epigraf icon indicating copy to clipboard operation
epigraf copied to clipboard

Published 20 hours ago • verified publisher icon universome

Can not get reasonable results.

Open Talegqz opened this issue 2 years ago • 4 comments

Thanks for your excellent work! I trained the model following python src/infra/launch.py hydra.run.dir=. exp_suffix=<EXPERIMENT_NAME> dataset=<DATASET_NAME> dataset.resolution=<DATASET_RESOLUTION> model.training.gamma=0.1 in FFHQ dataset, but I can not get reasonable results. Could you please provide configs for your training? Thanks for your help!

Talegqz avatar Jul 25 '22 08:07 Talegqz

Hi, thank you! Could you please tell whether you use the FFHQ dataset with pre-computed camera poses or without them? The FFHQ dataset which we use is located in configs/dataset/ffhq_posed.yaml

universome avatar Jul 27 '22 15:07 universome

Could you please tell in what way does the model fail for you? Does it fail to learn the texture or structure or both? If that's possible, can you please share your FID@2k plot?

universome avatar Jul 28 '22 02:07 universome

I'm having the same issue, using the FFHQ dataset you provided and the commands you showed in this Issue, FID_2k consistently stays at 433 for 5-7 first evaluation

bomcon123456 avatar Oct 10 '23 02:10 bomcon123456

It's hard to tell what is going wrong without digging deeper into your setup, for which I need more details. The Carver repo reproduced several 3D GAN papers, including ours, and they seem to have even better FID on FFHQ. I have not tried running their code, but maybe it's worth taking a look.

universome avatar Oct 13 '23 13:10 universome