Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

The structure of the 3D KiUNet model is incorrect #25

Open
lee-zq opened this issue May 26, 2021 · 4 comments
Open

The structure of the 3D KiUNet model is incorrect #25

lee-zq opened this issue May 26, 2021 · 4 comments

Comments

@lee-zq
Copy link

lee-zq commented May 26, 2021

There are some problems with your 3D kiunet. I compared the code with your paper and found that the model details do not correspond. Maybe you should explain these questions. E.g: out = F.pad(out,[0,0,0,0,0,1]), scale_factor=(0.5,0.25,0.25),(0.5,0.0625,0.0625), (2,0.25,0.25) and so on.
I hope you can reply or update the correct code, Thanks

@JalexDooo
Copy link

The same problem!!

@dzzhang96
Copy link

@jeya-maria-jose
out1 = torch.add(out1,F.interpolate(F.relu(self.inte3_2bn(self.intere3_2(tmp))),scale_factor=(2,16,16),mode ='trilinear'))
RuntimeError: The size of tensor a (6) must match the size of tensor b (2) at non-singleton dimension 2

@AasiaRehman
Copy link

I am facing the same issue anybody solved it??
out= torch.add(out1,F.interpolate(F.relu(self.inte3_2bn(self.intere3_2(tmp))),scale_factor=(2,16,16),mode ='trilinear'))
RuntimeError: The size of tensor a (6) must match the size of tensor b (2) at non-singleton dimension 2

@zhouyizhuo
Copy link

Did you solve the problem? @JalexDooo @lee-zq @dzzhang96 @AasiaRehman @jeya-maria-jose
Seeking for your help~

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants