Open PURSUETHESUN opened 3 months ago
Hello, you can check lines 28 to 29 in the vmunet.py
file. When the number of input image channels is 1, it will perform a repeat operation.
def forward(self, x):
if x.size()[1] == 1:
x = x.repeat(1,3,1,1)
logits = self.vmunet(x)
if self.num_classes == 1: return torch.sigmoid(logits)
else: return logits
While reproducing your multi-organ segmentation work, I noticed that the number of channels after image preprocessing is 1, which does not match the number of input channels (3) set in the source code you provided. Why is this?