You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Many GAN repos call calculate_fid_given_paths during training to monitor performance. We can train with n GPUS but have to pause all and run the validation with a single GPU, which is a speed bottleneck. Could it be distributed?
The text was updated successfully, but these errors were encountered:
Many GAN repos call calculate_fid_given_paths during training to monitor performance. We can train with n GPUS but have to pause all and run the validation with a single GPU, which is a speed bottleneck. Could it be distributed?
The text was updated successfully, but these errors were encountered: