PaddleOCR/docs/infer_deploy/paddle_js.en.md

31 lines
1.5 KiB
Markdown
Raw Normal View History

---
typora-copy-images-to: images
comments: true
hide:
- toc
---
# Paddle.js Introduction
[Paddle.js](https://github.com/PaddlePaddle/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 wechat miniprogram.
## Web Demo
Run OCR demo in browser refer to [tutorial](https://github.com/PaddlePaddle/FastDeploy/blob/cd0ee79c91d4ed1103abdc65ff12ccadd23d0827/examples/application/js/WebDemo.md).
|demo|web demo directory|visualization|
|-|-|-|
|PP-OCRv3|[TextDetection、TextRecognition](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/web_demo/src/pages/cv/ocr/)|![](./images/196874354-1b5eecb0-f273-403c-aa6c-4463bf6d78db.png)|
## Mini Program Demo
2025-03-04 11:04:41 +08:00
The Mini Program demo running tutorial reference
Run OCR demo in wechat miniprogram refer to [tutorial](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/mini_program).
|demo|directory|
|-|-|
|Text Detection| [ocrdetecXcx](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/mini_program/ocrdetectXcx/) |
|Text Recognition| [ocrXcx](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/mini_program/ocrXcx/) |
![](./images/197918203-c7d46f8a-75d4-47f9-9687-405ee0d6727e.gif)