Awesome
Paddle.js
<p > <img src="https://travis-ci.org/PaddlePaddle/Paddle.js.svg?branch=master" alt="building"> <img src="https://github.com/paddlepaddle/paddle.js/actions/workflows/ut.yml/badge.svg" alt="UnitTest"> <img src="https://img.shields.io/github/commit-activity/m/paddlepaddle/paddle.js/master?color=important" alt="commit-activity"> <img src="https://img.shields.io/github/license/paddlepaddle/paddle.js" alt="license"> <img src="https://img.shields.io/github/package-json/v/paddlepaddle/paddle.js/master?color=yellow" alt="license"> <img src="https://img.shields.io/github/v/release/paddlepaddle/paddle.js?color=skyblue" alt="license"> <img src="https://img.shields.io/pypi/pyversions/paddlejsconverter" alt="python"> </p>Paddle.js is a web project for Baidu PaddlePaddle, which is an open source deep learning framework running in the browser. Paddle.js can either load a pre-trained model, or transforming a model from paddle-hub with model transforming tools provided by Paddle.js. It could run in every browser with WebGL/WebGPU/WebAssembly supported. It could also run in Baidu Smartprogram and WX miniprogram.
Ecosystem
| Project | version | Description |
|---|---|---|
| paddlejs-core |  | inference engine |
| paddlejs-backend-webgl |  | webgl backend |
| paddlejs-backend-wasm |  | wasm backend |
| paddlejs-backend-webgpu |  | webgpu backend |
| paddlejsconverter |  | convert paddlepaddle model |
| humanseg |  | human segmentation library |
| ocr |  | optical character recognition library |
| gesture |  | gesture recognition library |
| mobilenet |  | image classification library |
| ocr detection |  | optical character detection library |
| facedetect |  | face detection library |
Website
Key Features
Module
- paddlejs-core, the core part of the Paddle.js ecosystem, which is responsible for the operation of the inference process of the entire engine. <img src="https://img.shields.io/bundlephobia/min/@paddlejs/paddlejs-core" alt="size"> <img src="https://img.shields.io/npm/dm/@paddlejs/paddlejs-core?color=orange" alt="downloads"> <img src="https://img.shields.io/npm/dt/@paddlejs/paddlejs-core" alt="downloads">
- paddlejsconverter, model transformation tool for Paddle.js, convert PaddlePaddle models (also known as fluid models) into a browser-friendly format.
- paddlejs-models, model projects, supply flexible low-level APIs for users to implement their AI scenario.
- paddlejs-examples, Paddle.js AI examples
- paddlejs-mediapipe, tools for live and streaming media, support webrtc camera and a lightweight opencv package
Backends
- paddlejs-backend-webgl, webgl backend, the main backend for Paddle.js, ops supported <img src="https://img.shields.io/bundlephobia/min/@paddlejs/paddlejs-backend-webgl" alt="size"> <img src="https://img.shields.io/npm/dm/@paddlejs/paddlejs-backend-webgl?color=orange" alt="downloads"> <img src="https://img.shields.io/npm/dt/@paddlejs/paddlejs-backend-webgl" alt="downloads">
- paddlejs-backend-webgpu, webgpu backend, an experimental backend, WebGPU draft, ops supported
- paddlejs-backend-wasm, WebAssembly backend, ops supported
- paddlejs-backend-cpu, cpu backend, ops supported
- paddlejs-backend-nodegl, nodegl backend, a backend in Node.js for Paddle.js, using the webgl backend ops. ops supported
Examples
- image classification game image classification game example in wx miniprogram
- gesture gesture recognition example online experience
- humanStream video-streaming human segmentation online experience
- humanseg human segmentation example online experience
- ocr optical character recognition example online experience
- ocr detection optical character detection example online experience
- mobilenet classify images into 1000 object categories online experience
- wine classify bottles into 7 categories online experience
- webglworker This demo help us to use Paddle.js in WebWorker.
Browser/Platforms Coverage
- PC: Chrome, Safari, Firefox
- Phone: Baidu App , Chrome , UC and QQ Browser
- Smartprogram: Baidu Smartprogram, WX miniprogram
- Platform: macOS, Windows
Load Model
- Support load model files on the network:
- model.json (model structure and operators' attributes)
- chunk_x.dat (model params binary data)
- Support use model obj
- modelObj.model (model structure json object)
- modelObj.params（model params Float32Array data）
If you dont' want to put model on the network, you can use method 2.
Feedback and Community Support
- Online video tutorial start video
- Questions, reports, and suggestions are welcome through Github Issues!
- Forum: Opinions and questions are welcome at our PaddlePaddle Forum！
- QQ group chat: 696965088