yassouali/pytorch-segmentation

:art: Semantic segmentation models, datasets and losses implemented in PyTorch.

51
/ 100
Established

This project helps scientists and researchers in fields like medical imaging or autonomous driving to precisely outline objects within images. It takes raw images and their corresponding pixel-level annotations (telling the system what each pixel represents, e.g., 'tumor', 'road', 'sky') and trains models to automatically identify and highlight specific regions. The output is a highly accurate model capable of segmenting new, unseen images, delineating boundaries of objects with pixel-perfect precision.

1,814 stars. No commits in the last 6 months.

Use this if you need to train a robust image segmentation model from scratch or fine-tune an existing one, and require detailed control over models, datasets, and training parameters.

Not ideal if you are looking for a pre-trained, off-the-shelf solution for common objects without needing to train on custom datasets.

biomedical-imaging autonomous-driving aerial-imagery-analysis scene-understanding image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,814

Forks

393

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 23, 2025

Commits (30d)

0

Get this data via API

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

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