WGAN-with-Cross-Attention

Project to get attention from discriminator: 1st modification

Modifications to the original WGAN implementation:

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