Segmentation Models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
At a glance
Is this tool relevant to you?
What it does
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
May suit
People building or extending an AI-powered product or workflow.
Before you try it
The repository reports a MIT license. Setup difficulty and device support still need to be checked upstream.
Evidence & freshness
What we know, and how recently we checked
This record comes from the wider automated directory. It has not yet passed the stronger catalog verification checks.
- Source
- Automated project sync
- Checked
- Evidence level
- Limited confidence
- Maintenance signal
- Healthy66/100
Generally healthy automated signals, with some areas worth checking in the breakdown.
The health score is an automated maintenance signal, not a security audit or a guarantee that the tool fits your needs.
How verification and health scoring work
⭐
11.7K
Stars
🍴
1.8K
Forks
👥
79
Contributors
💚
Healthy66/100
Health Score
Star History
Health Score Breakdown
Star Momentum
71
Commit Frequency
49
Issue Health
40
Contributors
100
Release Cadence
10
Documentation
100
Community Signal
100
Project Info
- Language
- Python
- License
- MIT
- Last Commit
- 1mo ago
- Last Release
- v0.5.0 (16mo ago)
- Open Issues
- 82
- Bus Factor
- 7
- Commits/Week
- 9.7
- Avg Issue Close
- 20.4 days
computer-visiondeeplab-v3-plusdeeplabv3dptfpnimage-processingimage-segmentationimagenetmodelspretrained-weightspspnetpytorchsegformersegmentationsegmentation-modelssemantic-segmentation
Project Badge
Embed a live health badge in a README or docs page.
[](https://ai-tools-scout.com/projects/segmentation-models-pytorch)Related tools to compare with Segmentation Models.pytorch
Suggested automatically from the same category and shared topics, then ordered by current maintenance and adoption signals.
Weekly AI open-source movers
Get the fastest-growing projects, useful MCP servers, and technical reads in one weekly email.