carpedm20/BEGAN-tensorflow

Training loss goes to NaN

Open

#11 ouverte le 14 avr. 2017

Voir sur GitHub
 (0 commentaires) (0 réactions) (0 assignés)Python (233 forks)github user discovery
bughelp wanted

Métriques du dépôt

Stars
 (924 stars)
Métriques de merge PR
 (Métriques PR en attente)

Description

I started training with Celeb database, but around 50k iteration, the loss goes to NaN & k_t goes to 1. Have you seen this before. 10%|█████▎ | 49650/500000 [5:29:56<49:13:32, 2.54it/s][49650/500000] Loss_D: 0.112764 Loss_G: 0.053848 measure: 0.1190, k_t: 0.0458 10%|█████▎ | 49700/500000 [5:30:16<49:18:01, 2.54it/s][49700/500000] Loss_D: nan Loss_G: nan measure: nan, k_t: 1.0000

Having said that, the output at 49k is starting to look good. Below are my last good outputs (real, d_real, g, d_fake). x_fixed 49500_d_real 49500_g 49500_d_fake

My training stats looks like this began_training_screenshot

Guide contributeur