SLEAP: Software framework for multi-animal pose tracking

[Andreas]

Social LEAP Estimates Animal Poses (SLEAP)

SLEAP is an open source deep-learning based framework for multi-animal pose tracking (Pereira et al., Nature Methods, 2022). It can be used to track any type or number of animals and includes an advanced labeling/training GUI for active learning and proofreading.

Publications

• Paper (Pereira et al., Nature Methods, 2022)
• Review on behavioral quantification (Pereira et al., Nature Neuroscience, 2020)

Abstract

We present Social LEAP Estimates Animal Poses (SLEAP), a machine learning system for multi-animal pose tracking. This system enables versatile workflows for data labeling, model training and inference on previously unseen data.

SLEAP features an accessible graphical user interface, a standardized data model, a reproducible configuration system, over 30 model architectures, two approaches to part grouping and two approaches to identity tracking.

We applied SLEAP to seven datasets across flies, bees, mice and gerbils to systematically evaluate each approach and architecture, and we compare it with other existing approaches.

Source code and documentation

• GitHub - talmolab/sleap: A deep learning framework for multi-animal pose tracking.
• GitHub - talmolab/sleap-io: Standalone utilities for SLEAP pose tracking data.
• https://sleap.ai/
• https://io.sleap.ai/

[Andreas]

P.S.: Einer der Autoren von VespAI, Thomas O’Shea-Wheller, hat mit SLEAP gearbeitet, siehe fix.