Lightning-AI / Lightning-AI/torchmetrics
Add OKS metric
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 526
- Avg merge
- 6d 11h
- Merged PRs (30d)
- 5
Description
## 🚀 Feature
Add support for keypoints inside [torchmetrics map](https://torchmetrics.readthedocs.io/en/stable/detection/mean_average_precision.html#).
### Additional context
Should be fairly simple to do that using the [iou_type](https://github.com/Lightning-AI/metrics/blob/master/src/torchmetrics/detection/mean_ap.py#L314) flag, since [torchmetrics map](https://torchmetrics.readthedocs.io/en/stable/detection/mean_average_precision.html#) is built upon [pycocotools](https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocotools/cocoeval.py#L110).
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 with src/torchmetrics/detection/mean_ap.py, especially the iou_type handling referenced in the issue, and compare it with pycocotools/cocoeval.py. Confirm the documented mean average precision integration and define done as torchmetrics map supporting keypoint evaluation through an appropriate keypoint setting.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100