pytorch/examples

Gradient vanishing of G in the DCGAN example

Open

#822 aperta il 11 set 2020

Vedi su GitHub
 (0 commenti) (0 reazioni) (0 assegnatari)Python (9429 fork)batch import
help wanted

Metriche repository

Star
 (21.634 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

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!

Guida contributor