denoising-diffusion-pytorch icon indicating copy to clipboard operation
denoising-diffusion-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon lucidrains

The config of celeba-HQ

Open pokameng opened this issue 2 years ago • 3 comments

hello, gays I used the default parameters directly when I trained with celeba-HQ, but I found that the results were not too good, has anyone had success with celeba-HQ training? Can you share the configuration file please? Thanks!!!

pokameng avatar Sep 28 '22 08:09 pokameng

@kashif @lucidrains

pokameng avatar Sep 28 '22 08:09 pokameng

hello, gays I used the default parameters directly when I trained with celeba-HQ, but I found that the results were not too good, has anyone had success with celeba-HQ training? Can you share the configuration file please? Thanks!!!

@pokameng Have you solved this problem? I also have the same question and would like to ask.

Ryhhhh avatar Mar 29 '23 04:03 Ryhhhh

@pokameng @Ryhhhh Were you able to train with Celeba-HQ dataset? could you also share the loss curve if possible.

akshita-sukhlecha avatar Aug 22 '23 01:08 akshita-sukhlecha