https://github.com/whai362/pan_pp.pytorch
Official implementations of PSENet, PAN and PAN++.
https://github.com/whai362/pan_pp.pytorch
pan psenet text-detection text-recognition text-spotting
Last synced: about 2 months ago
JSON representation
Official implementations of PSENet, PAN and PAN++.
- Host: GitHub
- URL: https://github.com/whai362/pan_pp.pytorch
- Owner: whai362
- License: apache-2.0
- Created: 2020-09-02T07:59:14.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2023-03-09T11:59:29.000Z (about 2 years ago)
- Last Synced: 2025-03-29T06:07:10.196Z (about 2 months ago)
- Topics: pan, psenet, text-detection, text-recognition, text-spotting
- Language: Python
- Homepage:
- Size: 814 KB
- Stars: 451
- Watchers: 10
- Forks: 90
- Open Issues: 59
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## News
- (2022/12/08) We will release the code and models of FAST in [link](https://github.com/czczup/FAST).
- (2022/10/09) We release stabler code for PAN++, see [pan_pp_stable](https://github.com/whai362/pan_pp_stable).
- (2022/04/22) Update PAN++ ICDAR 2015 joint training & post-processing with vocabulary & visualization code.
- (2021/11/03) Paddle implementation of PAN, see [Paddle-PANet](https://github.com/simplify23/Paddle-PANet). Thanks @simplify23.
- (2021/04/08) PSENet and PAN are included in [MMOCR](https://github.com/open-mmlab/mmocr).
## Introduction
This repository contains the official implementations of [PSENet](https://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Shape_Robust_Text_Detection_With_Progressive_Scale_Expansion_Network_CVPR_2019_paper.html), [PAN](https://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Efficient_and_Accurate_Arbitrary-Shaped_Text_Detection_With_Pixel_Aggregation_Network_ICCV_2019_paper.html), [PAN++](https://arxiv.org/abs/2105.00405).
Text Detection
- [x] [PSENet (CVPR'2019)](config/psenet/)
- [x] [PAN (ICCV'2019)](config/pan/)
- [x] [FAST (Arxiv'2021)](config/fast/)
Text Spotting
- [x] [PAN++ (TPAMI'2021)](config/pan_pp)
## Installation
First, clone the repository locally:
```shell
git clone https://github.com/whai362/pan_pp.pytorch.git
```
Then, install PyTorch 1.1.0+, torchvision 0.3.0+, and other requirements:
```shell
conda install pytorch torchvision -c pytorch
pip install -r requirement.txt
```
Finally, compile codes of post-processing:
```shell
# build pse and pa algorithms
sh ./compile.sh
```
## Dataset
Please refer to [dataset/README.md](dataset/README.md) for dataset preparation.
## Training
```shell
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py ${CONFIG_FILE}
```
For example:
```shell
CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py config/pan/pan_r18_ic15.py
```
## Testing
### Evaluate the performance
```shell
python test.py ${CONFIG_FILE} ${CHECKPOINT_FILE}
cd eval/
./eval_{DATASET}.sh
```
For example:
```shell
python test.py config/pan/pan_r18_ic15.py checkpoints/pan_r18_ic15/checkpoint.pth.tar
cd eval/
./eval_ic15.sh
```
### Evaluate the speed
```shell script
python test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --report_speed
```
For example:
```shell script
python test.py config/pan/pan_r18_ic15.py checkpoints/pan_r18_ic15/checkpoint.pth.tar --report_speed
```
### Visualization
```shell script
python test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --vis
```
For example:
```shell script
python test.py config/pan/pan_r18_ic15.py checkpoints/pan_r18_ic15/checkpoint.pth.tar --vis
```
## Citation
Please cite the related works in your publications if it helps your research:
### PSENet
```
@inproceedings{wang2019shape,
title={Shape Robust Text Detection with Progressive Scale Expansion Network},
author={Wang, Wenhai and Xie, Enze and Li, Xiang and Hou, Wenbo and Lu, Tong and Yu, Gang and Shao, Shuai},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={9336--9345},
year={2019}
}
```
### PAN
```
@inproceedings{wang2019efficient,
title={Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network},
author={Wang, Wenhai and Xie, Enze and Song, Xiaoge and Zang, Yuhang and Wang, Wenjia and Lu, Tong and Yu, Gang and Shen, Chunhua},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={8440--8449},
year={2019}
}
```
### PAN++
```
@article{wang2021pan++,
title={PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text},
author={Wang, Wenhai and Xie, Enze and Li, Xiang and Liu, Xuebo and Liang, Ding and Zhibo, Yang and Lu, Tong and Shen, Chunhua},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2021},
publisher={IEEE}
}
```
### FAST
```
@misc{chen2021fast,
title={FAST: Searching for a Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation},
author={Zhe Chen and Wenhai Wang and Enze Xie and ZhiBo Yang and Tong Lu and Ping Luo},
year={2021},
eprint={2111.02394},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## License
This project is developed and maintained by [IMAGINE Lab@National Key Laboratory for Novel Software Technology, Nanjing University](https://cs.nju.edu.cn/lutong/ImagineLab.html).
This project is released under the [Apache 2.0 license](https://github.com/whai362/pan_pp.pytorch/blob/master/LICENSE).