Text Prior Guided Scene Text Image Super-Resolution
https://arxiv.org/abs/2106.15368
Jianqi Ma, Shi Guo, Lei Zhang
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
Recovering TextZoom samples
Environment:
Other possible python packages like pyyaml, cv2, Pillow and imgaug
Main idea
Single stage with loss
Multi-stage version
Configure your training
Download the pretrained recognizer from:
Aster: https://github.com/ayumiymk/aster.pytorch
MORAN: https://github.com/Canjie-Luo/MORAN_v2
CRNN: https://github.com/meijieru/crnn.pytorch
Unzip the codes and walk into the '$TPGSR_ROOT$/', place the pretrained weights from recognizer in '$TPGSR_ROOT$/'.
Download the TextZoom dataset:
https://github.com/JasonBoy1/TextZoom
Train the corresponding model (e.g. TPGSR-TSRN):
chmod a+x train_TPGSR-TSRN.sh
./train_TPGSR-TSRN.sh
or
python3 main.py --arch="tsrn_tl_cascade" \ # The architecture
--batch_size=48 \ # The batch size
--STN \ # Using STN net for alignment
--mask \ # Using the contour mask
--use_distill \ # Using the TP loss
--gradient \ # Using the Gradient Prior Loss
--sr_share \ # Sharing weights for SR Module
--stu_iter=1 \ # The number of interations in multi-stage version
--vis_dir='vis_TPGSR-TSRN' \ # The checkpoint directory
Run the test-prefixed shell to test the corresponding model.
Adding '--go_test' in the shell file
Cite this paper:
@article{ma2021text,
title={Text Prior Guided Scene Text Image Super-resolution},
author={Ma, Jianqi and Guo, Shi and Zhang, Lei},
journal={arXiv preprint arXiv:2106.15368},
year={2021}
}
根据你提出的训练命令
python3 -u main.py --arch="tsrn_tl_cascade" --batch_size=48 --STN --mask --use_distill --gradient --sr_share --stu_iter=3 --vis_dir='vis_TPGSR-TSRN'
--sr_share 默认为False,训练时是True
79 Nov 29, 2022
19 Jun 30, 2022
49 Dec 26, 2022
41 Jan 3, 2023
3 Jan 14, 2022
740 Dec 24, 2022
612 Jan 4, 2023
79 Dec 27, 2022
36 Dec 18, 2022
76 Nov 12, 2022
1.8k Dec 27, 2022
41 Dec 15, 2022
3.6k Jan 2, 2023
2.6k Jan 4, 2023
169 Dec 21, 2022