Open lonelylingoes opened 4 years ago
Maybe you can have a try to modify the parameter 'crop-size' to 512. Or you can modify the size of input tensors yourself.
RuntimeError: The size of tensor a (1552) must match the size of tensor b(1548) at non-singleton dimension 1
Hi, when I train the model dfanet, it comes the error, at the core/models/dfanet.py line 77: fusion = fusion + stage1_fca_decoder + stage2_fca_decoder + stage3_fca_decoder RuntimeError: The size of tensor a (120) must match the size of tensor b(128) at non-singleton dimension 3. Is there something wrong?