Yilun Xu

Me too. I guess another repo https://github.com/eriklindernoren/PyTorch-GAN makes life much easier :)

Face the same issue here. Adding the following code solves the problem for me. ``` gpus = tf.config.list_physical_devices('GPU') if gpus: try: # Currently, memory growth needs to be the same...

I observed the FID of EDM fluctuates largely. Did you report the lowest FID among checkpoints?

I observe that such resize operation would change the FID score significantly.

Hi Michael, Please use the `--config.eval.save_images` flag in the command line, as well as setting the eval batch size `--config.eval.batch_size` to 64. Generated images would be saved to `eval_dir/ode_images_{ckpt}.png`. Please...

For command line of restoration of existing models, please see the Checkpoint section in README.

Hi, It seems that the snippet only contains partial error message. Could you please provide full one? Thanks. In addition, we recommend using our latest model PFGM++ for research projects...

Hi, Sorry for the huge delay. The code works for general dataset. Our method does not have the capability for idetifying the clean set. However, we prove that training with...

Hi, We will release the checkpoint in the near future, as you requested. Stay tuned :). Best, Yilun

HI, I guess the label for `real_logit_disc' is 1, as in loss_disc = 0.5 * ( sigmoid_xent(real_logit_disc, torch.ones_like(real_logit_disc, device='cuda')) + sigmoid_xent(fake_logit_disc, torch.zeros_like(fake_logit_disc, device='cuda')) ) , and the label for 'real_logit'...