France1/unet-multiclass-pytorch

Multiclass semantic segmentation using U-Net architecture combined with strong image augmentation

34
/ 100
Emerging

This project helps researchers and image analysts automatically identify and outline different objects within images, even with limited labeled examples. You provide images and their corresponding masks (outlines of objects), and it produces a model that can then predict detailed segmentation masks for new, unseen images. It's designed for someone who needs precise object boundary detection in complex images.

No commits in the last 6 months.

Use this if you need to segment multiple types of objects in images, especially when you have a small dataset of labeled examples, and require robust results through advanced augmentation.

Not ideal if you are looking for a simple object classification or detection system, or if you have a very large, well-labeled dataset where simpler models might suffice.

image-analysis biomedical-imaging materials-science quality-control remote-sensing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

62

Forks

14

Language

Jupyter Notebook

License

Last pushed

Feb 08, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/France1/unet-multiclass-pytorch"

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