mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

android audio-processing c-plus-plus calculator computer-vision deep-learning framework graph-based graph-framework inference machine-learning mediapipe mobile-development perception pipeline-framework stream-processing video-processing

Go to file

MediaPipe Team fcb23fd99d Project import generated by Copybara. PiperOrigin-RevId: 254337988		2019-06-20 23:05:07 -07:00
mediapipe	Project import generated by Copybara.	2019-06-20 23:05:07 -07:00
third_party	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
.bazelrc	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
.dockerignore	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
BUILD	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
CONTRIBUTING.md	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
Dockerfile	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
LICENSE	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
README.md	Project import generated by Copybara.	2019-06-20 23:05:07 -07:00
setup_android_sdk_and_ndk.sh	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
setup_opencv.sh	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00
WORKSPACE	Project import generated by Copybara.	2019-06-16 16:06:57 -07:00

README.md

We will be presenting at CVPR 2019 on June 17~20 in Long Beach, CA. Come join us!

MediaPipe is a framework for building multimodal (eg. video, audio, any time series data) applied ML pipelines. With MediaPipe, a perception pipeline can be built as a graph of modular components, including, for instance, inference models (e.g., TensorFlow, TFLite) and media processing functions.

Installation

Follow these instructions.

Getting started

See mobile and desktop examples.

Documentation

MediaPipe Read-the-Docs.

Visualizing MediaPipe graphs

A web-based visualizer is hosted on MediaPipe Visualizer. Please also see instructions here.

Publications

MediaPipe: A Framework for Building Perception Pipelines (draft)

Contributing

We welcome contributions. Please follow these guidelines.

We use GitHub issues for tracking requests and bugs. Please post questions to the MediaPipe Stack Overflow with a 'mediapipe' tag.