From f6ce5b279157fe6c1a6d849ca8845045038a5b82 Mon Sep 17 00:00:00 2001 From: SWHL Date: Mon, 15 Jul 2024 09:30:54 +0800 Subject: [PATCH] docs: Update README --- README.md | 55 ++++++++++++++++++++++------------------------- docs/README_zh.md | 45 ++++++++++++++------------------------ 2 files changed, 42 insertions(+), 58 deletions(-) diff --git a/README.md b/README.md index cefb5f022..c89fc6edb 100755 --- a/README.md +++ b/README.md @@ -29,49 +29,47 @@ [简体中文](./docs/README_zh.md) | English - ### Introduction -- The fastest running, most widely supported, completely open source and free multi-platform, multi-language OCR known to support rapid offline deployment. -- **Supported Languages**: The default is Chinese and English, other language recognition requires self-service conversion. For specific reference [here](https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/). -- **Cause**: [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) is not well engineered, and to make it easier for people to do OCR inference on various ends, we converted the model in PaddleOCR to ONNX format and ported it to various platforms using `Python/C++/Java/C#`. -- **Name Source**: Light, fast, economical and smart. OCR technology based on deep learning technology focuses on artificial intelligence advantages and small models, with speed as the mission and effect as the leading role. -- **Usage**: - - If the existing model in the repo meets the requirements → RapidOCR deployment can be used. - - Not meeting requirements → Based on PaddleOCR. Fine-tune your own data → RapidOCR deployment. --If this repo is helpful to you, please click on a small star ⭐ Bah! +💖 The fastest running, most widely supported, completely open source and free multi-platform, multi-language OCR known to support rapid offline deployment. It features ONNXRuntime inference engine inference, which is 4~5 times faster than PaddlePaddle inference engine and has no memory leak problem. + +**Supported Languages**: The default is Chinese and English, other language recognition requires self-service conversion. For specific reference [here](https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/). + +**Cause**: [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) is not well engineered, and to make it easier for people to do OCR inference on various ends, we converted the model in PaddleOCR to ONNX format and ported it to various platforms using `Python/C++/Java/C#`. + +**Name Source**: Light, fast, economical and smart. OCR technology based on deep learning technology focuses on artificial intelligence advantages and small models, with speed as the mission and effect as the leading role. + +**Usage**: + +- If the existing model in the repo meets the requirements → RapidOCR deployment can be used. +- Not meeting requirements → Based on PaddleOCR. Fine-tune your own data → RapidOCR deployment. -### [Demo](https://huggingface.co/spaces/SWHL/RapidOCRDemo) +If this repo is helpful to you, please click on a small star ⭐ Bah! + +### Visualization
- Demo + Demo
### Installation + ```bash pip install rapidocr_onnxruntime ``` ### Usage + ```bash rapidocr_onnxruntime -img 1.jpg ``` -### Related projects overview -> In the table below, except for the **Evaluation Collection** part which is hosted under the [Hugging Face](https://huggingface.co/SWHL) Community, the rest are all under Github. The details are as follows: -> -> The first line is the function introduction. -> -> The second line is the corresponding warehouse name. You can directly search for the name on Github. - -
- -
- ### Documentation + Full documentation can be found on [docs](https://rapidai.github.io/RapidOCRDocs/), in Chinese. ### Acknowledgements + - Many thanks to [DeliciaLaniD](https://github.com/DeliciaLaniD) for fixing the misplaced start position of scan animation in ocrweb. - Many thanks to [zhsunlight](https://github.com/zhsunlight) for the suggestion about parameterized call GPU reasoning and the careful and thoughtful testing. - Many thanks to [lzh111222334](https://github.com/lzh111222334) for fixing some bugs of rec preprocessing under python version. @@ -80,16 +78,14 @@ Full documentation can be found on [docs](https://rapidai.github.io/RapidOCRDocs - Many thanks to [Loovelj](https://github.com/Loovelj) for fixing the bug of sorting the text boxes. For details see [issue 75](https://github.com/RapidAI/RapidOCR/issues/75). ### Code Contributors +

-### Contributing -- Pull requests are welcome. For major changes, please open an issue first -to discuss what you would like to change. -- Please make sure to update tests as appropriate. +s ### [Sponsor](https://rapidai.github.io/RapidOCRDocs/sponsor/) @@ -98,7 +94,7 @@ to discuss what you would like to change. > If you want to sponsor the project, you can directly click the **Buy me a coffee** image, please write a note (e.g. your github account name) to facilitate adding to the sponsorship list below. > >
-> +> >
| Sponsor | Applied Products | @@ -106,9 +102,10 @@ to discuss what you would like to change. | | | | | - | - ### Citation + If you find this project useful in your research, please consider cite: + ```bibtex @misc{RapidOCR 2021, title={{Rapid OCR}: OCR Toolbox}, @@ -122,8 +119,8 @@ If you find this project useful in your research, please consider cite: [![Stargazers over time](https://starchart.cc/RapidAI/RapidOCR.svg)](https://starchart.cc/RapidAI/RapidOCR) - ### License + The copyright of the OCR model is held by Baidu, while the copyrights of all other engineering scripts are retained by the repository's owner. This project is released under the [Apache 2.0 license](./LICENSE). diff --git a/docs/README_zh.md b/docs/README_zh.md index 9e9d4c170..e8dc59316 100644 --- a/docs/README_zh.md +++ b/docs/README_zh.md @@ -32,19 +32,25 @@ ### 简介 -- 💖目前已知**运行速度最快、支持最广**，完全开源免费并支持离线快速部署的多平台多语言OCR。 -- **支持语言**：默认是中英文，其他语言识别需要自助转换。具体参考[这里](https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/) -- **缘起**：因为[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)工程化尚有提升空间，为了方便在各种端上进行OCR推理，我们将PaddleOCR中的模型转换为ONNX格式，使用`Python/C++/Java/C#` 将它移植到各个平台，方便大家使用。 -- **名称来源**：轻快好省并智能。基于深度学习的OCR技术，主打人工智能优势及小模型，以速度为使命，效果为导向。 -- **使用**： - - 如果仓库下已有模型满足要求 → RapidOCR部署使用即可。 - - 不满足要求 → 基于PaddleOCR在自己数据上微调 → RapidOCR部署。 -- 如果该仓库有帮助到你，还请点个小星星⭐呗！ +💖目前已知**运行速度最快、支持最广**，完全开源免费并支持离线快速部署的多平台多语言OCR。主打ONNXRuntime推理引擎推理，比PaddlePaddle推理引擎速度有4~5倍提升，且没有内存泄露问题。 -### [Demo](https://www.modelscope.cn/studios/liekkas/RapidOCRDemo/summary) +**支持语言**：默认是中英文，其他语言识别需要自助转换。具体参考[这里](https://rapidai.github.io/RapidOCRDocs/blog/2022/09/28/%E6%94%AF%E6%8C%81%E8%AF%86%E5%88%AB%E8%AF%AD%E8%A8%80/) + +**缘起**：因为[PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)工程化尚有提升空间，为了方便在各种端上进行OCR推理，我们将PaddleOCR中的模型转换为ONNX格式，使用`Python/C++/Java/C#` 将它移植到各个平台，方便大家使用。 + +**名称来源**：轻快好省并智能。基于深度学习的OCR技术，主打人工智能优势及小模型，以速度为使命，效果为导向。 + +**使用**： + +- 如果仓库下已有模型满足要求 → RapidOCR部署使用即可。 +- 不满足要求 → 基于PaddleOCR在自己数据上微调 → RapidOCR部署。 + +如果该仓库有帮助到你，还请点个小星星⭐呗！ + +### 效果展示
- Demo + Demo
### 安装 @@ -59,18 +65,6 @@ pip install rapidocr_onnxruntime rapidocr_onnxruntime -img 1.jpg ``` -### 相关产品概览图 -> -> 下图表格中，除**测评集**部分托管在[Hugging Face](https://huggingface.co/SWHL)下，其余均在Github下，详细介绍如下： -> -> 第一行是功能介绍 -> -> 第二行是对应的仓库名称，可直接去Github搜索该名称即可。 - -
- -
- ### 文档 完整文档请移步：[docs](https://rapidai.github.io/RapidOCRDocs) @@ -92,13 +86,6 @@ rapidocr_onnxruntime -img 1.jpg

-### 贡献指南 - -我们感谢所有的贡献者为改进和提升 RapidOCR 所作出的努力。 - -- 欢迎提交请求。对于重大更改，请先打开issue讨论您想要改变的内容。 -- 请确保适当更新测试。 - ### 加入我们 - 微信扫描以下二维码，关注**RapidAI公众号**，回复**OCR**即可加入RapidOCR微信交流群：