unet-stylegan2: Problems with parameters in face generation

Just tried to train a model with a 3.5K-face dataset but it seems strange. My command was this: unet_stylegan2 --batch_size 4 --network_capacity 32 --gradient_accumulate_every 8 --aug_prob 0.25 --attn-layers [1,2]

This is on the 14 epoch (14000)

14

Any suggestion to improve this or just wait a little bit more? I had better results at this point with regular stylegan2

About this issue

  • Original URL
  • State: open
  • Created 4 years ago
  • Comments: 15 (8 by maintainers)

Most upvoted comments

@rockdrigoma you want to see both numbers above 0, but also below 20

@rockdrigoma how did it go?

Epoch 32 1% 598/118000 [35:19<90:35:00, 2.78s/it]G: 2.40 | D: 4.00 | GP: 0.06 | PL: 1.17 | CR: 0.00

mr.jpg

32-mr

@rockdrigoma the way it works in GANs is there are two AIs. One AI learns to generate, and the other learns to determine if the image is fake (generated) or real. They are pit against each other, and they both become really good at some point. The numbers monitor that they are evenly balanced. If one becomes too powerful, both stop learning

@rockdrigoma hmmm, that looks fine actually… maybe let it sit overnight and see where it is at at 50k

What’s the meaning of each metric?

@rockdrigoma ohh darn, what’s the values for D: and G: at this point?

9% 13950/149000 [9:41:20<95:32:18, 2.55s/it]G: 0.84 | D: 0.71 | GP: 0.36 | PL: 0.50 | CR: 0.00 | Q: 0.00

i have to admit, this repository is a bit experimental, and i’m not sure if it will work for datasets with less than 10k samples