search

sihyun-yu / PVDM

Official PyTorch implementation of Video Probabilistic Diffusion Models in Projected Latent Space (CVPR 2023).
https://sihyun.me/PVDM
MIT License
287 stars 15 forks source link

vqloss #14

Closed dialuser closed 1 year ago

dialuser commented 1 year ago

the d_loss was always zero when I ran the code. I noticed in forward() of LPIPSWithDiscriminator, codebook_loss is never used. Is that related?

sihyun-yu commented 1 year ago

It is not related. We don't use VQ loss (see the paper) and to use GAN loss you need to load the checkpoint (that is trained without GAN loss) and execute with different config file that I provided.