pytorch>> WGAN-with-Feedback-Cross-Attention>> 返回
项目作者： rushhan

项目描述 ：
Project to get attention from discriminator: 1st combination
高级语言： Python
项目地址: git://github.com/rushhan/WGAN-with-Feedback-Cross-Attention.git
创建时间： 2020-09-12T18:34:42Z
项目社区：https://github.com/rushhan/WGAN-with-Feedback-Cross-Attention
开源协议：BSD 3-Clause "New" or "Revised" License
下载


WGAN-with-Cross-Attention

Project to get attention from discriminator: 1st modification

Modifications to the original WGAN implementation:

  1. Added feedback from the discriminator in the form of attention

Execute

python main.py —dataset lsun —dataroot /workspace/lsun —cuda —clamp —fdback —save_dir samples

Notes

Need the lsun data.
Follow the instruction in original implementation link

Sources

WGAN Model based on original paper link.

Cross Attention is my own implementation

To-Do

Rerun and recheck the results