Gradient penalty on the generator

igul222 / improved_wgan_training

Code for reproducing experiments in "Improved Training of Wasserstein GANs"

MIT License

2.35k stars 668 forks source link

Gradient penalty on the generator #35

Closed cjf00000 closed 6 years ago

cjf00000 commented 7 years ago

It seems that the gradient penalty term also has non-zero gradient w.r.t. the generator parameters. Shouldn't the penalty term be added to both the discriminator and the generator objective to ensure that the mini-max procedure finds a saddle point?

igul222 commented 6 years ago

This would indeed make sense to me, but when I tried it I was unable to find an experimental setup where doing that improved the results in any consistent way. In my experiments it at least doesn't seem to hurt though, so if you want more theoretical elegance and don't mind the extra computation time you can probably do that and it'll still work.