Yifan Jiang

Thanks!

I might need to rerun that experiment as it's hard to find it in my messy local files. I don't have much resource currently but I will do it when...

Did you use distributed training mode? This code only works on distributed training mode even on a single gpu. If you changed this setting you might meet this problem that...

what's your batch size and what's the number of gpu you used?

@Nanboy-Ronan What's your batch size?

@Nanboy-Ronan one gpu is not able to train it. But if you still one to train it, you should tune your batch size to a much smaller size.

Hi, thanks for your interests. 1. Custom dataset will be very easy, you can just use celeba dataloader and save your data in a specific directory. 2. Currently it does...

@meh-naz 1. This is a GAN model. cifar_checkpoint onl works for cifar 2. For training on your on dataset, you need to write custom dataloader and keep the other part...

Thanks so much! I'll fix it soon

yeah, training GAN is comparably tricky, I would suggest you to go with AutoGAN's repo and run the experiments, make sure you get the reasonable FIDs and then replace AutoGAN's...