pytorch/examples

Gradient vanishing of G in the DCGAN example

Open

#822 ouverte le 11 sept. 2020

Voir sur GitHub
 (0 commentaires) (0 réactions) (0 assignés)Python (9 429 forks)batch import
help wanted

Métriques du dépôt

Stars
 (21 634 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

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!

Guide contributeur