Question about up-convolution block

[xzhhzx]

Here in line 106: https://github.com/mattmacy/vnet.pytorch/blob/a00c8ea16bcaea2bddf73b2bf506796f70077687/vnet.py#L106

Should it be xcat = self.ops(xcat) instead? Thank you in advance!

[andreys42]

@xzhhzx Hi, It should if we going to follow original paper diagram, but it will raise error since "Element-wise sum" operation will not able to sum 256 and 128 channels ...

[LiB98]

maybe torch.cat(), expand the channels of the output?