GAN_stability

GAN_stability copied to clipboard

@LMescheder Hi, most GAN papers use Adam optimizer. What's the main reason here using RMSProp? Is it better than Adam here?

LynnHo

Hello, First, thank you very much for your paper, it was very interesting and it helped me a lot! In your paper, in figure 8 and figure 9 in the...

SimonVerlinden

Hi, I've recently read your paper and I think it is great. I have a question about Eq.1 in the article. I found that the equation could not be led...

yoon28

Hi, thank you for sharing the code. It seems like that you used a large model for ImageNet, and a ralatively small one for the other dataset, e.g. celeba, chruch....

MiaoyunZhao

Hi, I'm using gradient penalty with LSGAN loss but it did not work ,so I replace LSGAN with Standard GAN loss it work fine !! except WGAN loss which type...

Johnson-yue

Gradient Penalty with Auxiliary classifier

3

Gradient penalty claculation should change when D has an auxiliary classifier or the gradient penalty should only be calculated over the real/fake output? Is there any intuition behind of whatever...

dougsouza

Spectral Normalization

3

I'm curious if you've tried the Spectral Normalization technic for your approach? At least at resolution 128^2 it didn't work for me

oleksandrlazariev

Why multiply by 0.1 in the residual block?

5

In the paper and code (eg [here](https://github.com/LMescheder/GAN_stability/blob/master/gan_training/models/resnet.py#L133)), the output of the resnet blocks is multiplied by 0.1. I'm curious of the purpose of this. Does it have to do with...

zplizzi

Questions with batch normalization

1

Hello, I just added BN in resblock and run 'python train.py configs/celebA-HQ', then it cannot converge at all.(see the picture below)  I noticed the moving average in your training,...

LuChengTHU

question about config

1

Hi, Thank you for sharing your code on github. I have a question regarding the configs. In the config for ImageNet and CelebA, there are two lines that seem to...

wmpauli