Open SanaNazari opened 2 years ago
What cfg are you using? Stylegan3-r is only for datasets with rotational symmetry.
I am using stylegan3-r. Which cfg is better to use then?
stylegan3-t seems to be the recommended config for general use. the other option is stylegan2, but that's just a fallback to the previous ADA methods
btw, stylegan3-t uses less VRAM so you can probably increase your batch size from what it was on -R
I'd recommend using --cfg=stylegan2
if quality is your main goal. StyleGAN3 configs do not have a higher quality, just more capabilities (in specific, rotational and translational equivariances). If neither of these matter to you, then go for StyleGAN2-ADA, so it's best you know which augmentations to use depending on your dataset size. As per the figure in the ADA paper:
So e.g., if you have around 2k images, then set --aug=ada --augpipe=bgc --target=0.4
as per the figure above. Note that this is done with unconditional training of the models, so perhaps the conditional one you are training might differ.
Thank you for the explanation. I am using 10k images. But I don't see any --augpipe in train options in stylegan3 train.py
It already is using --augpipe=bgc
by default as you can see on this line. Since you have a 10k dataset, as per the previous figure, then it'd be best you set --augpipe=bg --target=0.6
. As you note, the vanilla StyleGAN3 code doesn't let you set the --augupipe
, so you have to add it yourself or use my repo, where I have done that already, plus some other things.
Amazing work by NVLabs. I just have one curiosity. I was watching the generated results on pretrained network. I noted that most of the faces generated by stylegan3-t-ffhq-1024x1024.pkl had some geometric patterns mostly in the areas where different shades merges. What is the reason for this?
As I understand it, it's due to the way stylegan3 does feature extraction. I noticed the same on my custom models trained with the same config, for the first 1000 kimg there were noticeable "deep dream"-esque artifacts that were not present on stylegan2.
Okay. So @isademigod I guess this was also not discussed in the paper as well considering it is a major bug in the model?
I am training stylegan3 on dermoscopic skin lesion dataset (HAM10000) in conditional mode with 7 classes . After almost 6k iterations I reached fid of 11. I assume 11 is a pretty good number to get. The issue is that when I generate samples there is a diamond or X shape patterns in the images that make the images unrealistic. Here are some samples of the real dataset:
![ISIC_0029480](https://user-images.githubusercontent.com/60878123/180216974-d60e1395-2cef-4891-a5a5-fd6b8e6608b5.jpg)
And here are some examples of generated samples:
Any advice on what id causing this or how can I overcome it?