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

Depth other than 1 does not work #14

Open
B-lanc opened this issue May 21, 2022 · 0 comments · May be fixed by #15
Open

Depth other than 1 does not work #14

B-lanc opened this issue May 21, 2022 · 0 comments · May be fixed by #15

Comments

@B-lanc
Copy link

B-lanc commented May 21, 2022

Changing the depth to anything other than 1 will result in this error

RuntimeError: Given groups=1, weight of size [512, 512, 5], expected input[1, 1024, 357] to have 512 channels, but got 1024 channels instead

I am pretty certain this is the cause of said error

[ConvLayer(n_outputs, n_outputs, kernel_size, 1, conv_type) for _ in range(depth - 1)])

and
combined = conv(torch.cat([combined, centre_crop(upsampled, combined)], dim=1))

line 24 implies that the next modules will not take the shortcut (n_outputs as opposed to n_outputs+n_shortcut)
while line 38 adds the shortcut after the first iteration.

It should be either all post shortcut convs to take the added shortcut, or the shortcut is only added once. I think the latter makes more sense, though.

@B-lanc B-lanc linked a pull request Jun 1, 2022 that will close this issue
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

Successfully merging a pull request may close this issue.

1 participant