Question about up-convolution block

mattmacy / vnet.pytorch

A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

https://mattmacy.github.io/vnet.pytorch

BSD 3-Clause "New" or "Revised" License

688 stars 201 forks source link

Question about up-convolution block #28

Open xzhhzx opened 4 years ago

xzhhzx commented 4 years ago

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 commented 3 years ago

@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 commented 1 year ago

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