pytorch / pytorch/vision

Use stable sort in nms

Open
#4,488 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement module: ops
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🚀 The feature

Please use stable sort in nms since torch1.9 has supported stable sort.

Motivation, pitch

Why we need stable sort:
In quantization model, many score are equal due to quantization, so when using unstable sort, the result of nms is non-reproducible.

Alternatives

No response

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the NMS implementation and its sorting call in the PyTorch Vision codebase. Check existing NMS tests, then verify that equal quantized scores produce deterministic results when stable sorting is used.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.