A question about the implementation in pytorch
Closed this issue · 1 comments
Tangzy7 commented
Hi, the way you implement siamese network is like that:
output1,output2 = model(x0, x1)
loss = criterion (output1,output2)
And here is the another way:
output1 = model.forward_once(x0)
output2 = model.forward_once(x1)
loss = criterion (output1,output2)
Are they different?
harveyslash commented
They are the same