Add RoI torchvision ops #1291
Merged
Add RoI torchvision ops #1291
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
majing921201
force-pushed
the
frost/torchvision_roi_ops
branch
from
8a8ee8f to
2968883
Compare
|
I fixed a bug in RoiAlign op where sampling_ratio wasn't being passed properly to the kernel. |
chunhuanMeng
approved these changes
Jan 21, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in 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Outdated suggestions cannot be applied.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.
Adds SYCL kernels for
roi_pool,ps_roi_pool, andps_roi_alignops, and registers them in torchvision. Code is adapted from existing CUDA kernels, with minimal changes, similar to the existingnmsandroi_alignops.Part of #1290
Testing
For testing, I copied the comprehensive ops test from torchvision repo. I removed the DefornConv test (support to come in a follow-up PR) and autocast xpu tests, since autocast registration in Pytorch would need to be updated.