New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
FastGAN grid artifacts #17
Comments
very cool samples! I also noticed that these patterns sometimes occur on higher resolutions, and I think you're probably right that the skip-excitation layers cause this... If not, you can try two things:
|
Alright, thanks for the quick reply! I'll fire up some runs with StyleGAN then. By 'don't use the skip-excitation layers,' do you mean essentially making the FastGAN generator an nn.Sequential of UpBlockComp()'s? Is this a configuration you've tested? |
Yes, that's exactly what I mean :) I did some testing and adding skip-excitation layers usually gave some minor improvements, so I kept them and didn't bother. |
gonna close this for now, feel free to reopen it or to post updates :) |
Yes, the CIFAR config is basically set up to:
if cfg == 'cifar':
args.loss_kwargs.pl_weight = 0 # disable path length regularization
args.loss_kwargs.style_mixing_prob = 0 # disable style mixing
args.D_kwargs.architecture = 'orig' # disable residual skip connections and with a slightly different config: cfg_specs = {
'paper512': dict(ref_gpus=8, kimg=25000, mb=64, mbstd=8, fmaps=1,
lrate=0.0025, gamma=0.5, ema=20, ramp=None, map=8),
'cifar': dict(ref_gpus=2, kimg=100000, mb=64, mbstd=32, fmaps=1,
lrate=0.0025, gamma=0.01, ema=500, ramp=0.05, map=2),
} cf. https://github.com/NVlabs/stylegan2-ada-pytorch/blob/d4b2afe9c27e3c305b721bc886d2cb5229458eba/train.py#L160 |
very interesting, thanks for the insights! Generally, we have seen that the current PG config might not be optimal for higher resolutions. As you can see in the results , the FIDs for higher resolution, e.g for Pokemon, are generally a bit higher (of course the task is also harder). This is likely due to the training resolution of the feature network being different, usually, it is at 224/256. As a check, have you tried training on 256? |
I've been noticing quite a lot of griddy/repetitive patterns in the outputs when training at high resolution with FastGAN.
Will the change from today help address those? Or are these inherent to the skip-excitation layers? (the grids do seem to be ~32x32, which is what is skipped to the 512x512 block). Alternatively, would you happen to know ways that these patterns could be reduced?
Example training grid with repetitive grid patterns (5000 image dataset after 919 kimg):
Example training grid with repetitive grid patterns and mode collapse (4000 image dataset after 680 kimg finetuning from above checkpoint)
The text was updated successfully, but these errors were encountered: