Skip to content

Project for Connectionist Temporal Classification with Maximum Entropy Regularization.

License

Notifications You must be signed in to change notification settings

saberSabersaber/enctc.crnn

 
 

Repository files navigation

PyTorch Project for NIPS 2018 paper:

Connectionist Temporal Classification with Maximum Entropy Regularization Hu Liu, Sheng Jin and Changshui Zhang. Neural Information Processing Systems (NIPS), 2018.

Requirements

  • python
  • pytorch

Datasets

  • ICDAR-2003 (IC03)
  • ICDAR-2013 (IC13)
  • IIIT5k-word (IIIT5k)
  • Street View Text (SVT)

Usage

Train

zsh shs/seg_ent_fb/seg_5k.sh

Test

CUDA_VISIBLE_DEVICES=0 python test.py --crnn_path model_dir --valroot data/svt1/testset.lmdb

Citation

If you use this code in your project, please cite this paper.

Contact

To ask questions or report issues, please open an issue on the issues tracker.

References

About

Project for Connectionist Temporal Classification with Maximum Entropy Regularization.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 96.4%
  • Shell 3.6%