAAC,CAAA;QACvD,IAAM,MAAM,GAAG,aAAK,CAAc,GAAG,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAC3D,IAAM,KAAK,GAAG,yCAAmB,CAAC,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;QACvD,IAAM,GAAG,GAAG,EAAE,CAAC,UAAU,CAAC,EAAE,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA;QAE9C,IAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CAAC,EAAE,CAAC,GAAG,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,CAAC,CAAgB,CAAA;QAC7D,IAAM,OAAO,GAAG,yCAAmB,CAAC,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;QACzD,IAAM,MAAM,GAAG,yCAAmB,CAAC,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;QAExD,IAAM,MAAM,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAgB,CAAA;QACpD,OAAO,EAAE,MAAM,QAAA,EAAE,OAAO,SAAA,EAAE,MAAM,QAAA,EAAE,CAAA;IACpC,CAAC,CAAC,CAAA;AACJ,CAAC;AArBD,oBAqBC"}
\ No newline at end of file

build/mtcnn/PNet.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { PNetParams } from './types';
+export declare function PNet(x: tf.Tensor4D, params: PNetParams): {
+    prob: tf.Tensor4D;
+    regions: tf.Tensor4D;
+};

build/mtcnn/PNet.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+var convLayer_1 = require("../commons/convLayer");
+var sharedLayers_1 = require("./sharedLayers");
+function PNet(x, params) {
+    return tf.tidy(function () {
+        var out = sharedLayers_1.sharedLayer(x, params, true);
+        var conv = convLayer_1.convLayer(out, params.conv4_1, 'valid');
+        var max = tf.expandDims(tf.max(conv, 3), 3);
+        var prob = tf.softmax(tf.sub(conv, max), 3);
+        var regions = convLayer_1.convLayer(out, params.conv4_2, 'valid');
+        return { prob: prob, regions: regions };
+    });
+}
+exports.PNet = PNet;
+//# sourceMappingURL=PNet.js.map
\ No newline at end of file

build/mtcnn/PNet.js.map

+{"version":3,"file":"PNet.js","sourceRoot":"","sources":["../../src/mtcnn/PNet.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,kDAAiD;AACjD,+CAA6C;AAG7C,cAAqB,CAAc,EAAE,MAAkB;IACrD,OAAO,EAAE,CAAC,IAAI,CAAC;QAEb,IAAI,GAAG,GAAG,0BAAW,CAAC,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,CAAA;QACtC,IAAM,IAAI,GAAG,qBAAS,CAAC,GAAG,EAAE,MAAM,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;QACpD,IAAM,GAAG,GAAG,EAAE,CAAC,UAAU,CAAC,EAAE,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA;QAC7C,IAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CAAC,EAAE,CAAC,GAAG,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,CAAC,CAAgB,CAAA;QAC5D,IAAM,OAAO,GAAG,qBAAS,CAAC,GAAG,EAAE,MAAM,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;QAEvD,OAAO,EAAE,IAAI,MAAA,EAAE,OAAO,SAAA,EAAE,CAAA;IAC1B,CAAC,CAAC,CAAA;AACJ,CAAC;AAXD,oBAWC"}
\ No newline at end of file

build/mtcnn/RNet.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { RNetParams } from './types';
+export declare function RNet(x: tf.Tensor4D, params: RNetParams): {
+    scores: tf.Tensor1D;
+    regions: tf.Tensor2D;
+};

build/mtcnn/RNet.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+var fullyConnectedLayer_1 = require("../faceLandmarkNet/fullyConnectedLayer");
+var prelu_1 = require("./prelu");
+var sharedLayers_1 = require("./sharedLayers");
+function RNet(x, params) {
+    return tf.tidy(function () {
+        var convOut = sharedLayers_1.sharedLayer(x, params);
+        var vectorized = tf.reshape(convOut, [convOut.shape[0], params.fc1.weights.shape[0]]);
+        var fc1 = fullyConnectedLayer_1.fullyConnectedLayer(vectorized, params.fc1);
+        var prelu4 = prelu_1.prelu(fc1, params.prelu4_alpha);
+        var fc2_1 = fullyConnectedLayer_1.fullyConnectedLayer(prelu4, params.fc2_1);
+        var max = tf.expandDims(tf.max(fc2_1, 1), 1);
+        var prob = tf.softmax(tf.sub(fc2_1, max), 1);
+        var regions = fullyConnectedLayer_1.fullyConnectedLayer(prelu4, params.fc2_2);
+        var scores = tf.unstack(prob, 1)[1];
+        return { scores: scores, regions: regions };
+    });
+}
+exports.RNet = RNet;
+//# sourceMappingURL=RNet.js.map
\ No newline at end of file

build/mtcnn/RNet.js.map

+{"version":3,"file":"RNet.js","sourceRoot":"","sources":["../../src/mtcnn/RNet.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,8EAA6E;AAC7E,iCAAgC;AAChC,+CAA6C;AAG7C,cAAqB,CAAc,EAAE,MAAkB;IACrD,OAAO,EAAE,CAAC,IAAI,CAAC;QAEb,IAAM,OAAO,GAAG,0BAAW,CAAC,CAAC,EAAE,MAAM,CAAC,CAAA;QACtC,IAAM,UAAU,GAAG,EAAE,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAgB,CAAA;QACtG,IAAM,GAAG,GAAG,yCAAmB,CAAC,UAAU,EAAE,MAAM,CAAC,GAAG,CAAC,CAAA;QACvD,IAAM,MAAM,GAAG,aAAK,CAAc,GAAG,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAC3D,IAAM,KAAK,GAAG,yCAAmB,CAAC,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;QACvD,IAAM,GAAG,GAAG,EAAE,CAAC,UAAU,CAAC,EAAE,CAAC,GAAG,CAAC,KAAK,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA;QAC9C,IAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CAAC,EAAE,CAAC,GAAG,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,CAAC,CAAgB,CAAA;QAC7D,IAAM,OAAO,GAAG,yCAAmB,CAAC,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;QAEzD,IAAM,MAAM,GAAG,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAgB,CAAA;QACpD,OAAO,EAAE,MAAM,QAAA,EAAE,OAAO,SAAA,EAAE,CAAA;IAC5B,CAAC,CAAC,CAAA;AACJ,CAAC;AAfD,oBAeC"}
\ No newline at end of file

build/mtcnn/bgrToRgbTensor.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+export declare function bgrToRgbTensor(tensor: tf.Tensor4D): tf.Tensor4D;

build/mtcnn/bgrToRgbTensor.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+function bgrToRgbTensor(tensor) {
+    return tf.tidy(function () { return tf.stack(tf.unstack(tensor, 3).reverse(), 3); });
+}
+exports.bgrToRgbTensor = bgrToRgbTensor;
+//# sourceMappingURL=bgrToRgbTensor.js.map
\ No newline at end of file

build/mtcnn/bgrToRgbTensor.js.map

+{"version":3,"file":"bgrToRgbTensor.js","sourceRoot":"","sources":["../../src/mtcnn/bgrToRgbTensor.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,wBAA+B,MAAmB;IAChD,OAAO,EAAE,CAAC,IAAI,CACZ,cAAM,OAAA,EAAE,CAAC,KAAK,CAAC,EAAE,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,EAA5C,CAA4C,CACpC,CAAA;AAClB,CAAC;AAJD,wCAIC"}
\ No newline at end of file

build/mtcnn/calculateScaleSteps.d.ts

+export declare function calculateScaleSteps(numScales: number, minFaceSize: number, dims: number[]): number[];

build/mtcnn/calculateScaleSteps.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+function calculateScaleSteps(numScales, minFaceSize, dims) {
+    var height = dims[0], width = dims[1];
+    var maxDim = Math.max(height, width);
+    if (Math.min(height, width) < minFaceSize) {
+        throw new Error("Image dimensions: " + height + " x " + width + " are smaller than specified minimum face size of " + minFaceSize);
+    }
+    var scaleStep = (maxDim - minFaceSize) / numScales;
+    return Array(numScales).fill(0).map(function (_, i) { return ((i + 1) * scaleStep + minFaceSize) / maxDim; }).reverse();
+}
+exports.calculateScaleSteps = calculateScaleSteps;
+//# sourceMappingURL=calculateScaleSteps.js.map
\ No newline at end of file

build/mtcnn/calculateScaleSteps.js.map

+{"version":3,"file":"calculateScaleSteps.js","sourceRoot":"","sources":["../../src/mtcnn/calculateScaleSteps.ts"],"names":[],"mappings":";;AAAA,6BAAoC,SAAiB,EAAE,WAAmB,EAAE,IAAc;IAEjF,IAAA,gBAAM,EAAE,eAAK,CAAQ;IAC5B,IAAM,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAA;IAEtC,IAAI,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,GAAG,WAAW,EAAE;QACzC,MAAM,IAAI,KAAK,CAAC,uBAAqB,MAAM,WAAM,KAAK,yDAAoD,WAAa,CAAC,CAAA;KACzH;IAED,IAAM,SAAS,GAAG,CAAC,MAAM,GAAG,WAAW,CAAC,GAAG,SAAS,CAAA;IAEpD,OAAO,KAAK,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,SAAS,GAAG,WAAW,CAAC,GAAG,MAAM,EAA5C,CAA4C,CAAC,CAAC,OAAO,EAAE,CAAA;AACvG,CAAC;AAZD,kDAYC"}
\ No newline at end of file

build/mtcnn/config.d.ts

+export declare const CELL_STRIDE = 2;
+export declare const CELL_SIZE = 12;

build/mtcnn/config.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.CELL_STRIDE = 2;
+exports.CELL_SIZE = 12;
+//# sourceMappingURL=config.js.map
\ No newline at end of file

build/mtcnn/config.js.map

+{"version":3,"file":"config.js","sourceRoot":"","sources":["../../src/mtcnn/config.ts"],"names":[],"mappings":";;AAAa,QAAA,WAAW,GAAG,CAAC,CAAA;AACf,QAAA,SAAS,GAAG,EAAE,CAAA"}
\ No newline at end of file

build/mtcnn/extractImagePatches.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { Dimensions } from '../types';
+import { BoundingBox } from './BoundingBox';
+export declare function extractImagePatches(img: HTMLCanvasElement, boxes: BoundingBox[], {width, height}: Dimensions): Promise<tf.Tensor4D[]>;

build/mtcnn/extractImagePatches.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var tf = require("@tensorflow/tfjs-core");
+var utils_1 = require("../utils");
+var normalize_1 = require("./normalize");
+function extractImagePatches(img, boxes, _a) {
+    var width = _a.width, height = _a.height;
+    return tslib_1.__awaiter(this, void 0, void 0, function () {
+        var _this = this;
+        var imgCtx, bitmaps, imagePatchesDatas;
+        return tslib_1.__generator(this, function (_b) {
+            switch (_b.label) {
+                case 0:
+                    imgCtx = utils_1.getContext2dOrThrow(img);
+                    return [4 /*yield*/, Promise.all(boxes.map(function (box) { return tslib_1.__awaiter(_this, void 0, void 0, function () {
+                            var _a, y, ey, x, ex, fromX, fromY, imgData;
+                            return tslib_1.__generator(this, function (_b) {
+                                _a = box.padAtBorders(img.height, img.width), y = _a.y, ey = _a.ey, x = _a.x, ex = _a.ex;
+                                fromX = x - 1;
+                                fromY = y - 1;
+                                imgData = imgCtx.getImageData(fromX, fromY, (ex - fromX), (ey - fromY));
+                                return [2 /*return*/, createImageBitmap(imgData)];
+                            });
+                        }); }))];
+                case 1:
+                    bitmaps = _b.sent();
+                    imagePatchesDatas = [];
+                    bitmaps.forEach(function (bmp) {
+                        var patch = utils_1.createCanvas({ width: width, height: height });
+                        var patchCtx = utils_1.getContext2dOrThrow(patch);
+                        patchCtx.drawImage(bmp, 0, 0, width, height);
+                        var data = patchCtx.getImageData(0, 0, width, height).data;
+                        var currData = [];
+                        // RGBA -> BGR
+                        for (var i = 0; i < data.length; i += 4) {
+                            currData.push(data[i + 2]);
+                            currData.push(data[i + 1]);
+                            currData.push(data[i]);
+                        }
+                        imagePatchesDatas.push(currData);
+                    });
+                    return [2 /*return*/, imagePatchesDatas.map(function (data) {
+                            var t = tf.tidy(function () {
+                                var imagePatchTensor = tf.transpose(tf.tensor4d(data, [1, width, height, 3]), [0, 2, 1, 3]).toFloat();
+                                return normalize_1.normalize(imagePatchTensor);
+                            });
+                            return t;
+                        })];
+            }
+        });
+    });
+}
+exports.extractImagePatches = extractImagePatches;
+//# sourceMappingURL=extractImagePatches.js.map
\ No newline at end of file

build/mtcnn/extractImagePatches.js.map

+{"version":3,"file":"extractImagePatches.js","sourceRoot":"","sources":["../../src/mtcnn/extractImagePatches.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAG5C,kCAA6D;AAE7D,yCAAwC;AAExC,6BACE,GAAsB,EACtB,KAAoB,EACpB,EAA6B;QAA3B,gBAAK,EAAE,kBAAM;;;;;;;oBAIT,MAAM,GAAG,2BAAmB,CAAC,GAAG,CAAC,CAAA;oBAEvB,qBAAM,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,UAAM,GAAG;;;gCAE7C,KAAmB,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,KAAK,CAAC,EAAxD,CAAC,OAAA,EAAE,EAAE,QAAA,EAAE,CAAC,OAAA,EAAE,EAAE,QAAA,CAA4C;gCAE1D,KAAK,GAAG,CAAC,GAAG,CAAC,CAAA;gCACb,KAAK,GAAG,CAAC,GAAG,CAAC,CAAA;gCACb,OAAO,GAAG,MAAM,CAAC,YAAY,CAAC,KAAK,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,KAAK,CAAC,EAAE,CAAC,EAAE,GAAG,KAAK,CAAC,CAAC,CAAA;gCAE7E,sBAAO,iBAAiB,CAAC,OAAO,CAAC,EAAA;;6BAClC,CAAC,CAAC,EAAA;;oBATG,OAAO,GAAG,SASb;oBAEG,iBAAiB,GAAe,EAAE,CAAA;oBAExC,OAAO,CAAC,OAAO,CAAC,UAAA,GAAG;wBACjB,IAAM,KAAK,GAAG,oBAAY,CAAC,EAAE,KAAK,OAAA,EAAE,MAAM,QAAA,EAAE,CAAC,CAAA;wBAC7C,IAAM,QAAQ,GAAG,2BAAmB,CAAC,KAAK,CAAC,CAAA;wBAC3C,QAAQ,CAAC,SAAS,CAAC,GAAG,EAAE,CAAC,EAAE,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,CAAA;wBACpC,IAAA,sDAAI,CAA+C;wBAE3D,IAAM,QAAQ,GAAG,EAAE,CAAA;wBACnB,cAAc;wBACd,KAAI,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,IAAE,CAAC,EAAE;4BACpC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAA;4BAC1B,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAA;4BAC1B,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;yBACvB;wBACD,iBAAiB,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;oBAClC,CAAC,CAAC,CAAA;oBAGF,sBAAO,iBAAiB,CAAC,GAAG,CAAC,UAAA,IAAI;4BAC/B,IAAM,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC;gCAChB,IAAM,gBAAgB,GAAG,EAAE,CAAC,SAAS,CACnC,EAAE,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,EACxC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CACb,CAAC,OAAO,EAAiB,CAAA;gCAE1B,OAAO,qBAAS,CAAC,gBAAgB,CAAC,CAAA;4BACpC,CAAC,CAAC,CAAA;4BACF,OAAO,CAAC,CAAA;wBACV,CAAC,CAAC,EAAA;;;;CACH;AAlDD,kDAkDC"}
\ No newline at end of file

build/mtcnn/extractParams.d.ts

+import { ParamMapping } from '../commons/types';
+import { NetParams } from './types';
+export declare function extractParams(weights: Float32Array): {
+    params: NetParams;
+    paramMappings: ParamMapping[];
+};

build/mtcnn/extractParams.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var tf = require("@tensorflow/tfjs-core");
+var extractConvParamsFactory_1 = require("../commons/extractConvParamsFactory");
+var extractFCParamsFactory_1 = require("../commons/extractFCParamsFactory");
+var extractWeightsFactory_1 = require("../commons/extractWeightsFactory");
+function extractorsFactory(extractWeights, paramMappings) {
+    var extractConvParams = extractConvParamsFactory_1.extractConvParamsFactory(extractWeights, paramMappings);
+    var extractFCParams = extractFCParamsFactory_1.extractFCParamsFactory(extractWeights, paramMappings);
+    function extractPReluParams(size, paramPath) {
+        var alpha = tf.tensor1d(extractWeights(size));
+        paramMappings.push({ paramPath: paramPath });
+        return alpha;
+    }
+    function extractSharedParams(numFilters, mappedPrefix, isRnet) {
+        if (isRnet === void 0) { isRnet = false; }
+        var conv1 = extractConvParams(numFilters[0], numFilters[1], 3, mappedPrefix + "/conv1");
+        var prelu1_alpha = extractPReluParams(numFilters[1], mappedPrefix + "/prelu1_alpha");
+        var conv2 = extractConvParams(numFilters[1], numFilters[2], 3, mappedPrefix + "/conv2");
+        var prelu2_alpha = extractPReluParams(numFilters[2], mappedPrefix + "/prelu2_alpha");
+        var conv3 = extractConvParams(numFilters[2], numFilters[3], isRnet ? 2 : 3, mappedPrefix + "/conv3");
+        var prelu3_alpha = extractPReluParams(numFilters[3], mappedPrefix + "/prelu3_alpha");
+        return { conv1: conv1, prelu1_alpha: prelu1_alpha, conv2: conv2, prelu2_alpha: prelu2_alpha, conv3: conv3, prelu3_alpha: prelu3_alpha };
+    }
+    function extractPNetParams() {
+        var sharedParams = extractSharedParams([3, 10, 16, 32], 'pnet');
+        var conv4_1 = extractConvParams(32, 2, 1, 'pnet/conv4_1');
+        var conv4_2 = extractConvParams(32, 4, 1, 'pnet/conv4_2');
+        return tslib_1.__assign({}, sharedParams, { conv4_1: conv4_1, conv4_2: conv4_2 });
+    }
+    function extractRNetParams() {
+        var sharedParams = extractSharedParams([3, 28, 48, 64], 'rnet', true);
+        var fc1 = extractFCParams(576, 128, 'rnet/fc1');
+        var prelu4_alpha = extractPReluParams(128, 'rnet/prelu4_alpha');
+        var fc2_1 = extractFCParams(128, 2, 'rnet/fc2_1');
+        var fc2_2 = extractFCParams(128, 4, 'rnet/fc2_2');
+        return tslib_1.__assign({}, sharedParams, { fc1: fc1, prelu4_alpha: prelu4_alpha, fc2_1: fc2_1, fc2_2: fc2_2 });
+    }
+    function extractONetParams() {
+        var sharedParams = extractSharedParams([3, 32, 64, 64], 'onet');
+        var conv4 = extractConvParams(64, 128, 2, 'onet/conv4');
+        var prelu4_alpha = extractPReluParams(128, 'onet/prelu4_alpha');
+        var fc1 = extractFCParams(1152, 256, 'onet/fc1');
+        var prelu5_alpha = extractPReluParams(256, 'onet/prelu5_alpha');
+        var fc2_1 = extractFCParams(256, 2, 'onet/fc2_1');
+        var fc2_2 = extractFCParams(256, 4, 'onet/fc2_2');
+        var fc2_3 = extractFCParams(256, 10, 'onet/fc2_3');
+        return tslib_1.__assign({}, sharedParams, { conv4: conv4, prelu4_alpha: prelu4_alpha, fc1: fc1, prelu5_alpha: prelu5_alpha, fc2_1: fc2_1, fc2_2: fc2_2, fc2_3: fc2_3 });
+    }
+    return {
+        extractPNetParams: extractPNetParams,
+        extractRNetParams: extractRNetParams,
+        extractONetParams: extractONetParams
+    };
+}
+function extractParams(weights) {
+    var _a = extractWeightsFactory_1.extractWeightsFactory(weights), extractWeights = _a.extractWeights, getRemainingWeights = _a.getRemainingWeights;
+    var paramMappings = [];
+    var _b = extractorsFactory(extractWeights, paramMappings), extractPNetParams = _b.extractPNetParams, extractRNetParams = _b.extractRNetParams, extractONetParams = _b.extractONetParams;
+    var pnet = extractPNetParams();
+    var rnet = extractRNetParams();
+    var onet = extractONetParams();
+    if (getRemainingWeights().length !== 0) {
+        throw new Error("weights remaing after extract: " + getRemainingWeights().length);
+    }
+    return { params: { pnet: pnet, rnet: rnet, onet: onet }, paramMappings: paramMappings };
+}
+exports.extractParams = extractParams;
+//# sourceMappingURL=extractParams.js.map
\ No newline at end of file

build/mtcnn/extractParams.js.map

+{"version":3,"file":"extractParams.js","sourceRoot":"","sources":["../../src/mtcnn/extractParams.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,gFAA+E;AAC/E,4EAA2E;AAC3E,0EAAyE;AAIzE,2BAA2B,cAAsC,EAAE,aAA6B;IAE9F,IAAM,iBAAiB,GAAG,mDAAwB,CAAC,cAAc,EAAE,aAAa,CAAC,CAAA;IACjF,IAAM,eAAe,GAAG,+CAAsB,CAAC,cAAc,EAAE,aAAa,CAAC,CAAA;IAE7E,4BAA4B,IAAY,EAAE,SAAiB;QACzD,IAAM,KAAK,GAAG,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC,CAAA;QAC/C,aAAa,CAAC,IAAI,CAAC,EAAE,SAAS,WAAA,EAAE,CAAC,CAAA;QACjC,OAAO,KAAK,CAAA;IACd,CAAC;IAED,6BAA6B,UAAoB,EAAE,YAAoB,EAAE,MAAuB;QAAvB,uBAAA,EAAA,cAAuB;QAE9F,IAAM,KAAK,GAAG,iBAAiB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,EAAE,CAAC,EAAK,YAAY,WAAQ,CAAC,CAAA;QACzF,IAAM,YAAY,GAAG,kBAAkB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAK,YAAY,kBAAe,CAAC,CAAA;QACtF,IAAM,KAAK,GAAG,iBAAiB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,EAAE,CAAC,EAAK,YAAY,WAAQ,CAAC,CAAA;QACzF,IAAM,YAAY,GAAG,kBAAkB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAK,YAAY,kBAAe,CAAC,CAAA;QACtF,IAAM,KAAK,GAAG,iBAAiB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,EAAK,YAAY,WAAQ,CAAC,CAAA;QACtG,IAAM,YAAY,GAAG,kBAAkB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAK,YAAY,kBAAe,CAAC,CAAA;QAEtF,OAAO,EAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,CAAA;IAC1E,CAAC;IAED;QAEE,IAAM,YAAY,GAAG,mBAAmB,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,MAAM,CAAC,CAAA;QACjE,IAAM,OAAO,GAAG,iBAAiB,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC,EAAE,cAAc,CAAC,CAAA;QAC3D,IAAM,OAAO,GAAG,iBAAiB,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC,EAAE,cAAc,CAAC,CAAA;QAE3D,4BAAY,YAAY,IAAE,OAAO,SAAA,EAAE,OAAO,SAAA,IAAE;IAC9C,CAAC;IAED;QAEE,IAAM,YAAY,GAAG,mBAAmB,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,CAAA;QACvE,IAAM,GAAG,GAAG,eAAe,CAAC,GAAG,EAAE,GAAG,EAAE,UAAU,CAAC,CAAA;QACjD,IAAM,YAAY,GAAG,kBAAkB,CAAC,GAAG,EAAE,mBAAmB,CAAC,CAAA;QACjE,IAAM,KAAK,GAAG,eAAe,CAAC,GAAG,EAAE,CAAC,EAAE,YAAY,CAAC,CAAA;QACnD,IAAM,KAAK,GAAG,eAAe,CAAC,GAAG,EAAE,CAAC,EAAE,YAAY,CAAC,CAAA;QAEnD,4BAAY,YAAY,IAAE,GAAG,KAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,KAAK,OAAA,IAAE;IAC7D,CAAC;IAED;QAEE,IAAM,YAAY,GAAG,mBAAmB,CAAC,CAAC,CAAC,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,CAAC,EAAE,MAAM,CAAC,CAAA;QACjE,IAAM,KAAK,GAAG,iBAAiB,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,EAAE,YAAY,CAAC,CAAA;QACzD,IAAM,YAAY,GAAG,kBAAkB,CAAC,GAAG,EAAE,mBAAmB,CAAC,CAAA;QACjE,IAAM,GAAG,GAAG,eAAe,CAAC,IAAI,EAAE,GAAG,EAAE,UAAU,CAAC,CAAA;QAClD,IAAM,YAAY,GAAG,kBAAkB,CAAC,GAAG,EAAE,mBAAmB,CAAC,CAAA;QACjE,IAAM,KAAK,GAAG,eAAe,CAAC,GAAG,EAAE,CAAC,EAAE,YAAY,CAAC,CAAA;QACnD,IAAM,KAAK,GAAG,eAAe,CAAC,GAAG,EAAE,CAAC,EAAE,YAAY,CAAC,CAAA;QACnD,IAAM,KAAK,GAAG,eAAe,CAAC,GAAG,EAAE,EAAE,EAAE,YAAY,CAAC,CAAA;QAEpD,4BAAY,YAAY,IAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,GAAG,KAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,KAAK,OAAA,EAAE,KAAK,OAAA,IAAE;IACzF,CAAC;IAED,OAAO;QACL,iBAAiB,mBAAA;QACjB,iBAAiB,mBAAA;QACjB,iBAAiB,mBAAA;KAClB,CAAA;AAEH,CAAC;AAED,uBAA8B,OAAqB;IAE3C,IAAA,2DAG4B,EAFhC,kCAAc,EACd,4CAAmB,CACa;IAElC,IAAM,aAAa,GAAmB,EAAE,CAAA;IAElC,IAAA,qDAI8C,EAHlD,wCAAiB,EACjB,wCAAiB,EACjB,wCAAiB,CACiC;IAEpD,IAAM,IAAI,GAAG,iBAAiB,EAAE,CAAA;IAChC,IAAM,IAAI,GAAG,iBAAiB,EAAE,CAAA;IAChC,IAAM,IAAI,GAAG,iBAAiB,EAAE,CAAA;IAEhC,IAAI,mBAAmB,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE;QACtC,MAAM,IAAI,KAAK,CAAC,oCAAkC,mBAAmB,EAAE,CAAC,MAAQ,CAAC,CAAA;KAClF;IAED,OAAO,EAAE,MAAM,EAAE,EAAE,IAAI,MAAA,EAAE,IAAI,MAAA,EAAE,IAAI,MAAA,EAAE,EAAE,aAAa,eAAA,EAAE,CAAA;AACxD,CAAC;AAxBD,sCAwBC"}
\ No newline at end of file

build/mtcnn/getDefaultMtcnnForwardParams.d.ts

+export declare function getDefaultMtcnnForwardParams(): {
+    minFaceSize: number;
+    scaleFactor: number;
+    maxNumScales: number;
+    scoreThresholds: number[];
+};

build/mtcnn/getDefaultMtcnnForwardParams.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+function getDefaultMtcnnForwardParams() {
+    return {
+        minFaceSize: 20,
+        scaleFactor: 0.709,
+        maxNumScales: 10,
+        scoreThresholds: [0.6, 0.7, 0.7]
+    };
+}
+exports.getDefaultMtcnnForwardParams = getDefaultMtcnnForwardParams;
+//# sourceMappingURL=getDefaultMtcnnForwardParams.js.map
\ No newline at end of file

build/mtcnn/getDefaultMtcnnForwardParams.js.map

+{"version":3,"file":"getDefaultMtcnnForwardParams.js","sourceRoot":"","sources":["../../src/mtcnn/getDefaultMtcnnForwardParams.ts"],"names":[],"mappings":";;AAAA;IACE,OAAO;QACL,WAAW,EAAE,EAAE;QACf,WAAW,EAAE,KAAK;QAClB,YAAY,EAAE,EAAE;QAChB,eAAe,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;KACjC,CAAA;AACH,CAAC;AAPD,oEAOC"}
\ No newline at end of file

build/mtcnn/getSizesForScale.d.ts

+export declare function getSizesForScale(scale: number, [height, width]: number[]): {
+    height: number;
+    width: number;
+};

build/mtcnn/getSizesForScale.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+function getSizesForScale(scale, _a) {
+    var height = _a[0], width = _a[1];
+    return {
+        height: Math.floor(height * scale),
+        width: Math.floor(width * scale)
+    };
+}
+exports.getSizesForScale = getSizesForScale;
+//# sourceMappingURL=getSizesForScale.js.map
\ No newline at end of file

build/mtcnn/getSizesForScale.js.map

+{"version":3,"file":"getSizesForScale.js","sourceRoot":"","sources":["../../src/mtcnn/getSizesForScale.ts"],"names":[],"mappings":";;AAAA,0BAAiC,KAAa,EAAE,EAAyB;QAAxB,cAAM,EAAE,aAAK;IAC5D,OAAO;QACL,MAAM,EAAE,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,KAAK,CAAC;QAClC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,KAAK,GAAG,KAAK,CAAC;KACjC,CAAA;AACH,CAAC;AALD,4CAKC"}
\ No newline at end of file

build/mtcnn/index.d.ts

+import { Mtcnn } from './Mtcnn';
+export * from './Mtcnn';
+export * from './FaceLandmarks5';
+export declare function createMtcnn(weights: Float32Array): Mtcnn;

build/mtcnn/index.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var Mtcnn_1 = require("./Mtcnn");
+tslib_1.__exportStar(require("./Mtcnn"), exports);
+tslib_1.__exportStar(require("./FaceLandmarks5"), exports);
+function createMtcnn(weights) {
+    var net = new Mtcnn_1.Mtcnn();
+    net.extractWeights(weights);
+    return net;
+}
+exports.createMtcnn = createMtcnn;
+//# sourceMappingURL=index.js.map
\ No newline at end of file

build/mtcnn/index.js.map

+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/mtcnn/index.ts"],"names":[],"mappings":";;;AAAA,iCAAgC;AAEhC,kDAAwB;AACxB,2DAAiC;AAEjC,qBAA4B,OAAqB;IAC/C,IAAM,GAAG,GAAG,IAAI,aAAK,EAAE,CAAA;IACvB,GAAG,CAAC,cAAc,CAAC,OAAO,CAAC,CAAA;IAC3B,OAAO,GAAG,CAAA;AACZ,CAAC;AAJD,kCAIC"}
\ No newline at end of file

build/mtcnn/loadQuantizedParams.d.ts

+import { ParamMapping } from '../commons/types';
+import { NetParams } from './types';
+export declare function loadQuantizedParams(uri: string | undefined): Promise<{
+    params: NetParams;
+    paramMappings: ParamMapping[];
+}>;

build/mtcnn/loadQuantizedParams.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var disposeUnusedWeightTensors_1 = require("../commons/disposeUnusedWeightTensors");
+var extractWeightEntryFactory_1 = require("../commons/extractWeightEntryFactory");
+var loadWeightMap_1 = require("../commons/loadWeightMap");
+var DEFAULT_MODEL_NAME = 'mtcnn_model';
+function extractorsFactory(weightMap, paramMappings) {
+    var extractWeightEntry = extractWeightEntryFactory_1.extractWeightEntryFactory(weightMap, paramMappings);
+    function extractConvParams(prefix) {
+        var filters = extractWeightEntry(prefix + "/weights", 4, prefix + "/filters");
+        var bias = extractWeightEntry(prefix + "/bias", 1);
+        return { filters: filters, bias: bias };
+    }
+    function extractFCParams(prefix) {
+        var weights = extractWeightEntry(prefix + "/weights", 2);
+        var bias = extractWeightEntry(prefix + "/bias", 1);
+        return { weights: weights, bias: bias };
+    }
+    function extractPReluParams(paramPath) {
+        return extractWeightEntry(paramPath, 1);
+    }
+    function extractSharedParams(prefix) {
+        var conv1 = extractConvParams(prefix + "/conv1");
+        var prelu1_alpha = extractPReluParams(prefix + "/prelu1_alpha");
+        var conv2 = extractConvParams(prefix + "/conv2");
+        var prelu2_alpha = extractPReluParams(prefix + "/prelu2_alpha");
+        var conv3 = extractConvParams(prefix + "/conv3");
+        var prelu3_alpha = extractPReluParams(prefix + "/prelu3_alpha");
+        return { conv1: conv1, prelu1_alpha: prelu1_alpha, conv2: conv2, prelu2_alpha: prelu2_alpha, conv3: conv3, prelu3_alpha: prelu3_alpha };
+    }
+    function extractPNetParams() {
+        var sharedParams = extractSharedParams('pnet');
+        var conv4_1 = extractConvParams('pnet/conv4_1');
+        var conv4_2 = extractConvParams('pnet/conv4_2');
+        return tslib_1.__assign({}, sharedParams, { conv4_1: conv4_1, conv4_2: conv4_2 });
+    }
+    function extractRNetParams() {
+        var sharedParams = extractSharedParams('rnet');
+        var fc1 = extractFCParams('rnet/fc1');
+        var prelu4_alpha = extractPReluParams('rnet/prelu4_alpha');
+        var fc2_1 = extractFCParams('rnet/fc2_1');
+        var fc2_2 = extractFCParams('rnet/fc2_2');
+        return tslib_1.__assign({}, sharedParams, { fc1: fc1, prelu4_alpha: prelu4_alpha, fc2_1: fc2_1, fc2_2: fc2_2 });
+    }
+    function extractONetParams() {
+        var sharedParams = extractSharedParams('onet');
+        var conv4 = extractConvParams('onet/conv4');
+        var prelu4_alpha = extractPReluParams('onet/prelu4_alpha');
+        var fc1 = extractFCParams('onet/fc1');
+        var prelu5_alpha = extractPReluParams('onet/prelu5_alpha');
+        var fc2_1 = extractFCParams('onet/fc2_1');
+        var fc2_2 = extractFCParams('onet/fc2_2');
+        var fc2_3 = extractFCParams('onet/fc2_3');
+        return tslib_1.__assign({}, sharedParams, { conv4: conv4, prelu4_alpha: prelu4_alpha, fc1: fc1, prelu5_alpha: prelu5_alpha, fc2_1: fc2_1, fc2_2: fc2_2, fc2_3: fc2_3 });
+    }
+    return {
+        extractPNetParams: extractPNetParams,
+        extractRNetParams: extractRNetParams,
+        extractONetParams: extractONetParams
+    };
+}
+function loadQuantizedParams(uri) {
+    return tslib_1.__awaiter(this, void 0, void 0, function () {
+        var weightMap, paramMappings, _a, extractPNetParams, extractRNetParams, extractONetParams, pnet, rnet, onet;
+        return tslib_1.__generator(this, function (_b) {
+            switch (_b.label) {
+                case 0: return [4 /*yield*/, loadWeightMap_1.loadWeightMap(uri, DEFAULT_MODEL_NAME)];
+                case 1:
+                    weightMap = _b.sent();
+                    paramMappings = [];
+                    _a = extractorsFactory(weightMap, paramMappings), extractPNetParams = _a.extractPNetParams, extractRNetParams = _a.extractRNetParams, extractONetParams = _a.extractONetParams;
+                    pnet = extractPNetParams();
+                    rnet = extractRNetParams();
+                    onet = extractONetParams();
+                    disposeUnusedWeightTensors_1.disposeUnusedWeightTensors(weightMap, paramMappings);
+                    return [2 /*return*/, { params: { pnet: pnet, rnet: rnet, onet: onet }, paramMappings: paramMappings }];
+            }
+        });
+    });
+}
+exports.loadQuantizedParams = loadQuantizedParams;
+//# sourceMappingURL=loadQuantizedParams.js.map
\ No newline at end of file

build/mtcnn/loadQuantizedParams.js.map

+{"version":3,"file":"loadQuantizedParams.js","sourceRoot":"","sources":["../../src/mtcnn/loadQuantizedParams.ts"],"names":[],"mappings":";;;AAEA,oFAAmF;AACnF,kFAAiF;AACjF,0DAAyD;AAIzD,IAAM,kBAAkB,GAAG,aAAa,CAAA;AAExC,2BAA2B,SAAc,EAAE,aAA6B;IAEtE,IAAM,kBAAkB,GAAG,qDAAyB,CAAC,SAAS,EAAE,aAAa,CAAC,CAAA;IAE9E,2BAA2B,MAAc;QACvC,IAAM,OAAO,GAAG,kBAAkB,CAAiB,MAAM,aAAU,EAAE,CAAC,EAAK,MAAM,aAAU,CAAC,CAAA;QAC5F,IAAM,IAAI,GAAG,kBAAkB,CAAiB,MAAM,UAAO,EAAE,CAAC,CAAC,CAAA;QAEjE,OAAO,EAAE,OAAO,SAAA,EAAE,IAAI,MAAA,EAAE,CAAA;IAC1B,CAAC;IAED,yBAAyB,MAAc;QACrC,IAAM,OAAO,GAAG,kBAAkB,CAAiB,MAAM,aAAU,EAAE,CAAC,CAAC,CAAA;QACvE,IAAM,IAAI,GAAG,kBAAkB,CAAiB,MAAM,UAAO,EAAE,CAAC,CAAC,CAAA;QAEjE,OAAO,EAAE,OAAO,SAAA,EAAE,IAAI,MAAA,EAAE,CAAA;IAC1B,CAAC;IAED,4BAA4B,SAAiB;QAC3C,OAAO,kBAAkB,CAAc,SAAS,EAAE,CAAC,CAAC,CAAA;IACtD,CAAC;IAED,6BAA6B,MAAc;QAEzC,IAAM,KAAK,GAAG,iBAAiB,CAAI,MAAM,WAAQ,CAAC,CAAA;QAClD,IAAM,YAAY,GAAG,kBAAkB,CAAI,MAAM,kBAAe,CAAC,CAAA;QACjE,IAAM,KAAK,GAAG,iBAAiB,CAAI,MAAM,WAAQ,CAAC,CAAA;QAClD,IAAM,YAAY,GAAG,kBAAkB,CAAI,MAAM,kBAAe,CAAC,CAAA;QACjE,IAAM,KAAK,GAAG,iBAAiB,CAAI,MAAM,WAAQ,CAAC,CAAA;QAClD,IAAM,YAAY,GAAG,kBAAkB,CAAI,MAAM,kBAAe,CAAC,CAAA;QAEjE,OAAO,EAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,CAAA;IAC1E,CAAC;IAED;QAEE,IAAM,YAAY,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;QAChD,IAAM,OAAO,GAAG,iBAAiB,CAAC,cAAc,CAAC,CAAA;QACjD,IAAM,OAAO,GAAG,iBAAiB,CAAC,cAAc,CAAC,CAAA;QAEjD,4BAAY,YAAY,IAAE,OAAO,SAAA,EAAE,OAAO,SAAA,IAAE;IAC9C,CAAC;IAED;QAEE,IAAM,YAAY,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;QAChD,IAAM,GAAG,GAAG,eAAe,CAAC,UAAU,CAAC,CAAA;QACvC,IAAM,YAAY,GAAG,kBAAkB,CAAC,mBAAmB,CAAC,CAAA;QAC5D,IAAM,KAAK,GAAG,eAAe,CAAC,YAAY,CAAC,CAAA;QAC3C,IAAM,KAAK,GAAG,eAAe,CAAC,YAAY,CAAC,CAAA;QAE3C,4BAAY,YAAY,IAAE,GAAG,KAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,KAAK,OAAA,IAAE;IAC7D,CAAC;IAED;QAEE,IAAM,YAAY,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;QAChD,IAAM,KAAK,GAAG,iBAAiB,CAAC,YAAY,CAAC,CAAA;QAC7C,IAAM,YAAY,GAAG,kBAAkB,CAAC,mBAAmB,CAAC,CAAA;QAC5D,IAAM,GAAG,GAAG,eAAe,CAAC,UAAU,CAAC,CAAA;QACvC,IAAM,YAAY,GAAG,kBAAkB,CAAC,mBAAmB,CAAC,CAAA;QAC5D,IAAM,KAAK,GAAG,eAAe,CAAC,YAAY,CAAC,CAAA;QAC3C,IAAM,KAAK,GAAG,eAAe,CAAC,YAAY,CAAC,CAAA;QAC3C,IAAM,KAAK,GAAG,eAAe,CAAC,YAAY,CAAC,CAAA;QAE3C,4BAAY,YAAY,IAAE,KAAK,OAAA,EAAE,YAAY,cAAA,EAAE,GAAG,KAAA,EAAE,YAAY,cAAA,EAAE,KAAK,OAAA,EAAE,KAAK,OAAA,EAAE,KAAK,OAAA,IAAE;IACzF,CAAC;IAED,OAAO;QACL,iBAAiB,mBAAA;QACjB,iBAAiB,mBAAA;QACjB,iBAAiB,mBAAA;KAClB,CAAA;AAEH,CAAC;AAED,6BACE,GAAuB;;;;;wBAGL,qBAAM,6BAAa,CAAC,GAAG,EAAE,kBAAkB,CAAC,EAAA;;oBAAxD,SAAS,GAAG,SAA4C;oBACxD,aAAa,GAAmB,EAAE,CAAA;oBAElC,KAIF,iBAAiB,CAAC,SAAS,EAAE,aAAa,CAAC,EAH7C,iBAAiB,uBAAA,EACjB,iBAAiB,uBAAA,EACjB,iBAAiB,uBAAA,CAC4B;oBAEzC,IAAI,GAAG,iBAAiB,EAAE,CAAA;oBAC1B,IAAI,GAAG,iBAAiB,EAAE,CAAA;oBAC1B,IAAI,GAAG,iBAAiB,EAAE,CAAA;oBAEhC,uDAA0B,CAAC,SAAS,EAAE,aAAa,CAAC,CAAA;oBAEpD,sBAAO,EAAE,MAAM,EAAE,EAAE,IAAI,MAAA,EAAE,IAAI,MAAA,EAAE,IAAI,MAAA,EAAE,EAAE,aAAa,eAAA,EAAE,EAAA;;;;CACvD;AApBD,kDAoBC"}
\ No newline at end of file

build/mtcnn/nms.d.ts

+import { BoundingBox } from './BoundingBox';
+export declare function nms(boxes: BoundingBox[], scores: number[], iouThreshold: number, isIOU?: boolean): number[];

build/mtcnn/nms.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+function nms(boxes, scores, iouThreshold, isIOU) {
+    if (isIOU === void 0) { isIOU = true; }
+    var areas = boxes.map(function (box) { return (box.width + 1) * (box.height + 1); });
+    var indicesSortedByScore = scores
+        .map(function (score, boxIndex) { return ({ score: score, boxIndex: boxIndex }); })
+        .sort(function (c1, c2) { return c1.score - c2.score; })
+        .map(function (c) { return c.boxIndex; });
+    var pick = [];
+    var _loop_1 = function () {
+        var curr = indicesSortedByScore.pop();
+        pick.push(curr);
+        var indices = indicesSortedByScore;
+        var outputs = [];
+        for (var i = 0; i < indices.length; i++) {
+            var idx = indices[i];
+            var currBox = boxes[curr];
+            var idxBox = boxes[idx];
+            var width = Math.max(0.0, Math.min(currBox.right, idxBox.right) - Math.max(currBox.left, idxBox.left) + 1);
+            var height = Math.max(0.0, Math.min(currBox.bottom, idxBox.bottom) - Math.max(currBox.top, idxBox.top) + 1);
+            var interSection = width * height;
+            var out = isIOU
+                ? interSection / (areas[curr] + areas[idx] - interSection)
+                : interSection / Math.min(areas[curr], areas[idx]);
+            outputs.push(out);
+        }
+        indicesSortedByScore = indicesSortedByScore.filter(function (_, j) { return outputs[j] <= iouThreshold; });
+    };
+    while (indicesSortedByScore.length > 0) {
+        _loop_1();
+    }
+    return pick;
+}
+exports.nms = nms;
+//# sourceMappingURL=nms.js.map
\ No newline at end of file

build/mtcnn/nms.js.map

+{"version":3,"file":"nms.js","sourceRoot":"","sources":["../../src/mtcnn/nms.ts"],"names":[],"mappings":";;AAEA,aACE,KAAoB,EACpB,MAAgB,EAChB,YAAoB,EACpB,KAAqB;IAArB,sBAAA,EAAA,YAAqB;IAGrB,IAAM,KAAK,GAAG,KAAK,CAAC,GAAG,CACrB,UAAA,GAAG,IAAI,OAAA,CAAC,GAAG,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,GAAG,CAAC,CAAC,EAAlC,CAAkC,CAC1C,CAAA;IAED,IAAI,oBAAoB,GAAG,MAAM;SAC9B,GAAG,CAAC,UAAC,KAAK,EAAE,QAAQ,IAAK,OAAA,CAAC,EAAE,KAAK,OAAA,EAAE,QAAQ,UAAA,EAAE,CAAC,EAArB,CAAqB,CAAC;SAC/C,IAAI,CAAC,UAAC,EAAE,EAAE,EAAE,IAAK,OAAA,EAAE,CAAC,KAAK,GAAG,EAAE,CAAC,KAAK,EAAnB,CAAmB,CAAC;SACrC,GAAG,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,QAAQ,EAAV,CAAU,CAAC,CAAA;IAEvB,IAAM,IAAI,GAAa,EAAE,CAAA;;QAGvB,IAAM,IAAI,GAAG,oBAAoB,CAAC,GAAG,EAAY,CAAA;QACjD,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAEf,IAAM,OAAO,GAAG,oBAAoB,CAAA;QAEpC,IAAM,OAAO,GAAa,EAAE,CAAA;QAC5B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;YACvC,IAAM,GAAG,GAAG,OAAO,CAAC,CAAC,CAAC,CAAA;YAEtB,IAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,CAAA;YAC3B,IAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,CAAA;YAEzB,IAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAA;YAC5G,IAAM,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,MAAM,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,GAAG,EAAE,MAAM,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,CAAA;YAC7G,IAAM,YAAY,GAAG,KAAK,GAAG,MAAM,CAAA;YAEnC,IAAM,GAAG,GAAG,KAAK;gBACf,CAAC,CAAC,YAAY,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,YAAY,CAAC;gBAC1D,CAAC,CAAC,YAAY,GAAG,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,CAAA;YAEpD,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;SAClB;QAED,oBAAoB,GAAG,oBAAoB,CAAC,MAAM,CAChD,UAAC,CAAC,EAAE,CAAC,IAAK,OAAA,OAAO,CAAC,CAAC,CAAC,IAAI,YAAY,EAA1B,CAA0B,CACrC,CAAA;IACH,CAAC;IA3BD,OAAM,oBAAoB,CAAC,MAAM,GAAG,CAAC;;KA2BpC;IAED,OAAO,IAAI,CAAA;AAEb,CAAC;AAjDD,kBAiDC"}
\ No newline at end of file

build/mtcnn/normalize.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+export declare function normalize(x: tf.Tensor4D): tf.Tensor4D;

build/mtcnn/normalize.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+function normalize(x) {
+    return tf.tidy(function () { return tf.mul(tf.sub(x, tf.scalar(127.5)), tf.scalar(0.0078125)); });
+}
+exports.normalize = normalize;
+//# sourceMappingURL=normalize.js.map
\ No newline at end of file

build/mtcnn/normalize.js.map

+{"version":3,"file":"normalize.js","sourceRoot":"","sources":["../../src/mtcnn/normalize.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,mBAA0B,CAAc;IACtC,OAAO,EAAE,CAAC,IAAI,CACZ,cAAM,OAAA,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,EAAzD,CAAyD,CAChE,CAAA;AACH,CAAC;AAJD,8BAIC"}
\ No newline at end of file

build/mtcnn/prelu.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+export declare function prelu<T extends tf.Tensor>(x: T, alpha: tf.Tensor1D): T;

build/mtcnn/prelu.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+function prelu(x, alpha) {
+    return tf.tidy(function () {
+        return tf.add(tf.relu(x), tf.mul(alpha, tf.neg(tf.relu(tf.neg(x)))));
+    });
+}
+exports.prelu = prelu;
+//# sourceMappingURL=prelu.js.map
\ No newline at end of file

build/mtcnn/prelu.js.map

+{"version":3,"file":"prelu.js","sourceRoot":"","sources":["../../src/mtcnn/prelu.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,eAA2C,CAAI,EAAE,KAAkB;IACjE,OAAO,EAAE,CAAC,IAAI,CAAC;QACb,OAAA,EAAE,CAAC,GAAG,CACJ,EAAE,CAAC,IAAI,CAAC,CAAC,CAAC,EACV,EAAE,CAAC,GAAG,CAAC,KAAK,EAAE,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAC1C;IAHD,CAGC,CACF,CAAA;AACH,CAAC;AAPD,sBAOC"}
\ No newline at end of file

build/mtcnn/pyramidDown.d.ts

+export declare function pyramidDown(minFaceSize: number, scaleFactor: number, dims: number[]): number[];

build/mtcnn/pyramidDown.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var config_1 = require("./config");
+function pyramidDown(minFaceSize, scaleFactor, dims) {
+    var height = dims[0], width = dims[1];
+    var m = config_1.CELL_SIZE / minFaceSize;
+    var scales = [];
+    var minLayer = Math.min(height, width) * m;
+    var exp = 0;
+    while (minLayer >= 12) {
+        scales.push(m * Math.pow(scaleFactor, exp));
+        minLayer = minLayer * scaleFactor;
+        exp += 1;
+    }
+    return scales;
+}
+exports.pyramidDown = pyramidDown;
+//# sourceMappingURL=pyramidDown.js.map
\ No newline at end of file

build/mtcnn/pyramidDown.js.map

+{"version":3,"file":"pyramidDown.js","sourceRoot":"","sources":["../../src/mtcnn/pyramidDown.ts"],"names":[],"mappings":";;AAAA,mCAAqC;AAErC,qBAA4B,WAAmB,EAAE,WAAmB,EAAE,IAAc;IAE3E,IAAA,gBAAM,EAAE,eAAK,CAAQ;IAC5B,IAAM,CAAC,GAAG,kBAAS,GAAG,WAAW,CAAA;IAEjC,IAAM,MAAM,GAAG,EAAE,CAAA;IAEjB,IAAI,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,GAAG,CAAC,CAAA;IAC1C,IAAI,GAAG,GAAG,CAAC,CAAA;IACX,OAAO,QAAQ,IAAI,EAAE,EAAE;QACrB,MAAM,CAAC,IAAI,CAAC,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,GAAG,CAAC,CAAC,CAAA;QAC3C,QAAQ,GAAG,QAAQ,GAAG,WAAW,CAAA;QACjC,GAAG,IAAI,CAAC,CAAA;KACT;IAED,OAAO,MAAM,CAAA;AACf,CAAC;AAhBD,kCAgBC"}
\ No newline at end of file

build/mtcnn/sharedLayers.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { SharedParams } from './types';
+export declare function sharedLayer(x: tf.Tensor4D, params: SharedParams, isPnet?: boolean): tf.Tensor<tf.Rank.R4>;

build/mtcnn/sharedLayers.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+var convLayer_1 = require("../commons/convLayer");
+var prelu_1 = require("./prelu");
+function sharedLayer(x, params, isPnet) {
+    if (isPnet === void 0) { isPnet = false; }
+    return tf.tidy(function () {
+        var out = convLayer_1.convLayer(x, params.conv1, 'valid');
+        out = prelu_1.prelu(out, params.prelu1_alpha);
+        out = tf.maxPool(out, isPnet ? [2, 2] : [3, 3], [2, 2], 'same');
+        out = convLayer_1.convLayer(out, params.conv2, 'valid');
+        out = prelu_1.prelu(out, params.prelu2_alpha);
+        out = isPnet ? out : tf.maxPool(out, [3, 3], [2, 2], 'valid');
+        out = convLayer_1.convLayer(out, params.conv3, 'valid');
+        out = prelu_1.prelu(out, params.prelu3_alpha);
+        return out;
+    });
+}
+exports.sharedLayer = sharedLayer;
+//# sourceMappingURL=sharedLayers.js.map
\ No newline at end of file

build/mtcnn/sharedLayers.js.map

+{"version":3,"file":"sharedLayers.js","sourceRoot":"","sources":["../../src/mtcnn/sharedLayers.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,kDAAiD;AACjD,iCAAgC;AAGhC,qBAA4B,CAAc,EAAE,MAAoB,EAAE,MAAuB;IAAvB,uBAAA,EAAA,cAAuB;IACvF,OAAO,EAAE,CAAC,IAAI,CAAC;QAEb,IAAI,GAAG,GAAG,qBAAS,CAAC,CAAC,EAAE,MAAM,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC7C,GAAG,GAAG,aAAK,CAAc,GAAG,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAClD,GAAG,GAAG,EAAE,CAAC,OAAO,CAAC,GAAG,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,MAAM,CAAC,CAAA;QAC9D,GAAG,GAAG,qBAAS,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC3C,GAAG,GAAG,aAAK,CAAc,GAAG,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAClD,GAAG,GAAG,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,OAAO,CAAC,CAAA;QAC7D,GAAG,GAAG,qBAAS,CAAC,GAAG,EAAE,MAAM,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC3C,GAAG,GAAG,aAAK,CAAc,GAAG,EAAE,MAAM,CAAC,YAAY,CAAC,CAAA;QAElD,OAAO,GAAG,CAAA;IACZ,CAAC,CAAC,CAAA;AACJ,CAAC;AAdD,kCAcC"}
\ No newline at end of file

build/mtcnn/stage1.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { BoundingBox } from './BoundingBox';
+import { PNetParams } from './types';
+export declare function stage1(imgTensor: tf.Tensor4D, scales: number[], scoreThreshold: number, params: PNetParams, stats: any): {
+    boxes: BoundingBox[];
+    scores: number[];
+};

build/mtcnn/stage1.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tf = require("@tensorflow/tfjs-core");
+var Point_1 = require("../Point");
+var BoundingBox_1 = require("./BoundingBox");
+var config_1 = require("./config");
+var nms_1 = require("./nms");
+var normalize_1 = require("./normalize");
+var PNet_1 = require("./PNet");
+var getSizesForScale_1 = require("./getSizesForScale");
+function rescaleAndNormalize(x, scale) {
+    return tf.tidy(function () {
+        var _a = getSizesForScale_1.getSizesForScale(scale, x.shape.slice(1)), height = _a.height, width = _a.width;
+        var resized = tf.image.resizeBilinear(x, [height, width]);
+        var normalized = normalize_1.normalize(resized);
+        return tf.transpose(normalized, [0, 2, 1, 3]);
+    });
+}
+function extractBoundingBoxes(scoresTensor, regionsTensor, scale, scoreThreshold) {
+    // TODO: fix this!, maybe better to use tf.gather here
+    var indices = [];
+    for (var y = 0; y < scoresTensor.shape[0]; y++) {
+        for (var x = 0; x < scoresTensor.shape[1]; x++) {
+            if (scoresTensor.get(y, x) >= scoreThreshold) {
+                indices.push(new Point_1.Point(x, y));
+            }
+        }
+    }
+    var boundingBoxes = indices.map(function (idx) {
+        var cell = new BoundingBox_1.BoundingBox(Math.round((idx.y * config_1.CELL_STRIDE + 1) / scale), Math.round((idx.x * config_1.CELL_STRIDE + 1) / scale), Math.round((idx.y * config_1.CELL_STRIDE + config_1.CELL_SIZE) / scale), Math.round((idx.x * config_1.CELL_STRIDE + config_1.CELL_SIZE) / scale));
+        var score = scoresTensor.get(idx.y, idx.x);
+        var region = new BoundingBox_1.BoundingBox(regionsTensor.get(idx.y, idx.x, 0), regionsTensor.get(idx.y, idx.x, 1), regionsTensor.get(idx.y, idx.x, 2), regionsTensor.get(idx.y, idx.x, 3));
+        return {
+            cell: cell,
+            score: score,
+            region: region
+        };
+    });
+    return boundingBoxes;
+}
+function stage1(imgTensor, scales, scoreThreshold, params, stats) {
+    stats.stage1 = [];
+    var pnetOutputs = scales.map(function (scale) { return tf.tidy(function () {
+        var statsForScale = { scale: scale };
+        var resized = rescaleAndNormalize(imgTensor, scale);
+        var ts = Date.now();
+        var _a = PNet_1.PNet(resized, params), prob = _a.prob, regions = _a.regions;
+        statsForScale.pnet = Date.now() - ts;
+        var scoresTensor = tf.unstack(tf.unstack(prob, 3)[1])[0];
+        var regionsTensor = tf.unstack(regions)[0];
+        return {
+            scoresTensor: scoresTensor,
+            regionsTensor: regionsTensor,
+            scale: scale,
+            statsForScale: statsForScale
+        };
+    }); });
+    var boxesForScale = pnetOutputs.map(function (_a) {
+        var scoresTensor = _a.scoresTensor, regionsTensor = _a.regionsTensor, scale = _a.scale, statsForScale = _a.statsForScale;
+        var boundingBoxes = extractBoundingBoxes(scoresTensor, regionsTensor, scale, scoreThreshold);
+        scoresTensor.dispose();
+        regionsTensor.dispose();
+        if (!boundingBoxes.length) {
+            stats.stage1.push(statsForScale);
+            return [];
+        }
+        var ts = Date.now();
+        var indices = nms_1.nms(boundingBoxes.map(function (bbox) { return bbox.cell; }), boundingBoxes.map(function (bbox) { return bbox.score; }), 0.5);
+        statsForScale.nms = Date.now() - ts;
+        statsForScale.numBoxes = indices.length;
+        stats.stage1.push(statsForScale);
+        return indices.map(function (boxIdx) { return boundingBoxes[boxIdx]; });
+    });
+    var allBoxes = boxesForScale.reduce(function (all, boxes) { return all.concat(boxes); }, []);
+    var finalBoxes = [];
+    var finalScores = [];
+    if (allBoxes.length > 0) {
+        var ts = Date.now();
+        var indices = nms_1.nms(allBoxes.map(function (bbox) { return bbox.cell; }), allBoxes.map(function (bbox) { return bbox.score; }), 0.7);
+        stats.stage1_nms = Date.now() - ts;
+        finalScores = indices.map(function (idx) { return allBoxes[idx].score; });
+        finalBoxes = indices
+            .map(function (idx) { return allBoxes[idx]; })
+            .map(function (_a) {
+            var cell = _a.cell, region = _a.region;
+            return new BoundingBox_1.BoundingBox(cell.left + (region.left * cell.width), cell.top + (region.top * cell.height), cell.right + (region.right * cell.width), cell.bottom + (region.bottom * cell.height)).toSquare().round();
+        });
+    }
+    return {
+        boxes: finalBoxes,
+        scores: finalScores
+    };
+}
+exports.stage1 = stage1;
+//# sourceMappingURL=stage1.js.map
\ No newline at end of file

build/mtcnn/stage1.js.map

+{"version":3,"file":"stage1.js","sourceRoot":"","sources":["../../src/mtcnn/stage1.ts"],"names":[],"mappings":";;AAAA,0CAA4C;AAE5C,kCAAiC;AACjC,6CAA4C;AAC5C,mCAAkD;AAClD,6BAA4B;AAC5B,yCAAwC;AACxC,+BAA8B;AAE9B,uDAAsD;AAEtD,6BAA6B,CAAc,EAAE,KAAa;IACxD,OAAO,EAAE,CAAC,IAAI,CAAC;QAEP,IAAA,iEAA6D,EAA3D,kBAAM,EAAE,gBAAK,CAA8C;QACnE,IAAM,OAAO,GAAG,EAAE,CAAC,KAAK,CAAC,cAAc,CAAC,CAAC,EAAE,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,CAAA;QAC3D,IAAM,UAAU,GAAG,qBAAS,CAAC,OAAO,CAAC,CAAA;QAErC,OAAQ,EAAE,CAAC,SAAS,CAAC,UAAU,EAAE,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAiB,CAAA;IAChE,CAAC,CAAC,CAAA;AACJ,CAAC;AAED,8BACE,YAAyB,EACzB,aAA0B,EAC1B,KAAa,EACb,cAAsB;IAGtB,sDAAsD;IACtD,IAAM,OAAO,GAAY,EAAE,CAAA;IAC3B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;QAC9C,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;YAC9C,IAAI,YAAY,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,cAAc,EAAE;gBAC5C,OAAO,CAAC,IAAI,CAAC,IAAI,aAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;aAC9B;SACF;KACF;IAED,IAAM,aAAa,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG;QACnC,IAAM,IAAI,GAAG,IAAI,yBAAW,CAC1B,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,oBAAW,GAAG,CAAC,CAAC,GAAG,KAAK,CAAC,EAC7C,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,oBAAW,GAAG,CAAC,CAAC,GAAG,KAAK,CAAC,EAC7C,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,oBAAW,GAAG,kBAAS,CAAC,GAAG,KAAK,CAAC,EACrD,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,GAAG,oBAAW,GAAG,kBAAS,CAAC,GAAG,KAAK,CAAC,CACtD,CAAA;QAED,IAAM,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,CAAA;QAE5C,IAAM,MAAM,GAAG,IAAI,yBAAW,CAC5B,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAClC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAClC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAClC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CACnC,CAAA;QAED,OAAO;YACL,IAAI,MAAA;YACJ,KAAK,OAAA;YACL,MAAM,QAAA;SACP,CAAA;IACH,CAAC,CAAC,CAAA;IAEF,OAAO,aAAa,CAAA;AACtB,CAAC;AAED,gBACE,SAAsB,EACtB,MAAgB,EAChB,cAAsB,EACtB,MAAkB,EAClB,KAAU;IAEV,KAAK,CAAC,MAAM,GAAG,EAAE,CAAA;IAEjB,IAAM,WAAW,GAAG,MAAM,CAAC,GAAG,CAAC,UAAC,KAAK,IAAK,OAAA,EAAE,CAAC,IAAI,CAAC;QAChD,IAAM,aAAa,GAAQ,EAAE,KAAK,OAAA,EAAE,CAAA;QACpC,IAAM,OAAO,GAAG,mBAAmB,CAAC,SAAS,EAAE,KAAK,CAAC,CAAA;QAErD,IAAI,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;QACb,IAAA,iCAAyC,EAAvC,cAAI,EAAE,oBAAO,CAA0B;QAC/C,aAAa,CAAC,IAAI,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;QAEpC,IAAM,YAAY,GAAG,EAAE,CAAC,OAAO,CAAC,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAgB,CAAA;QACzE,IAAM,aAAa,GAAG,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC,CAAC,CAAgB,CAAA;QAE3D,OAAO;YACL,YAAY,cAAA;YACZ,aAAa,eAAA;YACb,KAAK,OAAA;YACL,aAAa,eAAA;SACd,CAAA;IACH,CAAC,CAAC,EAjBwC,CAiBxC,CAAC,CAAA;IAEH,IAAM,aAAa,GAAG,WAAW,CAAC,GAAG,CAAC,UAAC,EAAqD;YAAnD,8BAAY,EAAE,gCAAa,EAAE,gBAAK,EAAE,gCAAa;QACxF,IAAM,aAAa,GAAG,oBAAoB,CACxC,YAAY,EACZ,aAAa,EACb,KAAK,EACL,cAAc,CACf,CAAA;QAED,YAAY,CAAC,OAAO,EAAE,CAAA;QACtB,aAAa,CAAC,OAAO,EAAE,CAAA;QAEvB,IAAI,CAAC,aAAa,CAAC,MAAM,EAAE;YACzB,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;YAChC,OAAO,EAAE,CAAA;SACV;QAED,IAAI,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;QACnB,IAAM,OAAO,GAAG,SAAG,CACjB,aAAa,CAAC,GAAG,CAAC,UAAA,IAAI,IAAI,OAAA,IAAI,CAAC,IAAI,EAAT,CAAS,CAAC,EACpC,aAAa,CAAC,GAAG,CAAC,UAAA,IAAI,IAAI,OAAA,IAAI,CAAC,KAAK,EAAV,CAAU,CAAC,EACrC,GAAG,CACJ,CAAA;QACD,aAAa,CAAC,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;QACnC,aAAa,CAAC,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAA;QAEvC,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;QAChC,OAAO,OAAO,CAAC,GAAG,CAAC,UAAA,MAAM,IAAI,OAAA,aAAa,CAAC,MAAM,CAAC,EAArB,CAAqB,CAAC,CAAA;IACrD,CAAC,CAAC,CAAA;IAEF,IAAM,QAAQ,GAAG,aAAa,CAAC,MAAM,CACnC,UAAC,GAAG,EAAE,KAAK,IAAK,OAAA,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,EAAjB,CAAiB,EAAE,EAAE,CACtC,CAAA;IAED,IAAI,UAAU,GAAkB,EAAE,CAAA;IAClC,IAAI,WAAW,GAAa,EAAE,CAAA;IAE9B,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE;QACvB,IAAI,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;QACnB,IAAM,OAAO,GAAG,SAAG,CACjB,QAAQ,CAAC,GAAG,CAAC,UAAA,IAAI,IAAI,OAAA,IAAI,CAAC,IAAI,EAAT,CAAS,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,UAAA,IAAI,IAAI,OAAA,IAAI,CAAC,KAAK,EAAV,CAAU,CAAC,EAChC,GAAG,CACJ,CAAA;QACD,KAAK,CAAC,UAAU,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;QAElC,WAAW,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,QAAQ,CAAC,GAAG,CAAC,CAAC,KAAK,EAAnB,CAAmB,CAAC,CAAA;QACrD,UAAU,GAAG,OAAO;aACjB,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,QAAQ,CAAC,GAAG,CAAC,EAAb,CAAa,CAAC;aACzB,GAAG,CAAC,UAAC,EAAgB;gBAAd,cAAI,EAAE,kBAAM;YAClB,OAAA,IAAI,yBAAW,CACb,IAAI,CAAC,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,EACtC,IAAI,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,GAAG,IAAI,CAAC,MAAM,CAAC,EACrC,IAAI,CAAC,KAAK,GAAG,CAAC,MAAM,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,EACxC,IAAI,CAAC,MAAM,GAAG,CAAC,MAAM,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC,CAC5C,CAAC,QAAQ,EAAE,CAAC,KAAK,EAAE;QALpB,CAKoB,CACrB,CAAA;KAEJ;IAED,OAAO;QACL,KAAK,EAAE,UAAU;QACjB,MAAM,EAAE,WAAW;KACpB,CAAA;AAEH,CAAC;AA5FD,wBA4FC"}
\ No newline at end of file

build/mtcnn/stage2.d.ts

+import { BoundingBox } from './BoundingBox';
+import { RNetParams } from './types';
+export declare function stage2(img: HTMLCanvasElement, inputBoxes: BoundingBox[], scoreThreshold: number, params: RNetParams, stats: any): Promise<{
+    boxes: BoundingBox[];
+    scores: number[];
+}>;

build/mtcnn/stage2.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var tf = require("@tensorflow/tfjs-core");
+var BoundingBox_1 = require("./BoundingBox");
+var extractImagePatches_1 = require("./extractImagePatches");
+var nms_1 = require("./nms");
+var RNet_1 = require("./RNet");
+function stage2(img, inputBoxes, scoreThreshold, params, stats) {
+    return tslib_1.__awaiter(this, void 0, void 0, function () {
+        var ts, rnetInputs, rnetOuts, scoresTensor, scores, _a, _b, indices, filteredBoxes, filteredScores, finalBoxes, finalScores, indicesNms, regions_1;
+        return tslib_1.__generator(this, function (_c) {
+            switch (_c.label) {
+                case 0:
+                    ts = Date.now();
+                    return [4 /*yield*/, extractImagePatches_1.extractImagePatches(img, inputBoxes, { width: 24, height: 24 })];
+                case 1:
+                    rnetInputs = _c.sent();
+                    stats.stage2_extractImagePatches = Date.now() - ts;
+                    ts = Date.now();
+                    rnetOuts = rnetInputs.map(function (rnetInput) {
+                        var out = RNet_1.RNet(rnetInput, params);
+                        rnetInput.dispose();
+                        return out;
+                    });
+                    stats.stage2_rnet = Date.now() - ts;
+                    scoresTensor = rnetOuts.length > 1
+                        ? tf.concat(rnetOuts.map(function (out) { return out.scores; }))
+                        : rnetOuts[0].scores;
+                    _b = (_a = Array).from;
+                    return [4 /*yield*/, scoresTensor.data()];
+                case 2:
+                    scores = _b.apply(_a, [_c.sent()]);
+                    scoresTensor.dispose();
+                    indices = scores
+                        .map(function (score, idx) { return ({ score: score, idx: idx }); })
+                        .filter(function (c) { return c.score > scoreThreshold; })
+                        .map(function (_a) {
+                        var idx = _a.idx;
+                        return idx;
+                    });
+                    filteredBoxes = indices.map(function (idx) { return inputBoxes[idx]; });
+                    filteredScores = indices.map(function (idx) { return scores[idx]; });
+                    finalBoxes = [];
+                    finalScores = [];
+                    if (filteredBoxes.length > 0) {
+                        ts = Date.now();
+                        indicesNms = nms_1.nms(filteredBoxes, filteredScores, 0.7);
+                        stats.stage2_nms = Date.now() - ts;
+                        regions_1 = indicesNms.map(function (idx) {
+                            return new BoundingBox_1.BoundingBox(rnetOuts[indices[idx]].regions.get(0, 0), rnetOuts[indices[idx]].regions.get(0, 1), rnetOuts[indices[idx]].regions.get(0, 2), rnetOuts[indices[idx]].regions.get(0, 3));
+                        });
+                        finalScores = indicesNms.map(function (idx) { return filteredScores[idx]; });
+                        finalBoxes = indicesNms.map(function (idx, i) { return filteredBoxes[idx].calibrate(regions_1[i]); });
+                    }
+                    rnetOuts.forEach(function (t) {
+                        t.regions.dispose();
+                        t.scores.dispose();
+                    });
+                    return [2 /*return*/, {
+                            boxes: finalBoxes,
+                            scores: finalScores
+                        }];
+            }
+        });
+    });
+}
+exports.stage2 = stage2;
+//# sourceMappingURL=stage2.js.map
\ No newline at end of file

build/mtcnn/stage2.js.map

+{"version":3,"file":"stage2.js","sourceRoot":"","sources":["../../src/mtcnn/stage2.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,6CAA4C;AAC5C,6DAA4D;AAC5D,6BAA4B;AAC5B,+BAA8B;AAG9B,gBACE,GAAsB,EACtB,UAAyB,EACzB,cAAsB,EACtB,MAAkB,EAClB,KAAU;;;;;;oBAGN,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;oBACA,qBAAM,yCAAmB,CAAC,GAAG,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,EAAE,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,EAAA;;oBAAlF,UAAU,GAAG,SAAqE;oBACxF,KAAK,CAAC,0BAA0B,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;oBAElD,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;oBACT,QAAQ,GAAG,UAAU,CAAC,GAAG,CAC7B,UAAA,SAAS;wBACP,IAAM,GAAG,GAAG,WAAI,CAAC,SAAS,EAAE,MAAM,CAAC,CAAA;wBACnC,SAAS,CAAC,OAAO,EAAE,CAAA;wBACnB,OAAO,GAAG,CAAA;oBACZ,CAAC,CACF,CAAA;oBACD,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;oBAE7B,YAAY,GAAG,QAAQ,CAAC,MAAM,GAAG,CAAC;wBACtC,CAAC,CAAC,EAAE,CAAC,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,GAAG,CAAC,MAAM,EAAV,CAAU,CAAC,CAAC;wBAC5C,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;oBACP,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;oBAAC,qBAAM,YAAY,CAAC,IAAI,EAAE,EAAA;;oBAA7C,MAAM,GAAG,cAAW,SAAyB,EAAC;oBACpD,YAAY,CAAC,OAAO,EAAE,CAAA;oBAEhB,OAAO,GAAG,MAAM;yBACnB,GAAG,CAAC,UAAC,KAAK,EAAE,GAAG,IAAK,OAAA,CAAC,EAAE,KAAK,OAAA,EAAE,GAAG,KAAA,EAAE,CAAC,EAAhB,CAAgB,CAAC;yBACrC,MAAM,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,KAAK,GAAG,cAAc,EAAxB,CAAwB,CAAC;yBACrC,GAAG,CAAC,UAAC,EAAO;4BAAL,YAAG;wBAAO,OAAA,GAAG;oBAAH,CAAG,CAAC,CAAA;oBAElB,aAAa,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,UAAU,CAAC,GAAG,CAAC,EAAf,CAAe,CAAC,CAAA;oBACnD,cAAc,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,MAAM,CAAC,GAAG,CAAC,EAAX,CAAW,CAAC,CAAA;oBAElD,UAAU,GAAkB,EAAE,CAAA;oBAC9B,WAAW,GAAa,EAAE,CAAA;oBAE9B,IAAI,aAAa,CAAC,MAAM,GAAG,CAAC,EAAE;wBAC5B,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBACT,UAAU,GAAG,SAAG,CACpB,aAAa,EACb,cAAc,EACd,GAAG,CACJ,CAAA;wBACD,KAAK,CAAC,UAAU,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;wBAE5B,YAAU,UAAU,CAAC,GAAG,CAAC,UAAA,GAAG;4BAChC,OAAA,IAAI,yBAAW,CACb,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EACxC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EACxC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EACxC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CACzC;wBALD,CAKC,CACF,CAAA;wBAED,WAAW,GAAG,UAAU,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,cAAc,CAAC,GAAG,CAAC,EAAnB,CAAmB,CAAC,CAAA;wBACxD,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,UAAC,GAAG,EAAE,CAAC,IAAK,OAAA,aAAa,CAAC,GAAG,CAAC,CAAC,SAAS,CAAC,SAAO,CAAC,CAAC,CAAC,CAAC,EAAxC,CAAwC,CAAC,CAAA;qBAClF;oBAED,QAAQ,CAAC,OAAO,CAAC,UAAA,CAAC;wBAChB,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,CAAA;wBACnB,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,CAAA;oBACpB,CAAC,CAAC,CAAA;oBAEF,sBAAO;4BACL,KAAK,EAAE,UAAU;4BACjB,MAAM,EAAE,WAAW;yBACpB,EAAA;;;;CACF;AAtED,wBAsEC"}
\ No newline at end of file

build/mtcnn/stage3.1.d.ts

+import { Point } from '../Point';
+import { BoundingBox } from './BoundingBox';
+import { ONetParams } from './types';
+export declare function stage3(img: HTMLCanvasElement, inputBoxes: BoundingBox[], scoreThreshold: number, params: ONetParams, stats: any): Promise<{
+    boxes: BoundingBox[];
+    scores: number[];
+    points: Point[][];
+}>;

build/mtcnn/stage3.1.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var Point_1 = require("../Point");
+var BoundingBox_1 = require("./BoundingBox");
+var extractImagePatches_1 = require("./extractImagePatches");
+var nms_1 = require("./nms");
+var ONet_1 = require("./ONet");
+var tf = require("@tensorflow/tfjs-core");
+function stage3(img, inputBoxes, scoreThreshold, params, stats) {
+    return tslib_1.__awaiter(this, void 0, void 0, function () {
+        var ts, onetInputs, onetOuts, scoresTensor, scores, _a, _b, indices, filteredRegions, filteredBoxes, filteredScores, finalBoxes, finalScores, points, indicesNms;
+        return tslib_1.__generator(this, function (_c) {
+            switch (_c.label) {
+                case 0:
+                    ts = Date.now();
+                    return [4 /*yield*/, extractImagePatches_1.extractImagePatches(img, inputBoxes, { width: 48, height: 48 })];
+                case 1:
+                    onetInputs = _c.sent();
+                    stats.stage3_extractImagePatches = Date.now() - ts;
+                    ts = Date.now();
+                    onetOuts = onetInputs.map(function (onetInput) {
+                        var out = ONet_1.ONet(onetInput, params);
+                        onetInput.dispose();
+                        return out;
+                    });
+                    stats.stage3_onet = Date.now() - ts;
+                    console.time('scoreDatas2');
+                    scoresTensor = onetOuts.length > 1
+                        ? tf.tidy(function () { return tf.concat(onetOuts.map(function (out) { return out.scores; })); })
+                        : onetOuts[0].scores;
+                    _b = (_a = Array).from;
+                    return [4 /*yield*/, scoresTensor.data()];
+                case 2:
+                    scores = _b.apply(_a, [_c.sent()]);
+                    scoresTensor.dispose();
+                    console.timeEnd('scoreDatas2');
+                    indices = scores
+                        .map(function (score, idx) { return ({ score: score, idx: idx }); })
+                        .filter(function (c) { return c.score > scoreThreshold; })
+                        .map(function (_a) {
+                        var idx = _a.idx;
+                        return idx;
+                    });
+                    filteredRegions = indices.map(function (idx) { return new BoundingBox_1.BoundingBox(onetOuts[idx].regions.get(0, 0), onetOuts[idx].regions.get(0, 1), onetOuts[idx].regions.get(0, 2), onetOuts[idx].regions.get(0, 3)); });
+                    filteredBoxes = indices
+                        .map(function (idx, i) { return inputBoxes[idx].calibrate(filteredRegions[i]); });
+                    filteredScores = indices.map(function (idx) { return scores[idx]; });
+                    finalBoxes = [];
+                    finalScores = [];
+                    points = [];
+                    if (filteredBoxes.length > 0) {
+                        ts = Date.now();
+                        indicesNms = nms_1.nms(filteredBoxes, filteredScores, 0.7, false);
+                        stats.stage3_nms = Date.now() - ts;
+                        finalBoxes = indicesNms.map(function (idx) { return filteredBoxes[idx]; });
+                        finalScores = indicesNms.map(function (idx) { return filteredScores[idx]; });
+                        points = indicesNms.map(function (idx, i) {
+                            return Array(5).fill(0).map(function (_, ptIdx) {
+                                return new Point_1.Point(((onetOuts[idx].points.get(0, ptIdx) * (finalBoxes[i].width + 1)) + finalBoxes[i].left), ((onetOuts[idx].points.get(0, ptIdx + 5) * (finalBoxes[i].height + 1)) + finalBoxes[i].top));
+                            });
+                        });
+                    }
+                    onetOuts.forEach(function (t) {
+                        t.regions.dispose();
+                        t.scores.dispose();
+                        t.points.dispose();
+                    });
+                    return [2 /*return*/, {
+                            boxes: finalBoxes,
+                            scores: finalScores,
+                            points: points
+                        }];
+            }
+        });
+    });
+}
+exports.stage3 = stage3;
+//# sourceMappingURL=stage3.1.js.map
\ No newline at end of file

build/mtcnn/stage3.1.js.map

+{"version":3,"file":"stage3.1.js","sourceRoot":"","sources":["../../src/mtcnn/stage3.1.ts"],"names":[],"mappings":";;;AAAA,kCAAiC;AACjC,6CAA4C;AAC5C,6DAA4D;AAC5D,6BAA4B;AAC5B,+BAA8B;AAE9B,0CAA4C;AAE5C,gBACE,GAAsB,EACtB,UAAyB,EACzB,cAAsB,EACtB,MAAkB,EAClB,KAAU;;;;;;oBAGN,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;oBACA,qBAAM,yCAAmB,CAAC,GAAG,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,EAAE,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,EAAA;;oBAAlF,UAAU,GAAG,SAAqE;oBACxF,KAAK,CAAC,0BAA0B,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;oBAElD,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;oBACT,QAAQ,GAAG,UAAU,CAAC,GAAG,CAC7B,UAAA,SAAS;wBACP,IAAM,GAAG,GAAG,WAAI,CAAC,SAAS,EAAE,MAAM,CAAC,CAAA;wBACnC,SAAS,CAAC,OAAO,EAAE,CAAA;wBACnB,OAAO,GAAG,CAAA;oBACZ,CAAC,CACF,CAAA;oBACD,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;oBAEnC,OAAO,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;oBACrB,YAAY,GAAG,QAAQ,CAAC,MAAM,GAAG,CAAC;wBACtC,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,cAAM,OAAA,EAAE,CAAC,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,GAAG,CAAC,MAAM,EAAV,CAAU,CAAC,CAAC,EAA1C,CAA0C,CAAC;wBAC3D,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;oBACP,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;oBAAC,qBAAM,YAAY,CAAC,IAAI,EAAE,EAAA;;oBAA7C,MAAM,GAAG,cAAW,SAAyB,EAAC;oBACpD,YAAY,CAAC,OAAO,EAAE,CAAA;oBACtB,OAAO,CAAC,OAAO,CAAC,aAAa,CAAC,CAAA;oBAExB,OAAO,GAAG,MAAM;yBACnB,GAAG,CAAC,UAAC,KAAK,EAAE,GAAG,IAAK,OAAA,CAAC,EAAE,KAAK,OAAA,EAAE,GAAG,KAAA,EAAE,CAAC,EAAhB,CAAgB,CAAC;yBACrC,MAAM,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,KAAK,GAAG,cAAc,EAAxB,CAAwB,CAAC;yBACrC,GAAG,CAAC,UAAC,EAAO;4BAAL,YAAG;wBAAO,OAAA,GAAG;oBAAH,CAAG,CAAC,CAAA;oBAElB,eAAe,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,IAAI,yBAAW,CACxD,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CAChC,EAL0C,CAK1C,CAAC,CAAA;oBACI,aAAa,GAAG,OAAO;yBAC1B,GAAG,CAAC,UAAC,GAAG,EAAE,CAAC,IAAK,OAAA,UAAU,CAAC,GAAG,CAAC,CAAC,SAAS,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC,EAA7C,CAA6C,CAAC,CAAA;oBAC3D,cAAc,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,MAAM,CAAC,GAAG,CAAC,EAAX,CAAW,CAAC,CAAA;oBAElD,UAAU,GAAkB,EAAE,CAAA;oBAC9B,WAAW,GAAa,EAAE,CAAA;oBAC1B,MAAM,GAAc,EAAE,CAAA;oBAE1B,IAAI,aAAa,CAAC,MAAM,GAAG,CAAC,EAAE;wBAE5B,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBACT,UAAU,GAAG,SAAG,CACpB,aAAa,EACb,cAAc,EACd,GAAG,EACH,KAAK,CACN,CAAA;wBACD,KAAK,CAAC,UAAU,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;wBAElC,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,aAAa,CAAC,GAAG,CAAC,EAAlB,CAAkB,CAAC,CAAA;wBACtD,WAAW,GAAG,UAAU,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,cAAc,CAAC,GAAG,CAAC,EAAnB,CAAmB,CAAC,CAAA;wBACxD,MAAM,GAAG,UAAU,CAAC,GAAG,CAAC,UAAC,GAAG,EAAE,CAAC;4BAC7B,OAAA,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,UAAC,CAAC,EAAE,KAAK;gCAC5B,OAAA,IAAI,aAAK,CACP,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,EACvF,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,GAAG,CAAC,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAC5F;4BAHD,CAGC,CACF;wBALD,CAKC,CACF,CAAA;qBACF;oBAED,QAAQ,CAAC,OAAO,CAAC,UAAA,CAAC;wBAChB,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,CAAA;wBACnB,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,CAAA;wBAClB,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,CAAA;oBACpB,CAAC,CAAC,CAAA;oBAEF,sBAAO;4BACL,KAAK,EAAE,UAAU;4BACjB,MAAM,EAAE,WAAW;4BACnB,MAAM,QAAA;yBACP,EAAA;;;;CAEF;AApFD,wBAoFC"}
\ No newline at end of file

build/mtcnn/stage3.d.ts

+import { Point } from '../Point';
+import { BoundingBox } from './BoundingBox';
+import { ONetParams } from './types';
+export declare function stage3(img: HTMLCanvasElement, inputBoxes: BoundingBox[], scoreThreshold: number, params: ONetParams, stats: any): Promise<{
+    boxes: BoundingBox[];
+    scores: number[];
+    points: Point[][];
+}>;

build/mtcnn/stage3.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+var tslib_1 = require("tslib");
+var tf = require("@tensorflow/tfjs-core");
+var Point_1 = require("../Point");
+var BoundingBox_1 = require("./BoundingBox");
+var extractImagePatches_1 = require("./extractImagePatches");
+var nms_1 = require("./nms");
+var ONet_1 = require("./ONet");
+function stage3(img, inputBoxes, scoreThreshold, params, stats) {
+    return tslib_1.__awaiter(this, void 0, void 0, function () {
+        var ts, onetInputs, onetOuts, scoresTensor, scores, _a, _b, indices, filteredRegions, filteredBoxes, filteredScores, finalBoxes, finalScores, points, indicesNms;
+        return tslib_1.__generator(this, function (_c) {
+            switch (_c.label) {
+                case 0:
+                    ts = Date.now();
+                    return [4 /*yield*/, extractImagePatches_1.extractImagePatches(img, inputBoxes, { width: 48, height: 48 })];
+                case 1:
+                    onetInputs = _c.sent();
+                    stats.stage3_extractImagePatches = Date.now() - ts;
+                    ts = Date.now();
+                    onetOuts = onetInputs.map(function (onetInput) {
+                        var out = ONet_1.ONet(onetInput, params);
+                        onetInput.dispose();
+                        return out;
+                    });
+                    stats.stage3_onet = Date.now() - ts;
+                    scoresTensor = onetOuts.length > 1
+                        ? tf.concat(onetOuts.map(function (out) { return out.scores; }))
+                        : onetOuts[0].scores;
+                    _b = (_a = Array).from;
+                    return [4 /*yield*/, scoresTensor.data()];
+                case 2:
+                    scores = _b.apply(_a, [_c.sent()]);
+                    scoresTensor.dispose();
+                    indices = scores
+                        .map(function (score, idx) { return ({ score: score, idx: idx }); })
+                        .filter(function (c) { return c.score > scoreThreshold; })
+                        .map(function (_a) {
+                        var idx = _a.idx;
+                        return idx;
+                    });
+                    filteredRegions = indices.map(function (idx) { return new BoundingBox_1.BoundingBox(onetOuts[idx].regions.get(0, 0), onetOuts[idx].regions.get(0, 1), onetOuts[idx].regions.get(0, 2), onetOuts[idx].regions.get(0, 3)); });
+                    filteredBoxes = indices
+                        .map(function (idx, i) { return inputBoxes[idx].calibrate(filteredRegions[i]); });
+                    filteredScores = indices.map(function (idx) { return scores[idx]; });
+                    finalBoxes = [];
+                    finalScores = [];
+                    points = [];
+                    if (filteredBoxes.length > 0) {
+                        ts = Date.now();
+                        indicesNms = nms_1.nms(filteredBoxes, filteredScores, 0.7, false);
+                        stats.stage3_nms = Date.now() - ts;
+                        finalBoxes = indicesNms.map(function (idx) { return filteredBoxes[idx]; });
+                        finalScores = indicesNms.map(function (idx) { return filteredScores[idx]; });
+                        points = indicesNms.map(function (idx, i) {
+                            return Array(5).fill(0).map(function (_, ptIdx) {
+                                return new Point_1.Point(((onetOuts[idx].points.get(0, ptIdx) * (finalBoxes[i].width + 1)) + finalBoxes[i].left), ((onetOuts[idx].points.get(0, ptIdx + 5) * (finalBoxes[i].height + 1)) + finalBoxes[i].top));
+                            });
+                        });
+                    }
+                    onetOuts.forEach(function (t) {
+                        t.regions.dispose();
+                        t.scores.dispose();
+                        t.points.dispose();
+                    });
+                    return [2 /*return*/, {
+                            boxes: finalBoxes,
+                            scores: finalScores,
+                            points: points
+                        }];
+            }
+        });
+    });
+}
+exports.stage3 = stage3;
+//# sourceMappingURL=stage3.js.map
\ No newline at end of file

build/mtcnn/stage3.js.map

+{"version":3,"file":"stage3.js","sourceRoot":"","sources":["../../src/mtcnn/stage3.ts"],"names":[],"mappings":";;;AAAA,0CAA4C;AAE5C,kCAAiC;AACjC,6CAA4C;AAC5C,6DAA4D;AAC5D,6BAA4B;AAC5B,+BAA8B;AAG9B,gBACE,GAAsB,EACtB,UAAyB,EACzB,cAAsB,EACtB,MAAkB,EAClB,KAAU;;;;;;oBAGN,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;oBACA,qBAAM,yCAAmB,CAAC,GAAG,EAAE,UAAU,EAAE,EAAE,KAAK,EAAE,EAAE,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,EAAA;;oBAAlF,UAAU,GAAG,SAAqE;oBACxF,KAAK,CAAC,0BAA0B,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;oBAElD,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;oBACT,QAAQ,GAAG,UAAU,CAAC,GAAG,CAC7B,UAAA,SAAS;wBACP,IAAM,GAAG,GAAG,WAAI,CAAC,SAAS,EAAE,MAAM,CAAC,CAAA;wBACnC,SAAS,CAAC,OAAO,EAAE,CAAA;wBACnB,OAAO,GAAG,CAAA;oBACZ,CAAC,CACF,CAAA;oBACD,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;oBAE7B,YAAY,GAAG,QAAQ,CAAC,MAAM,GAAG,CAAC;wBACtC,CAAC,CAAC,EAAE,CAAC,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,GAAG,CAAC,MAAM,EAAV,CAAU,CAAC,CAAC;wBAC5C,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;oBACP,KAAA,CAAA,KAAA,KAAK,CAAA,CAAC,IAAI,CAAA;oBAAC,qBAAM,YAAY,CAAC,IAAI,EAAE,EAAA;;oBAA7C,MAAM,GAAG,cAAW,SAAyB,EAAC;oBACpD,YAAY,CAAC,OAAO,EAAE,CAAA;oBAEhB,OAAO,GAAG,MAAM;yBACnB,GAAG,CAAC,UAAC,KAAK,EAAE,GAAG,IAAK,OAAA,CAAC,EAAE,KAAK,OAAA,EAAE,GAAG,KAAA,EAAE,CAAC,EAAhB,CAAgB,CAAC;yBACrC,MAAM,CAAC,UAAA,CAAC,IAAI,OAAA,CAAC,CAAC,KAAK,GAAG,cAAc,EAAxB,CAAwB,CAAC;yBACrC,GAAG,CAAC,UAAC,EAAO;4BAAL,YAAG;wBAAO,OAAA,GAAG;oBAAH,CAAG,CAAC,CAAA;oBAElB,eAAe,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,IAAI,yBAAW,CACxD,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,EAC/B,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CAChC,EAL0C,CAK1C,CAAC,CAAA;oBACI,aAAa,GAAG,OAAO;yBAC1B,GAAG,CAAC,UAAC,GAAG,EAAE,CAAC,IAAK,OAAA,UAAU,CAAC,GAAG,CAAC,CAAC,SAAS,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC,EAA7C,CAA6C,CAAC,CAAA;oBAC3D,cAAc,GAAG,OAAO,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,MAAM,CAAC,GAAG,CAAC,EAAX,CAAW,CAAC,CAAA;oBAElD,UAAU,GAAkB,EAAE,CAAA;oBAC9B,WAAW,GAAa,EAAE,CAAA;oBAC1B,MAAM,GAAc,EAAE,CAAA;oBAE1B,IAAI,aAAa,CAAC,MAAM,GAAG,CAAC,EAAE;wBAE5B,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;wBACT,UAAU,GAAG,SAAG,CACpB,aAAa,EACb,cAAc,EACd,GAAG,EACH,KAAK,CACN,CAAA;wBACD,KAAK,CAAC,UAAU,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;wBAElC,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,aAAa,CAAC,GAAG,CAAC,EAAlB,CAAkB,CAAC,CAAA;wBACtD,WAAW,GAAG,UAAU,CAAC,GAAG,CAAC,UAAA,GAAG,IAAI,OAAA,cAAc,CAAC,GAAG,CAAC,EAAnB,CAAmB,CAAC,CAAA;wBACxD,MAAM,GAAG,UAAU,CAAC,GAAG,CAAC,UAAC,GAAG,EAAE,CAAC;4BAC7B,OAAA,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,UAAC,CAAC,EAAE,KAAK;gCAC5B,OAAA,IAAI,aAAK,CACP,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,EACvF,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,GAAG,CAAC,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAC5F;4BAHD,CAGC,CACF;wBALD,CAKC,CACF,CAAA;qBACF;oBAED,QAAQ,CAAC,OAAO,CAAC,UAAA,CAAC;wBAChB,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,CAAA;wBACnB,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,CAAA;wBAClB,CAAC,CAAC,MAAM,CAAC,OAAO,EAAE,CAAA;oBACpB,CAAC,CAAC,CAAA;oBAEF,sBAAO;4BACL,KAAK,EAAE,UAAU;4BACjB,MAAM,EAAE,WAAW;4BACnB,MAAM,QAAA;yBACP,EAAA;;;;CAEF;AAlFD,wBAkFC"}
\ No newline at end of file

build/mtcnn/types.d.ts

+import * as tf from '@tensorflow/tfjs-core';
+import { ConvParams, FCParams } from '../commons/types';
+import { FaceDetection } from '../FaceDetection';
+import { FaceLandmarks5 } from './FaceLandmarks5';
+export declare type SharedParams = {
+    conv1: ConvParams;
+    prelu1_alpha: tf.Tensor1D;
+    conv2: ConvParams;
+    prelu2_alpha: tf.Tensor1D;
+    conv3: ConvParams;
+    prelu3_alpha: tf.Tensor1D;
+};
+export declare type PNetParams = SharedParams & {
+    conv4_1: ConvParams;
+    conv4_2: ConvParams;
+};
+export declare type RNetParams = SharedParams & {
+    fc1: FCParams;
+    prelu4_alpha: tf.Tensor1D;
+    fc2_1: FCParams;
+    fc2_2: FCParams;
+};
+export declare type ONetParams = SharedParams & {
+    conv4: ConvParams;
+    prelu4_alpha: tf.Tensor1D;
+    fc1: FCParams;
+    prelu5_alpha: tf.Tensor1D;
+    fc2_1: FCParams;
+    fc2_2: FCParams;
+    fc2_3: FCParams;
+};
+export declare type NetParams = {
+    pnet: PNetParams;
+    rnet: RNetParams;
+    onet: ONetParams;
+};
+export declare type MtcnnResult = {
+    faceDetection: FaceDetection;
+    faceLandmarks: FaceLandmarks5;
+};
+export declare type MtcnnForwardParams = {
+    minFaceSize?: number;
+    scaleFactor?: number;
+    maxNumScales?: number;
+    scoreThresholds?: number[];
+    scaleSteps?: number[];
+};

build/mtcnn/types.js

+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+//# sourceMappingURL=types.js.map
\ No newline at end of file

build/mtcnn/types.js.map

+{"version":3,"file":"types.js","sourceRoot":"","sources":["../../src/mtcnn/types.ts"],"names":[],"mappings":""}
\ No newline at end of file

build/toNetInput.d.ts

@@ -9,4 +9,4 @@ import { TNetInput } from './types';
  * determines, whether to set the NetInput as managed or not.
  * @returns A NetInput instance, which can be passed into one of the neural networks.
  */
-export declare function toNetInput(inputs: TNetInput, manageCreatedInput?: boolean): Promise<NetInput>;
+export declare function toNetInput(inputs: TNetInput, manageCreatedInput?: boolean, keepCanvases?: boolean): Promise<NetInput>;

build/toNetInput.js

@@ -14,8 +14,9 @@ var utils_1 = require("./utils");
  * determines, whether to set the NetInput as managed or not.
  * @returns A NetInput instance, which can be passed into one of the neural networks.
  */
-function toNetInput(inputs, manageCreatedInput) {
+function toNetInput(inputs, manageCreatedInput, keepCanvases) {
     if (manageCreatedInput === void 0) { manageCreatedInput = false; }
+    if (keepCanvases === void 0) { keepCanvases = false; }
     return tslib_1.__awaiter(this, void 0, void 0, function () {
         var afterCreate, inputArgArray, getIdxHint, inputArray;
         return tslib_1.__generator(this, function (_a) {
@@ -58,7 +59,7 @@ function toNetInput(inputs, manageCreatedInput) {
                 case 1:
                     // wait for all media elements being loaded
                     _a.sent();
-                    return [2 /*return*/, afterCreate(new NetInput_1.NetInput(inputArray, Array.isArray(inputs)))];
+                    return [2 /*return*/, afterCreate(new NetInput_1.NetInput(inputArray, Array.isArray(inputs), keepCanvases))];
             }
         });
     });

build/toNetInput.js.map

-{"version":3,"file":"toNetInput.js","sourceRoot":"","sources":["../src/toNetInput.ts"],"names":[],"mappings":";;;AAEA,2DAA0D;AAC1D,+CAA4D;AAC5D,uCAAsC;AAEtC,iCAAyD;AAEzD;;;;;;;;GAQG;AACH,oBACE,MAAiB,EACjB,kBAAmC;IAAnC,mCAAA,EAAA,0BAAmC;;;;;;oBAEnC,IAAI,MAAM,YAAY,mBAAQ,EAAE;wBAC9B,sBAAO,MAAM,EAAA;qBACd;oBAEK,WAAW,GAAG,UAAC,QAAkB,IAAK,OAAA,kBAAkB;wBAC5D,CAAC,CAAC,QAAQ,CAAC,OAAO,EAAE;wBACpB,CAAC,CAAC,QAAQ,EAFgC,CAEhC,CAAA;oBAEZ,IAAI,qBAAU,CAAC,MAAM,CAAC,EAAE;wBACtB,sBAAO,WAAW,CAAC,IAAI,mBAAQ,CAAC,MAAqB,CAAC,CAAC,EAAA;qBACxD;oBAEG,aAAa,GAAG,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC;wBACrC,CAAC,CAAC,MAAM;wBACR,CAAC,CAAC,CAAC,MAAM,CAAC,CAAA;oBAEd,IAAI,CAAC,aAAa,CAAC,MAAM,EAAE;wBACzB,MAAM,IAAI,KAAK,CAAC,0CAA0C,CAAC,CAAA;qBAC5D;oBAEK,UAAU,GAAG,UAAC,GAAW,IAAK,OAAA,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,qBAAmB,GAAG,MAAG,CAAC,CAAC,CAAC,EAAE,EAAtD,CAAsD,CAAA;oBAEpF,UAAU,GAAG,aAAa,CAAC,GAAG,CAAC,oBAAY,CAAC,CAAA;oBAElD,UAAU,CAAC,OAAO,CAAC,UAAC,KAAK,EAAE,CAAC;wBAC1B,IAAI,CAAC,+BAAc,CAAC,KAAK,CAAC,IAAI,CAAC,qBAAU,CAAC,KAAK,CAAC,IAAI,CAAC,qBAAU,CAAC,KAAK,CAAC,EAAE;4BAEtE,IAAI,OAAO,aAAa,CAAC,CAAC,CAAC,KAAK,QAAQ,EAAE;gCACxC,MAAM,IAAI,KAAK,CAAC,iBAAe,UAAU,CAAC,CAAC,CAAC,yEAAoE,aAAa,CAAC,CAAC,CAAG,CAAC,CAAA;6BACpI;4BAED,MAAM,IAAI,KAAK,CAAC,iBAAe,UAAU,CAAC,CAAC,CAAC,gIAA6H,CAAC,CAAA;yBAC3K;wBAED,IAAI,qBAAU,CAAC,KAAK,CAAC,EAAE;4BACrB,0EAA0E;4BAC1E,IAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;4BAChC,IAAI,SAAS,KAAK,CAAC,EAAE;gCACnB,MAAM,IAAI,KAAK,CAAC,iBAAe,UAAU,CAAC,CAAC,CAAC,oCAA+B,SAAS,8CAA2C,CAAC,CAAA;6BACjI;yBACF;oBACH,CAAC,CAAC,CAAA;oBAEF,2CAA2C;oBAC3C,qBAAM,OAAO,CAAC,GAAG,CACf,UAAU,CAAC,GAAG,CAAC,UAAA,KAAK,IAAI,OAAA,+BAAc,CAAC,KAAK,CAAC,IAAI,wBAAgB,CAAC,KAAK,CAAC,EAAhD,CAAgD,CAAC,CAC1E,EAAA;;oBAHD,2CAA2C;oBAC3C,SAEC,CAAA;oBAED,sBAAO,WAAW,CAAC,IAAI,mBAAQ,CAAC,UAAU,EAAE,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,EAAA;;;;CACpE;AArDD,gCAqDC"}
\ No newline at end of file
+{"version":3,"file":"toNetInput.js","sourceRoot":"","sources":["../src/toNetInput.ts"],"names":[],"mappings":";;;AAEA,2DAA0D;AAC1D,+CAA4D;AAC5D,uCAAsC;AAEtC,iCAAyD;AAEzD;;;;;;;;GAQG;AACH,oBACE,MAAiB,EACjB,kBAAmC,EACnC,YAA6B;IAD7B,mCAAA,EAAA,0BAAmC;IACnC,6BAAA,EAAA,oBAA6B;;;;;;oBAE7B,IAAI,MAAM,YAAY,mBAAQ,EAAE;wBAC9B,sBAAO,MAAM,EAAA;qBACd;oBAEK,WAAW,GAAG,UAAC,QAAkB,IAAK,OAAA,kBAAkB;wBAC5D,CAAC,CAAC,QAAQ,CAAC,OAAO,EAAE;wBACpB,CAAC,CAAC,QAAQ,EAFgC,CAEhC,CAAA;oBAEZ,IAAI,qBAAU,CAAC,MAAM,CAAC,EAAE;wBACtB,sBAAO,WAAW,CAAC,IAAI,mBAAQ,CAAC,MAAqB,CAAC,CAAC,EAAA;qBACxD;oBAEG,aAAa,GAAG,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC;wBACrC,CAAC,CAAC,MAAM;wBACR,CAAC,CAAC,CAAC,MAAM,CAAC,CAAA;oBAEd,IAAI,CAAC,aAAa,CAAC,MAAM,EAAE;wBACzB,MAAM,IAAI,KAAK,CAAC,0CAA0C,CAAC,CAAA;qBAC5D;oBAEK,UAAU,GAAG,UAAC,GAAW,IAAK,OAAA,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,qBAAmB,GAAG,MAAG,CAAC,CAAC,CAAC,EAAE,EAAtD,CAAsD,CAAA;oBAEpF,UAAU,GAAG,aAAa,CAAC,GAAG,CAAC,oBAAY,CAAC,CAAA;oBAElD,UAAU,CAAC,OAAO,CAAC,UAAC,KAAK,EAAE,CAAC;wBAC1B,IAAI,CAAC,+BAAc,CAAC,KAAK,CAAC,IAAI,CAAC,qBAAU,CAAC,KAAK,CAAC,IAAI,CAAC,qBAAU,CAAC,KAAK,CAAC,EAAE;4BAEtE,IAAI,OAAO,aAAa,CAAC,CAAC,CAAC,KAAK,QAAQ,EAAE;gCACxC,MAAM,IAAI,KAAK,CAAC,iBAAe,UAAU,CAAC,CAAC,CAAC,yEAAoE,aAAa,CAAC,CAAC,CAAG,CAAC,CAAA;6BACpI;4BAED,MAAM,IAAI,KAAK,CAAC,iBAAe,UAAU,CAAC,CAAC,CAAC,gIAA6H,CAAC,CAAA;yBAC3K;wBAED,IAAI,qBAAU,CAAC,KAAK,CAAC,EAAE;4BACrB,0EAA0E;4BAC1E,IAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;4BAChC,IAAI,SAAS,KAAK,CAAC,EAAE;gCACnB,MAAM,IAAI,KAAK,CAAC,iBAAe,UAAU,CAAC,CAAC,CAAC,oCAA+B,SAAS,8CAA2C,CAAC,CAAA;6BACjI;yBACF;oBACH,CAAC,CAAC,CAAA;oBAEF,2CAA2C;oBAC3C,qBAAM,OAAO,CAAC,GAAG,CACf,UAAU,CAAC,GAAG,CAAC,UAAA,KAAK,IAAI,OAAA,+BAAc,CAAC,KAAK,CAAC,IAAI,wBAAgB,CAAC,KAAK,CAAC,EAAhD,CAAgD,CAAC,CAC1E,EAAA;;oBAHD,2CAA2C;oBAC3C,SAEC,CAAA;oBAED,sBAAO,WAAW,CAAC,IAAI,mBAAQ,CAAC,UAAU,EAAE,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,YAAY,CAAC,CAAC,EAAA;;;;CAClF;AAtDD,gCAsDC"}
\ No newline at end of file

examples/public/commons.js

@@ -115,6 +115,18 @@ function renderNavBar(navbarId, exampleUri) {
       name: 'Detect and Recognize Faces'
     },
     {
+      uri: 'mtcnn_face_detection',
+      name: 'MTCNN Face Detection'
+    },
+    {
+      uri: 'mtcnn_face_detection_video',
+      name: 'MTCNN Face Detection Video'
+    },
+    {
+      uri: 'mtcnn_face_detection_webcam',
+      name: 'MTCNN Face Detection Webcam'
+    },
+    {
       uri: 'batch_face_landmarks',
       name: 'Batch Face Landmarks'
     },
@@ -151,7 +163,7 @@ function renderNavBar(navbarId, exampleUri) {
   githubLink.id = 'github-link'
   githubLink.href = 'https://github.com/justadudewhohacks/face-api.js'
   const h5 = document.createElement('h5')
-  h5.innerHTML = 'face-api.js'//'If you like this project, feel free to leave a star on github :)'
+  h5.innerHTML = 'face-api.js'
   githubLink.appendChild(h5)
   const githubLinkIcon = document.createElement('img')
   githubLinkIcon.src = 'github_link_icon.png'
@@ -168,7 +180,10 @@ function renderNavBar(navbarId, exampleUri) {
       const a = document.createElement('a')
       a.classList.add('waves-effect', 'waves-light')
       a.href = ex.uri
-      a.innerHTML = ex.name
+      const span = document.createElement('span')
+      span.innerHTML = ex.name
+      span.style.whiteSpace = 'nowrap'
+      a.appendChild(span)
       li.appendChild(a)
       menuContent.appendChild(li)
     })

examples/server.js

@@ -24,6 +24,9 @@ app.get('/detect_and_draw_faces', (req, res) => res.sendFile(path.join(viewsDir,
 app.get('/detect_and_draw_landmarks', (req, res) => res.sendFile(path.join(viewsDir, 'detectAndDrawLandmarks.html')))
 app.get('/face_alignment', (req, res) => res.sendFile(path.join(viewsDir, 'faceAlignment.html')))
 app.get('/detect_and_recognize_faces', (req, res) => res.sendFile(path.join(viewsDir, 'detectAndRecognizeFaces.html')))
+app.get('/mtcnn_face_detection', (req, res) => res.sendFile(path.join(viewsDir, 'mtcnnFaceDetection.html')))
+app.get('/mtcnn_face_detection_video', (req, res) => res.sendFile(path.join(viewsDir, 'mtcnnFaceDetectionVideo.html')))
+app.get('/mtcnn_face_detection_webcam', (req, res) => res.sendFile(path.join(viewsDir, 'mtcnnFaceDetectionWebcam.html')))
 app.get('/batch_face_landmarks', (req, res) => res.sendFile(path.join(viewsDir, 'batchFaceLandmarks.html')))
 app.get('/batch_face_recognition', (req, res) => res.sendFile(path.join(viewsDir, 'batchFaceRecognition.html')))
 

examples/views/mtcnnFaceDetection.html

+<!DOCTYPE html>
+<html>
+<head>
+  <script src="face-api.js"></script>
+  <script src="commons.js"></script>
+  <link rel="stylesheet" href="styles.css">
+  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/0.100.2/css/materialize.css">
+  <script type="text/javascript" src="https://code.jquery.com/jquery-2.1.1.min.js"></script>
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/materialize/0.100.2/js/materialize.min.js"></script>
+</head>
+<body>
+  <div id="navbar"></div>
+  <div class="center-content page-container">
+    <div class="progress" id="loader">
+      <div class="indeterminate"></div>
+    </div>
+    <div style="position: relative" class="margin">
+      <img id="inputImg" src="" style="max-width: 800px;" />
+      <canvas id="overlay" />
+    </div>
+    <div class="row side-by-side">
+      <div id="selectList"></div>
+      <div class="row">
+        <label for="imgUrlInput">Get image from URL:</label>
+        <input id="imgUrlInput" type="text" class="bold">
+      </div>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="loadImageFromUrl()"
+      >
+        Ok
+      </button>
+    </div>
+    <div class="row side-by-side">
+      <div class="row">
+        <label for="minConfidence">Min Confidence:</label>
+        <input disabled value="0.7" id="minConfidence" type="text" class="bold">
+      </div>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="onDecreaseThreshold()"
+      >
+        <i class="material-icons left">-</i>
+      </button>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="onIncreaseThreshold()"
+      >
+        <i class="material-icons left">+</i>
+      </button>
+    </div>
+  </div>
+
+  <script>
+    let minFaceSize = 50
+    let scaleFactor = 0.709
+    let maxNumScales = 10
+    let stage1Threshold = 0.7
+    let stage2Threshold = 0.7
+    let stage3Threshold = 0.7
+    let mtcnn
+
+    function onIncreaseThreshold() {
+      minConfidence = Math.min(faceapi.round(minConfidence + 0.1), 1.0)
+      $('#minConfidence').val(minConfidence)
+      updateResults()
+    }
+
+    function onDecreaseThreshold() {
+      minConfidence = Math.max(faceapi.round(minConfidence - 0.1), 0.1)
+      $('#minConfidence').val(minConfidence)
+      updateResults()
+    }
+
+    async function loadImageFromUrl(url) {
+      const img = await requestExternalImage($('#imgUrlInput').val())
+      $('#inputImg').get(0).src = img.src
+      updateResults()
+    }
+
+    async function updateResults() {
+      const inputImgEl = $('#inputImg').get(0)
+      const { width, height } = inputImgEl
+      const canvas = $('#overlay').get(0)
+      canvas.width = width
+      canvas.height = height
+
+      const mtcnnParams = {
+        minFaceSize,
+        scaleFactor,
+        maxNumScales,
+        scoreThresholds: [stage1Threshold, stage2Threshold, stage3Threshold]
+      }
+      const results = await faceapi.mtcnn(inputImgEl, mtcnnParams)
+
+      if (results) {
+        results.forEach(({ faceDetection, faceLandmarks }) => {
+          faceapi.drawDetection('overlay', faceDetection.forSize(width, height))
+          faceapi.drawLandmarks('overlay', faceLandmarks.forSize(width, height), { lineWidth: 4, color: 'red' })
+        })
+      }
+    }
+
+    async function onSelectionChanged(uri) {
+      const imgBuf = await fetchImage(uri)
+      $(`#inputImg`).get(0).src = (await faceapi.bufferToImage(imgBuf)).src
+      updateResults()
+    }
+
+    async function run() {
+      await faceapi.loadMtcnnModel('/')
+      $('#loader').hide()
+      onSelectionChanged($('#selectList select').val())
+    }
+
+    $(document).ready(function() {
+      renderNavBar('#navbar', 'mtcnn_face_detection')
+      renderImageSelectList(
+        '#selectList',
+        async (uri) => {
+          await onSelectionChanged(uri)
+        },
+        'bbt1.jpg'
+      )
+      run()
+    })
+  </script>
+</body>
+</html>
\ No newline at end of file

examples/views/mtcnnFaceDetectionVideo.html

+<!DOCTYPE html>
+<html>
+<head>
+  <script src="face-api.js"></script>
+  <script src="commons.js"></script>
+  <link rel="stylesheet" href="styles.css">
+  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/0.100.2/css/materialize.css">
+  <script type="text/javascript" src="https://code.jquery.com/jquery-2.1.1.min.js"></script>
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/materialize/0.100.2/js/materialize.min.js"></script>
+</head>
+<body>
+  <div id="navbar"></div>
+  <div class="center-content page-container">
+    <div class="progress" id="loader">
+      <div class="indeterminate"></div>
+    </div>
+    <div style="position: relative" class="margin">
+      <video src="media/bbt.mp4" onplay="onPlay(this)" id="inputVideo" autoplay muted></video>
+      <canvas id="overlay" />
+    </div>
+    <div class="row side-by-side">
+      <div class="row">
+        <label for="minFaceSize">Minimum Face Size:</label>
+        <input disabled value="80" id="minFaceSize" type="text" class="bold">
+      </div>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="onDecreaseMinFaceSize()"
+      >
+        <i class="material-icons left">-</i>
+      </button>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="onIncreaseMinFaceSize()"
+      >
+        <i class="material-icons left">+</i>
+      </button>
+    </div>
+    <div class="row side-by-side">
+      <div class="row">
+        <label for="time">Time:</label>
+        <input disabled value="-" id="time" type="text" class="bold">
+      </div>
+      <div class="row">
+        <label for="fps">Estimated Fps:</label>
+        <input disabled value="-" id="fps" type="text" class="bold">
+      </div>
+    </div>
+  </div>
+
+  <script>
+    let modelLoaded = false
+    let minFaceSize = 80
+    let minConfidence = 0.9
+    let forwardTimes = []
+
+    function onIncreaseMinFaceSize() {
+      minFaceSize = Math.min(faceapi.round(minFaceSize + 20), 200)
+      $('#minFaceSize').val(minFaceSize)
+    }
+
+    function onDecreaseMinFaceSize() {
+      minFaceSize = Math.max(faceapi.round(minFaceSize - 20), 20)
+      $('#minFaceSize').val(minFaceSize)
+    }
+
+    function updateTimeStats(timeInMs) {
+      forwardTimes = [timeInMs].concat(forwardTimes).slice(0, 30)
+      const avgTimeInMs = forwardTimes.reduce((total, t) => total + t) / forwardTimes.length
+      $('#time').val(`${Math.round(avgTimeInMs)} ms`)
+      $('#fps').val(`${faceapi.round(1000 / avgTimeInMs)}`)
+    }
+
+    async function onPlay(videoEl) {
+      if(videoEl.paused || videoEl.ended || !modelLoaded)
+        return false
+
+      const { width, height } = faceapi.getMediaDimensions(videoEl)
+      const canvas = $('#overlay').get(0)
+      canvas.width = width
+      canvas.height = height
+
+      const mtcnnParams = {
+        minFaceSize
+      }
+
+      const ts = Date.now()
+      const results = await faceapi.mtcnn(videoEl, mtcnnParams)
+      updateTimeStats(Date.now() - ts)
+
+      if (results) {
+        results.forEach(({ faceDetection, faceLandmarks }) => {
+          if (faceDetection.score < minConfidence) {
+            return
+          }
+          faceapi.drawDetection('overlay', faceDetection.forSize(width, height))
+          faceapi.drawLandmarks('overlay', faceLandmarks.forSize(width, height), { lineWidth: 4, color: 'red' })
+        })
+      }
+      setTimeout(() => onPlay(videoEl))
+    }
+
+    async function run() {
+      await faceapi.loadMtcnnModel('/')
+      modelLoaded = true
+      onPlay($('#inputVideo').get(0))
+      $('#loader').hide()
+    }
+
+    $(document).ready(function() {
+      renderNavBar('#navbar', 'mtcnn_face_detection_video')
+      run()
+    })
+  </script>
+</body>
+</html>
\ No newline at end of file

examples/views/mtcnnFaceDetectionWebcam.html

+<!DOCTYPE html>
+<html>
+<head>
+  <script src="face-api.js"></script>
+  <script src="commons.js"></script>
+  <link rel="stylesheet" href="styles.css">
+  <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/0.100.2/css/materialize.css">
+  <script type="text/javascript" src="https://code.jquery.com/jquery-2.1.1.min.js"></script>
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/materialize/0.100.2/js/materialize.min.js"></script>
+</head>
+<body>
+  <div id="navbar"></div>
+  <div class="center-content page-container">
+    <div class="progress" id="loader">
+      <div class="indeterminate"></div>
+    </div>
+    <div style="position: relative" class="margin">
+      <video onplay="onPlay(this)" id="inputVideo" autoplay muted></video>
+      <canvas id="overlay" />
+    </div>
+    <div class="row side-by-side">
+      <div class="row">
+        <label for="minFaceSize">Minimum Face Size:</label>
+        <input disabled value="200" id="minFaceSize" type="text" class="bold">
+      </div>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="onDecreaseMinFaceSize()"
+      >
+        <i class="material-icons left">-</i>
+      </button>
+      <button
+        class="waves-effect waves-light btn"
+        onclick="onIncreaseMinFaceSize()"
+      >
+        <i class="material-icons left">+</i>
+      </button>
+    </div>
+    <div class="row side-by-side">
+      <div class="row">
+        <label for="time">Time:</label>
+        <input disabled value="-" id="time" type="text" class="bold">
+      </div>
+      <div class="row">
+        <label for="fps">Estimated Fps:</label>
+        <input disabled value="-" id="fps" type="text" class="bold">
+      </div>
+    </div>
+  </div>
+
+  <script>
+    let modelLoaded = false
+    let minFaceSize = 200
+    let minConfidence = 0.9
+    let forwardTimes = []
+
+    function onIncreaseMinFaceSize() {
+      minFaceSize = Math.min(faceapi.round(minFaceSize + 50), 300)
+      $('#minFaceSize').val(minFaceSize)
+    }
+
+    function onDecreaseMinFaceSize() {
+      minFaceSize = Math.max(faceapi.round(minFaceSize - 50), 50)
+      $('#minFaceSize').val(minFaceSize)
+    }
+
+    function updateTimeStats(timeInMs) {
+      forwardTimes = [timeInMs].concat(forwardTimes).slice(0, 30)
+      const avgTimeInMs = forwardTimes.reduce((total, t) => total + t) / forwardTimes.length
+      $('#time').val(`${Math.round(avgTimeInMs)} ms`)
+      $('#fps').val(`${faceapi.round(1000 / avgTimeInMs)}`)
+    }
+
+    async function onPlay(videoEl) {
+      if(videoEl.paused || videoEl.ended || !modelLoaded)
+        return false
+
+      const { width, height } = faceapi.getMediaDimensions(videoEl)
+      const canvas = $('#overlay').get(0)
+      canvas.width = width
+      canvas.height = height
+
+      const mtcnnParams = {
+        minFaceSize
+      }
+
+      const c = faceapi.createCanvas({ width: width , height: height })
+      c.getContext('2d').drawImage(videoEl, 0, 0)
+
+      const { results, stats } = await faceapi.nets.mtcnn.forwardWithStats(c, mtcnnParams)
+      updateTimeStats(stats.total)
+
+      if (results) {
+        results.forEach(({ faceDetection, faceLandmarks }) => {
+          if (faceDetection.score < minConfidence) {
+            return
+          }
+          faceapi.drawDetection('overlay', faceDetection.forSize(width, height))
+          faceapi.drawLandmarks('overlay', faceLandmarks.forSize(width, height), { lineWidth: 4, color: 'red' })
+        })
+      }
+      setTimeout(() => onPlay(videoEl))
+    }
+
+    async function run() {
+      await faceapi.loadMtcnnModel('/')
+      modelLoaded = true
+
+      const videoEl = $('#inputVideo').get(0)
+      navigator.getUserMedia(
+        { video: {} },
+        stream => videoEl.srcObject = stream,
+        err => console.error(err)
+      )
+      $('#loader').hide()
+    }
+
+    $(document).ready(function() {
+      renderNavBar('#navbar', 'mtcnn_face_detection_webcam')
+      run()
+    })
+  </script>
+</body>
+</html>
\ No newline at end of file

src/faceDetectionNet/FaceDetection.ts → src/FaceDetection.ts

-import { Rect } from '../Rect';
-import { Dimensions } from '../types';
+import { Rect } from './Rect';
+import { Dimensions } from './types';
 
 export class FaceDetection {
   private _score: number
@@ -24,23 +24,23 @@ export class FaceDetection {
     )
   }
 
-  public getScore() {
+  public get score(): number {
     return this._score
   }
 
-  public getBox() {
+  public get box(): Rect {
     return this._box
   }
 
-  public getImageWidth() {
+  public get imageWidth(): number {
     return this._imageWidth
   }
 
-  public getImageHeight() {
+  public get imageHeight(): number {
     return this._imageHeight
   }
 
-  public getRelativeBox() {
+  public get relativeBox(): Rect {
     return new Rect(
       this._box.x / this._imageWidth,
       this._box.y / this._imageHeight,
@@ -49,6 +49,26 @@ export class FaceDetection {
     )
   }
 
+  public getScore() {
+    return this.score
+  }
+
+  public getBox() {
+    return this.box
+  }
+
+  public getImageWidth() {
+    return this.imageWidth
+  }
+
+  public getImageHeight() {
+    return this.imageHeight
+  }
+
+  public getRelativeBox() {
+    return this.relativeBox
+  }
+
   public forSize(width: number, height: number): FaceDetection {
     return new FaceDetection(
       this._score,

src/FaceLandmarks.ts

+import { Point } from './Point';
+import { Dimensions } from './types';
+
+export class FaceLandmarks {
+  protected _imageWidth: number
+  protected _imageHeight: number
+  protected _shift: Point
+  protected _faceLandmarks: Point[]
+
+  constructor(
+    relativeFaceLandmarkPositions: Point[],
+    imageDims: Dimensions,
+    shift: Point = new Point(0, 0)
+  ) {
+    const { width, height } = imageDims
+    this._imageWidth = width
+    this._imageHeight = height
+    this._shift = shift
+    this._faceLandmarks = relativeFaceLandmarkPositions.map(
+      pt => pt.mul(new Point(width, height)).add(shift)
+    )
+  }
+
+  public getShift(): Point {
+    return new Point(this._shift.x, this._shift.y)
+  }
+
+  public getImageWidth(): number {
+    return this._imageWidth
+  }
+
+  public getImageHeight(): number {
+    return this._imageHeight
+  }
+
+  public getPositions(): Point[] {
+    return this._faceLandmarks
+  }
+
+  public getRelativePositions(): Point[] {
+    return this._faceLandmarks.map(
+      pt => pt.sub(this._shift).div(new Point(this._imageWidth, this._imageHeight))
+    )
+  }
+}
\ No newline at end of file

src/FullFaceDescription.ts

-import { FaceDetection } from './faceDetectionNet/FaceDetection';
-import { FaceLandmarks } from './faceLandmarkNet/FaceLandmarks';
+import { FaceDetection } from './FaceDetection';
+import { FaceLandmarks68 } from './faceLandmarkNet/FaceLandmarks68';
 
 export class FullFaceDescription {
   constructor(
     private _detection: FaceDetection,
-    private _landmarks: FaceLandmarks,
+    private _landmarks: FaceLandmarks68,
     private _descriptor: Float32Array
   ) {}
 
@@ -12,7 +12,7 @@ export class FullFaceDescription {
     return this._detection
   }
 
-  public get landmarks(): FaceLandmarks {
+  public get landmarks(): FaceLandmarks68 {
     return this._landmarks
   }
 

src/NetInput.ts

@@ -8,6 +8,7 @@ import { createCanvasFromMedia } from './utils';
 
 export class NetInput {
   private _inputs: tf.Tensor3D[] = []
+  private _canvases: HTMLCanvasElement[] = []
   private _isManaged: boolean = false
   private _isBatchInput: boolean = false
 
@@ -16,14 +17,15 @@ export class NetInput {
 
   constructor(
     inputs: tf.Tensor4D | Array<TResolvedNetInput>,
-    isBatchInput: boolean = false
+    isBatchInput: boolean = false,
+    keepCanvases: boolean = false
   ) {
     if (isTensor4D(inputs)) {
       this._inputs = tf.unstack(inputs as tf.Tensor4D) as tf.Tensor3D[]
     }
 
     if (Array.isArray(inputs)) {
-      this._inputs = inputs.map(input => {
+      this._inputs = inputs.map((input, idx) => {
         if (isTensor3D(input)) {
           // TODO: make sure not to dispose original tensors passed in by the user
           return tf.clone(input as tf.Tensor3D)
@@ -39,9 +41,11 @@ export class NetInput {
           return (input as tf.Tensor4D).reshape(shape.slice(1) as [number, number, number]) as tf.Tensor3D
         }
 
-        return tf.fromPixels(
-          input instanceof HTMLCanvasElement ? input : createCanvasFromMedia(input as HTMLImageElement | HTMLVideoElement)
-        )
+        const canvas = input instanceof HTMLCanvasElement ? input : createCanvasFromMedia(input as HTMLImageElement | HTMLVideoElement)
+        if (keepCanvases) {
+          this._canvases[idx] = canvas
+        }
+        return tf.fromPixels(canvas)
       })
     }
 
@@ -53,6 +57,10 @@ export class NetInput {
     return this._inputs
   }
 
+  public get canvases(): HTMLCanvasElement[] {
+    return this._canvases
+  }
+
   public get isManaged(): boolean {
     return this._isManaged
   }

src/allFacesFactory.ts

 import { extractFaceTensors } from './extractFaceTensors';
 import { FaceDetectionNet } from './faceDetectionNet/FaceDetectionNet';
 import { FaceLandmarkNet } from './faceLandmarkNet/FaceLandmarkNet';
-import { FaceLandmarks } from './faceLandmarkNet/FaceLandmarks';
+import { FaceLandmarks68 } from './faceLandmarkNet/FaceLandmarks68';
 import { FaceRecognitionNet } from './faceRecognitionNet/FaceRecognitionNet';
 import { FullFaceDescription } from './FullFaceDescription';
 import { TNetInput } from './types';
@@ -22,10 +22,10 @@ export function allFacesFactory(
     const faceTensors = await extractFaceTensors(input, detections)
 
     const faceLandmarksByFace = useBatchProcessing
-      ? await landmarkNet.detectLandmarks(faceTensors) as FaceLandmarks[]
+      ? await landmarkNet.detectLandmarks(faceTensors) as FaceLandmarks68[]
       : await Promise.all(faceTensors.map(
         faceTensor => landmarkNet.detectLandmarks(faceTensor)
-      )) as FaceLandmarks[]
+      )) as FaceLandmarks68[]
 
     faceTensors.forEach(t => t.dispose())
 

src/commons/extractConvParamsFactory.ts

+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 }
+  }
+
+}

src/commons/extractFCParamsFactory.ts

+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
+    }
+  }
+
+}

src/commons/types.ts

@@ -5,6 +5,11 @@ export type ConvParams = {
   bias: tf.Tensor1D
 }
 
+export type FCParams = {
+  weights: tf.Tensor2D
+  bias: tf.Tensor1D
+}
+
 export type ExtractWeightsFunction = (numWeights: number) => Float32Array
 
 export type BatchReshapeInfo = {

src/drawing/index.ts

-import { FaceDetection } from '../faceDetectionNet/FaceDetection';
-import { FaceLandmarks } from '../faceLandmarkNet/FaceLandmarks';
+import { FaceDetection } from '../FaceDetection';
+import { FaceLandmarks68 } from '../faceLandmarkNet';
+import { FaceLandmarks } from '../FaceLandmarks';
 import { Point } from '../Point';
 import { getContext2dOrThrow, resolveInput, round } from '../utils';
 import { DrawBoxOptions, DrawLandmarksOptions, DrawOptions, DrawTextOptions } from './types';
@@ -150,7 +151,7 @@ export function drawLandmarks(
   const faceLandmarksArray = Array.isArray(faceLandmarks) ? faceLandmarks : [faceLandmarks]
 
   faceLandmarksArray.forEach(landmarks => {
-    if (drawLines) {
+    if (drawLines && landmarks instanceof FaceLandmarks68) {
       ctx.strokeStyle = color
       ctx.lineWidth = lineWidth
       drawContour(ctx, landmarks.getJawOutline())

src/extractFaceTensors.ts

 import * as tf from '@tensorflow/tfjs-core';
 
-import { FaceDetection } from './faceDetectionNet/FaceDetection';
+import { FaceDetection } from './FaceDetection';
 import { Rect } from './Rect';
 import { toNetInput } from './toNetInput';
 import { TNetInput } from './types';

src/extractFaces.ts

-import { FaceDetection } from './faceDetectionNet/FaceDetection';
+import { FaceDetection } from './FaceDetection';
 import { Rect } from './Rect';
 import { toNetInput } from './toNetInput';
 import { TNetInput } from './types';
 import { createCanvas, getContext2dOrThrow, imageTensorToCanvas } from './utils';
-import * as tf from '@tensorflow/tfjs-core';
 
 /**
  * Extracts the image regions containing the detected faces.

src/faceDetectionNet/FaceDetectionNet.ts

 import * as tf from '@tensorflow/tfjs-core';
 
 import { NeuralNetwork } from '../commons/NeuralNetwork';
+import { FaceDetection } from '../FaceDetection';
 import { NetInput } from '../NetInput';
 import { Rect } from '../Rect';
 import { toNetInput } from '../toNetInput';
 import { TNetInput } from '../types';
 import { extractParams } from './extractParams';
-import { FaceDetection } from './FaceDetection';
 import { loadQuantizedParams } from './loadQuantizedParams';
 import { mobileNetV1 } from './mobileNetV1';
 import { nonMaxSuppression } from './nonMaxSuppression';

src/faceDetectionNet/index.ts

 import { FaceDetectionNet } from './FaceDetectionNet';
 
 export * from './FaceDetectionNet';
-export * from './FaceDetection';
 
-export function faceDetectionNet(weights: Float32Array) {
+export function createFaceDetectionNet(weights: Float32Array) {
   const net = new FaceDetectionNet()
   net.extractWeights(weights)
   return net
+}
+
+export function faceDetectionNet(weights: Float32Array) {
+  console.warn('faceDetectionNet(weights: Float32Array) will be deprecated in future, use createFaceDetectionNet instead')
+  return createFaceDetectionNet(weights)
 }
\ No newline at end of file

src/faceDetectionNet/loadQuantizedParams.ts

-import { tf } from '..';
+import * as tf from '@tensorflow/tfjs-core';
+
 import { disposeUnusedWeightTensors } from '../commons/disposeUnusedWeightTensors';
 import { extractWeightEntryFactory } from '../commons/extractWeightEntryFactory';
-import { isTensor1D, isTensor3D, isTensor4D } from '../commons/isTensor';
+import { isTensor3D } from '../commons/isTensor';
 import { loadWeightMap } from '../commons/loadWeightMap';
 import { ConvParams, ParamMapping } from '../commons/types';
 import { BoxPredictionParams, MobileNetV1, NetParams, PointwiseConvParams, PredictionLayerParams } from './types';

src/faceLandmarkNet/FaceLandmarkNet.ts

@@ -9,7 +9,7 @@ import { toNetInput } from '../toNetInput';
 import { TNetInput } from '../types';
 import { isEven } from '../utils';
 import { extractParams } from './extractParams';
-import { FaceLandmarks } from './FaceLandmarks';
+import { FaceLandmarks68 } from './FaceLandmarks68';
 import { fullyConnectedLayer } from './fullyConnectedLayer';
 import { loadQuantizedParams } from './loadQuantizedParams';
 import { NetParams } from './types';
@@ -93,7 +93,7 @@ export class FaceLandmarkNet extends NeuralNetwork<NetParams> {
     return this.forwardInput(await toNetInput(input, true))
   }
 
-  public async detectLandmarks(input: TNetInput): Promise<FaceLandmarks | FaceLandmarks[]> {
+  public async detectLandmarks(input: TNetInput): Promise<FaceLandmarks68 | FaceLandmarks68[]> {
     const netInput = await toNetInput(input, true)
 
     const landmarkTensors = tf.tidy(
@@ -106,7 +106,7 @@ export class FaceLandmarkNet extends NeuralNetwork<NetParams> {
         const xCoords = landmarksArray.filter((_, i) => isEven(i))
         const yCoords = landmarksArray.filter((_, i) => !isEven(i))
 
-        return new FaceLandmarks(
+        return new FaceLandmarks68(
           Array(68).fill(0).map((_, i) => new Point(xCoords[i], yCoords[i])),
           {
             height: netInput.getInputHeight(batchIdx),

src/faceLandmarkNet/FaceLandmarks.ts → src/faceLandmarkNet/FaceLandmarks68.ts

 import { getCenterPoint } from '../commons/getCenterPoint';
-import { FaceDetection } from '../faceDetectionNet/FaceDetection';
+import { FaceDetection } from '../FaceDetection';
+import { FaceLandmarks } from '../FaceLandmarks';
 import { IPoint, Point } from '../Point';
 import { Rect } from '../Rect';
-import { Dimensions } from '../types';
 
 // face alignment constants
 const relX = 0.5
 const relY = 0.43
 const relScale = 0.45
 
-export class FaceLandmarks {
-  private _imageWidth: number
-  private _imageHeight: number
-  private _shift: Point
-  private _faceLandmarks: Point[]
-
-  constructor(
-    relativeFaceLandmarkPositions: Point[],
-    imageDims: Dimensions,
-    shift: Point = new Point(0, 0)
-  ) {
-    const { width, height } = imageDims
-    this._imageWidth = width
-    this._imageHeight = height
-    this._shift = shift
-    this._faceLandmarks = relativeFaceLandmarkPositions.map(
-      pt => pt.mul(new Point(width, height)).add(shift)
-    )
-  }
-
-  public getShift(): Point {
-    return new Point(this._shift.x, this._shift.y)
-  }
-
-  public getImageWidth(): number {
-    return this._imageWidth
-  }
-
-  public getImageHeight(): number {
-    return this._imageHeight
-  }
-
-  public getPositions(): Point[] {
-    return this._faceLandmarks
-  }
-
-  public getRelativePositions(): Point[] {
-    return this._faceLandmarks.map(
-      pt => pt.sub(this._shift).div(new Point(this._imageWidth, this._imageHeight))
-    )
-  }
-
+export class FaceLandmarks68 extends FaceLandmarks {
   public getJawOutline(): Point[] {
     return this._faceLandmarks.slice(0, 17)
   }
@@ -79,22 +38,22 @@ export class FaceLandmarks {
     return this._faceLandmarks.slice(48, 68)
   }
 
-  public forSize(width: number, height: number): FaceLandmarks {
-    return new FaceLandmarks(
+  public forSize(width: number, height: number): FaceLandmarks68 {
+    return new FaceLandmarks68(
       this.getRelativePositions(),
       { width, height }
     )
   }
 
-  public shift(x: number, y: number): FaceLandmarks {
-    return new FaceLandmarks(
+  public shift(x: number, y: number): FaceLandmarks68 {
+    return new FaceLandmarks68(
       this.getRelativePositions(),
       { width: this._imageWidth, height: this._imageHeight },
       new Point(x, y)
     )
   }
 
-  public shiftByPoint(pt: IPoint): FaceLandmarks {
+  public shiftByPoint(pt: IPoint): FaceLandmarks68 {
     return this.shift(pt.x, pt.y)
   }
 
@@ -110,7 +69,7 @@ export class FaceLandmarks {
    * @returns The bounding box of the aligned face.
    */
   public align(
-    detection?: Rect
+    detection?: FaceDetection | Rect
   ): Rect {
     if (detection) {
       const box = detection instanceof FaceDetection

src/faceLandmarkNet/extractParams.ts

-import * as tf from '@tensorflow/tfjs-core';
-
+import { extractConvParamsFactory } from '../commons/extractConvParamsFactory';
+import { extractFCParamsFactory } from '../commons/extractFCParamsFactory';
 import { extractWeightsFactory } from '../commons/extractWeightsFactory';
-import { ConvParams, ParamMapping } from '../commons/types';
-import { FCParams, NetParams } from './types';
+import { ParamMapping } from '../commons/types';
+import { NetParams } from './types';
 
 export function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {
 
@@ -13,42 +13,8 @@ export function extractParams(weights: Float32Array): { params: NetParams, param
     getRemainingWeights
   } = extractWeightsFactory(weights)
 
-  function extractConvParams(
-    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 }
-  }
-
-  function extractFcParams(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
-    }
-  }
+  const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings)
+  const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings)
 
   const conv0 = extractConvParams(3, 32, 3, 'conv0')
   const conv1 = extractConvParams(32, 64, 3, 'conv1')
@@ -58,8 +24,8 @@ export function extractParams(weights: Float32Array): { params: NetParams, param
   const conv5 = extractConvParams(64, 128, 3, 'conv5')
   const conv6 = extractConvParams(128, 128, 3, 'conv6')
   const conv7 = extractConvParams(128, 256, 3, 'conv7')
-  const fc0 = extractFcParams(6400, 1024, 'fc0')
-  const fc1 = extractFcParams(1024, 136, 'fc1')
+  const fc0 = extractFCParams(6400, 1024, 'fc0')
+  const fc1 = extractFCParams(1024, 136, 'fc1')
 
   if (getRemainingWeights().length !== 0) {
     throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`)

src/faceLandmarkNet/fullyConnectedLayer.ts

 import * as tf from '@tensorflow/tfjs-core';
 
-import { FCParams } from './types';
+import { FCParams } from '../commons/types';
 
 export function fullyConnectedLayer(
   x: tf.Tensor2D,

src/faceLandmarkNet/index.ts

 import { FaceLandmarkNet } from './FaceLandmarkNet';
 
 export * from './FaceLandmarkNet';
-export * from './FaceLandmarks';
+export * from './FaceLandmarks68';
 
-export function faceLandmarkNet(weights: Float32Array) {
+export function createFaceLandmarkNet(weights: Float32Array) {
   const net = new FaceLandmarkNet()
   net.extractWeights(weights)
   return net
+}
+
+export function faceLandmarkNet(weights: Float32Array) {
+  console.warn('faceLandmarkNet(weights: Float32Array) will be deprecated in future, use createFaceLandmarkNet instead')
+  return createFaceLandmarkNet(weights)
 }
\ No newline at end of file

src/faceLandmarkNet/loadQuantizedParams.ts

@@ -3,8 +3,8 @@ import * as tf from '@tensorflow/tfjs-core';
 import { disposeUnusedWeightTensors } from '../commons/disposeUnusedWeightTensors';
 import { extractWeightEntryFactory } from '../commons/extractWeightEntryFactory';
 import { loadWeightMap } from '../commons/loadWeightMap';
-import { ConvParams, ParamMapping } from '../commons/types';
-import { FCParams, NetParams } from './types';
+import { ConvParams, FCParams, ParamMapping } from '../commons/types';
+import { NetParams } from './types';
 
 const DEFAULT_MODEL_NAME = 'face_landmark_68_model'
 

src/faceLandmarkNet/types.ts

-import * as tf from '@tensorflow/tfjs-core';
-
-import { ConvParams } from '../commons/types';
-
-export type FCParams = {
-  weights: tf.Tensor2D
-  bias: tf.Tensor1D
-}
+import { ConvParams, FCParams } from '../commons/types';
 
 export type NetParams = {
   conv0: ConvParams

src/faceRecognitionNet/index.ts

@@ -2,8 +2,13 @@ import { FaceRecognitionNet } from './FaceRecognitionNet';
 
 export * from './FaceRecognitionNet';
 
-export function faceRecognitionNet(weights: Float32Array) {
+export function createFaceRecognitionNet(weights: Float32Array) {
   const net = new FaceRecognitionNet()
   net.extractWeights(weights)
   return net
+}
+
+export function faceRecognitionNet(weights: Float32Array) {
+  console.warn('faceRecognitionNet(weights: Float32Array) will be deprecated in future, use createFaceRecognitionNet instead')
+  return createFaceRecognitionNet(weights)
 }
\ No newline at end of file

src/globalApi.ts

 import * as tf from '@tensorflow/tfjs-core';
 
 import { allFacesFactory } from './allFacesFactory';
-import { FaceDetection } from './faceDetectionNet/FaceDetection';
+import { FaceDetection } from './FaceDetection';
 import { FaceDetectionNet } from './faceDetectionNet/FaceDetectionNet';
 import { FaceLandmarkNet } from './faceLandmarkNet/FaceLandmarkNet';
-import { FaceLandmarks } from './faceLandmarkNet/FaceLandmarks';
+import { FaceLandmarks68 } from './faceLandmarkNet/FaceLandmarks68';
 import { FaceRecognitionNet } from './faceRecognitionNet/FaceRecognitionNet';
 import { FullFaceDescription } from './FullFaceDescription';
+import { getDefaultMtcnnForwardParams } from './mtcnn/getDefaultMtcnnForwardParams';
+import { Mtcnn } from './mtcnn/Mtcnn';
+import { MtcnnForwardParams, MtcnnResult } from './mtcnn/types';
 import { NetInput } from './NetInput';
 import { TNetInput } from './types';
 
@@ -14,23 +17,37 @@ export const detectionNet = new FaceDetectionNet()
 export const landmarkNet = new FaceLandmarkNet()
 export const recognitionNet = new FaceRecognitionNet()
 
+// nets need more specific names, to avoid ambiguity in future
+// when alternative net implementations are provided
+export const nets = {
+  ssdMobilenet: detectionNet,
+  faceLandmark68Net: landmarkNet,
+  faceNet: recognitionNet,
+  mtcnn: new Mtcnn()
+}
+
 export function loadFaceDetectionModel(url: string) {
-  return detectionNet.load(url)
+  return nets.ssdMobilenet.load(url)
 }
 
 export function loadFaceLandmarkModel(url: string) {
-  return landmarkNet.load(url)
+  return nets.faceLandmark68Net.load(url)
 }
 
 export function loadFaceRecognitionModel(url: string) {
-  return recognitionNet.load(url)
+  return nets.faceNet.load(url)
+}
+
+export function loadMtcnnModel(url: string) {
+  return nets.mtcnn.load(url)
 }
 
 export function loadModels(url: string) {
   return Promise.all([
     loadFaceDetectionModel(url),
     loadFaceLandmarkModel(url),
-    loadFaceRecognitionModel(url)
+    loadFaceRecognitionModel(url),
+    loadMtcnnModel(url)
   ])
 }
 
@@ -39,19 +56,26 @@ export function locateFaces(
   minConfidence?: number,
   maxResults?: number
 ): Promise<FaceDetection[]> {
-  return detectionNet.locateFaces(input, minConfidence, maxResults)
+  return nets.ssdMobilenet.locateFaces(input, minConfidence, maxResults)
 }
 
 export function detectLandmarks(
   input: TNetInput
-): Promise<FaceLandmarks | FaceLandmarks[]> {
-  return landmarkNet.detectLandmarks(input)
+): Promise<FaceLandmarks68 | FaceLandmarks68[]> {
+  return nets.faceLandmark68Net.detectLandmarks(input)
 }
 
 export function computeFaceDescriptor(
   input: TNetInput
 ): Promise<Float32Array | Float32Array[]>  {
-  return recognitionNet.computeFaceDescriptor(input)
+  return nets.faceNet.computeFaceDescriptor(input)
+}
+
+export function mtcnn(
+  input: TNetInput,
+  forwardParams: MtcnnForwardParams
+): Promise<MtcnnResult[]> {
+  return nets.mtcnn.forward(input, forwardParams)
 }
 
 export const allFaces: (

src/index.ts

@@ -4,6 +4,8 @@ export {
   tf
 }
 
+
+export * from './FaceDetection';
 export * from './FullFaceDescription';
 export * from './NetInput';
 export * from './Point';
@@ -17,6 +19,7 @@ export * from './faceDetectionNet';
 export * from './faceLandmarkNet';
 export * from './faceRecognitionNet';
 export * from './globalApi';
+export * from './mtcnn';
 export * from './padToSquare';
 export * from './toNetInput';
 export * from './utils'
\ No newline at end of file

src/mtcnn/BoundingBox.ts

+export class BoundingBox {
+  constructor(
+    private _left: number,
+    private _top: number,
+    private _right: number,
+    private _bottom: number
+  ) {}
+
+
+  public get left() : number {
+    return this._left
+  }
+
+  public get top() : number {
+    return this._top
+  }
+
+  public get right() : number {
+    return this._right
+  }
+
+  public get bottom() : number {
+    return this._bottom
+  }
+
+  public get width() : number {
+    return this.right - this.left
+  }
+
+  public get height() : number {
+    return this.bottom - this.top
+  }
+
+
+  public toSquare(): BoundingBox {
+    let { left, top, right, bottom } = this
+
+    const off = (Math.abs(this.width - this.height) / 2)
+    if (this.width < this.height) {
+      left -= off
+      right += off
+    }
+    if (this.height < this.width) {
+      top -= off
+      bottom += off
+    }
+    return new BoundingBox(left, top, right, bottom)
+  }
+
+  public round(): BoundingBox {
+    return new BoundingBox(
+      Math.round(this.left),
+      Math.round(this.top),
+      Math.round(this.right),
+      Math.round(this.bottom)
+    )
+  }
+
+  public padAtBorders(imageHeight: number, imageWidth: number) {
+    const w = this.width + 1
+    const h = this.height + 1
+
+    let dx = 1
+    let dy = 1
+    let edx = w
+    let edy = h
+
+    let x = this.left
+    let y = this.top
+    let ex = this.right
+    let ey = this.bottom
+
+    if (ex > imageWidth) {
+      edx = -ex + imageWidth + w
+      ex = imageWidth
+    }
+    if (ey > imageHeight) {
+      edy = -ey + imageHeight + h
+      ey = imageHeight
+    }
+    if (x < 1) {
+      edy = 2 - x
+      x = 1
+    }
+    if (y < 1) {
+      edy = 2 - y
+      y = 1
+    }
+
+    return { dy, edy, dx, edx, y, ey, x, ex, w, h }
+  }
+
+  public calibrate(region: BoundingBox) {
+    return new BoundingBox(
+      this.left + (region.left * this.width),
+      this.top + (region.top * this.height),
+      this.right + (region.right * this.width),
+      this.bottom + (region.bottom * this.height)
+    ).toSquare().round()
+  }
+}
\ No newline at end of file

src/mtcnn/FaceLandmarks5.ts

+import { FaceLandmarks } from '../FaceLandmarks';
+import { IPoint, Point } from '../Point';
+
+export class FaceLandmarks5 extends FaceLandmarks {
+
+  public forSize(width: number, height: number): FaceLandmarks5 {
+    return new FaceLandmarks5(
+      this.getRelativePositions(),
+      { width, height }
+    )
+  }
+
+  public shift(x: number, y: number): FaceLandmarks5 {
+    return new FaceLandmarks5(
+      this.getRelativePositions(),
+      { width: this._imageWidth, height: this._imageHeight },
+      new Point(x, y)
+    )
+  }
+
+  public shiftByPoint(pt: IPoint): FaceLandmarks5 {
+    return this.shift(pt.x, pt.y)
+  }
+}
\ No newline at end of file

src/mtcnn/Mtcnn.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { NeuralNetwork } from '../commons/NeuralNetwork';
+import { FaceDetection } from '../FaceDetection';
+import { NetInput } from '../NetInput';
+import { Point } from '../Point';
+import { Rect } from '../Rect';
+import { toNetInput } from '../toNetInput';
+import { TNetInput } from '../types';
+import { bgrToRgbTensor } from './bgrToRgbTensor';
+import { CELL_SIZE } from './config';
+import { extractParams } from './extractParams';
+import { FaceLandmarks5 } from './FaceLandmarks5';
+import { getDefaultMtcnnForwardParams } from './getDefaultMtcnnForwardParams';
+import { getSizesForScale } from './getSizesForScale';
+import { loadQuantizedParams } from './loadQuantizedParams';
+import { pyramidDown } from './pyramidDown';
+import { stage1 } from './stage1';
+import { stage2 } from './stage2';
+import { stage3 } from './stage3';
+import { MtcnnForwardParams, MtcnnResult, NetParams } from './types';
+
+export class Mtcnn extends NeuralNetwork<NetParams> {
+
+  constructor() {
+    super('Mtcnn')
+  }
+
+  public async forwardInput(
+    input: NetInput,
+    forwardParams: MtcnnForwardParams
+  ): Promise<{ results: MtcnnResult[], stats: any }> {
+
+    const { params } = this
+
+    if (!params) {
+      throw new Error('Mtcnn - load model before inference')
+    }
+
+    const inputTensor = input.inputs[0]
+    const inputCanvas = input.canvases[0]
+
+    if (!inputCanvas) {
+      throw new Error('Mtcnn - inputCanvas is not defined, note that passing tensors into Mtcnn.forwardInput is not supported yet.')
+    }
+
+    const stats: any = {}
+
+    const tsTotal = Date.now()
+
+    const imgTensor = tf.tidy(() =>
+      bgrToRgbTensor(
+        tf.expandDims(inputTensor).toFloat() as tf.Tensor4D
+      )
+    )
+
+    const onReturn = (results: any) => {
+      // dispose tensors on return
+      imgTensor.dispose()
+      input.dispose()
+      stats.total = Date.now() - tsTotal
+      return results
+    }
+
+    const [height, width] = imgTensor.shape.slice(1)
+
+    const {
+      minFaceSize,
+      scaleFactor,
+      maxNumScales,
+      scoreThresholds,
+      scaleSteps
+    } = Object.assign({}, getDefaultMtcnnForwardParams(), forwardParams)
+
+    const scales = (scaleSteps || pyramidDown(minFaceSize, scaleFactor, [height, width]))
+      .filter(scale => {
+        const sizes = getSizesForScale(scale, [height, width])
+        return Math.min(sizes.width, sizes.height) > CELL_SIZE
+      })
+      .slice(0, maxNumScales)
+
+    stats.scales = scales
+    stats.pyramid = scales.map(scale => getSizesForScale(scale, [height, width]))
+
+    let ts = Date.now()
+    const out1 = await stage1(imgTensor, scales, scoreThresholds[0], params.pnet, stats)
+    stats.total_stage1 = Date.now() - ts
+
+    if (!out1.boxes.length) {
+      return onReturn({ results: [], stats })
+    }
+
+    stats.stage2_numInputBoxes = out1.boxes.length
+    // using the inputCanvas to extract and resize the image patches, since it is faster
+    // than doing this on the gpu
+    ts = Date.now()
+    const out2 = await stage2(inputCanvas, out1.boxes, scoreThresholds[1], params.rnet, stats)
+    stats.total_stage2 = Date.now() - ts
+
+    if (!out2.boxes.length) {
+      return onReturn({ results: [], stats })
+    }
+
+    stats.stage3_numInputBoxes = out2.boxes.length
+
+    ts = Date.now()
+    const out3 = await stage3(inputCanvas, out2.boxes, scoreThresholds[2], params.onet, stats)
+    stats.total_stage3 = Date.now() - ts
+
+    const results = out3.boxes.map((box, idx) => ({
+      faceDetection: new FaceDetection(
+        out3.scores[idx],
+        new Rect(
+          box.left / width,
+          box.top / height,
+          box.width / width,
+          box.height / height
+        ),
+        {
+          height,
+          width
+        }
+      ),
+      faceLandmarks: new FaceLandmarks5(
+        out3.points[idx].map(pt => pt.div(new Point(width, height))),
+        { width, height }
+      )
+    }))
+
+    return onReturn({ results, stats })
+  }
+
+  public async forward(
+    input: TNetInput,
+    forwardParams: MtcnnForwardParams
+  ): Promise<MtcnnResult[]> {
+    return (
+      await this.forwardInput(
+        await toNetInput(input, true, true),
+        forwardParams
+      )
+    ).results
+  }
+
+  public async forwardWithStats(
+    input: TNetInput,
+    forwardParams: MtcnnForwardParams
+  ): Promise<{ results: MtcnnResult[], stats: any }> {
+    return this.forwardInput(
+      await toNetInput(input, true, true),
+      forwardParams
+    )
+  }
+
+  // none of the param tensors are quantized yet
+  protected loadQuantizedParams(uri: string | undefined) {
+    return loadQuantizedParams(uri)
+  }
+
+  protected extractParams(weights: Float32Array) {
+    return extractParams(weights)
+  }
+}
\ No newline at end of file

src/mtcnn/ONet.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { convLayer } from '../commons/convLayer';
+import { fullyConnectedLayer } from '../faceLandmarkNet/fullyConnectedLayer';
+import { prelu } from './prelu';
+import { sharedLayer } from './sharedLayers';
+import { ONetParams } from './types';
+
+export function ONet(x: tf.Tensor4D, params: ONetParams): { scores: tf.Tensor1D, regions: tf.Tensor2D, points: tf.Tensor2D } {
+  return tf.tidy(() => {
+
+    let out = sharedLayer(x, params)
+    out = tf.maxPool(out, [2, 2], [2, 2], 'same')
+    out = convLayer(out, params.conv4, 'valid')
+    out = prelu<tf.Tensor4D>(out, params.prelu4_alpha)
+
+    const vectorized = tf.reshape(out, [out.shape[0], params.fc1.weights.shape[0]]) as tf.Tensor2D
+    const fc1 = fullyConnectedLayer(vectorized, params.fc1)
+    const prelu5 = prelu<tf.Tensor2D>(fc1, params.prelu5_alpha)
+    const fc2_1 = fullyConnectedLayer(prelu5, params.fc2_1)
+    const max = tf.expandDims(tf.max(fc2_1, 1), 1)
+
+    const prob = tf.softmax(tf.sub(fc2_1, max), 1) as tf.Tensor2D
+    const regions = fullyConnectedLayer(prelu5, params.fc2_2)
+    const points = fullyConnectedLayer(prelu5, params.fc2_3)
+
+    const scores = tf.unstack(prob, 1)[1] as tf.Tensor1D
+    return { scores, regions, points }
+  })
+}
\ No newline at end of file

src/mtcnn/PNet.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { convLayer } from '../commons/convLayer';
+import { sharedLayer } from './sharedLayers';
+import { PNetParams } from './types';
+
+export function PNet(x: tf.Tensor4D, params: PNetParams): { prob: tf.Tensor4D, regions: tf.Tensor4D } {
+  return tf.tidy(() => {
+
+    let out = sharedLayer(x, params, true)
+    const conv = convLayer(out, params.conv4_1, 'valid')
+    const max = tf.expandDims(tf.max(conv, 3), 3)
+    const prob = tf.softmax(tf.sub(conv, max), 3) as tf.Tensor4D
+    const regions = convLayer(out, params.conv4_2, 'valid')
+
+    return { prob, regions }
+  })
+}
\ No newline at end of file

src/mtcnn/RNet.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { fullyConnectedLayer } from '../faceLandmarkNet/fullyConnectedLayer';
+import { prelu } from './prelu';
+import { sharedLayer } from './sharedLayers';
+import { RNetParams } from './types';
+
+export function RNet(x: tf.Tensor4D, params: RNetParams): { scores: tf.Tensor1D, regions: tf.Tensor2D } {
+  return tf.tidy(() => {
+
+    const convOut = sharedLayer(x, params)
+    const vectorized = tf.reshape(convOut, [convOut.shape[0], params.fc1.weights.shape[0]]) as tf.Tensor2D
+    const fc1 = fullyConnectedLayer(vectorized, params.fc1)
+    const prelu4 = prelu<tf.Tensor2D>(fc1, params.prelu4_alpha)
+    const fc2_1 = fullyConnectedLayer(prelu4, params.fc2_1)
+    const max = tf.expandDims(tf.max(fc2_1, 1), 1)
+    const prob = tf.softmax(tf.sub(fc2_1, max), 1) as tf.Tensor2D
+    const regions = fullyConnectedLayer(prelu4, params.fc2_2)
+
+    const scores = tf.unstack(prob, 1)[1] as tf.Tensor1D
+    return { scores, regions }
+  })
+}
\ No newline at end of file

src/mtcnn/bgrToRgbTensor.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+export function bgrToRgbTensor(tensor: tf.Tensor4D): tf.Tensor4D {
+  return tf.tidy(
+    () => tf.stack(tf.unstack(tensor, 3).reverse(), 3)
+  ) as tf.Tensor4D
+}
\ No newline at end of file

src/mtcnn/config.ts

+export const CELL_STRIDE = 2
+export const CELL_SIZE = 12
\ No newline at end of file

src/mtcnn/extractImagePatches.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { Dimensions } from '../types';
+import { createCanvas, getContext2dOrThrow } from '../utils';
+import { BoundingBox } from './BoundingBox';
+import { normalize } from './normalize';
+
+export async function extractImagePatches(
+  img: HTMLCanvasElement,
+  boxes: BoundingBox[],
+  { width, height }: Dimensions
+): Promise<tf.Tensor4D[]> {
+
+
+  const imgCtx = getContext2dOrThrow(img)
+
+  const bitmaps = await Promise.all(boxes.map(async box => {
+    // TODO: correct padding
+    const { y, ey, x, ex } = box.padAtBorders(img.height, img.width)
+
+    const fromX = x - 1
+    const fromY = y - 1
+    const imgData = imgCtx.getImageData(fromX, fromY, (ex - fromX), (ey - fromY))
+
+    return createImageBitmap(imgData)
+  }))
+
+  const imagePatchesDatas: number[][] = []
+
+  bitmaps.forEach(bmp => {
+    const patch = createCanvas({ width, height })
+    const patchCtx = getContext2dOrThrow(patch)
+    patchCtx.drawImage(bmp, 0, 0, width, height)
+    const { data } = patchCtx.getImageData(0, 0, width, height)
+
+    const currData = []
+    // RGBA -> BGR
+    for(let i = 0; i < data.length; i+=4) {
+      currData.push(data[i + 2])
+      currData.push(data[i + 1])
+      currData.push(data[i])
+    }
+    imagePatchesDatas.push(currData)
+  })
+
+
+  return imagePatchesDatas.map(data => {
+    const t = tf.tidy(() => {
+      const imagePatchTensor = tf.transpose(
+        tf.tensor4d(data, [1, width, height, 3]),
+        [0, 2, 1, 3]
+      ).toFloat() as tf.Tensor4D
+
+      return normalize(imagePatchTensor)
+    })
+    return t
+  })
+}
\ No newline at end of file

src/mtcnn/extractParams.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { extractConvParamsFactory } from '../commons/extractConvParamsFactory';
+import { extractFCParamsFactory } from '../commons/extractFCParamsFactory';
+import { extractWeightsFactory } from '../commons/extractWeightsFactory';
+import { ExtractWeightsFunction, ParamMapping } from '../commons/types';
+import { NetParams, PNetParams, RNetParams, SharedParams, ONetParams } from './types';
+
+function extractorsFactory(extractWeights: ExtractWeightsFunction, paramMappings: ParamMapping[]) {
+
+  const extractConvParams = extractConvParamsFactory(extractWeights, paramMappings)
+  const extractFCParams = extractFCParamsFactory(extractWeights, paramMappings)
+
+  function extractPReluParams(size: number, paramPath: string): tf.Tensor1D {
+    const alpha = tf.tensor1d(extractWeights(size))
+    paramMappings.push({ paramPath })
+    return alpha
+  }
+
+  function extractSharedParams(numFilters: number[], mappedPrefix: string, isRnet: boolean = false): SharedParams {
+
+    const conv1 = extractConvParams(numFilters[0], numFilters[1], 3, `${mappedPrefix}/conv1`)
+    const prelu1_alpha = extractPReluParams(numFilters[1], `${mappedPrefix}/prelu1_alpha`)
+    const conv2 = extractConvParams(numFilters[1], numFilters[2], 3, `${mappedPrefix}/conv2`)
+    const prelu2_alpha = extractPReluParams(numFilters[2], `${mappedPrefix}/prelu2_alpha`)
+    const conv3 = extractConvParams(numFilters[2], numFilters[3], isRnet ? 2 : 3, `${mappedPrefix}/conv3`)
+    const prelu3_alpha = extractPReluParams(numFilters[3], `${mappedPrefix}/prelu3_alpha`)
+
+    return { conv1, prelu1_alpha, conv2, prelu2_alpha, conv3, prelu3_alpha }
+  }
+
+  function extractPNetParams(): PNetParams {
+
+    const sharedParams = extractSharedParams([3, 10, 16, 32], 'pnet')
+    const conv4_1 = extractConvParams(32, 2, 1, 'pnet/conv4_1')
+    const conv4_2 = extractConvParams(32, 4, 1, 'pnet/conv4_2')
+
+    return { ...sharedParams, conv4_1, conv4_2 }
+  }
+
+  function extractRNetParams(): RNetParams {
+
+    const sharedParams = extractSharedParams([3, 28, 48, 64], 'rnet', true)
+    const fc1 = extractFCParams(576, 128, 'rnet/fc1')
+    const prelu4_alpha = extractPReluParams(128, 'rnet/prelu4_alpha')
+    const fc2_1 = extractFCParams(128, 2, 'rnet/fc2_1')
+    const fc2_2 = extractFCParams(128, 4, 'rnet/fc2_2')
+
+    return { ...sharedParams, fc1, prelu4_alpha, fc2_1, fc2_2 }
+  }
+
+  function extractONetParams(): ONetParams {
+
+    const sharedParams = extractSharedParams([3, 32, 64, 64], 'onet')
+    const conv4 = extractConvParams(64, 128, 2, 'onet/conv4')
+    const prelu4_alpha = extractPReluParams(128, 'onet/prelu4_alpha')
+    const fc1 = extractFCParams(1152, 256, 'onet/fc1')
+    const prelu5_alpha = extractPReluParams(256, 'onet/prelu5_alpha')
+    const fc2_1 = extractFCParams(256, 2, 'onet/fc2_1')
+    const fc2_2 = extractFCParams(256, 4, 'onet/fc2_2')
+    const fc2_3 = extractFCParams(256, 10, 'onet/fc2_3')
+
+    return { ...sharedParams, conv4, prelu4_alpha, fc1, prelu5_alpha, fc2_1, fc2_2, fc2_3 }
+  }
+
+  return {
+    extractPNetParams,
+    extractRNetParams,
+    extractONetParams
+  }
+
+}
+
+export function extractParams(weights: Float32Array): { params: NetParams, paramMappings: ParamMapping[] } {
+
+  const {
+    extractWeights,
+    getRemainingWeights
+  } = extractWeightsFactory(weights)
+
+  const paramMappings: ParamMapping[] = []
+
+  const {
+    extractPNetParams,
+    extractRNetParams,
+    extractONetParams
+  } = extractorsFactory(extractWeights, paramMappings)
+
+  const pnet = extractPNetParams()
+  const rnet = extractRNetParams()
+  const onet = extractONetParams()
+
+  if (getRemainingWeights().length !== 0) {
+    throw new Error(`weights remaing after extract: ${getRemainingWeights().length}`)
+  }
+
+  return { params: { pnet, rnet, onet }, paramMappings }
+}
\ No newline at end of file

src/mtcnn/getDefaultMtcnnForwardParams.ts

+export function getDefaultMtcnnForwardParams() {
+  return {
+    minFaceSize: 20,
+    scaleFactor: 0.709,
+    maxNumScales: 10,
+    scoreThresholds: [0.6, 0.7, 0.7]
+  }
+}
\ No newline at end of file

src/mtcnn/getSizesForScale.ts

+export function getSizesForScale(scale: number, [height, width]: number[]) {
+  return {
+    height: Math.floor(height * scale),
+    width: Math.floor(width * scale)
+  }
+}
\ No newline at end of file

src/mtcnn/index.ts

+import { Mtcnn } from './Mtcnn';
+
+export * from './Mtcnn';
+export * from './FaceLandmarks5';
+
+export function createMtcnn(weights: Float32Array) {
+  const net = new Mtcnn()
+  net.extractWeights(weights)
+  return net
+}
\ No newline at end of file

src/mtcnn/loadQuantizedParams.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { disposeUnusedWeightTensors } from '../commons/disposeUnusedWeightTensors';
+import { extractWeightEntryFactory } from '../commons/extractWeightEntryFactory';
+import { loadWeightMap } from '../commons/loadWeightMap';
+import { ConvParams, FCParams, ParamMapping } from '../commons/types';
+import { NetParams, ONetParams, PNetParams, RNetParams, SharedParams } from './types';
+
+const DEFAULT_MODEL_NAME = 'mtcnn_model'
+
+function extractorsFactory(weightMap: any, paramMappings: ParamMapping[]) {
+
+  const extractWeightEntry = extractWeightEntryFactory(weightMap, paramMappings)
+
+  function extractConvParams(prefix: string): ConvParams {
+    const filters = extractWeightEntry<tf.Tensor4D>(`${prefix}/weights`, 4, `${prefix}/filters`)
+    const bias = extractWeightEntry<tf.Tensor1D>(`${prefix}/bias`, 1)
+
+    return { filters, bias }
+  }
+
+  function extractFCParams(prefix: string): FCParams {
+    const weights = extractWeightEntry<tf.Tensor2D>(`${prefix}/weights`, 2)
+    const bias = extractWeightEntry<tf.Tensor1D>(`${prefix}/bias`, 1)
+
+    return { weights, bias }
+  }
+
+  function extractPReluParams(paramPath: string): tf.Tensor1D {
+    return extractWeightEntry<tf.Tensor1D>(paramPath, 1)
+  }
+
+  function extractSharedParams(prefix: string): SharedParams {
+
+    const conv1 = extractConvParams(`${prefix}/conv1`)
+    const prelu1_alpha = extractPReluParams(`${prefix}/prelu1_alpha`)
+    const conv2 = extractConvParams(`${prefix}/conv2`)
+    const prelu2_alpha = extractPReluParams(`${prefix}/prelu2_alpha`)
+    const conv3 = extractConvParams(`${prefix}/conv3`)
+    const prelu3_alpha = extractPReluParams(`${prefix}/prelu3_alpha`)
+
+    return { conv1, prelu1_alpha, conv2, prelu2_alpha, conv3, prelu3_alpha }
+  }
+
+  function extractPNetParams(): PNetParams {
+
+    const sharedParams = extractSharedParams('pnet')
+    const conv4_1 = extractConvParams('pnet/conv4_1')
+    const conv4_2 = extractConvParams('pnet/conv4_2')
+
+    return { ...sharedParams, conv4_1, conv4_2 }
+  }
+
+  function extractRNetParams(): RNetParams {
+
+    const sharedParams = extractSharedParams('rnet')
+    const fc1 = extractFCParams('rnet/fc1')
+    const prelu4_alpha = extractPReluParams('rnet/prelu4_alpha')
+    const fc2_1 = extractFCParams('rnet/fc2_1')
+    const fc2_2 = extractFCParams('rnet/fc2_2')
+
+    return { ...sharedParams, fc1, prelu4_alpha, fc2_1, fc2_2 }
+  }
+
+  function extractONetParams(): ONetParams {
+
+    const sharedParams = extractSharedParams('onet')
+    const conv4 = extractConvParams('onet/conv4')
+    const prelu4_alpha = extractPReluParams('onet/prelu4_alpha')
+    const fc1 = extractFCParams('onet/fc1')
+    const prelu5_alpha = extractPReluParams('onet/prelu5_alpha')
+    const fc2_1 = extractFCParams('onet/fc2_1')
+    const fc2_2 = extractFCParams('onet/fc2_2')
+    const fc2_3 = extractFCParams('onet/fc2_3')
+
+    return { ...sharedParams, conv4, prelu4_alpha, fc1, prelu5_alpha, fc2_1, fc2_2, fc2_3 }
+  }
+
+  return {
+    extractPNetParams,
+    extractRNetParams,
+    extractONetParams
+  }
+
+}
+
+export async function loadQuantizedParams(
+  uri: string | undefined
+): Promise<{ params: NetParams, paramMappings: ParamMapping[] }> {
+
+  const weightMap = await loadWeightMap(uri, DEFAULT_MODEL_NAME)
+  const paramMappings: ParamMapping[] = []
+
+  const {
+    extractPNetParams,
+    extractRNetParams,
+    extractONetParams
+  } = extractorsFactory(weightMap, paramMappings)
+
+  const pnet = extractPNetParams()
+  const rnet = extractRNetParams()
+  const onet = extractONetParams()
+
+  disposeUnusedWeightTensors(weightMap, paramMappings)
+
+  return { params: { pnet, rnet, onet }, paramMappings }
+}
\ No newline at end of file

src/mtcnn/nms.ts

+import { BoundingBox } from './BoundingBox';
+
+export function nms(
+  boxes: BoundingBox[],
+  scores: number[],
+  iouThreshold: number,
+  isIOU: boolean = true
+): number[] {
+
+  const areas = boxes.map(
+    box => (box.width + 1) * (box.height + 1)
+  )
+
+  let indicesSortedByScore = scores
+    .map((score, boxIndex) => ({ score, boxIndex }))
+    .sort((c1, c2) => c1.score - c2.score)
+    .map(c => c.boxIndex)
+
+  const pick: number[] = []
+
+  while(indicesSortedByScore.length > 0) {
+    const curr = indicesSortedByScore.pop() as number
+    pick.push(curr)
+
+    const indices = indicesSortedByScore
+
+    const outputs: number[] = []
+    for (let i = 0; i < indices.length; i++) {
+      const idx = indices[i]
+
+      const currBox = boxes[curr]
+      const idxBox = boxes[idx]
+
+      const width = Math.max(0.0, Math.min(currBox.right, idxBox.right) - Math.max(currBox.left, idxBox.left) + 1)
+      const height = Math.max(0.0, Math.min(currBox.bottom, idxBox.bottom) - Math.max(currBox.top, idxBox.top) + 1)
+      const interSection = width * height
+
+      const out = isIOU
+        ? interSection / (areas[curr] + areas[idx] - interSection)
+        : interSection / Math.min(areas[curr], areas[idx])
+
+      outputs.push(out)
+    }
+
+    indicesSortedByScore = indicesSortedByScore.filter(
+      (_, j) => outputs[j] <= iouThreshold
+    )
+  }
+
+  return pick
+
+}
\ No newline at end of file

src/mtcnn/normalize.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+export function normalize(x: tf.Tensor4D): tf.Tensor4D {
+  return tf.tidy(
+    () => tf.mul(tf.sub(x, tf.scalar(127.5)), tf.scalar(0.0078125))
+  )
+}
\ No newline at end of file

src/mtcnn/prelu.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+export function prelu<T extends tf.Tensor>(x: T, alpha: tf.Tensor1D): T {
+  return tf.tidy(() =>
+    tf.add(
+      tf.relu(x),
+      tf.mul(alpha, tf.neg(tf.relu(tf.neg(x))))
+    )
+  )
+}

src/mtcnn/pyramidDown.ts

+import { CELL_SIZE } from './config';
+
+export function pyramidDown(minFaceSize: number, scaleFactor: number, dims: number[]): number[] {
+
+  const [height, width] = dims
+  const m = CELL_SIZE / minFaceSize
+
+  const scales = []
+
+  let minLayer = Math.min(height, width) * m
+  let exp = 0
+  while (minLayer >= 12) {
+    scales.push(m * Math.pow(scaleFactor, exp))
+    minLayer = minLayer * scaleFactor
+    exp += 1
+  }
+
+  return scales
+}
\ No newline at end of file

src/mtcnn/sharedLayers.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { convLayer } from '../commons/convLayer';
+import { prelu } from './prelu';
+import { SharedParams } from './types';
+
+export function sharedLayer(x: tf.Tensor4D, params: SharedParams, isPnet: boolean = false) {
+  return tf.tidy(() => {
+
+    let out = convLayer(x, params.conv1, 'valid')
+    out = prelu<tf.Tensor4D>(out, params.prelu1_alpha)
+    out = tf.maxPool(out, isPnet ? [2, 2]: [3, 3], [2, 2], 'same')
+    out = convLayer(out, params.conv2, 'valid')
+    out = prelu<tf.Tensor4D>(out, params.prelu2_alpha)
+    out = isPnet ? out : tf.maxPool(out, [3, 3], [2, 2], 'valid')
+    out = convLayer(out, params.conv3, 'valid')
+    out = prelu<tf.Tensor4D>(out, params.prelu3_alpha)
+
+    return out
+  })
+}
\ No newline at end of file

src/mtcnn/stage1.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { Point } from '../Point';
+import { BoundingBox } from './BoundingBox';
+import { CELL_SIZE, CELL_STRIDE } from './config';
+import { nms } from './nms';
+import { normalize } from './normalize';
+import { PNet } from './PNet';
+import { PNetParams } from './types';
+import { getSizesForScale } from './getSizesForScale';
+
+function rescaleAndNormalize(x: tf.Tensor4D, scale: number): tf.Tensor4D {
+  return tf.tidy(() => {
+
+    const { height, width } = getSizesForScale(scale, x.shape.slice(1))
+    const resized = tf.image.resizeBilinear(x, [height, width])
+    const normalized = normalize(resized)
+
+    return (tf.transpose(normalized, [0, 2, 1, 3]) as tf.Tensor4D)
+  })
+}
+
+function extractBoundingBoxes(
+  scoresTensor: tf.Tensor2D,
+  regionsTensor: tf.Tensor3D,
+  scale: number,
+  scoreThreshold: number
+) {
+
+  // TODO: fix this!, maybe better to use tf.gather here
+  const indices: Point[] = []
+  for (let y = 0; y < scoresTensor.shape[0]; y++) {
+    for (let x = 0; x < scoresTensor.shape[1]; x++) {
+      if (scoresTensor.get(y, x) >= scoreThreshold) {
+        indices.push(new Point(x, y))
+      }
+    }
+  }
+
+  const boundingBoxes = indices.map(idx => {
+    const cell = new BoundingBox(
+      Math.round((idx.y * CELL_STRIDE + 1) / scale),
+      Math.round((idx.x * CELL_STRIDE + 1) / scale),
+      Math.round((idx.y * CELL_STRIDE + CELL_SIZE) / scale),
+      Math.round((idx.x * CELL_STRIDE + CELL_SIZE) / scale)
+    )
+
+    const score = scoresTensor.get(idx.y, idx.x)
+
+    const region = new BoundingBox(
+      regionsTensor.get(idx.y, idx.x, 0),
+      regionsTensor.get(idx.y, idx.x, 1),
+      regionsTensor.get(idx.y, idx.x, 2),
+      regionsTensor.get(idx.y, idx.x, 3)
+    )
+
+    return {
+      cell,
+      score,
+      region
+    }
+  })
+
+  return boundingBoxes
+}
+
+export function stage1(
+  imgTensor: tf.Tensor4D,
+  scales: number[],
+  scoreThreshold: number,
+  params: PNetParams,
+  stats: any
+) {
+  stats.stage1 = []
+
+  const pnetOutputs = scales.map((scale) => tf.tidy(() => {
+    const statsForScale: any = { scale }
+    const resized = rescaleAndNormalize(imgTensor, scale)
+
+    let ts = Date.now()
+    const { prob, regions } = PNet(resized, params)
+    statsForScale.pnet = Date.now() - ts
+
+    const scoresTensor = tf.unstack(tf.unstack(prob, 3)[1])[0] as tf.Tensor2D
+    const regionsTensor = tf.unstack(regions)[0] as tf.Tensor3D
+
+    return {
+      scoresTensor,
+      regionsTensor,
+      scale,
+      statsForScale
+    }
+  }))
+
+  const boxesForScale = pnetOutputs.map(({ scoresTensor, regionsTensor, scale, statsForScale }) => {
+    const boundingBoxes = extractBoundingBoxes(
+      scoresTensor,
+      regionsTensor,
+      scale,
+      scoreThreshold
+    )
+
+    scoresTensor.dispose()
+    regionsTensor.dispose()
+
+    if (!boundingBoxes.length) {
+      stats.stage1.push(statsForScale)
+      return []
+    }
+
+    let ts = Date.now()
+    const indices = nms(
+      boundingBoxes.map(bbox => bbox.cell),
+      boundingBoxes.map(bbox => bbox.score),
+      0.5
+    )
+    statsForScale.nms = Date.now() - ts
+    statsForScale.numBoxes = indices.length
+
+    stats.stage1.push(statsForScale)
+    return indices.map(boxIdx => boundingBoxes[boxIdx])
+  })
+
+  const allBoxes = boxesForScale.reduce(
+    (all, boxes) => all.concat(boxes), []
+  )
+
+  let finalBoxes: BoundingBox[] = []
+  let finalScores: number[] = []
+
+  if (allBoxes.length > 0) {
+    let ts = Date.now()
+    const indices = nms(
+      allBoxes.map(bbox => bbox.cell),
+      allBoxes.map(bbox => bbox.score),
+      0.7
+    )
+    stats.stage1_nms = Date.now() - ts
+
+    finalScores = indices.map(idx => allBoxes[idx].score)
+    finalBoxes = indices
+      .map(idx => allBoxes[idx])
+      .map(({ cell, region }) =>
+        new BoundingBox(
+          cell.left + (region.left * cell.width),
+          cell.top + (region.top * cell.height),
+          cell.right + (region.right * cell.width),
+          cell.bottom + (region.bottom * cell.height)
+        ).toSquare().round()
+      )
+
+  }
+
+  return {
+    boxes: finalBoxes,
+    scores: finalScores
+  }
+
+}

src/mtcnn/stage2.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { BoundingBox } from './BoundingBox';
+import { extractImagePatches } from './extractImagePatches';
+import { nms } from './nms';
+import { RNet } from './RNet';
+import { RNetParams } from './types';
+
+export async function stage2(
+  img: HTMLCanvasElement,
+  inputBoxes: BoundingBox[],
+  scoreThreshold: number,
+  params: RNetParams,
+  stats: any
+) {
+
+  let ts = Date.now()
+  const rnetInputs = await extractImagePatches(img, inputBoxes, { width: 24, height: 24 })
+  stats.stage2_extractImagePatches = Date.now() - ts
+
+  ts = Date.now()
+  const rnetOuts = rnetInputs.map(
+    rnetInput => {
+      const out = RNet(rnetInput, params)
+      rnetInput.dispose()
+      return out
+    }
+  )
+  stats.stage2_rnet = Date.now() - ts
+
+  const scoresTensor = rnetOuts.length > 1
+    ? tf.concat(rnetOuts.map(out => out.scores))
+    : rnetOuts[0].scores
+  const scores = Array.from(await scoresTensor.data())
+  scoresTensor.dispose()
+
+  const indices = scores
+    .map((score, idx) => ({ score, idx }))
+    .filter(c => c.score > scoreThreshold)
+    .map(({ idx }) => idx)
+
+  const filteredBoxes = indices.map(idx => inputBoxes[idx])
+  const filteredScores = indices.map(idx => scores[idx])
+
+  let finalBoxes: BoundingBox[] = []
+  let finalScores: number[] = []
+
+  if (filteredBoxes.length > 0) {
+    ts = Date.now()
+    const indicesNms = nms(
+      filteredBoxes,
+      filteredScores,
+      0.7
+    )
+    stats.stage2_nms = Date.now() - ts
+
+    const regions = indicesNms.map(idx =>
+      new BoundingBox(
+        rnetOuts[indices[idx]].regions.get(0, 0),
+        rnetOuts[indices[idx]].regions.get(0, 1),
+        rnetOuts[indices[idx]].regions.get(0, 2),
+        rnetOuts[indices[idx]].regions.get(0, 3)
+      )
+    )
+
+    finalScores = indicesNms.map(idx => filteredScores[idx])
+    finalBoxes = indicesNms.map((idx, i) => filteredBoxes[idx].calibrate(regions[i]))
+  }
+
+  rnetOuts.forEach(t => {
+    t.regions.dispose()
+    t.scores.dispose()
+  })
+
+  return {
+    boxes: finalBoxes,
+    scores: finalScores
+  }
+}
\ No newline at end of file

src/mtcnn/stage3.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { Point } from '../Point';
+import { BoundingBox } from './BoundingBox';
+import { extractImagePatches } from './extractImagePatches';
+import { nms } from './nms';
+import { ONet } from './ONet';
+import { ONetParams } from './types';
+
+export async function stage3(
+  img: HTMLCanvasElement,
+  inputBoxes: BoundingBox[],
+  scoreThreshold: number,
+  params: ONetParams,
+  stats: any
+) {
+
+  let ts = Date.now()
+  const onetInputs = await extractImagePatches(img, inputBoxes, { width: 48, height: 48 })
+  stats.stage3_extractImagePatches = Date.now() - ts
+
+  ts = Date.now()
+  const onetOuts = onetInputs.map(
+    onetInput => {
+      const out = ONet(onetInput, params)
+      onetInput.dispose()
+      return out
+    }
+  )
+  stats.stage3_onet = Date.now() - ts
+
+  const scoresTensor = onetOuts.length > 1
+    ? tf.concat(onetOuts.map(out => out.scores))
+    : onetOuts[0].scores
+  const scores = Array.from(await scoresTensor.data())
+  scoresTensor.dispose()
+
+  const indices = scores
+    .map((score, idx) => ({ score, idx }))
+    .filter(c => c.score > scoreThreshold)
+    .map(({ idx }) => idx)
+
+  const filteredRegions = indices.map(idx => new BoundingBox(
+    onetOuts[idx].regions.get(0, 0),
+    onetOuts[idx].regions.get(0, 1),
+    onetOuts[idx].regions.get(0, 2),
+    onetOuts[idx].regions.get(0, 3)
+  ))
+  const filteredBoxes = indices
+    .map((idx, i) => inputBoxes[idx].calibrate(filteredRegions[i]))
+  const filteredScores = indices.map(idx => scores[idx])
+
+  let finalBoxes: BoundingBox[] = []
+  let finalScores: number[] = []
+  let points: Point[][] = []
+
+  if (filteredBoxes.length > 0) {
+
+    ts = Date.now()
+    const indicesNms = nms(
+      filteredBoxes,
+      filteredScores,
+      0.7,
+      false
+    )
+    stats.stage3_nms = Date.now() - ts
+
+    finalBoxes = indicesNms.map(idx => filteredBoxes[idx])
+    finalScores = indicesNms.map(idx => filteredScores[idx])
+    points = indicesNms.map((idx, i) =>
+      Array(5).fill(0).map((_, ptIdx) =>
+        new Point(
+          ((onetOuts[idx].points.get(0, ptIdx) * (finalBoxes[i].width + 1)) + finalBoxes[i].left) ,
+          ((onetOuts[idx].points.get(0, ptIdx + 5) * (finalBoxes[i].height + 1)) + finalBoxes[i].top)
+        )
+      )
+    )
+  }
+
+  onetOuts.forEach(t => {
+    t.regions.dispose()
+    t.scores.dispose()
+    t.points.dispose()
+  })
+
+  return {
+    boxes: finalBoxes,
+    scores: finalScores,
+    points
+  }
+
+}

src/mtcnn/types.ts

+import * as tf from '@tensorflow/tfjs-core';
+
+import { ConvParams, FCParams } from '../commons/types';
+import { FaceDetection } from '../FaceDetection';
+import { FaceLandmarks5 } from './FaceLandmarks5';
+
+export type SharedParams = {
+  conv1: ConvParams
+  prelu1_alpha: tf.Tensor1D
+  conv2: ConvParams
+  prelu2_alpha: tf.Tensor1D
+  conv3: ConvParams
+  prelu3_alpha: tf.Tensor1D
+}
+
+export type PNetParams = SharedParams & {
+  conv4_1: ConvParams
+  conv4_2: ConvParams
+}
+
+export type RNetParams = SharedParams & {
+  fc1: FCParams
+  prelu4_alpha: tf.Tensor1D
+  fc2_1: FCParams
+  fc2_2: FCParams
+}
+
+export type ONetParams = SharedParams & {
+  conv4: ConvParams
+  prelu4_alpha: tf.Tensor1D
+  fc1: FCParams
+  prelu5_alpha: tf.Tensor1D
+  fc2_1: FCParams
+  fc2_2: FCParams
+  fc2_3: FCParams
+}
+
+export type NetParams = {
+  pnet: PNetParams
+  rnet: RNetParams
+  onet: ONetParams
+}
+
+export type MtcnnResult = {
+  faceDetection: FaceDetection,
+  faceLandmarks: FaceLandmarks5
+}
+
+export type MtcnnForwardParams = {
+  minFaceSize?: number
+  scaleFactor?: number
+  maxNumScales?: number
+  scoreThresholds?: number[]
+  scaleSteps?: number[]
+}

src/toNetInput.ts

@@ -17,7 +17,8 @@ import { awaitMediaLoaded, resolveInput } from './utils';
  */
 export async function toNetInput(
   inputs: TNetInput,
-  manageCreatedInput: boolean = false
+  manageCreatedInput: boolean = false,
+  keepCanvases: boolean = false
 ): Promise<NetInput> {
   if (inputs instanceof NetInput) {
     return inputs
@@ -67,5 +68,5 @@ export async function toNetInput(
     inputArray.map(input => isMediaElement(input) && awaitMediaLoaded(input))
   )
 
-  return afterCreate(new NetInput(inputArray, Array.isArray(inputs)))
+  return afterCreate(new NetInput(inputArray, Array.isArray(inputs), keepCanvases))
 }
\ No newline at end of file

test/tests/NetInput.test.ts

-import * as tf from '@tensorflow/tfjs-core';
-
 import { NetInput } from '../../src/NetInput';
-import { bufferToImage, createCanvasFromMedia } from '../../src/utils';
+import { bufferToImage } from '../../src/utils';
 import { expectAllTensorsReleased, tensor3D } from '../utils';
 
-
 describe('NetInput', () => {
 
   let imgEl: HTMLImageElement

test/tests/e2e/faceDetectionNet.test.ts

 import * as faceapi from '../../../src';
-import { FaceDetection } from '../../../src/faceDetectionNet/FaceDetection';
-import { IRect } from '../../../src/Rect';
-import { describeWithNets, expectAllTensorsReleased, expectMaxDelta } from '../../utils';
-
-function expectRectClose(
-  result: IRect,
-  expectedBox: IRect,
-  maxDelta: number
-) {
-  const { x, y, width, height } = result
-  expectMaxDelta(x, expectedBox.x, maxDelta)
-  expectMaxDelta(y, expectedBox.y, maxDelta)
-  expectMaxDelta(width, expectedBox.width, maxDelta)
-  expectMaxDelta(height, expectedBox.height, maxDelta)
-}
+import { describeWithNets, expectAllTensorsReleased, expectRectClose } from '../../utils';
 
 const expectedBoxes = [
   { x: 48, y: 253, width: 104, height: 129 },
@@ -39,7 +25,7 @@ describe('faceDetectionNet', () => {
     const maxBoxDelta = 1
 
     it('scores > 0.8', async () => {
-      const detections = await faceDetectionNet.locateFaces(imgEl) as FaceDetection[]
+      const detections = await faceDetectionNet.locateFaces(imgEl) as faceapi.FaceDetection[]
 
       expect(detections.length).toEqual(3)
       detections.forEach((det, i) => {
@@ -51,7 +37,7 @@ describe('faceDetectionNet', () => {
     })
 
     it('scores > 0.5', async () => {
-      const detections = await faceDetectionNet.locateFaces(imgEl, 0.5) as FaceDetection[]
+      const detections = await faceDetectionNet.locateFaces(imgEl, 0.5) as faceapi.FaceDetection[]
 
       expect(detections.length).toEqual(6)
       detections.forEach((det, i) => {
@@ -70,7 +56,7 @@ describe('faceDetectionNet', () => {
     const maxBoxDelta = 5
 
     it('scores > 0.8', async () => {
-      const detections = await faceDetectionNet.locateFaces(imgEl) as FaceDetection[]
+      const detections = await faceDetectionNet.locateFaces(imgEl) as faceapi.FaceDetection[]
 
       expect(detections.length).toEqual(4)
       detections.forEach((det, i) => {
@@ -82,7 +68,7 @@ describe('faceDetectionNet', () => {
     })
 
     it('scores > 0.5', async () => {
-      const detections = await faceDetectionNet.locateFaces(imgEl, 0.5) as FaceDetection[]
+      const detections = await faceDetectionNet.locateFaces(imgEl, 0.5) as faceapi.FaceDetection[]
 
       expect(detections.length).toEqual(6)
       detections.forEach((det, i) => {
@@ -103,7 +89,7 @@ describe('faceDetectionNet', () => {
         await expectAllTensorsReleased(async () => {
           const res = await fetch('base/weights/uncompressed/face_detection_model.weights')
           const weights = new Float32Array(await res.arrayBuffer())
-          const net = faceapi.faceDetectionNet(weights)
+          const net = faceapi.createFaceDetectionNet(weights)
           net.dispose()
         })
       })

test/tests/e2e/faceLandmarkNet.test.ts

@@ -2,7 +2,6 @@ import * as tf from '@tensorflow/tfjs-core';
 
 import * as faceapi from '../../../src';
 import { isTensor3D } from '../../../src/commons/isTensor';
-import { FaceLandmarks } from '../../../src/faceLandmarkNet/FaceLandmarks';
 import { Point } from '../../../src/Point';
 import { Dimensions, TMediaElement } from '../../../src/types';
 import { expectMaxDelta, expectAllTensorsReleased, tensor3D, describeWithNets } from '../../utils';
@@ -43,7 +42,7 @@ describe('faceLandmarkNet', () => {
     it('computes face landmarks for squared input', async () => {
       const { width, height } = imgEl1
 
-      const result = await faceLandmarkNet.detectLandmarks(imgEl1) as FaceLandmarks
+      const result = await faceLandmarkNet.detectLandmarks(imgEl1) as faceapi.FaceLandmarks68
       expect(result.getImageWidth()).toEqual(width)
       expect(result.getImageHeight()).toEqual(height)
       expect(result.getShift().x).toEqual(0)
@@ -57,7 +56,7 @@ describe('faceLandmarkNet', () => {
     it('computes face landmarks for rectangular input', async () => {
       const { width, height } = imgElRect
 
-      const result = await faceLandmarkNet.detectLandmarks(imgElRect) as FaceLandmarks
+      const result = await faceLandmarkNet.detectLandmarks(imgElRect) as faceapi.FaceLandmarks68
       expect(result.getImageWidth()).toEqual(width)
       expect(result.getImageHeight()).toEqual(height)
       expect(result.getShift().x).toEqual(0)
@@ -75,7 +74,7 @@ describe('faceLandmarkNet', () => {
     it('computes face landmarks for squared input', async () => {
       const { width, height } = imgEl1
 
-      const result = await faceLandmarkNet.detectLandmarks(imgEl1) as FaceLandmarks
+      const result = await faceLandmarkNet.detectLandmarks(imgEl1) as faceapi.FaceLandmarks68
       expect(result.getImageWidth()).toEqual(width)
       expect(result.getImageHeight()).toEqual(height)
       expect(result.getShift().x).toEqual(0)
@@ -89,7 +88,7 @@ describe('faceLandmarkNet', () => {
     it('computes face landmarks for rectangular input', async () => {
       const { width, height } = imgElRect
 
-      const result = await faceLandmarkNet.detectLandmarks(imgElRect) as FaceLandmarks
+      const result = await faceLandmarkNet.detectLandmarks(imgElRect) as faceapi.FaceLandmarks68
       expect(result.getImageWidth()).toEqual(width)
       expect(result.getImageHeight()).toEqual(height)
       expect(result.getShift().x).toEqual(0)
@@ -113,7 +112,7 @@ describe('faceLandmarkNet', () => {
         faceLandmarkPositionsRect
       ]
 
-      const results = await faceLandmarkNet.detectLandmarks(inputs) as FaceLandmarks[]
+      const results = await faceLandmarkNet.detectLandmarks(inputs) as faceapi.FaceLandmarks68[]
       expect(Array.isArray(results)).toBe(true)
       expect(results.length).toEqual(3)
       results.forEach((result, batchIdx) => {
@@ -138,7 +137,7 @@ describe('faceLandmarkNet', () => {
         faceLandmarkPositionsRect
       ]
 
-      const results = await faceLandmarkNet.detectLandmarks(inputs) as FaceLandmarks[]
+      const results = await faceLandmarkNet.detectLandmarks(inputs) as faceapi.FaceLandmarks68[]
       expect(Array.isArray(results)).toBe(true)
       expect(results.length).toEqual(3)
       results.forEach((result, batchIdx) => {
@@ -163,7 +162,7 @@ describe('faceLandmarkNet', () => {
         faceLandmarkPositionsRect
       ]
 
-      const results = await faceLandmarkNet.detectLandmarks(tf.stack(inputs) as tf.Tensor4D) as FaceLandmarks[]
+      const results = await faceLandmarkNet.detectLandmarks(tf.stack(inputs) as tf.Tensor4D) as faceapi.FaceLandmarks68[]
       expect(Array.isArray(results)).toBe(true)
       expect(results.length).toEqual(2)
       results.forEach((result, batchIdx) => {
@@ -188,7 +187,7 @@ describe('faceLandmarkNet', () => {
         faceLandmarkPositionsRect
       ]
 
-      const results = await faceLandmarkNet.detectLandmarks(inputs) as FaceLandmarks[]
+      const results = await faceLandmarkNet.detectLandmarks(inputs) as faceapi.FaceLandmarks68[]
       expect(Array.isArray(results)).toBe(true)
       expect(results.length).toEqual(3)
       results.forEach((result, batchIdx) => {
@@ -214,7 +213,7 @@ describe('faceLandmarkNet', () => {
         await expectAllTensorsReleased(async () => {
           const res = await fetch('base/weights/uncompressed/face_landmark_68_model.weights')
           const weights = new Float32Array(await res.arrayBuffer())
-          const net = faceapi.faceLandmarkNet(weights)
+          const net = faceapi.createFaceLandmarkNet(weights)
           net.dispose()
         })
       })

test/tests/e2e/faceRecognitionNet.test.ts

@@ -141,7 +141,7 @@ describe('faceRecognitionNet', () => {
         await expectAllTensorsReleased(async () => {
           const res = await fetch('base/weights/uncompressed/face_recognition_model.weights')
           const weights = new Float32Array(await res.arrayBuffer())
-          const net = faceapi.faceRecognitionNet(weights)
+          const net = faceapi.createFaceRecognitionNet(weights)
           net.dispose()
         })
       })

test/tests/e2e/mtcnn.test.ts

+import * as faceapi from '../../../src';
+import { MtcnnResult } from '../../../src/mtcnn/types';
+import { Point } from '../../../src/Point';
+import { describeWithNets, expectAllTensorsReleased, expectPointClose, expectRectClose, expectMaxDelta } from '../../utils';
+
+const expectedBoxes = [
+  { x: 70, y: 21, width: 112, height: 112 },
+  { x: 36, y: 250, width: 133, height: 132 },
+  { x: 221, y: 43, width: 112, height: 111 },
+  { x: 247, y: 231, width: 106, height: 107 },
+  { x: 566, y: 67, width: 104, height: 104 },
+  { x: 451, y: 176, width: 122, height: 122 }
+]
+
+const expectedFaceLandmarks = [
+  [new Point(117, 58), new Point(156, 63), new Point(141, 86), new Point(109, 98), new Point(147, 104)],
+  [new Point(82, 292), new Point(134, 304), new Point(104, 330), new Point(72, 342), new Point(120, 353)],
+  [new Point(261, 82), new Point(306, 83), new Point(282, 113), new Point(257, 124), new Point(306, 126)],
+  [new Point(277, 273), new Point(318, 273), new Point(295, 300), new Point(279, 311), new Point(316, 313)],
+  [new Point(607, 110), new Point(645, 115), new Point(626, 138), new Point(601, 144), new Point(639, 150)],
+  [new Point(489, 224), new Point(534, 223), new Point(507, 250), new Point(493, 271), new Point(530, 270)]
+]
+
+describe('mtcnn', () => {
+
+  let imgEl: HTMLImageElement
+
+  beforeAll(async () => {
+    const img = await (await fetch('base/test/images/faces.jpg')).blob()
+    imgEl = await faceapi.bufferToImage(img)
+  })
+
+  describeWithNets('uncompressed weights', { withMtcnn: { quantized: false } }, ({ mtcnn }) => {
+
+    function expectResults(
+      results: MtcnnResult[],
+      boxOrder: number[],
+      maxBoxDelta: number,
+      maxLandmarkPointsDelta: number
+    ) {
+      results.forEach((result, i) => {
+        const { faceDetection, faceLandmarks } = result
+        expect(faceDetection instanceof faceapi.FaceDetection).toBe(true)
+        expect(faceLandmarks instanceof faceapi.FaceLandmarks5).toBe(true)
+        expectRectClose(faceDetection.getBox(), expectedBoxes[boxOrder[i]], maxBoxDelta)
+        faceLandmarks.getPositions().forEach((pt, j) => expectPointClose(pt, expectedFaceLandmarks[boxOrder[i]][j], maxLandmarkPointsDelta))
+        expectMaxDelta(faceDetection.getScore(), 0.99, 0.01)
+      })
+    }
+
+    it('minFaceSize = 20, finds all faces', async () => {
+      const forwardParams = {
+        minFaceSize: 20
+      }
+
+      const results = await mtcnn.forward(imgEl, forwardParams)
+      expect(results.length).toEqual(6)
+      expectResults(results, [0, 1, 2, 3, 4, 5], 1, 1)
+    })
+
+    it('minFaceSize = 80, finds all faces', async () => {
+      const forwardParams = {
+        minFaceSize: 80
+      }
+
+      const results = await mtcnn.forward(imgEl, forwardParams)
+
+      expect(results.length).toEqual(6)
+      expectResults(results, [0, 5, 3, 1, 2, 4], 12, 12)
+    })
+
+    it('all optional params passed, finds all faces', async () => {
+      const forwardParams = {
+        maxNumScales: 10,
+        scaleFactor: 0.8,
+        scoreThresholds: [0.8, 0.8, 0.9],
+        minFaceSize: 20
+      }
+
+      const results = await mtcnn.forward(imgEl, forwardParams)
+      expect(results.length).toEqual(6)
+      expectResults(results, [5, 1, 4, 3, 2, 0], 6, 10)
+    })
+
+    it('scale steps passed, finds all faces', async () => {
+      const forwardParams = {
+        scaleSteps: [0.6, 0.4, 0.2, 0.15, 0.1, 0.08, 0.02]
+      }
+
+      const results = await mtcnn.forward(imgEl, forwardParams)
+      expect(results.length).toEqual(6)
+      expectResults(results, [5, 1, 3, 0, 2, 4], 7, 15)
+    })
+
+  })
+
+  describe('no memory leaks', () => {
+
+    describe('NeuralNetwork, uncompressed model', () => {
+
+      it('disposes all param tensors', async () => {
+        await expectAllTensorsReleased(async () => {
+          const res = await fetch('base/weights/uncompressed/mtcnn_model.weights')
+          const weights = new Float32Array(await res.arrayBuffer())
+          const net = faceapi.createMtcnn(weights)
+          net.dispose()
+        })
+      })
+
+    })
+
+    describe('NeuralNetwork, quantized model', () => {
+
+      it('disposes all param tensors', async () => {
+        await expectAllTensorsReleased(async () => {
+          const net = new faceapi.Mtcnn()
+          await net.load('base/weights')
+          net.dispose()
+        })
+      })
+
+    })
+
+  })
+
+})
\ No newline at end of file

test/tests/toNetInput.test.ts

-import { tf } from '../../src';
+import * as tf from '@tensorflow/tfjs-core';
+
 import { NetInput } from '../../src/NetInput';
 import { toNetInput } from '../../src/toNetInput';
 import { bufferToImage, createCanvasFromMedia } from '../../src/utils';

test/utils.ts

 import * as tf from '@tensorflow/tfjs-core';
 
+import { IRect } from '../build/Rect';
 import * as faceapi from '../src/';
 import { NeuralNetwork } from '../src/commons/NeuralNetwork';
+import { IPoint } from '../src/';
 
 export function zeros(length: number): Float32Array {
   return new Float32Array(length)
@@ -25,6 +27,27 @@ export function tensor3D() {
   return tf.tensor3d([[[0]]])
 }
 
+export function expectPointClose(
+  result: IPoint,
+  expectedPoint: IPoint,
+  maxDelta: number
+) {
+  const { x, y } = result
+  expectMaxDelta(x, expectedPoint.x, maxDelta)
+  expectMaxDelta(y, expectedPoint.y, maxDelta)
+}
+
+export function expectRectClose(
+  result: IRect,
+  expectedBox: IRect,
+  maxDelta: number
+) {
+  const { width, height } = result
+  expectPointClose(result, expectedBox, maxDelta)
+  expectMaxDelta(width, expectedBox.width, maxDelta)
+  expectMaxDelta(height, expectedBox.height, maxDelta)
+}
+
 export type WithNetOptions = {
   quantized?: boolean
 }
@@ -33,12 +56,14 @@ export type InjectNetArgs = {
   faceDetectionNet: faceapi.FaceDetectionNet
   faceLandmarkNet: faceapi.FaceLandmarkNet
   faceRecognitionNet: faceapi.FaceRecognitionNet
+  mtcnn: faceapi.Mtcnn
 }
 
 export type DescribeWithNetsOptions = {
   withFaceDetectionNet?: WithNetOptions
   withFaceLandmarkNet?: WithNetOptions
   withFaceRecognitionNet?: WithNetOptions
+  withMtcnn?: WithNetOptions
 }
 
 async function loadNetWeights(uri: string): Promise<Float32Array> {
@@ -63,16 +88,17 @@ export function describeWithNets(
 ) {
 
   describe(description, () => {
-
     let faceDetectionNet: faceapi.FaceDetectionNet = new faceapi.FaceDetectionNet()
     let faceLandmarkNet: faceapi.FaceLandmarkNet = new faceapi.FaceLandmarkNet()
     let faceRecognitionNet: faceapi.FaceRecognitionNet = new faceapi.FaceRecognitionNet()
+    let mtcnn: faceapi.Mtcnn = new faceapi.Mtcnn()
 
     beforeAll(async () => {
       const {
         withFaceDetectionNet,
         withFaceLandmarkNet,
-        withFaceRecognitionNet
+        withFaceRecognitionNet,
+        withMtcnn
       } = options
 
       if (withFaceDetectionNet) {
@@ -93,15 +119,22 @@ export function describeWithNets(
           !withFaceRecognitionNet.quantized && 'face_recognition_model.weights'
         )
       }
+      if (withMtcnn) {
+        await initNet<faceapi.Mtcnn>(
+          mtcnn,
+          !withMtcnn.quantized && 'mtcnn_model.weights'
+        )
+      }
     })
 
     afterAll(() => {
       faceDetectionNet && faceDetectionNet.dispose()
       faceLandmarkNet && faceLandmarkNet.dispose()
       faceRecognitionNet && faceRecognitionNet.dispose()
+      mtcnn && mtcnn.dispose()
     })
 
-    specDefinitions({ faceDetectionNet, faceLandmarkNet, faceRecognitionNet })
+    specDefinitions({ faceDetectionNet, faceLandmarkNet, faceRecognitionNet, mtcnn })
   })
 }
 

weights/mtcnn_model-weights_manifest.json

+[{"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]}]}]
\ No newline at end of file