search

AlexiaJM / RelativisticGAN

Code for replication of the paper "The relativistic discriminator: a key element missing from standard GAN"
719 stars 103 forks source link

Suggestion: Use ProGAN in your experiments too. #9

Closed akanimax closed 6 years ago

akanimax commented 6 years ago

Hi @AlexiaJM; firstly, great job with your work. I am currently still reading your paper. Just upon scrolling to the FID comparison results, I didn't notice ProGAN (Progressive growing of GANs) in your experiments. The reason why I suggested ProGAN, is that I have recently worked on them and found them to be quite good and stable. Perhaps augmenting the RaLSGAN with Progressive growing, you could achieve an even better FID. This is just a suggestion though. Again great job :+1:.

Best regards, akanimax

AlexiaJM commented 6 years ago

Hi Animesh,

Thanks! I agree but it looks very computationally demanding and I only have a Geforce 1060 which I can run at night. Now that @FrigEgg has added better resuming capabilities to the code, it might be doable though. I could add an overview of other interesting results found by fellow Githubers that are not in the paper in the github page, so feel free to report any interesting results.

FeepingCreature commented 6 years ago

Hi my name is FrigEgg I frig eggs :ok_hand: :egg: :+1: :egg:

:smiley: