prioritize batching for torchvision::nms
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
🚀 The feature
Implement batched nms!
Motivation, pitch
My motivation to create this issue was this warning:
[W BatchedFallback.cpp:84] Warning: There is a performance drop because we have not yet implemented the batching rule for torchvision::nms. Please file us an issue on GitHub so that we can prioritize its implementation. (function warnFallback)
Alternatives
No response
Additional context
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the torchvision::nms implementation and the batching-rule path referenced by the BatchedFallback warning. Determine the existing tests for NMS and add coverage for batched inputs; done means batched NMS is supported without the fallback performance warning.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100