/hand_tracking

Minimal Python interface for Google's Mediapipe HandTracking pipeline

Primary LanguagePythonApache License 2.0Apache-2.0

Hand Tracker

Binder

Simple Python wrapper for Google's Mediapipe Hand Tracking pipeline.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Requirements

These are required to use the HandTracker module

numpy
opencv
tensorflow

To run the Jupyter demo you'll also need jupyter and matplotlib

Setup

Download models using load_models.sh, or load them manually from metalwhale's repo and put them inside models dir.

Anchors

To get the SSD anchors I've written a C++ program that executes the SsdAnchorsCalculator::GenerateAnchors function from this calculator. As there's no reason to modify provided anchors I do not include it into the repository, but you can find the script here

Acknowledgments

This work is a study of models developed by Google and distributed as a part of the Mediapipe framework.
Big thanks to @metalwhale for removing cusom operation dependencies.