README.md 13.1 KB
Newer Older
D
dyning 已提交
1
English | [简体中文](README_cn.md)
2

D
dyning 已提交
3 4
## Introduction
PaddleOCR aims to create rich, leading, and practical OCR tools that help users train better models and apply them into practice.
D
dyning 已提交
5

D
dyning 已提交
6
**Recent updates**
D
dyning 已提交
7
- 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)
D
dyning 已提交
8
- 2020.7.15, Add mobile App demo , support both iOS and  Android  ( based on easyedge and Paddle Lite)
D
dyning 已提交
9
- 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.
D
dyning 已提交
10 11 12 13
- 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)
D
dyning 已提交
14

M
MissPenguin 已提交
15
## Features
D
dyning 已提交
16
- Ultra-lightweight OCR model, total model size is only 8.6M
D
dyning 已提交
17
    - Single model supports Chinese/English numbers combination recognition, vertical text recognition, long text recognition
D
dyning 已提交
18 19 20 21
    - 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.
D
dyning 已提交
22

D
dyning 已提交
23
## Visualization
T
tink2123 已提交
24

D
dyning 已提交
25
![](doc/imgs_results/11.jpg)
L
LDOUBLEV 已提交
26

D
dyning 已提交
27
![](doc/imgs_results/img_10.jpg)
D
dyning 已提交
28

D
dyning 已提交
29
[More visualization](./doc/doc_en/visualization_en.md)
D
dyning 已提交
30

D
dyning 已提交
31
You can also quickly experience the ultra-lightweight OCR : [Online Experience](https://www.paddlepaddle.org.cn/hub/scene/ocr)
D
dyning 已提交
32

D
dyning 已提交
33 34 35
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**)
D
dyning 已提交
36 37 38 39 40

<div align="center">
<img src="./doc/ocr-android-easyedge.png"  width = "200" height = "200" />
</div>

D
dyning 已提交
41
- [**OCR Quick Start**](./doc/doc_en/quickstart_en.md)
D
dyning 已提交
42

D
dyning 已提交
43
<a name="Supported-Chinese-model-list"></a>
D
dyning 已提交
44

D
dyning 已提交
45
### Supported Models:
D
dyning 已提交
46

D
dyning 已提交
47
|Model Name|Description |Detection Model link|Recognition Model link| Support for space Recognition Model link|
D
dyning 已提交
48
|-|-|-|-|-|
D
dyning 已提交
49 50
|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)
D
dyning 已提交
51 52 53 54 55 56 57 58 59 60 61 62 63 64


## 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)
D
dyning 已提交
65
- Deployment
D
dyning 已提交
66 67 68 69 70 71
    - [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)
D
dyning 已提交
72
- Datasets
D
dyning 已提交
73 74 75 76 77
    - [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)
D
dyning 已提交
78
- [FAQ](#FAQ)
D
dyning 已提交
79 80 81 82
- Visualization
    - [Ultra-lightweight Chinese/English OCR Visualization](#UCOCRVIS)
    - [General Chinese/English OCR Visualization](#GeOCRVIS)
    - [Chinese/English OCR Visualization (Support Space Recognization )](#SpaceOCRVIS)
M
MissPenguin 已提交
83 84 85 86
- [Community](#Community)
- [References](./doc/doc_en/reference_en.md)
- [License](#LICENSE)
- [Contribution](#CONTRIBUTION)
D
dyning 已提交
87 88 89 90 91

<a name="TEXTDETECTIONALGORITHM"></a>
## Text Detection Algorithm

PaddleOCR open source text detection algorithms list:
T
tink2123 已提交
92
- [x]  EAST([paper](https://arxiv.org/abs/1704.03155))
T
fix url  
tink2123 已提交
93
- [x]  DB([paper](https://arxiv.org/abs/1911.08947))
D
dyning 已提交
94
- [ ]  SAST([paper](https://arxiv.org/abs/1908.05498))(Baidu Self-Research, comming soon)
T
tink2123 已提交
95

D
dyning 已提交
96
On the ICDAR2015 dataset, the text detection result is as follows:
T
tink2123 已提交
97

D
dyning 已提交
98
|Model|Backbone|precision|recall|Hmean|Download link|
99
|-|-|-|-|-|-|
D
dyning 已提交
100 101 102 103
|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)|
L
LDOUBLEV 已提交
104

D
dyning 已提交
105
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:
D
dyning 已提交
106
|Model|Backbone|Configuration file|Pre-trained model|
T
tink2123 已提交
107
|-|-|-|-|
D
dyning 已提交
108 109
|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)|
T
tink2123 已提交
110

D
dyning 已提交
111
* 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.
T
tink2123 已提交
112

D
dyning 已提交
113
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)
T
tink2123 已提交
114

D
dyning 已提交
115 116
<a name="TEXTRECOGNITIONALGORITHM"></a>
## Text Recognition Algorithm
T
tink2123 已提交
117

D
dyning 已提交
118
PaddleOCR open-source text recognition algorithms list:
T
tink2123 已提交
119 120 121 122
- [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))
D
dyning 已提交
123
- [ ]  SRN([paper](https://arxiv.org/abs/2003.12294))(Baidu Self-Research, comming soon)
T
tink2123 已提交
124

D
dyning 已提交
125
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:
T
tink2123 已提交
126

D
dyning 已提交
127
|Model|Backbone|Avg Accuracy|Module combination|Download link|
D
dyning 已提交
128
|-|-|-|-|-|
D
dyning 已提交
129 130 131 132 133 134 135 136 137
|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)|

D
dyning 已提交
138
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:
D
dyning 已提交
139
|Model|Backbone|Configuration file|Pre-trained model|
T
tink2123 已提交
140
|-|-|-|-|
D
dyning 已提交
141 142
|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)|
T
tink2123 已提交
143

D
dyning 已提交
144
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)
T
tink2123 已提交
145

D
dyning 已提交
146 147 148
<a name="ENDENDOCRALGORITHM"></a>
## END-TO-END OCR Algorithm
- [ ]  [End2End-PSL](https://arxiv.org/abs/1909.07808)(Baidu Self-Research, comming soon)
T
tink2123 已提交
149

D
dyning 已提交
150
## Visualization
D
dyning 已提交
151

D
dyning 已提交
152 153
<a name="UCOCRVIS"></a>
### 1.Ultra-lightweight Chinese/English OCR Visualization [more](./doc/doc_en/visualization_en.md)
T
tink2123 已提交
154

D
dyning 已提交
155
<div align="center">
D
dyning 已提交
156
    <img src="doc/imgs_results/1.jpg" width="800">
D
dyning 已提交
157
</div>
T
tink2123 已提交
158

D
dyning 已提交
159 160
<a name="GeOCRVIS"></a>
### 2. General Chinese/English OCR Visualization [more](./doc/doc_en/visualization_en.md)
D
dyning 已提交
161 162 163 164

<div align="center">
    <img src="doc/imgs_results/chinese_db_crnn_server/11.jpg" width="800">
</div>
165

D
dyning 已提交
166 167
<a name="SpaceOCRVIS"></a>
### 3.Chinese/English OCR Visualization (Space_support) [more](./doc/doc_en/visualization_en.md)
T
tink2123 已提交
168

D
dyning 已提交
169 170 171
<div align="center">
    <img src="doc/imgs_results/chinese_db_crnn_server/en_paper.jpg" width="800">
</div>
T
tink2123 已提交
172

D
dyning 已提交
173
<a name="FAQ"></a>
D
dyning 已提交
174

D
dyning 已提交
175
## FAQ
D
dyning 已提交
176 177 178 179 180 181 182 183 184
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
T
tink2123 已提交
185

D
dyning 已提交
186
    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.
M
MissPenguin 已提交
187

D
dyning 已提交
188
4. Release time of self-developed algorithm
T
tink2123 已提交
189

D
dyning 已提交
190
    Baidu Self-developed algorithms such as SAST, SRN and end2end PSL will be released in June or July. Please be patient.
M
MissPenguin 已提交
191

D
dyning 已提交
192
[more](./doc/doc_en/FAQ_en.md)
D
dyning 已提交
193

D
dyning 已提交
194
<a name="Community"></a>
M
MissPenguin 已提交
195
## Community
D
dyning 已提交
196
Scan  the QR code below with your wechat and completing the questionnaire, you can access to offical technical exchange group.
D
dyning 已提交
197

D
dyning 已提交
198 199 200
<div align="center">
<img src="./doc/joinus.jpg"  width = "200" height = "200" />
</div>
M
MissPenguin 已提交
201

D
dyning 已提交
202
<a name="LICENSE"></a>
M
MissPenguin 已提交
203
## License
D
dyning 已提交
204
This project is released under <a href="https://github.com/PaddlePaddle/PaddleOCR/blob/master/LICENSE">Apache 2.0 license</a>
D
dyning 已提交
205

D
dyning 已提交
206
<a name="CONTRIBUTION"></a>
M
MissPenguin 已提交
207
## Contribution
D
dyning 已提交
208
We welcome all the contributions to PaddleOCR and appreciate for your feedback very much.
T
tink2123 已提交
209

D
dyning 已提交
210 211 212 213 214
- 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.
littletomatodonkey's avatar
littletomatodonkey 已提交
215
- Thanks [BeyondYourself](https://github.com/BeyondYourself) for contributing many great suggestions and simplifying part of the code style.