PyTracking

A general python framework for training and running visual object trackers, based on PyTorch.

News: Upgraded to latest version of PyTorch (v1.x).

Highlights

ATOM

Official implementation of the ATOM tracker (CVPR 2019), including complete training code and trained models.

Tracking Libraries

Libraries for implementing and evaluating visual trackers. Including:

• All common tracking datasets.
• General building blocks, including optimization, feature extraction and utilities for correlation filter tracking.

Training Code

General framework for training networks for visual tracking.

• All common training datasets for visual tracking.
• Functions for data sampling, processing etc.
• Integration of ATOM models
• More to come ... ;)

Installation

Clone the GIT repository.

git clone https://github.com/visionml/pytracking.git

Clone the submodules.

In the repository directory, run the commands:

git submodule update --init  

Install dependencies

Run the installation script to install all the dependencies. You need to provide the conda install path (e.g. ~/anaconda3) and the name for the created conda environment (here pytracking).

bash install.sh conda_install_path pytracking

This script will also download the default networks and set-up the environment.

Note: The install script has been tested on an Ubuntu 18.04 system. In case of issues, check the detailed installation instructions.

Let's test it!

Activate the conda environment and run the script pytracking/run_webcam.py to run ATOM using the webcam input.

conda activate pytracking
cd pytracking
python run_webcam.py atom default    

What's next?

pytracking - for implementing your tracker

ltr - for training your tracker

Contributors

• Martin Danelljan
• Goutam Bhat