README_ch.md 14.8 KB
Newer Older
WenmuZhou's avatar
WenmuZhou committed
1
2
[English](README.md) | 简体中文

Leif's avatar
Leif committed
3
4
5
6
7
8
9
10
11
12
13
14
15
<p align="center">
 <img src="./doc/PaddleOCR_log.png" align="middle" width = "600"/>
<p align="center">
<p align="left">
    <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache%202-dfd.svg"></a>
    <a href="https://github.com/PaddlePaddle/PaddleOCR/releases"><img src="https://img.shields.io/github/v/release/PaddlePaddle/PaddleOCR?color=ffa"></a>
    <a href=""><img src="https://img.shields.io/badge/python-3.7+-aff.svg"></a>
    <a href=""><img src="https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg"></a>
    <a href=""><img src="https://img.shields.io/pypi/format/PaddleOCR?color=c77"></a>
    <a href="https://pypi.org/project/PaddleOCR/"><img src="https://img.shields.io/pypi/dm/PaddleOCR?color=9cf"></a>
    <a href="https://github.com/PaddlePaddle/PaddleOCR/stargazers"><img src="https://img.shields.io/github/stars/PaddlePaddle/PaddleOCR?color=ccf"></a>
</p>

WenmuZhou's avatar
WenmuZhou committed
16
## 简介
Leif's avatar
Leif committed
17

Leif's avatar
Leif committed
18
PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库,助力开发者训练出更好的模型,并应用落地。
WenmuZhou's avatar
WenmuZhou committed
19

MissPenguin's avatar
update  
MissPenguin committed
20
<div align="center">
MissPenguin's avatar
update  
MissPenguin committed
21
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
MissPenguin's avatar
update  
MissPenguin committed
22
23
24
</div>

<div align="center">
littletomatodonkey's avatar
fix doc  
littletomatodonkey committed
25
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/00006737.jpg" width="800">
MissPenguin's avatar
update  
MissPenguin committed
26
</div>
MissPenguin's avatar
update  
MissPenguin committed
27

Leif's avatar
Leif committed
28
## 近期更新
WenmuZhou's avatar
WenmuZhou committed
29

MissPenguin's avatar
MissPenguin committed
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
- **🔥2022.5.11~13 每晚8:30【超强OCR技术详解与产业应用实战】三日直播课**
  - 11日:开源最强OCR系统PP-OCRv3揭秘
  - 12日:云边端全覆盖的PP-OCRv3训练部署实战
  - 13日:OCR产业应用全流程拆解与实战
  
   赶紧扫码报名吧!
<div align="center">
<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "150" height = "150" />
</div>

- **🔥2022.5.9 发布PaddleOCR [release/2.5](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.5)**
    - 发布[PP-OCRv3](./doc/doc_ch/ppocr_introduction.md#pp-ocrv3),速度可比情况下,中文场景效果相比于PP-OCRv2再提升5%,英文场景提升11%,80语种多语言模型平均识别准确率提升5%以上;
    - 发布半自动标注工具[PPOCRLabelv2](./PPOCRLabel):新增表格文字图像、图像关键信息抽取任务和不规则文字图像的标注功能;
    - 发布OCR产业落地工具集:打通22种训练部署软硬件环境与方式,覆盖企业90%的训练部署环境需求;
    - 发布交互式OCR开源电子书[《动手学OCR》](./doc/doc_ch/ocr_book.md),覆盖OCR全栈技术的前沿理论与代码实践,并配套教学视频。
- 2021.12.21 发布PaddleOCR [release/2.4](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.4)
    - OCR算法新增1种文本检测算法(PSENet),3种文本识别算法(NRTR、SEED、SAR);
    - 文档结构化算法新增1种关键信息提取算法(SDMGR,[文档](./ppstructure/docs/kie.md)),3种DocVQA算法(LayoutLM、LayoutLMv2,LayoutXLM,[文档](./ppstructure/vqa))。
- 2021.9.7 发布PaddleOCR [release/2.3](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.3)
    - 发布[PP-OCRv2](./doc/doc_ch/ppocr_introduction.md#pp-ocrv2),CPU推理速度相比于PP-OCR server提升220%;效果相比于PP-OCR mobile 提升7%。
- 2021.8.3 发布PaddleOCR [release/2.2](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.2)
    - 发布文档结构分析[PP-Structure](./ppstructure/README_ch.md)工具包,支持版面分析与表格识别(含Excel导出)。
Leif's avatar
Leif committed
52

MissPenguin's avatar
MissPenguin committed
53
> [更多](./doc/doc_ch/update.md)
tink2123's avatar
tink2123 committed
54

WenmuZhou's avatar
WenmuZhou committed
55
56
## 特性

MissPenguin's avatar
update  
MissPenguin committed
57
支持多种OCR相关前沿算法,在此基础上打造产业级特色模型[PP-OCR](./doc/doc_ch/ppocr_introduction.md)[PP-Structure](./ppstructure/README_ch.md),并打通数据生产、模型训练、压缩、预测部署全流程。
MissPenguin's avatar
MissPenguin committed
58

MissPenguin's avatar
MissPenguin committed
59
![](./doc/features.png)
WenmuZhou's avatar
WenmuZhou committed
60

Leif's avatar
Leif committed
61
> 上述内容的使用方法建议从文档教程中的快速开始体验
dyning's avatar
dyning committed
62

MissPenguin's avatar
MissPenguin committed
63

MissPenguin's avatar
MissPenguin committed
64
## 快速开始
MissPenguin's avatar
MissPenguin committed
65
66

- 在线网站体验:超轻量PP-OCR mobile模型体验地址:https://www.paddlepaddle.org.cn/hub/scene/ocr
MissPenguin's avatar
MissPenguin committed
67
- 移动端demo体验:[安装包DEMO下载地址](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)(基于EasyEdge和Paddle-Lite, 支持iOS和Android系统)
MissPenguin's avatar
update  
MissPenguin committed
68
- 一行命令快速使用:[快速开始(中英文/多语言/文档分析)](./doc/doc_ch/quickstart.md)
MissPenguin's avatar
MissPenguin committed
69

MissPenguin's avatar
MissPenguin committed
70
<a name="电子书"></a>
MissPenguin's avatar
MissPenguin committed
71
72
73
74
## 《动手学OCR》电子书
- [《动手学OCR》电子书📚](./doc/doc_ch/ocr_book.md)


MissPenguin's avatar
MissPenguin committed
75
76
<a name="开源社区"></a>
## 开源社区
WenmuZhou's avatar
WenmuZhou committed
77

MissPenguin's avatar
MissPenguin committed
78
- **加入社区👬:** 微信扫描二维码并填写问卷之后,加入交流群领取福利
Leif's avatar
Leif committed
79
80
81
  - **获取5月11-13日每晚20:30《OCR超强技术详解与产业应用实战》的直播课链接**
  - **10G重磅OCR学习大礼包:**《动手学OCR》电子书,配套讲解视频和notebook项目;66篇OCR相关顶会前沿论文打包放送,包括CVPR、AAAI、IJCAI、ICCV等;PaddleOCR历次发版直播课视频;OCR社区优秀开发者项目分享视频。

MissPenguin's avatar
MissPenguin committed
82
83
- **社区贡献**🏅️:[社区贡献](./doc/doc_ch/thirdparty.md)文档中包含了社区用户**使用PaddleOCR开发的各种工具、应用**以及**为PaddleOCR贡献的功能、优化的文档与代码**等,是官方为社区开发者打造的荣誉墙,也是帮助优质项目宣传的广播站。
- **社区常规赛**🎁:社区常规赛是面向OCR开发者的积分赛事,覆盖文档、代码、模型和应用四大类型,以季度为单位评选并发放奖励,赛题详情与报名方法可参考[链接](https://github.com/PaddlePaddle/PaddleOCR/issues/4982)
WenmuZhou's avatar
WenmuZhou committed
84
85

<div align="center">
Leif's avatar
Leif committed
86
<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "200" height = "200" />
WenmuZhou's avatar
WenmuZhou committed
87
</div>
MissPenguin's avatar
MissPenguin committed
88

grasswolfs's avatar
grasswolfs committed
89

Leif's avatar
Leif committed
90
91
92
93
94
<a name="模型下载"></a>
## PP-OCR系列模型列表(更新中)

| 模型简介                              | 模型名称                | 推荐场景        | 检测模型                                                     | 方向分类器                                                   | 识别模型                                                     |
| ------------------------------------- | ----------------------- | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
littletomatodonkey's avatar
littletomatodonkey committed
95
96
| 中英文超轻量PP-OCRv3模型(16.2M)     | ch_PP-OCRv3_xx          | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
| 英文超轻量PP-OCRv3模型(13.4M)     | en_PP-OCRv3_xx          | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
Leif's avatar
Leif committed
97
98
99
100
| 中英文超轻量PP-OCRv2模型(13.0M)     | ch_PP-OCRv2_xx          | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) |
| 中英文超轻量PP-OCR mobile模型(9.4M) | ch_ppocr_mobile_v2.0_xx | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
| 中英文通用PP-OCR server模型(143.4M) | ch_ppocr_server_v2.0_xx | 服务器端        | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |

MissPenguin's avatar
update  
MissPenguin committed
101
更多模型下载(包括多语言),可以参考[PP-OCR 系列模型下载](./doc/doc_ch/models_list.md),文档分析相关模型参考[PP-Structure 系列模型下载](./ppstructure/docs/models_list.md)
WenmuZhou's avatar
WenmuZhou committed
102

MissPenguin's avatar
MissPenguin committed
103

WenmuZhou's avatar
WenmuZhou committed
104
## 文档教程
Leif's avatar
Leif committed
105

Leif's avatar
Leif committed
106
- [运行环境准备](./doc/doc_ch/environment.md)
MissPenguin's avatar
MissPenguin committed
107
- [PP-OCR文本检测识别🔥](./doc/doc_ch/ppocr_introduction.md)
MissPenguin's avatar
update  
MissPenguin committed
108
    - [快速开始](./doc/doc_ch/quickstart.md)
MissPenguin's avatar
MissPenguin committed
109
110
    - [模型库](./doc/doc_ch/models_list.md)
    - [模型训练](./doc/doc_ch/training.md)
Leif's avatar
Leif committed
111
112
        - [文本检测](./doc/doc_ch/detection.md)
        - [文本识别](./doc/doc_ch/recognition.md)
113
        - [文本方向分类器](./doc/doc_ch/angle_class.md)
MissPenguin's avatar
MissPenguin committed
114
    - 模型压缩
Leif's avatar
Leif committed
115
116
        - [模型量化](./deploy/slim/quantization/README.md)
        - [模型裁剪](./deploy/slim/prune/README.md)
MissPenguin's avatar
MissPenguin committed
117
        - [知识蒸馏](./doc/doc_ch/knowledge_distillation.md)
MissPenguin's avatar
update  
MissPenguin committed
118
    - [推理部署](./deploy/README_ch.md)
MissPenguin's avatar
MissPenguin committed
119
        - [基于Python预测引擎推理](./doc/doc_ch/inference_ppocr.md)
Leif's avatar
Leif committed
120
121
122
        - [基于C++预测引擎推理](./deploy/cpp_infer/readme.md)
        - [服务化部署](./deploy/pdserving/README_CN.md)
        - [端侧部署](./deploy/lite/readme.md)
Leif's avatar
Leif committed
123
        - [Paddle2ONNX模型转化与预测](./deploy/paddle2onnx/readme.md)
Leif's avatar
Leif committed
124
        - [Benchmark](./doc/doc_ch/benchmark.md)
MissPenguin's avatar
MissPenguin committed
125
- [PP-Structure文档分析🔥](./ppstructure/README_ch.md)
MissPenguin's avatar
update  
MissPenguin committed
126
127
    - [快速开始](./ppstructure/docs/quickstart.md)
    - [模型库](./ppstructure/docs/models_list.md)
MissPenguin's avatar
MissPenguin committed
128
129
130
    - [模型训练](./doc/doc_ch/training.md)
        - [版面分析](./ppstructure/layout/README_ch.md)
        - [表格识别](./ppstructure/table/README_ch.md)
MissPenguin's avatar
update  
MissPenguin committed
131
        - [关键信息提取](./ppstructure/docs/kie.md)
MissPenguin's avatar
update  
MissPenguin committed
132
        - [DocVQA](./ppstructure/vqa/README_ch.md)
MissPenguin's avatar
update  
MissPenguin committed
133
    - [推理部署](./deploy/README_ch.md)
MissPenguin's avatar
update  
MissPenguin committed
134
135
        - [基于Python预测引擎推理](./ppstructure/docs/inference.md)
        - [基于C++预测引擎推理]()
MissPenguin's avatar
MissPenguin committed
136
        - [服务化部署](./deploy/pdserving/README_CN.md)
MissPenguin's avatar
MissPenguin committed
137
- [前沿算法与模型🚀](./doc/doc_ch/algorithm.md)
MissPenguin's avatar
MissPenguin committed
138
139
140
    - [文本检测算法](./doc/doc_ch/algorithm_overview.md#11-%E6%96%87%E6%9C%AC%E6%A3%80%E6%B5%8B%E7%AE%97%E6%B3%95)
    - [文本识别算法](./doc/doc_ch/algorithm_overview.md#12-%E6%96%87%E6%9C%AC%E8%AF%86%E5%88%AB%E7%AE%97%E6%B3%95)
    - [端到端算法](./doc/doc_ch/algorithm_overview.md#2-%E6%96%87%E6%9C%AC%E8%AF%86%E5%88%AB%E7%AE%97%E6%B3%95)
141
    - [使用PaddleOCR架构添加新算法](./doc/doc_ch/add_new_algorithm.md)
MissPenguin's avatar
MissPenguin committed
142
- [场景应用](./doc/doc_ch/application.md)
MissPenguin's avatar
update  
MissPenguin committed
143
144
145
146
    - [金融场景(表单/票据等)]()
    - [工业场景(电表度数/车牌等)]()
    - [教育场景(手写体/公式等)]()
    - [医疗场景(化验单等)]()
grasswolfs's avatar
grasswolfs committed
147
148
- 数据标注与合成
    - [半自动标注工具PPOCRLabel](./PPOCRLabel/README_ch.md)
dyning's avatar
dyning committed
149
    - [数据合成工具Style-Text](./StyleText/README_ch.md)
grasswolfs's avatar
grasswolfs committed
150
151
    - [其它数据标注工具](./doc/doc_ch/data_annotation.md)
    - [其它数据合成工具](./doc/doc_ch/data_synthesis.md)
Leif's avatar
Leif committed
152
- 数据集
153
154
155
156
    - [通用中英文OCR数据集](doc/doc_ch/dataset/datasets.md)
    - [手写中文OCR数据集](doc/doc_ch/dataset/handwritten_datasets.md)
    - [垂类多语言OCR数据集](doc/doc_ch/dataset/vertical_and_multilingual_datasets.md)
    - [版面分析数据集](doc/doc_ch/dataset/layout_datasets.md)
WenmuZhou's avatar
WenmuZhou committed
157
    - [表格识别数据集](doc/doc_ch/dataset/table_datasets.md)
158
    - [DocVQA数据集](doc/doc_ch/dataset/docvqa_datasets.md)
MissPenguin's avatar
MissPenguin committed
159
- [代码组织结构](./doc/doc_ch/tree.md)
WenmuZhou's avatar
WenmuZhou committed
160
- [效果展示](#效果展示)
MissPenguin's avatar
update  
MissPenguin committed
161
- [《动手学OCR》电子书📚](./doc/doc_ch/ocr_book.md)
MissPenguin's avatar
MissPenguin committed
162
- [开源社区](#开源社区)
WenmuZhou's avatar
WenmuZhou committed
163
- FAQ
Leif's avatar
Leif committed
164
165
    - [通用问题](./doc/doc_ch/FAQ.md)
    - [PaddleOCR实战问题](./doc/doc_ch/FAQ.md)
WenmuZhou's avatar
WenmuZhou committed
166
167
- [参考文献](./doc/doc_ch/reference.md)
- [许可证书](#许可证书)
grasswolfs's avatar
grasswolfs committed
168

WenmuZhou's avatar
WenmuZhou committed
169
170

<a name="效果展示"></a>
Leif's avatar
Leif committed
171

WenmuZhou's avatar
WenmuZhou committed
172
## 效果展示 [more](./doc/doc_ch/visualization.md)
MissPenguin's avatar
MissPenguin committed
173
174

<details open>
littletomatodonkey's avatar
littletomatodonkey committed
175
<summary>PP-OCRv3 中文模型</summary>
Leif's avatar
Leif committed
176
177

<div align="center">
littletomatodonkey's avatar
littletomatodonkey committed
178
179
180
    <img src="doc/imgs_results/PP-OCRv3/ch/PP-OCRv3-pic001.jpg" width="800">
    <img src="doc/imgs_results/PP-OCRv3/ch/PP-OCRv3-pic002.jpg" width="800">
    <img src="doc/imgs_results/PP-OCRv3/ch/PP-OCRv3-pic003.jpg" width="800">
WenmuZhou's avatar
WenmuZhou committed
181
</div>
WenmuZhou's avatar
WenmuZhou committed
182

MissPenguin's avatar
MissPenguin committed
183
184
</details>

WenmuZhou's avatar
WenmuZhou committed
185

MissPenguin's avatar
MissPenguin committed
186
<details open>
littletomatodonkey's avatar
littletomatodonkey committed
187
<summary>PP-OCRv3 英文模型</summary>
WenmuZhou's avatar
WenmuZhou committed
188

WenmuZhou's avatar
WenmuZhou committed
189
<div align="center">
littletomatodonkey's avatar
littletomatodonkey committed
190
191
    <img src="doc/imgs_results/PP-OCRv3/en/en_1.png" width="800">
    <img src="doc/imgs_results/PP-OCRv3/en/en_2.png" width="800">
WenmuZhou's avatar
WenmuZhou committed
192
193
</div>

MissPenguin's avatar
MissPenguin committed
194
195
196
197
</details>


<details open>
littletomatodonkey's avatar
littletomatodonkey committed
198
<summary>PP-OCRv3 多语言模型</summary>
WenmuZhou's avatar
WenmuZhou committed
199

WenmuZhou's avatar
WenmuZhou committed
200
<div align="center">
littletomatodonkey's avatar
littletomatodonkey committed
201
202
    <img src="doc/imgs_results/PP-OCRv3/multi_lang/japan_2.jpg" width="800">
    <img src="doc/imgs_results/PP-OCRv3/multi_lang/korean_1.jpg" width="800">
WenmuZhou's avatar
WenmuZhou committed
203
</div>
WenmuZhou's avatar
WenmuZhou committed
204

MissPenguin's avatar
MissPenguin committed
205
206
</details>

MissPenguin's avatar
update  
MissPenguin committed
207
208
209
210
211
212
213
214
215
216
217
218
<details open>
<summary>PP-Structure 文档分析</summary>

- 版面分析+表格识别  
<div align="center">
    <img src="./ppstructure/docs/table/ppstructure.GIF" width="800">
</div>

- SER(语义实体识别)  
<div align="center">
    <img src="./ppstructure/docs/vqa/result_ser/zh_val_0_ser.jpg" width="800">
</div>
WenmuZhou's avatar
WenmuZhou committed
219
220

- RE(关系提取)
MissPenguin's avatar
update  
MissPenguin committed
221
222
223
224
225
<div align="center">
    <img src="./ppstructure/docs/vqa/result_re/zh_val_21_re.jpg" width="800">
</div>

</details>
MissPenguin's avatar
MissPenguin committed
226

WenmuZhou's avatar
WenmuZhou committed
227
<a name="许可证书"></a>
Leif's avatar
Leif committed
228

WenmuZhou's avatar
WenmuZhou committed
229
230
## 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。