pytorch/examples

Gradient vanishing of G in the DCGAN example

Aberta

#822 aberto em 11 de set. de 2020

 (0 comentário) (0 reação) (0 responsável)Python (9.429 forks)batch import
help wanted

Métricas do repositório

Stars
 (21.634 estrelas)
Métricas de merge de PR
 (Métricas PR pendentes)

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