DonaldsonDLC

Using markerless pose estimation to quantify mating bouts. The project uses a convolutional neural network to analyze mating videos and return a csv formatted file of poses. This file is then processed using a python script and graphed to show the covariation of movement between two voles. When complete, this project will save the lab hours of time which previously would have been used to hand mark each video.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

Run in a windows 10 environment using Anaconda 4.7.5 and python 3.7.3

• Deep Lab Cut

  • Download Instructions

• Python 3

  • Download

• Anaconda

  • Download

Installing

Hello World!

Deployment

Additional notes about how to deploy this on a live system

Python 3.7.3
conda 4.7.5

Built With

• Anaconda - Platform
• Visual Studio Code - IDE
• Python 3 - Code Language
• DeepLabCut - Markerless pose estimator

Versioning

I use vole related versioning. For the versions available, see the tags on this repository. No Current Versions Available

Authors

• Chase Dudas - ML/Scripts/Analysis - Personal GitHub

License

This project is not licensed

Acknowledgments

• Nath, Mathis et al, 2019
• David Protter w/ Donaldson Lab