ResidualAttentionNetwork-pytorch icon indicating copy to clipboard operation
ResidualAttentionNetwork-pytorch copied to clipboard

Errors when I run train.py

Open KrystalCWT opened this issue 4 years ago • 2 comments

File "/home//ResidualAttentionNetwork-pytorch-master/Residual-Attention-Network/model/attention_module.py", line 249, in forward out_interp3 = self.interpolation3(out_softmax3) + out_softmax2 RuntimeError: The size of tensor a (14) must match the size of tensor b (2) at non-singleton dimension 3

KrystalCWT avatar Dec 21 '20 08:12 KrystalCWT

any solution found regarding this?

alakhrasSandy avatar Apr 10 '21 19:04 alakhrasSandy

Found the issue from my case it was that i didnt resize/scale in the transformer , ( transforms.Scale(224) )

alakhrasSandy avatar Apr 11 '21 02:04 alakhrasSandy