Giters

rosinality / style-based-gan-pytorch

Implementation A Style-Based Generator Architecture for Generative Adversarial Networks in PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Possibly wrong R1 penalty

TropComplique opened this issue · comments

commented

Hi.
Why do you use softplus before computing gradient here?
In the original implementation they don't do it. Look at this line.

commented

Thank you, corrected it at bc4bd85.