-
-
Notifications
You must be signed in to change notification settings - Fork 1.7k
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
Pixel Shuffle layer #2563
Pixel Shuffle layer #2563
Conversation
Looks good to me. Just take care of the conflicts and I'll merge it. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Second approval provided automatically after 24 hours. 👍
Could you fix this once more? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Marking changes requested until build is fixed :)
Resolving the conflict here. |
Any clue regarding the failing tests on this one? |
Can you merge in or rebase against the latest master branch? |
Looks like this one is pretty close to ready---should I put it in the mlpack 3.4.2 milestone? I'm hoping to do a quick release in the next couple days. :) |
Yep, from my end, the implementation of this feature is complete. All it would need is pulling in the recent changes, before we can merge this. So, you can add it to the 3.4.2 milestone, yes :) |
Merged the latest master banch in, let's see if the CI pipeline comes back green. |
@zoq Can i take over this PR? |
It's fine with me if @abh2k would like to update the PR. I guess the only change would be in the serialize() method, right? |
Thanks. I will update the pr. |
Oh cool, since the followup, #2833 was merged, github automatically tagged this as merged too! |
Pixel Shuffle layer
To compare PyTorch/numpy implementation with mlpack/armadillo implementation of the functionality, check this Google Colab notebook.