tlpss/keypoint-detection

2D keypoint detection with Pytorch Lightning and wandb

40
/ 100
Emerging

This project helps computer vision practitioners detect specific points on objects or people within images. You input images along with corresponding 'keypoint' annotations (like joints on a person or corners of an object), and it outputs a trained model capable of locating these keypoints in new images. This tool is designed for computer vision engineers or researchers who need to precisely pinpoint features for tasks like pose estimation or object manipulation.

No commits in the last 6 months.

Use this if you need a flexible framework to train models for identifying specific points on various objects or subjects in images, especially if your dataset uses the COCO format.

Not ideal if you need a ready-to-use, pre-trained keypoint detection model without any training or customization.

computer-vision pose-estimation object-localization image-analysis robotics-perception
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

93

Forks

11

Language

Python

License

MIT

Last pushed

Jul 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tlpss/keypoint-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.