# PaddlePaddle/Paddle.js

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.

Repository: https://github.com/PaddlePaddle/Paddle.js
Canonical: https://ross.abutalabs.com/products/paddlejs
Homepage: https://paddlejs.baidu.com
Language: JavaScript
License: Apache-2.0
License Family: permissive
Topics: webgl, webgpu, webassembly, model, inference-engine, paddlepaddle, ocr, deep-learning
Last push: 2024-04-03T03:25:39+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2351, "days_push": 882, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1103, forks 154 (observed 2026-08-28T04:03:36.030890+00:00)

## What it is
Paddle.js is a browser-based deep learning inference engine for Baidu PaddlePaddle models, running via WebGL, WebGPU, or WebAssembly backends. It can load pre-trained models or convert PaddlePaddle/PaddleHub models, and ships ready-made libraries for OCR, segmentation, face and gesture detection.

## Use cases
- run deep learning model inference in the browser
- convert a paddlepaddle model to run on the web
- do ocr in a web page without a server
- human segmentation in the browser
- face detection in a javascript app
- run ai models in a wechat miniprogram
- webgpu accelerated inference in the browser

## When to choose
- you need client-side inference of PaddlePaddle models with no backend GPU
- you want prebuilt browser AI features like OCR, face detection, or segmentation
- you target browsers, Baidu Smartprogram, or WeChat miniprograms

## When to avoid
- you train models rather than run inference
- you use PyTorch or TensorFlow models without converting to PaddlePaddle format
- you need server-side high-throughput inference
- you need a framework with broad active community support outside the Paddle ecosystem

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-inference, ocr, image-processing, computer-vision
- domain: deep-learning, machine-learning, web-development, frontend, computer-vision
- platform: browser, wasm
- tags: webgl, webgpu, webassembly, inference-engine, paddlepaddle, browser-ai, miniprogram, model-conversion, web-server, nodejs, javascript

## Member repositories
- PaddlePaddle/Paddle.js (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.030890+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:45:31.199988+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/Paddle.js (fetched 2026-08-28T04:03:36.030890+00:00, sha 68a6dfe07c43)
  - homepage: https://paddlejs.baidu.com (fetched 2026-08-29T12:48:12.166598+00:00, sha 519d5d97967a)
- Data as of 2026-08-30T08:39:29.467469+00:00.