the LeakyReLU layer after dense1

Open Walstruzz opened this issue 5 years ago • 1 comments

Hi, thanks for your reimplementation. It is so elegant.

But I found that you have a LeakyReLU layer after dense1, which does not exist in the tensorflow implementation. https://github.com/tomguluson92/StyleGAN_PyTorch/blob/92b7a3dc7711f617994dce3c7531177cc9940e04/networks_stylegan.py#L670

https://github.com/NVlabs/stylegan/blob/66813a32aac5045fcde72751522a0c0ba963f6f2/training/networks_stylegan.py#L617

I think that adding activation after the last fully connected layer is not a good idea.

Mar 27 '20 11:03 Walstruzz

Thanks for pointing that problem, do you found that useful if removing this?

Aug 10 '20 07:08 tomguluson92