sniklaus/pytorch-hed

a reimplementation of Holistically-Nested Edge Detection in PyTorch

50
/ 100
Established

This project helps computer vision researchers and practitioners accurately detect all edges within an image. You provide an input image, and it outputs a new image highlighting the detected edges. This is useful for anyone working on tasks like object recognition, image segmentation, or scene understanding.

521 stars. No commits in the last 6 months.

Use this if you need to precisely identify boundaries and contours in your images for further analysis or processing.

Not ideal if you need an exact replication of the original Caffe-based HED implementation, as this version has slight differences in performance.

computer-vision image-processing edge-detection image-analysis segmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

521

Forks

110

Language

Python

License

GPL-3.0

Last pushed

Jan 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sniklaus/pytorch-hed"

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