Hi, What are steps that need to be done ? 1.pacakge json for @vladmandic/face-api we used: "@tensorflow/tfjs-node": "^3.9.0", "@vladmandic/face-api": "^1.5.4", what are in old face-api ? 2.The project old face-api written in typescript, can I used it in js ? 3.What about modal they can be loaded in startup like in @vladmandic/face-api ? 4.const faceapi = require('@vladmandic/face-api'); in old api how is it in js? 5.Does the interface(methods of faceapi are same on both platform ? Thanks,

I run this function:

  async function analyzeFrame (frameData, index) {
    const tensor = await getTensorFromBuffer(frameData)
    const faces = await faceapi.detectAllFaces(tensor, optionsSSDMobileNet).withFaceLandmarks().withFaceDescriptors()
    tensor.dispose()
    faces.forEach(async (face) => {
      // console.log(face)
    })
  }

for hundreds of frames of a video. When doing so, it takes about half the time as if it where using only tfjs-node. It fills the RAM of my two 1080s, however the only usage that changes when I start the script is GPU 1s copy utilization goes to about 15%.

I want to take better advantage of my hardware and run this faster.

Windows 10, cuda 10, TFJS 2.7.0

hey! im using your package in my project for face recognition and it works fine. i copied the same project to different computer and im getting this error. tried all solutions available online, reinstalled node modules a number of times, tried all versions of node and tensorflow as well as your package, not sure where is the error coming from.

here is the error stack:

return process.dlopen(module, path.toNamespacedPath(filename)); ^

Error: A dynamic link library (DLL) initialization routine failed. \?\C:\Users\User\Documents\digitallending_sql\node_modules@tensorflow\tfjs-node\lib\napi-v5\tfjs_binding.node at Object.Module._extensions..node (internal/modules/cjs/loader.js:1206:18) at Module.load (internal/modules/cjs/loader.js:1000:32) at Function.Module._load (internal/modules/cjs/loader.js:899:14) at Module.require (internal/modules/cjs/loader.js:1042:19) at require (internal/modules/cjs/helpers.js:77:18) at Object. (C:\Users\User\Documents\digitallending_sql\node_modules@tensorflow\tfjs-node\dist\index.js:58:16) at Module._compile (internal/modules/cjs/loader.js:1156:30) at Object.Module._extensions..js (internal/modules/cjs/loader.js:1176:10) at Module.load (internal/modules/cjs/loader.js:1000:32) at Function.Module._load (internal/modules/cjs/loader.js:899:14) at Module.require (internal/modules/cjs/loader.js:1042:19) at require (internal/modules/cjs/helpers.js:77:18) at Object. (C:\Users\User\Documents\digitallending_sql\functions\facedetection.js:2:1) at Module._compile (internal/modules/cjs/loader.js:1156:30) at Object.Module._extensions..js (internal/modules/cjs/loader.js:1176:10) at Module.load (internal/modules/cjs/loader.js:1000:32) at Function.Module._load (internal/modules/cjs/loader.js:899:14) at Module.require (internal/modules/cjs/loader.js:1042:19) at require (internal/modules/cjs/helpers.js:77:18) at Object. (C:\Users\User\Documents\digitallending_sql\controllers\applicationController.js:6:20) at Module._compile (internal/modules/cjs/loader.js:1156:30) at Object.Module._extensions..js (internal/modules/cjs/loader.js:1176:10) at Module.load (internal/modules/cjs/loader.js:1000:32) at Function.Module._load (internal/modules/cjs/loader.js:899:14) at Module.require (internal/modules/cjs/loader.js:1042:19) at require (internal/modules/cjs/helpers.js:77:18) at Object. (C:\Users\User\Documents\digitallending_sql\routes\applicationRouter.js:3:29) at Module._compile (internal/modules/cjs/loader.js:1156:30)

im using windows 10, node 12.16.2

Issue Description Getting the following error:

error - ./node_modules/@vladmandic/face-api/dist/face-api.esm.js:8:25031 Module not found: Can't resolve 'fs'

Steps to Reproduce create a nextjs application as given here:

https://nextjs.org/learn/basics/create-nextjs-app/setup

added face api packages (npm install). Including tensorflow Invoked the api to load the models: await faceapi.nets.ssdMobilenetv1.loadFromUri('/models')

And got the error:

Expected Behavior It should have loaded the models.

**Environment Windows 10. Nodejs. React application. Using VS code editor. Browser is chrome/Edge.

• Module version?
• Built-in demo or custom code? - custom
• Type of module used (e.g. js, esm, esm-nobundle)? js
• Browser or NodeJS and version (e.g. NodeJS 14.15 or Chrome 89)? - Node v14.13.1, Chrome Version 89.0.4389.90 (Official Build) (64-bit)
• OS and Hardware platform (e.g. Windows 10, Ubuntu Linux on x64, Android 10)? Windows 10
• Packager (if any) (e.g, webpack, rollup, parcel, esbuild, etc.)? standard webpack

Additional

• For installation or startup issues include your package.json
• For usage issues, it is recommended to post your code as gist

I am using the library in a TypeScript lerna module which is build with tsc and then bundled as part of a create-react-app. I had no issue with the original face-api but wanted the latest fdjs. I am using the npm module with npm install.

If I only do:

import * as faceapi from '@vladmandic/face-api'

I get a compile error:

Failed to compile ../face-detect-plugin/node_modules/@vladmandic/face-api/dist/face-api.js 344:47 Module parse failed: Unexpected token (344:47) File was processed with these loaders:

• ./node_modules/babel-loader/lib/index.js You may need an additional loader to handle the result of these loaders. | } : T || {}; |

    var E = g(f(T.entropy ? [x, w(e)] : x ?? y(), 3), _),

| F = new d(_), | D = function () {

if I add:

import * as tf from '@tensorflow/tfjs'

before importing face-api then I get an error in the console:

Uncaught SyntaxError: Unexpected token '!'

If I look at the code I see this:

class MathBackendCPU extends !(function webpackMissingModule() { var e = new Error("Cannot find module '@tensorflow/tfjs-core'"); e.code = 'MODULE_NOT_FOUND'; throw e; }()) { constructor() { super(); this.blockSize = 48; this.firstUse = true; this.data = new !(function webpackMissingModule() { var e = new Error("Cannot find module '@tensorflow/tfjs-core'"); e.code = 'MODULE_NOT_FOUND'; throw e; }())(this, !(function webpackMissingModule() { var e = new Error("Cannot find module '@tensorflow/tfjs-core'"); e.code = 'MODULE_NOT_FOUND'; throw e; }())()); }

HI do you have plan to implement Head position angle of (Yaw, Roll, Pitch)

pose: {
  pitch_angle: {value: 11.102898}
  roll_angle: {value: -20.291693}
  yaw_angle: {value: 14.172521}
}

like face-api discuss here https://github.com/justadudewhohacks/face-api.js/issues/107

faceapi.tf.setBackend('webgl');
faceapi.tf.enableProdMode();
faceapi.tf.ENV.set('DEBUG', false);
faceapi.tf.ready();

.......
const videoTensor = await faceapi.tf.browser.fromPixels(video);
const detections = await faceapi.detectAllFaces(videoTensor, new faceapi.SsdMobilenetv1Options({ minConfidence: minScore, maxResults }));
const faceImages = await faceapi.extractFaceTensors(videoTensor, detections);

await videoTensor.dispose();
await faceImages[0].dispose();

I follow my GPU memory. I detect a leak memory. Maybe we can use x.dispose(); I tried it, but this problem continue... I checked faceapi.detectAllFaces function. There is not any leak. I think faceapi.extractFaceTensors function. How can I fix it?

trying to migrate to your fork of face-api

Using:

let faceapi   = require('@vladmandic/face-api/dist/face-api.node.js');

I get:

Error [ERR_REQUIRE_ESM]: Must use import to load ES Module: /home/meeki/node-red-contrib-facial-recognition/node_modules/@vladmandic/face-api/dist/face-api.node.js
require() of ES modules is not supported.
require() of /home/meeki/node-red-contrib-facial-recognition/node_modules/@vladmandic/face-api/dist/face-api.node.js from /home/meeki/node-red-contrib-facial-recognition/facial-recognition.js is an ES module file as it is a .js file whose nearest parent package.json contains "type": "module" which defines all .js files in that package scope as ES modules.
Instead rename face-api.node.js to end in .cjs, change the requiring code to use import(), or remove "type": "module" from /home/meeki/node-red-contrib-facial-recognition/node_modules/@vladmandic/face-api/package.json.

interesting

Hi, I used this code that detect all faces, I want to avoid that user will photo himself by cellular and show the cellular photo to camera , how I avoid by code ? For know fake image by cellular also work. I saw this link in history issue and there is no option do install through npm ? https://github.com/vladmandic/anti-spoofing

 const ssdOptions = { minConfidence: 0.1, maxResults: 10 };
      const optionsSSDMobileNet = new faceapi.SsdMobilenetv1Options(ssdOptions);
      const faces = await faceapi
        .detectAllFaces(tensor, optionsSSDMobileNet)
        .withFaceLandmarks()
        .withFaceExpressions()
        .withFaceDescriptors()
        .withAgeAndGender();

Issue Description Vue2 builds a demo, loadFromUri loads tinyFaceDetector, and loads loadFaceLandmarkModel, PC loads resources successfully, but Apple mobile safari fails to load

Expected Behavior Resources can be loaded on both PC and mobile

**Environment window 10 + chrome 98.0.4758.102(PC) + safari(mobile)

• Module version? "@vladmandic/face-api": "^1.6.5" "vue": "^2.5.2"

• Built-in demo or custom code? https://busyshadow.github.io/#/

• Type of module used (e.g. js, esm, esm-nobundle)? js

• Packager (if any) (e.g, webpack, rollup, parcel, esbuild, etc.)? webpack

• For installation or startup issues include your package.json

{
  "name": "faceDemo",
  "version": "1.0.0",
  "description": "A Vue.js project",
  "author": "",
  "private": true,
  "scripts": {
    "dev": "vue-cli-service serve",
    "build": "vue-cli-service build"
  },
  "dependencies": {
    "@vladmandic/face-api": "^1.6.5",
    "uglifyjs-webpack-plugin": "^2.2.0",
    "vconsole": "^3.12.0",
    "vue": "^2.5.2",
    "vue-router": "^3.1.6"
  },
  "devDependencies": {
    "@vue/cli-plugin-babel": "~4.3.1",
    "@vue/cli-plugin-router": "~4.3.1",
    "@vue/cli-service": "~4.3.1",
    "vue-template-compiler": "^2.6.11"
  },
  "engines": {
    "node": ">= 6.0.0",
    "npm": ">= 3.0.0"
  },
  "browserslist": [
    "> 1%",
    "last 2 versions",
    "not ie <= 8"
  ]
}

index.vue

<template>
    <div>
        <div>err1:{{err1}}</div>
        <div>err2:{{err2}}</div>
    </div>
</template>
<script>
    import * as faceapi from '@vladmandic/face-api';
    // import * as faceapi from "face-api.js";
    import vconsole from 'vconsole';
    let _this;
    export default {
        data(){
            return {
                err1:"",
                err2:"",
            }
        },
        created(){
            new vconsole();
        },
        mounted(){
            _this = this;
            this.$nextTick(() => {
                this.fnInit();
            });
        },
        methods:{
            async fnInit(){
                try {
                    await faceapi.nets['tinyFaceDetector'].loadFromUri("https://busyshadow.github.io/models");
                }catch(e){
                    this.err1 = e;
                }
                try {
                    await faceapi.loadFaceLandmarkModel("https://busyshadow.github.io/models");
                } catch(e){
                    this.err2 = e;
                }

                _this.options = new faceapi.TinyFaceDetectorOptions({
                    inputSize: 224, // 160 224 320 416 512 608
                    scoreThreshold: 0.3, // 0.1 ~ 0.9
                });
            }
        }
    }
</script>

success

error

faceapi is working for me on desktop but not on mobile.

I am using wasm, as recommended to me and it worked perfect for a long time, both on desktop and mobil.

import * as faceapi from "@vladmandic/face-api/dist/face-api.esm.js";

async start() { /**el face api solo se necesita para el selfie */ if (this.type == "selfie") { await this.backendWasm(); await this.setupFaceAPI(); } } async setupFaceAPI() { await faceapi.nets.tinyFaceDetector.loadFromUri("/statics/models"); },

async backendWasm() {
  await faceapi.tf.setWasmPaths("../statics/");
  await faceapi.tf.setBackend("wasm");
},

for a couple of days it stopped working on mobile, will it be a question of versions of the libraries?

tensorflow face api ??

if you look at the first image they don't load all the wasm files, that's in mobile.

but in the other two images, if you see if they load all the files, that's on desktop

uso chrome.

"@tensorflow/tfjs": "^3.3.0", "@tensorflow/tfjs-backend-wasm": "^3.3.0", "@vladmandic/face-api": "^1.1.12",