Skip to content

Latest commit

 

History

History
15 lines (11 loc) · 994 Bytes

README.md

File metadata and controls

15 lines (11 loc) · 994 Bytes

DeepLabCut-Demo

DeepLabCut is a state-of-the-art pose estimation tool, allowing researchers to annotate videos, train models, and refine their annotations within one workflow. Here you can find a couple of demos to try it out.

Demo: Creating a New DeepLabCut Project and Using the Annotation Tool

Does not work on Google Colab - you will have to install DeepLabCut on your own machine. See installation instructions at the bottom.

annotation_setup_demo.ipynb

Demo: Training DeepLabCut on Labeled Data

Meant to be executed in Google Colab

gpu_training_demo.ipynb

Local Install Instructions

Detailed installation instructions can be found here

These demos were largely based on those found on the DeepLabCut GitHub Page. Be sure to check it out for more tutorials and detailed documentation!