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
Hi @1211sh, this code is used for initializing the feature extractor networks and auxiliary optimizers, instead of the multi-gpu training. The code is based on the CUT.
Hi,
I am wondering how the multi-gpu process works in the line 102 and 103.
Line 102 : self.real_A = self.real_A[:bs_per_gpu]
I think self.real_A[:bs_per_gpu] is just simply removing a part of self.real_A, not working as spliting data for multi-gpu.
Is it a typo? or am I wrong?
The text was updated successfully, but these errors were encountered: