@vladmandic/face-api
Advanced tools
FaceAPI: AI-powered Face Detection, Face Embedding & Recognition Using Tensorflow/JS
Face detection and recognition libary for Browser and NodeJS implemented on top of TensorFlow/JS
Live Demo: https://vladmandic.github.io/face-api/demo/webcam.html
This is updated face-api.js with latest available TensorFlow/JS as the original is not compatible with tfjs 2.0+.
Forked from face-api.js version 0.22.2 which was released on March 22nd, 2020
Currently based on TensorFlow/JS 3.3.0
Why? I needed Face-API that does not cause version conflict with newer versions of TensorFlow
And since original Face-API was open-source, I've released this version as well
Changes ended up being too large for a simple pull request
and it ended up being a full-fledged version on its own
Plus many features were added since original inception
Browser example that uses static images and showcases both models
as well as all of the extensions is included in /demo/index.html
Example can be accessed directly using Git pages using URL:
https://vladmandic.github.io/face-api/demo/index.html
Browser example that uses live webcam is included in /demo/webcam.html
Example can be accessed directly using Git pages using URL:
https://vladmandic.github.io/face-api/demo/webcam.html
Demo using FaceAPI to process images
Note: Photos shown below are taken by me
Demo using FaceAPI to process live webcam
Two NodeJS examples are:
/demo/node-singleprocess.js:FaceAPI from NodeJS/demo/node-multiprocess.js:node-multiprocess-worker.js)FaceAPI2021-03-14 08:42:03 INFO: @vladmandic/face-api version 1.0.2
2021-03-14 08:42:03 INFO: User: vlado Platform: linux Arch: x64 Node: v15.7.0
2021-03-14 08:42:03 INFO: FaceAPI multi-process test
2021-03-14 08:42:03 STATE: Main: started worker: 1888019
2021-03-14 08:42:03 STATE: Main: started worker: 1888025
2021-03-14 08:42:04 STATE: Worker: PID: 1888025 TensorFlow/JS 3.3.0 FaceAPI 1.0.2 Backend: tensorflow
2021-03-14 08:42:04 STATE: Worker: PID: 1888019 TensorFlow/JS 3.3.0 FaceAPI 1.0.2 Backend: tensorflow
2021-03-14 08:42:04 STATE: Main: dispatching to worker: 1888019
2021-03-14 08:42:04 STATE: Main: dispatching to worker: 1888025
2021-03-14 08:42:04 DATA: Worker received message: 1888019 { image: 'demo/sample1.jpg' }
2021-03-14 08:42:04 DATA: Worker received message: 1888025 { image: 'demo/sample2.jpg' }
2021-03-14 08:42:06 DATA: Main: worker finished: 1888025 detected faces: 3
2021-03-14 08:42:06 STATE: Main: dispatching to worker: 1888025
2021-03-14 08:42:06 DATA: Worker received message: 1888025 { image: 'demo/sample3.jpg' }
2021-03-14 08:42:06 DATA: Main: worker finished: 1888019 detected faces: 3
2021-03-14 08:42:06 STATE: Main: dispatching to worker: 1888019
2021-03-14 08:42:06 DATA: Worker received message: 1888019 { image: 'demo/sample4.jpg' }
2021-03-14 08:42:07 DATA: Main: worker finished: 1888025 detected faces: 3
2021-03-14 08:42:07 STATE: Main: dispatching to worker: 1888025
2021-03-14 08:42:07 DATA: Worker received message: 1888025 { image: 'demo/sample5.jpg' }
2021-03-14 08:42:08 DATA: Main: worker finished: 1888019 detected faces: 4
2021-03-14 08:42:08 STATE: Main: dispatching to worker: 1888019
2021-03-14 08:42:08 DATA: Worker received message: 1888019 { image: 'demo/sample6.jpg' }
2021-03-14 08:42:09 DATA: Main: worker finished: 1888025 detected faces: 5
2021-03-14 08:42:09 STATE: Main: worker exit: 1888025 0
2021-03-14 08:42:09 DATA: Main: worker finished: 1888019 detected faces: 4
2021-03-14 08:42:09 INFO: Processed 15 images in 5944 ms
2021-03-14 08:42:09 STATE: Main: worker exit: 1888019 0
Note that @tensorflow/tfjs-node or @tensorflow/tfjs-node-gpu
must be installed before using NodeJS example
Face-API ships with several pre-build versions of the library:
dist/face-api.js: IIFE format for client-side Browser executiondist/face-api.esm.js: ESM format for client-side Browser executiondist/face-api.esm-nobundle.js: ESM format for client-side Browser executiondist/face-api.node.js: CommonJS format for server-side NodeJS executiondist/face-api.node-gpu.js: CommonJS format for server-side NodeJS executiondist/face-api.node-cpu.js: CommonJS format for server-side NodeJS executionDefaults are:
{
"main": "dist/face-api.node-js",
"module": "dist/face-api.esm.js",
"browser": "dist/face-api.esm.js",
}
Bundled TFJS can be used directly via export: faceapi.tf
Reason for additional nobundle version is if you want to
include a specific version of TFJS and not rely on pre-packaged one
FaceAPI is compatible with TFJS 2.0+
All versions include sourcemap
There are several ways to use Face-API:
Recommened for quick tests and backward compatibility with older Browsers that do not support ESM such as IE
This is simplest way for usage within Browser
Simply download dist/face-api.js, include it in your HTML file & it's ready to use
<script src="dist/face-api.js"><script>
IIFE script bundles TFJS and auto-registers global namespace faceapi within Window object which can be accessed directly from a <script> tag or from your JS file.
Recommended for usage within Browser
To use ESM import directly in a Browser, you must import your script (e.g. index.js) with a type="module"
<script src="./index.js" type="module">
and then in your index.js
import * as faceapi from 'dist/face-api.esm.js';
Same as above, but expectation is that you've installed @vladmandic/faceapi package:
npm install @vladmandic/face-api
and that you'll package your application using a bundler such as webpack, rollup or esbuild
in which case, you do not need to import a script as module - that depends on your bundler configuration
import * as faceapi from '@vladmandic/face-api';
or if your bundler doesn't recognize recommended type, force usage with:
import * as faceapi from '@vladmandic/face-api/dist/face-api.esm.js';
or to use non-bundled version
import * as tf from `@tensorflow/tfjs`;
import * as faceapi from '@vladmandic/face-api/dist/face-api.esm-nobundle.js';
Recommended for NodeJS projects
Node: Face-API for NodeJS does not bundle TFJS due to binary dependencies that are installed during TFJS installation
Install with:
npm install @tensorflow/tfjs-node
npm install @vladmandic/face-api
And then use with:
const tf = require('@tensorflow/tfjs-node')
const faceapi = require('@vladmandic/face-api');
If you want to force CommonJS module instead of relying on recommended field:
const faceapi = require('@vladmandic/face-api/dist/face-api.node.js');
If you want to GPU Accelerated execution in NodeJS, you must have CUDA libraries already installed and working
Then install appropriate version of Face-API:
npm install @tensorflow/tfjs-node
npm install @vladmandic/face-api
And then use with:
const tf = require('@tensorflow/tfjs-node-gpu')
const faceapi = require('@vladmandic/face-api/dist/face-api.node-gpu.js'); // this loads face-api version with correct bindings for tfjs-node-gpu
If you want to use Face-API in a NodeJS on platforms where NodeJS binary libraries are not supported, you can use JavaScript CPU backend.
npm install @tensorflow/tfjs
npm install @vladmandic/face-api
And then use with:
const tf = require('@tensorflow/tfjs')
const faceapi = require('@vladmandic/face-api/dist/face-api.node-cpu.js');
If you want to use graphical functions inside NodeJS,
you must provide appropriate graphical library as
NodeJS does not include implementation for DOM elements
such as HTMLImageElement or HTMLCanvasElement:
Install Canvas for NodeJS:
npm install canvas
Patch NodeJS environment to use newly installed Canvas library:
const canvas = require('canvas');
const faceapi = require('@vladmandic/face-api');
const { Canvas, Image, ImageData } = canvas
faceapi.env.monkeyPatch({ Canvas, Image, ImageData })
Pretrained models and their weights are includes in ./model.
Built-in test&dev web server can be started using
npm run dev
By default it starts HTTP server on port 8000 and HTTPS server on port 8001 and can be accessed as:
2021-03-14 08:41:09 INFO: @vladmandic/face-api version 1.0.2
2021-03-14 08:41:09 INFO: User: vlado Platform: linux Arch: x64 Node: v15.7.0
2021-03-14 08:41:09 INFO: Build: file startup all target: es2018
2021-03-14 08:41:09 STATE: HTTP server listening: 8000
2021-03-14 08:41:09 STATE: HTTP2 server listening: 8001
2021-03-14 08:41:09 STATE: Monitoring: [ 'package.json', 'demo', 'src', [length]: 3 ]
2021-03-14 08:41:10 STATE: Build for: browserBundle type: tfjs: { modules: 1258, moduleBytes: 4040087, imports: 7, importBytes: 276, outputBytes: 1072314, outputFiles: 'dist/tfjs.esm.js' }
2021-03-14 08:41:10 STATE: Build for: browserBundle type: iife: { imports: 160, importBytes: 1305679, outputBytes: 1151683, outputFiles: 'dist/face-api.js' }
2021-03-14 08:41:10 STATE: Build for: browserBundle type: esm: { imports: 160, importBytes: 1305679, outputBytes: 1151520, outputFiles: 'dist/face-api.esm.js' }
If you want to do a full rebuild, either download npm module
npm install @vladmandic/face-api
cd node_modules/@vladmandic/face-api
or clone a git project
git clone https://github.com/vladmandic/face-api
cd face-api
Then install all dependencies and run rebuild:
npm install
npm run build
Build process uses script build.js that creates optimized build for each target:
> @vladmandic/face-api@1.0.2 build
> rimraf dist/* types/* typedoc/* && node server/build.js
2021-03-14 08:39:21 INFO: @vladmandic/face-api version 1.0.2
2021-03-14 08:39:21 INFO: User: vlado Platform: linux Arch: x64 Node: v15.7.0
2021-03-14 08:39:21 INFO: Build: file startup all target: es2018
2021-03-14 08:39:21 STATE: Build for: node type: tfjs: { imports: 1, importBytes: 143, outputBytes: 731, outputFiles: 'dist/tfjs.esm.js' }
2021-03-14 08:39:21 STATE: Build for: node type: node: { imports: 160, importBytes: 234096, outputBytes: 85371, outputFiles: 'dist/face-api.node.js' }
2021-03-14 08:39:21 STATE: Build for: nodeGPU type: tfjs: { imports: 1, importBytes: 147, outputBytes: 735, outputFiles: 'dist/tfjs.esm.js' }
2021-03-14 08:39:21 STATE: Build for: nodeGPU type: node: { imports: 160, importBytes: 234100, outputBytes: 85379, outputFiles: 'dist/face-api.node-gpu.js' }
2021-03-14 08:39:21 STATE: Build for: nodeCPU type: tfjs: { imports: 1, importBytes: 138, outputBytes: 726, outputFiles: 'dist/tfjs.esm.js' }
2021-03-14 08:39:21 STATE: Build for: nodeCPU type: node: { imports: 160, importBytes: 234091, outputBytes: 85370, outputFiles: 'dist/face-api.node-cpu.js' }
2021-03-14 08:39:21 STATE: Build for: browserNoBundle type: tfjs: { imports: 1, importBytes: 276, outputBytes: 244, outputFiles: 'dist/tfjs.esm.js' }
2021-03-14 08:39:21 STATE: Build for: browserNoBundle type: esm: { imports: 160, importBytes: 233609, outputBytes: 82634, outputFiles: 'dist/face-api.esm-nobundle.js' }
2021-03-14 08:39:22 STATE: Build for: browserBundle type: tfjs: { modules: 1258, moduleBytes: 4040087, imports: 7, importBytes: 276, outputBytes: 1072314, outputFiles: 'dist/tfjs.esm.js' }
2021-03-14 08:39:22 STATE: Build for: browserBundle type: iife: { imports: 160, importBytes: 1305679, outputBytes: 1151683, outputFiles: 'dist/face-api.js' }
2021-03-14 08:39:22 STATE: Build for: browserBundle type: esm: { imports: 160, importBytes: 1305679, outputBytes: 1151520, outputFiles: 'dist/face-api.esm.js' }
2021-03-14 08:39:22 INFO: Compile typings: [ 'src/index.ts', [length]: 1 ]
2021-03-14 08:39:27 INFO: Update Change log: [ '/home/vlado/dev/face-api/CHANGELOG.md', [length]: 1 ]
2021-03-14 08:39:27 INFO: Generate TypeDocs: [ 'src/index.ts', [length]: 1 ]
FaceAPI landmark model returns 68-point face mesh as detailed in the image below:
Compared to face-api.js version 0.22.2:
TensorFlow/JS 2.0+ & 3.0+WebGL, CPU and WASM TFJS Browser backendstfjs-node and tfjs-node-gpu TFJS NodeJS backendsTypeScript 4.2UMD to ESM + CommonJS with fallback to IIFE
Resulting code is optimized per-platform instead of being universal
Fully tree shakable when imported as an ESM module
Browser bundle process uses ESBuild instead of RollupES2018 and instead of dual ES5/ES6
Resulting code is clean ES2018 JavaScript without polyfillskarma, jasmine, babel, etc.)@tensorflow/tfjs-corebatchNorm() dependencyversion class that returns JSON object with version of FaceAPI as well as linked TFJSmtcnn and tinyYolov2 models as they were non-functional in latest public version of Face-API
Which means valid models are tinyFaceDetector and mobileNetv1
If there is a demand, I can re-implement them back.face angle calculations that returns roll, yaw and pitchtypdoc automatic API specification generation during buildchangelog automatic generation during build
1.1.2 2021/03/15 mandic00@live.com
FAQs
FaceAPI: AI-powered Face Detection & Rotation Tracking, Face Description & Recognition, Age & Gender & Emotion Prediction for Browser and NodeJS using TensorFlow/JS
The npm package @vladmandic/face-api receives a total of 11,866 weekly downloads. As such, @vladmandic/face-api popularity was classified as popular.
We found that @vladmandic/face-api demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 0 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
PyPI confirms no security flaws were exploited in the Ultralytics supply chain attack and highlights improvements for safer package publishing.
Security News
Research
The Socket Research Team breaks down a malicious wrapper package that uses obfuscation to harvest credentials and exfiltrate sensitive data.
Research
Security News
Attackers used a malicious npm package typosquatting a popular ESLint plugin to steal sensitive data, execute commands, and exploit developer systems.
