What it does
Segmentation Models PyTorch (SMP) helps programmers build image segmentation models. Segmentation means the AI labels every pixel in a picture, for example marking which pixels are road, car or sky.
It offers a dozen well-known model designs and hundreds of pre-trained starting points, so you don't have to train everything from zero. Its makers say a model can be created in two lines of code.
It also includes common ways to measure accuracy, and models can be exported for use in other software.
Who it's for
Developers and researchers working on medical images, satellite photos, self-driving or other vision projects.
Can I use it without coding?
Developers only. This is a Python library for people who write and train their own models. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe