introduce trilinear upsampling #315
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The CUDA part of this belongs in NNlibCUDA.jl |
|
Ööhm it should be, isn‘t it? :) |
|
Seems like you are based on an old commit, NNlibCUDA now is here https://github.com/FluxML/NNlibCUDA.jl |
|
Oh I see. Why did you move it out? Now I have to make 2 forks, 2 branches, 2 PRs and the possibility of version incompatibilities arises. |
|
yeah, I agree, I wanted to keep it here in fact but didn't get much support #300 |
|
Just updated this PR. NNlibCUDA will follow. |
|
For completeness I just added the CPU implementation as well. Lots of duplicate code, but works. |
|
this looks ready, should we merge it @maxfreu ? |
|
You can if you want to :) FluxML/NNlibCUDA.jl#5 is also ready. Or should I squash everything into one commit first? |
92 tasks
# for free
to join this conversation on GitHub.
Already have an account?
# to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi everybody!
This introduces trilinear (3D) upsampling on GPU. Maybe we can rethink the dispatch; I think the code can be deflated by smart choices.