pytorch/examples

Gradient vanishing of G in the DCGAN example

Open

#822 aberto em 11 de set. de 2020

Ver no GitHub
 (0 comments) (0 reactions) (0 assignees)Python (9.429 forks)batch import
help wanted

Métricas do repositório

Stars
 (21.634 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

Hello,

I have trained the DCGAN with the default hyper-parameter settings on the downloaded "img_align_celeba" dataset (recommended in the tutorial). However, the results reveal strong gradient vanishing of G. While Loss_D keeps decreasing towards 0, Loss_G grows high (towards 100).

It seems that D is trained so well, preventing a good training on G. I didn't do any modifications on the code. Do you know what happened?

Thanks!

Guia do colaborador