carpedm20/BEGAN-tensorflow

Training loss goes to NaN

Open

#11 aberto em 14 de abr. de 2017

Ver no GitHub
 (0 comments) (0 reactions) (0 assignees)Python (233 forks)github user discovery
bughelp wanted

Métricas do repositório

Stars
 (924 stars)
Métricas de merge de PR
 (Métricas PR pendentes)

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

Guia do colaborador