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

Confused with nll_loss #876

Open

haichao2023 opened this issue Nov 26, 2024 · 2 comments

haichao2023 commented Nov 26, 2024

Is this correct? Sum all pixels and divide by batch_size?

stable-diffusion/ldm/modules/losses/contperceptual.py

Line 57 in 21f890f

weighted_nll_loss = torch.sum(weighted_nll_loss) / weighted_nll_loss.shape[0]

onlyonewater commented Dec 9, 2024

+1, I am also confused about this loss

ljw919 commented Jan 13, 2025

also confused, anyone already train a VAE result ? is it OK ?

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