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

Added PixelShuffle Operation #735

Closed
wants to merge 3 commits into from

Conversation

shreyas-kowshik
Copy link
Contributor

Added Pixel Shuffle Operation used frequently in super-resolution networks for up-sampling.

@DhairyaLGandhi
Copy link
Member

DhairyaLGandhi commented Apr 15, 2019

I think this makes more sense as a function. We aren't exactly storing any parameters, so as long as the Ops are differentiable, we should be good. Thanks for adding this!

@shreyas-kowshik
Copy link
Contributor Author

shreyas-kowshik commented Apr 16, 2019

@dhairyagandhi96 So where do you suggest moving this file to? I had initially modified conv.jl thinking it would make more sense to put it in there as all convolution related functions would be together.
This was in analogy to pytorch where the module is added in torch.nn.modules.PixelShuffle.

@DhairyaLGandhi
Copy link
Member

I would put this in perhaps in NNlib.jl.

@shreyas-kowshik
Copy link
Contributor Author

@dhairyagandhi96 Added it here : FluxML/NNlib.jl#112

@ToucheSir
Copy link
Member

We can close this now that #1468 is merged :)

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 this pull request may close these issues.

3 participants