qubvel-org/segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
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.
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.
Recent Releases
Related models
tue-mps/eomt
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
OSUPCVLab/SegFormer3D
Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image...
jeya-maria-jose/Medical-Transformer
Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image...
davidiommi/Pytorch--3D-Medical-Images-Segmentation--SALMON
Segmentation deep learning ALgorithm based on MONai toolbox: single and multi-label segmentation...
lambdavi/SatDrive-SegFL
MLDL '23 Project: Federated Learning and Semantic Segmentation for Autonomous Driving and...