Closed 1378dm closed 2 years ago
You are not using the rgba
branch. How did you clone the repository? The easiest way is to use git clone https://github.com/PDillis/stylegan3-fun.git -b rgba
. If you don't specify the branch, you will use the main
branch and I haven't moved the changes there (yet).
I'm sure I've cloned the RGBA branch. The error seems to appear in augment.py
, but you don't seem to have modified it.
You're completely right, thank you for pointing it out, sorry for not reading your error more carefully. I forgot to change augment.py
because I usually only use --augpipe=bg
and it didn't occur to me that the color augmentation will of course fail. If you can show me the complete command you use to train just in case I miss something, that would be extremely helpful. Will take a look and update the code as soon as possible.
I am not using --augpipe
in my config, below is the command I am running.
python train.py --cfg=stylegan3-t --data=datasets/test_1.zip --gpus=1 --batch=32 --gamma=6.6 --kimg=10000 --snap=50 --img-snap=10 --snap-res=1080p --workers=1 --batch-gpu=32
Ok thanks. By default, you will use --aug=ada
and --augpipge=bgc
, so the color augmentations need to be done correctly with RGBA data. It may be simpler than I think, but will need a bit of time to check everything is right. If you want to train something in the meantime without the color augmentations, set --augpipe=bg
and it should train (I am currently training a --cfg=stylegan3-r
with only blit and geometric augmentations and everything is going ok). Will update here once the corrections are done for the color augmentations.
By the way, how should the rgba model be used? Is it possible to use gen_images.py
directly?
I haven't touched gen_images.py
, but generate.py
works so far, even saving videos. However, .mp4
videos (which is what I mostly use) do not support RGBA format, so I need to think a bit on how to do this. In turn, I only save the RGB part for the video, but I imagine generating images is more important for you. Run python generate.py images --help
for knowing all the options available.
See if 3b107d4 fixes the augmentations issue you were having.
I tried to train images with transparency using train.py from argb branch, but it still fails, here are some error messages, can you help me with it?