search

akanimax / BMSG-GAN

[MSG-GAN] Any body can GAN! Highly stable and robust architecture. Requires little to no hyperparameter tuning. Pytorch Implementation
MIT License
630 stars 104 forks source link

WGAN-GP loss: averaging penalties or not? #41

Open remicres opened 3 years ago

remicres commented 3 years ago

Hi @akanimax

First of all many thanks for this amazing contribution.

In the paper, it is stated we modified the gradient penalty to be the average of the penalties over each input. I didn't see any of that in the original MSG-GAN tensorflow implementation, neither in the BMSG-GAN implementation: it seems rather like only the gradient penalty of the higher resolution image is used.

Did I miss something, or is it a slight variation between the paper and the implementation?

Cheers

edit: related to #35