ResNet50

[buaaswf]

Hi@Kaixhin, I am trying to improve the resnet34 to ResNet50, but I met the reshape problems File "/data2/FCN-semantic-segmentation_new/model.py", line 92, in forward x = self.relu(self.bn8(self.conv8(x + x2))) RuntimeError: The size of tensor a (256) must match the size of tensor b (64) at non-single

Cloud you please help me?

[Kaixhin]

The error message indicates that you haven't matched up the downsampled versions of the input with the upsampled versions. If you are using a different network as the backbone for segmentation, you will need to match these up properly. An easy way to do this is to put print('conv_y', x.size()) statements in the forward pass of your new resnet, and then see at which points these are.

[HPL123]

@buaaswf 你好，这个代码你跑通了吗？