qubvel-org/segmentation_models.pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

81
/ 100
Verified

This tool helps machine learning engineers and researchers build and train advanced image segmentation models more efficiently. You provide raw image data and desired segmentation masks, and it outputs a ready-to-use neural network model capable of identifying and outlining specific objects or regions within new images. It’s for anyone working on computer vision tasks that require precise object localization.

11,398 stars. Used by 1 other package. Actively maintained with 53 commits in the last 30 days. Available on PyPI.

Use this if you need to develop highly accurate image segmentation models for tasks like medical imaging analysis, autonomous driving, or satellite imagery processing, and you want to leverage pre-trained architectures for faster development.

Not ideal if your primary goal is simple object detection (bounding boxes) or image classification, as this tool is specifically designed for pixel-level segmentation.

computer-vision medical-imaging autonomous-vehicles remote-sensing image-analysis
Maintenance 22 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

11,398

Forks

1,832

Language

Python

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

53

Dependencies

8

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/qubvel-org/segmentation_models.pytorch"

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