if i just want to seg one class，such as seg_list only have ’road‘.
Then i run train.py ,
in loss.py line 538,
in soft_tversky_score assert output.size() == target.size()
AssertionError
then i debug code,find output.size() = torch.Size([2, 1, 245760]) target.size() = torch.Size([2, 1, 491520])
Btw, I fixed this by using softmax for both binary and multi-class. While it is learnable, some advocate against this approach. I'll separate binary, multi-class and multi-label in #40.
xoiga123
commented
2 years ago
if i just want to seg one class，such as seg_list only have ’road‘. Then i run train.py , in loss.py line 538, in soft_tversky_score assert output.size() == target.size() AssertionError
then i debug code,find output.size() = torch.Size([2, 1, 245760]) target.size() = torch.Size([2, 1, 491520])
How to fix that???