Mingdong Wu

Looking forward to offical TPU-version BigGAN code~

1

Hi ajbrock, Thanks for open-source BigGAN code, which benefits a lot on other explore of BigGAN. But considering the cost of time, we hope to train biggan on TPU, so...

I wonder wether you have test your code on imagenet? Imagenet results shown in ReadMe seems to be directly drawn from paper, while the celebA's are not. I'd like to...

After running 300K on TPU, we didn't achieve satisfactory results.

6

We run **'launch_train_tpu_sagan.sh' on V3 pod for 300k steps, but it seems to collapse from 10k. And the generation quality is not good, i wonder wether you've managed to achieve...