[CVPR2020] Adversarial Latent Autoencoders
python
machine-learning
computer-vision
deep-learning
neural-network
paper
pytorch
generative-adversarial-network
gan
generative-model
autoencoder
celeba
paper-implementations
face-generation
pytorch-implementation
celeba-hq
stylegan
ffhq
cvpr2020
alae
-
Updated
Jun 20, 2020 - Python
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