This repository is build upon AdelaiDet.
- CUDA 11.3
- Python 3.8
- PyTorch 1.10.1
- Official Pre-Built Detectron2
Please refer to the Installation section of AdelaiDet: README.md.
If you have not installed Detectron2, following the official guide: INSTALL.md.
Please following the offlical guide provided by AdelaiDet to prepare the datasets.
After that, download polygonal annotations, along with evaluation files and extract them under datasets
folder provided by TESTR.
You can train the model by putting pretrained weights in weights
folder.
Example commands:
python tools/train_net.py --config-file /path/to/config --num-gpus 8
Configuration files can be found in configs
.
python tools/train_net.py --config-file /path/to/config --eval-only MODEL.WEIGHTS /path/to/model
@inproceedings{Yu2023TurningAC,
title={Turning a CLIP Model into a Scene Text Detector},
author={Wenwen Yu and Yuliang Liu and Wei Hua and Deqiang Jiang and Bo Ren and Xiang Bai},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
year={2023}
}
@article{Yu2024TurningAC,
title={Turning a CLIP Model into a Scene Text Spotter},
author={Wenwen Yu and Yuliang Liu and Xingkui Zhu and Haoyu Cao and Xing Sun and Xiang Bai},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2024}
}
This project is under the CC-BY-NC 4.0 license.
The project partially based on AdelaiDet, CLIP, DenseCLIP, Deformable-DETR, TESTR. Thanks for their great works.