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, when reading the code, I found that "torch.mm(K.t(),a)" is used in perform_sinkhorn function. Does that mean only 2D correlation tensor can be processed per time. But in most cases, corretation tensor is 3D or 4D tensor.
The text was updated successfully, but these errors were encountered:
Hi, when reading the code, I found that "torch.mm(K.t(),a)" is used in perform_sinkhorn function. Does that mean only 2D correlation tensor can be processed per time. But in most cases, corretation tensor is 3D or 4D tensor.
The text was updated successfully, but these errors were encountered: