typo of discriminator loss in non-saturating type #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Closed

XiaoluDing opened this issue Sep 18, 2023 · 1 comment

XiaoluDing commented Sep 18, 2023

https://github.com/SerezD/vqvae-vqgan-pytorch-lightning/blob/master/vqvae/modules/loss/loss.py#L38C14-L38C14
fake_loss = functional.binary_cross_entropy_with_logits(logits_fake, target=torch.ones_like(logits_fake))

maybe fix it using zeros_like

Owner

SerezD commented Sep 18, 2023

Hi, thank you for pointing that out.
The corrected version is now online.

SerezD closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment