Open wwlCape opened 4 years ago
Very sorry for the delayed reply. This is due to the stride of conv and devonc layers. You may need to modify the input size to a number can be divided by 4.
feature[s]['lv2_1'] = encoder[s]['lv2'](images['lv2_1'] + residual[s]['lv3_top']) + feature[s]['lv3_top']
RuntimeError: The size of tensor a (2508) must match the size of tensor b (2512) at non-singleton dimension 3
The image size was 2508x1672 which is divisible by 4, but I got this error.
hello, thanks for your great work, I want to test my 800x450 image, but some error raises up:
RuntimeError: The size of tensor a (225) must match the size of tensor b (228) at non-singleton dimension 2
Could you tell me how to address this problem? Thanks a lot!