Lightning-AI / Lightning-AI/torchmetrics

Pose estimation metrics

Open
#3,026 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement New metric
Dominant language
Python
Stars
2.5k
Forks
526
Avg merge
6d 11h
Merged PRs (30d)
5

Description

## 🚀 Feature

### Motivation

Currently torchmetrics doesn't support any metrics for pose estimation, example AP for pose estimation which is used for COCO and reported in all pose estimation code/papers such as:
https://github.com/facebookresearch/sapiens
https://github.com/Tau-J/rtmlib

### Pitch
Let's add pose estimation metrics to torchmetrics to make it more feature rich

### Alternatives

One alternative for users is to write the metric themselves

I can work on this if agreed

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

No source file, test, or entry point is identified. Start by reviewing the existing torchmetrics metric structure and the pose-estimation AP use cases linked in the issue, then clarify which metrics and COCO behavior are required. Done should mean an agreed, implemented pose-estimation metric scope with corresponding validation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.