What it does
DeepLabCut is a toolbox for pose estimation, which means finding and following body points like paws, noses or joints in video. It works without stickers or markers on the animal.
You label a few frames to show what you want to track, and it trains a model to do the rest. It also offers pretrained models for four-legged animals and for mice seen from above.
It has a graphical interface and a Python interface, and is widely used by life scientists studying behaviour.
Who it's for
Researchers in biology, neuroscience and animal behaviour.
Can I use it without coding?
With some setup. It has a graphical interface, but you install it with Python first. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Install Python and PyTorch, choosing the graphics card version if you have one.
- Install DeepLabCut with its graphical interface using Python's package installer.
- Follow the demo notebooks to label frames and train your first tracker.
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 (LGPL-3.0): Free to use, including for business; changes to the library itself must be shared.
- More on staying safe