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

Replace deconvolutional upsampling in decoder with nearest upsampling plus convs #44

Closed
daniel-j-h opened this issue Jun 21, 2018 · 1 comment

Comments

@daniel-j-h
Copy link
Collaborator

At the moment we upsample with a scaling factor of two in the decoder by using deconvolutions (transposed convolutions). Instead we should use the following simpler approach which should work just as well an not have the segmentation mask checker board problem:

  • upsample in nearest neighbor mode
  • add convolutions after upsampling

We could also switch the order first doing convolution on the low-res feature maps in case we need to save some memory. But I don't think that's a constraint we have right now.

bkowshik added a commit that referenced this issue Jul 3, 2018
Uses pretrained ResNet for U-Net encoder, closes #45 and #44
@daniel-j-h
Copy link
Collaborator Author

This landed with #46.

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

1 participant