Merge pull request #2 from PaddlePaddle/develop

mergepaddleocr

.clang_format.hook

+#!/bin/bash
+set -e
+
+readonly VERSION="3.8"
+
+version=$(clang-format -version)
+
+if ! [[ $version == *"$VERSION"* ]]; then
+    echo "clang-format version check failed."
+    echo "a version contains '$VERSION' is needed, but get '$version'"
+    echo "you can install the right version, and make an soft-link to '\$PATH' env"
+    exit -1
+fi
+
+clang-format $@

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+.ipynb_checkpoints/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+inference/
+inference_results/
+output/
+
+*.DS_Store
+*.vs
+*.user
+*~
+*.vscode
+*.idea
+
+*.log
+.clang-format
+.clang_format.hook

README.md

-# PaddleOCR
-OCR algorithms with PaddlePaddle （still under develop)
+English | [简体中文](README_cn.md)
+
+## Introduction
+PaddleOCR aims to create rich, leading, and practical OCR tools that help users train better models and apply them into practice.
+
+**Recent updates**
+- 2020.7.23, Release the playback and PPT of live class on BiliBili station, PaddleOCR Introduction, [address](https://aistudio.baidu.com/aistudio/course/introduce/1519)
+- 2020.7.15, Add mobile App demo , support both iOS and  Android  ( based on easyedge and Paddle Lite)
+- 2020.7.15, Improve the  deployment ability, add the C + +  inference , serving deployment. In addtion, the benchmarks of the ultra-lightweight OCR model are provided.
+- 2020.7.15, Add several related datasets, data annotation and synthesis tools.
+- 2020.7.9 Add a new model to support recognize the  character "space".
+- 2020.7.9 Add the data augument and learning rate decay strategies during training.
+- [more](./doc/doc_en/update_en.md)
+
+## Features
+- Ultra-lightweight OCR model, total model size is only 8.6M
+    - Single model supports Chinese/English numbers combination recognition, vertical text recognition, long text recognition
+    - Detection model DB (4.1M) + recognition model CRNN (4.5M)
+- Various text detection algorithms: EAST, DB
+- Various text recognition algorithms: Rosetta, CRNN, STAR-Net, RARE
+- Support Linux, Windows, MacOS and other systems.
+
+## Visualization
+
+![](doc/imgs_results/11.jpg)
+
+![](doc/imgs_results/img_10.jpg)
+
+[More visualization](./doc/doc_en/visualization_en.md)
+
+You can also quickly experience the ultra-lightweight OCR : [Online Experience](https://www.paddlepaddle.org.cn/hub/scene/ocr)
+
+Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Android systems): [Sign in the website to obtain the QR code for  installing the App](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)
+
+ Also, you can scan the QR code blow to install the App (**Android support only**)
+
+<div align="center">
+<img src="./doc/ocr-android-easyedge.png"  width = "200" height = "200" />
+</div>
+
+- [**OCR Quick Start**](./doc/doc_en/quickstart_en.md)
+
+<a name="Supported-Chinese-model-list"></a>
+
+### Supported Models:
+
+|Model Name|Description |Detection Model link|Recognition Model link| Support for space Recognition Model link|
+|-|-|-|-|-|
+|db_crnn_mobile|ultra-lightweight OCR model|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db.tar)|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn.tar)|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_enhance_infer.tar) / [pre-train model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_enhance.tar)
+|db_crnn_server|General OCR model|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db.tar)|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn.tar)|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance_infer.tar) / [pre-train model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance.tar)
+
+
+## Tutorials
+- [Installation](./doc/doc_en/installation_en.md)
+- [Quick Start](./doc/doc_en/quickstart_en.md)
+- Algorithm introduction
+    - [Text Detection Algorithm](#TEXTDETECTIONALGORITHM)
+    - [Text Recognition Algorithm](#TEXTRECOGNITIONALGORITHM)
+    - [END-TO-END OCR Algorithm](#ENDENDOCRALGORITHM)
+- Model training/evaluation
+    - [Text Detection](./doc/doc_en/detection_en.md)
+    - [Text Recognition](./doc/doc_en/recognition_en.md)
+    - [Yml Configuration](./doc/doc_en/config_en.md)
+    - [Tricks](./doc/doc_en/tricks_en.md)
+- Deployment
+    - [Python Inference](./doc/doc_en/inference_en.md)
+    - [C++ Inference](./deploy/cpp_infer/readme_en.md)
+    - [Serving](./doc/doc_en/serving_en.md)
+    - [Mobile](./deploy/lite/readme_en.md)
+    - Model Quantization and Compression (coming soon)
+    - [Benchmark](./doc/doc_en/benchmark_en.md)
+- Datasets
+    - [General OCR Datasets(Chinese/English)](./doc/doc_en/datasets_en.md)
+    - [HandWritten_OCR_Datasets(Chinese)](./doc/doc_en/handwritten_datasets_en.md)
+    - [Various OCR Datasets(multilingual)](./doc/doc_en/vertical_and_multilingual_datasets_en.md)
+    - [Data Annotation Tools](./doc/doc_en/data_annotation_en.md)
+    - [Data Synthesis Tools](./doc/doc_en/data_synthesis_en.md)
+- [FAQ](#FAQ)
+- Visualization
+    - [Ultra-lightweight Chinese/English OCR Visualization](#UCOCRVIS)
+    - [General Chinese/English OCR Visualization](#GeOCRVIS)
+    - [Chinese/English OCR Visualization (Support Space Recognization )](#SpaceOCRVIS)
+- [Community](#Community)
+- [References](./doc/doc_en/reference_en.md)
+- [License](#LICENSE)
+- [Contribution](#CONTRIBUTION)
+
+<a name="TEXTDETECTIONALGORITHM"></a>
+## Text Detection Algorithm
+
+PaddleOCR open source text detection algorithms list:
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
+- [x]  DB([paper](https://arxiv.org/abs/1911.08947))
+- [ ]  SAST([paper](https://arxiv.org/abs/1908.05498))(Baidu Self-Research, comming soon)
+
+On the ICDAR2015 dataset, the text detection result is as follows:
+
+|Model|Backbone|precision|recall|Hmean|Download link|
+|-|-|-|-|-|-|
+|EAST|ResNet50_vd|88.18%|85.51%|86.82%|[Download link](https://paddleocr.bj.bcebos.com/det_r50_vd_east.tar)|
+|EAST|MobileNetV3|81.67%|79.83%|80.74%|[Download link](https://paddleocr.bj.bcebos.com/det_mv3_east.tar)|
+|DB|ResNet50_vd|83.79%|80.65%|82.19%|[Download link](https://paddleocr.bj.bcebos.com/det_r50_vd_db.tar)|
+|DB|MobileNetV3|75.92%|73.18%|74.53%|[Download link](https://paddleocr.bj.bcebos.com/det_mv3_db.tar)|
+
+For use of [LSVT](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/datasets_en.md#1-icdar2019-lsvt) street view dataset with a total of 3w training data，the related configuration and pre-trained models for text detection task are as follows:
+|Model|Backbone|Configuration file|Pre-trained model|
+|-|-|-|-|
+|ultra-lightweight OCR model|MobileNetV3|det_mv3_db.yml|[Download link](https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db.tar)|
+|General OCR model|ResNet50_vd|det_r50_vd_db.yml|[Download link](https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db.tar)|
+
+* Note: For the training and evaluation of the above DB model, post-processing parameters box_thresh=0.6 and unclip_ratio=1.5 need to be set. If using different datasets and different models for training, these two parameters can be adjusted for better result.
+
+For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./doc/doc_en/detection_en.md)
+
+<a name="TEXTRECOGNITIONALGORITHM"></a>
+## Text Recognition Algorithm
+
+PaddleOCR open-source text recognition algorithms list:
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
+- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
+- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))
+- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294))(Baidu Self-Research, comming soon)
+
+Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
+
+|Model|Backbone|Avg Accuracy|Module combination|Download link|
+|-|-|-|-|-|
+|Rosetta|Resnet34_vd|80.24%|rec_r34_vd_none_none_ctc|[Download link](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_none_ctc.tar)|
+|Rosetta|MobileNetV3|78.16%|rec_mv3_none_none_ctc|[Download link](https://paddleocr.bj.bcebos.com/rec_mv3_none_none_ctc.tar)|
+|CRNN|Resnet34_vd|82.20%|rec_r34_vd_none_bilstm_ctc|[Download link](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_bilstm_ctc.tar)|
+|CRNN|MobileNetV3|79.37%|rec_mv3_none_bilstm_ctc|[Download link](https://paddleocr.bj.bcebos.com/rec_mv3_none_bilstm_ctc.tar)|
+|STAR-Net|Resnet34_vd|83.93%|rec_r34_vd_tps_bilstm_ctc|[Download link](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_ctc.tar)|
+|STAR-Net|MobileNetV3|81.56%|rec_mv3_tps_bilstm_ctc|[Download link](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_ctc.tar)|
+|RARE|Resnet34_vd|84.90%|rec_r34_vd_tps_bilstm_attn|[Download link](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_attn.tar)|
+|RARE|MobileNetV3|83.32%|rec_mv3_tps_bilstm_attn|[Download link](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_attn.tar)|
+
+We use [LSVT](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/datasets_en.md#1-icdar2019-lsvt) dataset and cropout 30w  traning data from original photos by using position groundtruth and make some calibration needed. In addition, based on the LSVT corpus, 500w synthetic data is generated to train the model. The related configuration and pre-trained models are as follows:
+|Model|Backbone|Configuration file|Pre-trained model|
+|-|-|-|-|
+|ultra-lightweight OCR model|MobileNetV3|rec_chinese_lite_train.yml|[Download link](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn.tar)|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_enhance_infer.tar) & [pre-trained model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_enhance.tar)|
+|General OCR model|Resnet34_vd|rec_chinese_common_train.yml|[Download link](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn.tar)|[inference model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance_infer.tar) & [pre-trained model](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance.tar)|
+
+Please refer to the document for training guide and use of PaddleOCR text recognition algorithms [Text recognition model training/evaluation/prediction](./doc/doc_en/recognition_en.md)
+
+<a name="ENDENDOCRALGORITHM"></a>
+## END-TO-END OCR Algorithm
+- [ ]  [End2End-PSL](https://arxiv.org/abs/1909.07808)(Baidu Self-Research, comming soon)
+
+## Visualization
+
+<a name="UCOCRVIS"></a>
+### 1.Ultra-lightweight Chinese/English OCR Visualization [more](./doc/doc_en/visualization_en.md)
+
+<div align="center">
+    <img src="doc/imgs_results/1.jpg" width="800">
+</div>
+
+<a name="GeOCRVIS"></a>
+### 2. General Chinese/English OCR Visualization [more](./doc/doc_en/visualization_en.md)
+
+<div align="center">
+    <img src="doc/imgs_results/chinese_db_crnn_server/11.jpg" width="800">
+</div>
+
+<a name="SpaceOCRVIS"></a>
+### 3.Chinese/English OCR Visualization (Space_support) [more](./doc/doc_en/visualization_en.md)
+
+<div align="center">
+    <img src="doc/imgs_results/chinese_db_crnn_server/en_paper.jpg" width="800">
+</div>
+
+<a name="FAQ"></a>
+
+## FAQ
+1. Error when using attention-based recognition model: KeyError: 'predict'
+
+    The inference of recognition model based on attention loss is still being debugged. For Chinese text recognition, it is recommended to choose the recognition model based on CTC loss first. In practice, it is also found that the recognition model based on attention loss is not as effective as the one based on CTC loss.
+
+2. About inference speed
+
+    When there are a lot of texts in the picture, the prediction time will increase. You can use `--rec_batch_num` to set a smaller prediction batch size. The default value is 30, which can be changed to 10 or other values.
+
+3. Service deployment and mobile deployment
+
+    It is expected that the service deployment based on Serving and the mobile deployment based on Paddle Lite will be released successively in mid-to-late June. Stay tuned for more updates.
+
+4. Release time of self-developed algorithm
+
+    Baidu Self-developed algorithms such as SAST, SRN and end2end PSL will be released in June or July. Please be patient.
+
+[more](./doc/doc_en/FAQ_en.md)
+
+<a name="Community"></a>
+## Community
+Scan  the QR code below with your wechat and completing the questionnaire, you can access to offical technical exchange group.
+
+<div align="center">
+<img src="./doc/joinus.jpg"  width = "200" height = "200" />
+</div>
+
+<a name="LICENSE"></a>
+## License
+This project is released under <a href="https://github.com/PaddlePaddle/PaddleOCR/blob/master/LICENSE">Apache 2.0 license</a>
+
+<a name="CONTRIBUTION"></a>
+## Contribution
+We welcome all the contributions to PaddleOCR and appreciate for your feedback very much.
+
+- Many thanks to [Khanh Tran](https://github.com/xxxpsyduck) for contributing the English documentation.
+- Many thanks to [zhangxin](https://github.com/ZhangXinNan) for contributing the new visualize function、add .gitgnore and discard set PYTHONPATH manually.
+- Many thanks to [lyl120117](https://github.com/lyl120117) for contributing the code for printing the network structure.
+- Thanks [xiangyubo](https://github.com/xiangyubo) for contributing the handwritten Chinese OCR datasets.
+- Thanks [authorfu](https://github.com/authorfu) for contributing Android demo  and [xiadeye](https://github.com/xiadeye) contributing iOS demo, respectively.
+- Thanks [BeyondYourself](https://github.com/BeyondYourself) for contributing many great suggestions and simplifying part of the code style.

README_cn.md

+[English](README.md) | 简体中文
+
+## 简介
+PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力使用者训练出更好的模型，并应用落地。
+
+**近期更新**
+- 2020.7.23 发布7月21日B站直播课回放和PPT，PaddleOCR开源大礼包全面解读，[获取地址](https://aistudio.baidu.com/aistudio/course/introduce/1519)
+- 2020.7.15 添加基于EasyEdge和Paddle-Lite的移动端DEMO，支持iOS和Android系统
+- 2020.7.15 完善预测部署，添加基于C++预测引擎推理、服务化部署和端侧部署方案，以及超轻量级中文OCR模型预测耗时Benchmark
+- 2020.7.15 整理OCR相关数据集、常用数据标注以及合成工具
+- 2020.7.9 添加支持空格的识别模型，识别效果，预测及训练方式请参考快速开始和文本识别训练相关文档
+- 2020.7.9 添加数据增强、学习率衰减策略,具体参考[配置文件](./doc/doc_ch/config.md)
+- [more](./doc/doc_ch/update.md)
+
+
+## 特性
+- 超轻量级中文OCR模型，总模型仅8.6M
+    - 单模型支持中英文数字组合识别、竖排文本识别、长文本识别
+    - 检测模型DB（4.1M）+识别模型CRNN（4.5M）
+- 实用通用中文OCR模型
+- 多种预测推理部署方案，包括服务部署和端侧部署
+- 多种文本检测训练算法，EAST、DB
+- 多种文本识别训练算法，Rosetta、CRNN、STAR-Net、RARE
+- 可运行于Linux、Windows、MacOS等多种系统
+
+## 快速体验
+
+<div align="center">
+    <img src="doc/imgs_results/11.jpg" width="800">
+</div>
+
+上图是超轻量级中文OCR模型效果展示，更多效果图请见[效果展示页面](./doc/doc_ch/visualization.md)。
+
+- 超轻量级中文OCR在线体验地址：https://www.paddlepaddle.org.cn/hub/scene/ocr
+- 移动端DEMO体验(基于EasyEdge和Paddle-Lite, 支持iOS和Android系统)：[安装包二维码获取地址](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)
+
+   Android手机也可以扫描下面二维码安装体验。
+
+<div align="center">
+<img src="./doc/ocr-android-easyedge.png"  width = "200" height = "200" />
+</div>
+
+- [**中文OCR模型快速使用**](./doc/doc_ch/quickstart.md)
+
+
+## 中文OCR模型列表
+
+|模型名称|模型简介|检测模型地址|识别模型地址|支持空格的识别模型地址|
+|-|-|-|-|-|
+|chinese_db_crnn_mobile|超轻量级中文OCR模型|[inference模型](https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db.tar)|[inference模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn.tar)|[inference模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_enhance_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn_enhance.tar)
+|chinese_db_crnn_server|通用中文OCR模型|[inference模型](https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db.tar)|[inference模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn.tar)|[inference模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_enhance.tar)
+
+## 文档教程
+- [快速安装](./doc/doc_ch/installation.md)
+- [中文OCR模型快速使用](./doc/doc_ch/quickstart.md)
+- 算法介绍
+    - [文本检测](#文本检测算法)
+    - [文本识别](#文本识别算法)
+    - [端到端OCR](#端到端OCR算法)
+- 模型训练/评估
+    - [文本检测](./doc/doc_ch/detection.md)
+    - [文本识别](./doc/doc_ch/recognition.md)
+    - [yml参数配置文件介绍](./doc/doc_ch/config.md)
+    - [中文OCR训练预测技巧](./doc/doc_ch/tricks.md)
+- 预测部署
+    - [基于Python预测引擎推理](./doc/doc_ch/inference.md)
+    - [基于C++预测引擎推理](./deploy/cpp_infer/readme.md)
+    - [服务化部署](./doc/doc_ch/serving.md)
+    - [端侧部署](./deploy/lite/readme.md)
+    - 模型量化压缩（coming soon）
+    - [Benchmark](./doc/doc_ch/benchmark.md)
+- 数据集
+    - [通用中英文OCR数据集](./doc/doc_ch/datasets.md)
+    - [手写中文OCR数据集](./doc/doc_ch/handwritten_datasets.md)
+    - [垂类多语言OCR数据集](./doc/doc_ch/vertical_and_multilingual_datasets.md)
+    - [常用数据标注工具](./doc/doc_ch/data_annotation.md)
+    - [常用数据合成工具](./doc/doc_ch/data_synthesis.md)
+- [FAQ](#FAQ)
+- 效果展示
+    - [超轻量级中文OCR效果展示](#超轻量级中文OCR效果展示)
+    - [通用中文OCR效果展示](#通用中文OCR效果展示)
+    - [支持空格的中文OCR效果展示](#支持空格的中文OCR效果展示)
+- [技术交流群](#欢迎加入PaddleOCR技术交流群)
+- [参考文献](./doc/doc_ch/reference.md)
+- [许可证书](#许可证书)
+- [贡献代码](#贡献代码)
+
+<a name="算法介绍"></a>
+## 算法介绍
+<a name="文本检测算法"></a>
+### 1.文本检测算法
+
+PaddleOCR开源的文本检测算法列表：
+- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
+- [x]  DB([paper](https://arxiv.org/abs/1911.08947))
+- [ ]  SAST([paper](https://arxiv.org/abs/1908.05498))(百度自研, coming soon)
+
+在ICDAR2015文本检测公开数据集上，算法效果如下：
+
+|模型|骨干网络|precision|recall|Hmean|下载链接|
+|-|-|-|-|-|-|
+|EAST|ResNet50_vd|88.18%|85.51%|86.82%|[下载链接](https://paddleocr.bj.bcebos.com/det_r50_vd_east.tar)|
+|EAST|MobileNetV3|81.67%|79.83%|80.74%|[下载链接](https://paddleocr.bj.bcebos.com/det_mv3_east.tar)|
+|DB|ResNet50_vd|83.79%|80.65%|82.19%|[下载链接](https://paddleocr.bj.bcebos.com/det_r50_vd_db.tar)|
+|DB|MobileNetV3|75.92%|73.18%|74.53%|[下载链接](https://paddleocr.bj.bcebos.com/det_mv3_db.tar)|
+
+使用[LSVT](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/datasets.md#1icdar2019-lsvt)街景数据集共3w张数据，训练中文检测模型的相关配置和预训练文件如下：
+|模型|骨干网络|配置文件|预训练模型|
+|-|-|-|-|
+|超轻量中文模型|MobileNetV3|det_mv3_db.yml|[下载链接](https://paddleocr.bj.bcebos.com/ch_models/ch_det_mv3_db.tar)|
+|通用中文OCR模型|ResNet50_vd|det_r50_vd_db.yml|[下载链接](https://paddleocr.bj.bcebos.com/ch_models/ch_det_r50_vd_db.tar)|
+
+* 注： 上述DB模型的训练和评估，需设置后处理参数box_thresh=0.6，unclip_ratio=1.5，使用不同数据集、不同模型训练，可调整这两个参数进行优化
+
+PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训练/评估中的文本检测部分](./doc/doc_ch/detection.md)。
+
+<a name="文本识别算法"></a>
+### 2.文本识别算法
+
+PaddleOCR开源的文本识别算法列表：
+- [x]  CRNN([paper](https://arxiv.org/abs/1507.05717))
+- [x]  Rosetta([paper](https://arxiv.org/abs/1910.05085))
+- [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
+- [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))
+- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294))(百度自研, coming soon)
+
+参考[DTRB](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
+
+|模型|骨干网络|Avg Accuracy|模型存储命名|下载链接|
+|-|-|-|-|-|
+|Rosetta|Resnet34_vd|80.24%|rec_r34_vd_none_none_ctc|[下载链接](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_none_ctc.tar)|
+|Rosetta|MobileNetV3|78.16%|rec_mv3_none_none_ctc|[下载链接](https://paddleocr.bj.bcebos.com/rec_mv3_none_none_ctc.tar)|
+|CRNN|Resnet34_vd|82.20%|rec_r34_vd_none_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/rec_r34_vd_none_bilstm_ctc.tar)|
+|CRNN|MobileNetV3|79.37%|rec_mv3_none_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/rec_mv3_none_bilstm_ctc.tar)|
+|STAR-Net|Resnet34_vd|83.93%|rec_r34_vd_tps_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_ctc.tar)|
+|STAR-Net|MobileNetV3|81.56%|rec_mv3_tps_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_ctc.tar)|
+|RARE|Resnet34_vd|84.90%|rec_r34_vd_tps_bilstm_attn|[下载链接](https://paddleocr.bj.bcebos.com/rec_r34_vd_tps_bilstm_attn.tar)|
+|RARE|MobileNetV3|83.32%|rec_mv3_tps_bilstm_attn|[下载链接](https://paddleocr.bj.bcebos.com/rec_mv3_tps_bilstm_attn.tar)|
+
+使用[LSVT](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/datasets.md#1icdar2019-lsvt)街景数据集根据真值将图crop出来30w数据，进行位置校准。此外基于LSVT语料生成500w合成数据训练中文模型，相关配置和预训练文件如下：  
+
+|模型|骨干网络|配置文件|预训练模型|
+|-|-|-|-|
+|超轻量中文模型|MobileNetV3|rec_chinese_lite_train.yml|[下载链接](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_mv3_crnn.tar)|
+|通用中文OCR模型|Resnet34_vd|rec_chinese_common_train.yml|[下载链接](https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn.tar)|
+
+PaddleOCR文本识别算法的训练和使用请参考文档教程中[模型训练/评估中的文本识别部分](./doc/doc_ch/recognition.md)。
+
+<a name="端到端OCR算法"></a>
+### 3.端到端OCR算法
+- [ ]  [End2End-PSL](https://arxiv.org/abs/1909.07808)(百度自研, coming soon)
+
+## 效果展示
+
+<a name="超轻量级中文OCR效果展示"></a>
+### 1.超轻量级中文OCR效果展示  [more](./doc/doc_ch/visualization.md)
+
+<div align="center">
+    <img src="doc/imgs_results/1.jpg" width="800">
+</div>
+
+<a name="通用中文OCR效果展示"></a>
+### 2.通用中文OCR效果展示  [more](./doc/doc_ch/visualization.md)
+
+<div align="center">
+    <img src="doc/imgs_results/chinese_db_crnn_server/11.jpg" width="800">
+</div>
+
+<a name="支持空格的中文OCR效果展示"></a>
+### 3.支持空格的中文OCR效果展示  [more](./doc/doc_ch/visualization.md)
+
+<div align="center">
+    <img src="doc/imgs_results/chinese_db_crnn_server/en_paper.jpg" width="800">
+</div>
+
+<a name="FAQ"></a>
+## FAQ
+1. **转换attention识别模型时报错：KeyError: 'predict'**  
+问题已解，请更新到最新代码。  
+
+2. **关于推理速度**  
+图片中的文字较多时，预测时间会增，可以使用--rec_batch_num设置更小预测batch num，默认值为30，可以改为10或其他数值。  
+
+3. **服务部署与移动端部署**  
+预计6月中下旬会先后发布基于Serving的服务部署方案和基于Paddle Lite的移动端部署方案，欢迎持续关注。  
+
+4. **自研算法发布时间**  
+自研算法SAST、SRN、End2End-PSL都将在7-8月陆续发布，敬请期待。  
+
+[more](./doc/doc_ch/FAQ.md)
+
+<a name="欢迎加入PaddleOCR技术交流群"></a>
+## 欢迎加入PaddleOCR技术交流群
+请扫描下面二维码，完成问卷填写，获取加群二维码和OCR方向的炼丹秘籍
+
+<div align="center">
+<img src="./doc/joinus.jpg"  width = "200" height = "200" />
+</div>
+
+<a name="许可证书"></a>
+## 许可证书
+本项目的发布受<a href="https://github.com/PaddlePaddle/PaddleOCR/blob/master/LICENSE">Apache 2.0 license</a>许可认证。
+
+<a name="贡献代码"></a>
+## 贡献代码
+我们非常欢迎你为PaddleOCR贡献代码，也十分感谢你的反馈。
+
+- 非常感谢 [Khanh Tran](https://github.com/xxxpsyduck) 贡献了英文文档
+- 非常感谢 [zhangxin](https://github.com/ZhangXinNan)([Blog](https://blog.csdn.net/sdlypyzq)) 贡献新的可视化方式、添加.gitgnore、处理手动设置PYTHONPATH环境变量的问题
+- 非常感谢 [lyl120117](https://github.com/lyl120117) 贡献打印网络结构的代码
+- 非常感谢 [xiangyubo](https://github.com/xiangyubo) 贡献手写中文OCR数据集
+- 非常感谢 [authorfu](https://github.com/authorfu) 贡献Android和[xiadeye](https://github.com/xiadeye) 贡献IOS的demo代码
+- 非常感谢 [BeyondYourself](https://github.com/BeyondYourself) 给PaddleOCR提了很多非常棒的建议，并简化了PaddleOCR的部分代码风格。

configs/det/det_db_icdar15_reader.yml

@@ -15,7 +15,7 @@ EvalReader:
 TestReader:
   reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
   process_function: ppocr.data.det.db_process,DBProcessTest
-  single_img_path: 
+  infer_img:
   img_set_dir: ./train_data/icdar2015/text_localization/
   label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
   test_image_shape: [736, 1280]

configs/det/det_east_icdar15_reader.yml

@@ -17,7 +17,7 @@ EvalReader:
 TestReader:
   reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
   process_function: ppocr.data.det.east_process,EASTProcessTest
-  single_img_path: 
+  infer_img:
   img_set_dir: ./train_data/icdar2015/text_localization/
   label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
   do_eval: True

configs/det/det_db_mv3.yml → configs/det/det_mv3_db.yml

@@ -4,15 +4,18 @@ Global:
   epoch_num: 1200
   log_smooth_window: 20
   print_batch_step: 2
-  save_model_dir: output
+  save_model_dir: ./output/det_db/
   save_epoch_step: 200
-  eval_batch_step: 5000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
   train_batch_size_per_card: 16
   test_batch_size_per_card: 16
   image_shape: [3, 640, 640]
   reader_yml: ./configs/det/det_db_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/MobileNetV3_pretrained/MobileNetV3_large_x0_5_pretrained/
-  save_res_path: ./output/predicts_db.txt
+  pretrain_weights: ./pretrain_models/MobileNetV3_large_x0_5_pretrained/
+  checkpoints:
+  save_res_path: ./output/det_db/predicts_db.txt
+  save_inference_dir:
   
 Architecture:
   function: ppocr.modeling.architectures.det_model,DetModel
@@ -48,4 +51,4 @@ PostProcess:
   thresh: 0.3
   box_thresh: 0.7
   max_candidates: 1000
-  unclip_ratio: 1.5
\ No newline at end of file
+  unclip_ratio: 2.0

configs/det/det_east_mv3.yml → configs/det/det_mv3_east.yml

@@ -4,15 +4,17 @@ Global:
   epoch_num: 100000
   log_smooth_window: 20
   print_batch_step: 5
-  save_model_dir: output
+  save_model_dir: ./output/det_east/
   save_epoch_step: 200
-  eval_batch_step: 5000
+  eval_batch_step: [5000, 5000]
   train_batch_size_per_card: 16
   test_batch_size_per_card: 16
   image_shape: [3, 512, 512]
   reader_yml: ./configs/det/det_east_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/MobileNetV3_pretrained/MobileNetV3_large_x0_5_pretrained/
-  save_res_path: ./output/predicts_east.txt
+  pretrain_weights: ./pretrain_models/MobileNetV3_large_x0_5_pretrained/
+  checkpoints:
+  save_res_path: ./output/det_east/predicts_east.txt
+  save_inference_dir:
   
 Architecture:
   function: ppocr.modeling.architectures.det_model,DetModel

configs/det/det_db_r50_vd.yml → configs/det/det_r50_vd_db.yml

@@ -4,15 +4,17 @@ Global:
   epoch_num: 1200
   log_smooth_window: 20
   print_batch_step: 2
-  save_model_dir: output
+  save_model_dir: ./output/det_db/
   save_epoch_step: 200
-  eval_batch_step: 5000
+  eval_batch_step: [5000, 5000]
   train_batch_size_per_card: 8
   test_batch_size_per_card: 16
   image_shape: [3, 640, 640]
   reader_yml: ./configs/det/det_db_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/ResNet50_vd_pretrained/
-  save_res_path: ./output/predicts_db.txt
+  pretrain_weights: ./pretrain_models/ResNet50_vd_ssld_pretrained/
+  save_res_path: ./output/det_db/predicts_db.txt
+  checkpoints:
+  save_inference_dir:
 
 Architecture:
   function: ppocr.modeling.architectures.det_model,DetModel

configs/det/det_east_r50_vd.yml → configs/det/det_r50_vd_east.yml

@@ -4,15 +4,17 @@ Global:
   epoch_num: 100000
   log_smooth_window: 20
   print_batch_step: 5
-  save_model_dir: output
+  save_model_dir: ./output/det_east/
   save_epoch_step: 200
-  eval_batch_step: 5000
+  eval_batch_step: [5000, 5000]
   train_batch_size_per_card: 8
   test_batch_size_per_card: 16
   image_shape: [3, 512, 512]
   reader_yml: ./configs/det/det_east_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/ResNet50_vd_pretrained/
-  save_res_path: ./output/predicts_east.txt
+  pretrain_weights: ./pretrain_models/ResNet50_vd_ssld_pretrained/
+  save_res_path: ./output/det_east/predicts_east.txt
+  checkpoints:
+  save_inference_dir:
 
 Architecture:
   function: ppocr.modeling.architectures.det_model,DetModel

configs/rec/rec_chinese_common_train.yml

+Global:
+  algorithm: CRNN
+  use_gpu: true
+  epoch_num: 3000
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_CRNN
+  save_epoch_step: 3
+  eval_batch_step: 2000
+  train_batch_size_per_card: 128
+  test_batch_size_per_card: 128
+  image_shape: [3, 32, 320]
+  max_text_length: 25
+  character_type: ch
+  character_dict_path: ./ppocr/utils/ppocr_keys_v1.txt
+  loss_type: ctc
+  distort: false
+  use_space_char: false
+  reader_yml: ./configs/rec/rec_chinese_reader.yml
+  pretrain_weights:
+  checkpoints:
+  save_inference_dir:
+  infer_img:
+
+Architecture:
+  function: ppocr.modeling.architectures.rec_model,RecModel
+
+Backbone:
+  function: ppocr.modeling.backbones.rec_resnet_vd,ResNet
+  layers: 34
+
+Head:
+  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
+  encoder_type: rnn
+  SeqRNN:
+    hidden_size: 256
+    
+Loss:
+  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
+
+Optimizer:
+  function: ppocr.optimizer,AdamDecay
+  base_lr: 0.0005
+  beta1: 0.9
+  beta2: 0.999

configs/rec/rec_chinese_lite_train.yml

 Global:
   algorithm: CRNN
-  dataset: common
   use_gpu: true
-  epoch_num: 300
+  epoch_num: 3000
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: output
+  save_model_dir: ./output/rec_CRNN
   save_epoch_step: 3
   eval_batch_step: 2000
   train_batch_size_per_card: 256
   test_batch_size_per_card: 256
-  image_shape: [3, 32, 100]
+  image_shape: [3, 32, 320]
   max_text_length: 25
   character_type: ch
   character_dict_path: ./ppocr/utils/ppocr_keys_v1.txt
   loss_type: ctc
+  distort: false
+  use_space_char: false
   reader_yml: ./configs/rec/rec_chinese_reader.yml
   pretrain_weights:
+  checkpoints:
+  save_inference_dir:
+  infer_img:
 
 Architecture:
   function: ppocr.modeling.architectures.rec_model,RecModel
@@ -37,6 +41,6 @@ Loss:
 
 Optimizer:
   function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
+  base_lr: 0.0005
   beta1: 0.9
   beta2: 0.999

configs/rec/rec_chinese_reader.yml

 TrainReader:
   reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
   num_workers: 8
-  img_set_dir: .
-  label_file_path: ./train_data/hard_label.txt
+  img_set_dir: ./train_data
+  label_file_path: ./train_data/rec_gt_train.txt
   
 EvalReader:
   reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
-  img_set_dir: .
-  label_file_path: ./train_data/label_val_all.txt
+  img_set_dir: ./train_data
+  label_file_path: ./train_data/rec_gt_test.txt
 
 TestReader:
   reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
-  infer_img: ./infer_img

configs/rec/rec_icdar15_reader.yml

+TrainReader:
+  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
+  num_workers: 8
+  img_set_dir: ./train_data/ic15_data
+  label_file_path: ./train_data/ic15_data/rec_gt_train.txt
+  
+EvalReader:
+  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
+  img_set_dir: ./train_data/ic15_data
+  label_file_path: ./train_data/ic15_data/rec_gt_test.txt
+
+TestReader:
+  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader

configs/rec/rec_icdar15_train.yml

+Global:
+  algorithm: CRNN
+  use_gpu: true
+  epoch_num: 1000
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_CRNN
+  save_epoch_step: 300
+  eval_batch_step: 500
+  train_batch_size_per_card: 256
+  test_batch_size_per_card: 256
+  image_shape: [3, 32, 100]
+  max_text_length: 25
+  character_type: en
+  loss_type: ctc
+  distort: true
+  debug: false
+  reader_yml: ./configs/rec/rec_icdar15_reader.yml
+  pretrain_weights: ./pretrain_models/rec_mv3_none_bilstm_ctc/best_accuracy
+  checkpoints:
+  save_inference_dir:
+  infer_img:
+
+Architecture:
+  function: ppocr.modeling.architectures.rec_model,RecModel
+
+Backbone:
+  function: ppocr.modeling.backbones.rec_mobilenet_v3,MobileNetV3
+  scale: 0.5
+  model_name: large
+
+Head:
+  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
+  encoder_type: rnn
+  SeqRNN:
+    hidden_size: 96
+    
+Loss:
+  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
+
+Optimizer:
+  function: ppocr.optimizer,AdamDecay
+  base_lr: 0.0005
+  beta1: 0.9
+  beta2: 0.999
+  decay:
+    function: cosine_decay
+    step_each_epoch: 20
+    total_epoch: 1000

configs/rec/rec_mv3_none_bilstm_ctc.yml

@@ -4,7 +4,7 @@ Global:
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: output
+  save_model_dir: output/rec_CRNN
   save_epoch_step: 3
   eval_batch_step: 2000
   train_batch_size_per_card: 256
@@ -15,6 +15,9 @@ Global:
   loss_type: ctc
   reader_yml: ./configs/rec/rec_benchmark_reader.yml
   pretrain_weights:
+  checkpoints:
+  save_inference_dir:
+  infer_img:
   
 Architecture:
   function: ppocr.modeling.architectures.rec_model,RecModel

configs/rec/rec_mv3_none_none_ctc.yml

@@ -4,7 +4,7 @@ Global:
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: output
+  save_model_dir: output/rec_Rosetta
   save_epoch_step: 3
   eval_batch_step: 2000
   train_batch_size_per_card: 256
@@ -15,6 +15,9 @@ Global:
   loss_type: ctc
   reader_yml: ./configs/rec/rec_benchmark_reader.yml
   pretrain_weights: 
+  checkpoints:
+  save_inference_dir:
+  infer_img:
 
 Architecture:
   function: ppocr.modeling.architectures.rec_model,RecModel

configs/rec/rec_mv3_tps_bilstm_attn.yml

@@ -4,7 +4,7 @@ Global:
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: output
+  save_model_dir: output/rec_RARE
   save_epoch_step: 3
   eval_batch_step: 2000
   train_batch_size_per_card: 256
@@ -13,8 +13,13 @@ Global:
   max_text_length: 25
   character_type: en
   loss_type: attention
+  tps: true
   reader_yml: ./configs/rec/rec_benchmark_reader.yml
   pretrain_weights:
+  checkpoints:
+  save_inference_dir:
+  infer_img:
+
 
 Architecture:
   function: ppocr.modeling.architectures.rec_model,RecModel

configs/rec/rec_mv3_tps_bilstm_ctc.yml

@@ -4,7 +4,7 @@ Global:
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: output
+  save_model_dir: output/rec_STARNet
   save_epoch_step: 3
   eval_batch_step: 2000
   train_batch_size_per_card: 256
@@ -13,8 +13,13 @@ Global:
   max_text_length: 25
   character_type: en
   loss_type: ctc
+  tps: true
   reader_yml: ./configs/rec/rec_benchmark_reader.yml
   pretrain_weights:
+  checkpoints:
+  save_inference_dir:
+  infer_img:
+
   
 Architecture:
   function: ppocr.modeling.architectures.rec_model,RecModel