DeepLabCut/DeepLabCut

Health v2 · maintenance only

Adoption not part of the score

5745 stars · 1788 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

DeepLabCut is an open-source Python toolbox for markerless 2D and 3D pose estimation of user-defined body parts using deep neural networks and transfer learning. It works across species including humans and animals, requiring only 50-200 labeled frames for training, and includes a GUI, model zoo, and multi-animal tracking support.

Use cases

• track animal body parts in videos without physical markers
• estimate 3D pose from multi-camera video
• label and annotate video frames for pose training
• analyze animal behavior in neuroscience experiments
• track multiple animals simultaneously in a video
• detect human pose keypoints from video

When to choose

• you need markerless pose tracking for animals or humans with minimal training data
• you want a well-established, research-validated tool with a model zoo and GUI
• you need multi-animal or 3D pose estimation from video

When to avoid

• you need real-time pose estimation on low-power edge devices
• you only need simple object detection or tracking rather than fine-grained keypoints
• you cannot use GPU acceleration for training or inference

Facets

library · maturity stable

machine-learning deep-learning computer-vision image-processing video-processing ui-components computer-vision machine-learning deep-learning bioinformatics healthcare robotics data-science python cross-platform windows pose-estimation keypoint-detection animal-behavior markerless-tracking neuroscience labeling-tool transfer-learning multi-animal-tracking 3d-pose gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="DeepLabCut/DeepLabCut")