Skip to content

The project was initially built with CUDA 10.6 and PyTorch 1.6.0. To support RTX 3090, a Dockerfile with CUDA 11.1 and PyTorch 1.8.1 was created. NumPy-based image generation was used in testing to resolve MMCV environment conflicts.

License

Notifications You must be signed in to change notification settings

CQUwilliam/EDTER_CUDA11.1_Torch1.8

 
 

Repository files navigation

EDTER

EDTER: Edge Detection with Transformer
Mengyang Pu, Yaping Huang, Yuming Liu, Qingji Guan and Haibin Ling
CVPR 2022

🔥Update
*For the main tutorial, please refer to https://github.com/MengyangPu/EDTER.
The environment has been modified for compatibility, enabling training on the latest GPUs.
A Docker container was configured using a Dockerfile.
Currently, only test.py has been used.

Acknowledgements

  • We thank the anonymous reviewers for their valuable and inspiring comments and suggestions.
  • Thanks to the previous open-sourced repo:
    SETR
    MMsegmentation

Reference

@InProceedings{Pu_2022_CVPR,
    author    = {Pu, Mengyang and Huang, Yaping and Liu, Yuming and Guan, Qingji and Ling, Haibin},
    title     = {EDTER: Edge Detection With Transformer},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {1402-1412}
}

About

The project was initially built with CUDA 10.6 and PyTorch 1.6.0. To support RTX 3090, a Dockerfile with CUDA 11.1 and PyTorch 1.8.1 was created. NumPy-based image generation was used in testing to resolve MMCV environment conflicts.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • MATLAB 33.4%
  • Python 31.5%
  • HTML 26.9%
  • C++ 6.8%
  • C 1.3%
  • Shell 0.1%