https://github.com/google-ai-edge/mediapipe

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

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Committers with academic emails
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (11.3%) to scientific vocabulary

Keywords

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

Keywords from Contributors

deep-neural-networks distributed jax fuzz-testing fuzzing oss-fuzz stability vulnerabilities reinforcement-learning autograd

Last synced: 5 months ago · JSON representation

Repository

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

Basic Info

Host: GitHub
Owner: google-ai-edge
License: apache-2.0
Language: C++
Default Branch: master
Homepage: https://ai.google.dev/edge/mediapipe
Size: 576 MB

Statistics

Stars: 31,184
Watchers: 522
Forks: 5,516
Open Issues: 591
Releases: 0

Topics

Created over 6 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License

README.md

layout: forward target: https://developers.google.com/mediapipe title: Home

nav_order: 1

Attention: We have moved to https://developers.google.com/mediapipe as the primary developer documentation site for MediaPipe as of April 3, 2023.

MediaPipe

Attention: MediaPipe Solutions Preview is an early release. Learn more.

On-device machine learning for everyone

Delight your customers with innovative machine learning features. MediaPipe contains everything that you need to customize and deploy to mobile (Android, iOS), web, desktop, edge devices, and IoT, effortlessly.

Get started

You can get started with MediaPipe Solutions by by checking out any of the developer guides for vision, text, and audio tasks. If you need help setting up a development environment for use with MediaPipe Tasks, check out the setup guides for Android, web apps, and Python.

Solutions

MediaPipe Solutions provides a suite of libraries and tools for you to quickly apply artificial intelligence (AI) and machine learning (ML) techniques in your applications. You can plug these solutions into your applications immediately, customize them to your needs, and use them across multiple development platforms. MediaPipe Solutions is part of the MediaPipe open source project, so you can further customize the solutions code to meet your application needs.

These libraries and resources provide the core functionality for each MediaPipe Solution:

MediaPipe Tasks: Cross-platform APIs and libraries for deploying solutions. Learn more.
MediaPipe models: Pre-trained, ready-to-run models for use with each solution.

These tools let you customize and evaluate solutions:

MediaPipe Model Maker: Customize models for solutions with your data. Learn more.
MediaPipe Studio: Visualize, evaluate, and benchmark solutions in your browser. Learn more.

Legacy solutions

We have ended support for these MediaPipe Legacy Solutions as of March 1, 2023. All other MediaPipe Legacy Solutions will be upgraded to a new MediaPipe Solution. See the Solutions guide for details. The code repository and prebuilt binaries for all MediaPipe Legacy Solutions will continue to be provided on an as-is basis.

For more on the legacy solutions, see the documentation.

Framework

To start using MediaPipe Framework, install MediaPipe Framework and start building example applications in C++, Android, and iOS.

MediaPipe Framework is the low-level component used to build efficient on-device machine learning pipelines, similar to the premade MediaPipe Solutions.

Before using MediaPipe Framework, familiarize yourself with the following key Framework concepts:

Community

Slack community for MediaPipe users.
Discuss - General community discussion around MediaPipe.
Awesome MediaPipe - A curated list of awesome MediaPipe related frameworks, libraries and software.

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.

Resources

Publications

Bringing artworks to life with AR in Google Developers Blog
Prosthesis control via Mirru App using MediaPipe hand tracking in Google Developers Blog
SignAll SDK: Sign language interface using MediaPipe is now available for developers in Google Developers Blog
MediaPipe Holistic - Simultaneous Face, Hand and Pose Prediction, on Device in Google AI Blog
Background Features in Google Meet, Powered by Web ML in Google AI Blog
MediaPipe 3D Face Transform in Google Developers Blog
Instant Motion Tracking With MediaPipe in Google Developers Blog
BlazePose - On-device Real-time Body Pose Tracking in Google AI Blog
MediaPipe Iris: Real-time Eye Tracking and Depth Estimation in Google AI Blog
MediaPipe KNIFT: Template-based feature matching in Google Developers Blog
Alfred Camera: Smart camera features using MediaPipe in Google Developers Blog
Real-Time 3D Object Detection on Mobile Devices with MediaPipe in Google AI Blog
AutoFlip: An Open Source Framework for Intelligent Video Reframing in Google AI Blog
MediaPipe on the Web in Google Developers Blog
Object Detection and Tracking using MediaPipe in Google Developers Blog
On-Device, Real-Time Hand Tracking with MediaPipe in Google AI Blog
MediaPipe: A Framework for Building Perception Pipelines

Videos

YouTube Channel

Owner

Name: google-ai-edge
Login: google-ai-edge
Kind: organization

Repositories: 1
Profile: https://github.com/google-ai-edge

Committers

Last synced: 10 months ago

All Time

Total Commits: 4,345
Total Committers: 97
Avg Commits per committer: 44.794
Development Distribution Score (DDS): 0.521

Past Year

Commits: 890
Committers: 43
Avg Commits per committer: 20.698
Development Distribution Score (DDS): 0.385

Top Committers

Name	Email	Commits
MediaPipe Team	m**m@g**m	2,080
Sebastian Schmidt	m**t@g**m	566
Prianka Liz Kariat	p**t@y**m	394
Prianka Liz Kariat	p**t@c**m	319
kinaryml	k**r@y**m	202
Jiuqiang Tang	j**g@g**m	171
kuaashish	9****h	134
Camillo Lugaresi	c**l@g**m	61
Wai Hon Law	w**e@g**m	48
Yuqi Li	y**i@g**m	30
Alan Kelly	a**y@g**m	27
Hadon Nash	h**n@g**m	23
Youchuan Hu	y**u@g**m	22
Dmitri Gribenko	d**g@g**m	21
Nikolay Chirkov	c**v@g**m	20
Kinar R	4****l	19
Mark McDonald	m**d@g**m	15
Yishuang Pang	y**g@g**m	14
Mohammadreza Heydary	m**y@g**m	12
Joe Zou	z**j@g**m	11
Chris McClanahan	c**n@g**m	8
Khanh LeViet	k**g@g**m	7
vrabaud	v**d@g**m	6
Fergus Henderson	f**s@g**m	6
T.J. Alumbaugh	t**u@g**m	5
Grant Jensen	g**n@g**m	4
Daniel Cheng	d**g@g**m	4
Chunlei Niu	n**l@g**m	4
Zu Kim	z**m@g**m	4
Liam Miller-Cushon	c**n@g**m	4
and 67 more...

Committer Domains (Top 20 + Academic)

google.com: 78 ymedialabs.com: 2 teladochealth.com: 1 hpcnt.com: 1 tanotech.jp: 1 codeandtheory.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 806
Total pull requests: 153
Average time to close issues: 2 months
Average time to close pull requests: 3 months
Total issue authors: 641
Total pull request authors: 72
Average comments per issue: 3.98
Average comments per pull request: 0.76
Merged pull requests: 35
Bot issues: 0
Bot pull requests: 4

Past Year

Issues: 386
Pull requests: 97
Average time to close issues: 14 days
Average time to close pull requests: 10 days
Issue authors: 301
Pull request authors: 38
Average comments per issue: 1.85
Average comments per pull request: 0.45
Merged pull requests: 21
Bot issues: 0
Bot pull requests: 3

View more stats

Top Authors

Issue Authors

trailyunkel (11)
jhlibra (7)
yiyinglai (6)
RansomBroker (5)
gzhhong (5)
matanox (5)
akau16 (4)
llamauser (4)
ChristianNSchmitz (4)
adblock25 (4)
ly0303521 (4)
Criminal-9527 (4)
JC3 (3)
jinpengfei (3)
ly15927086342 (3)

Pull Request Authors

priankakariatyml (31)
kuaashish (7)
definability (4)
JamesJang26 (4)
dependabot[bot] (4)
PeterPocsi (4)
Ioann44 (4)
hr-cosnet (4)
xKHUNx (4)
j20001970 (3)
jk4e (3)
haiggoh (2)
XingRay (2)
joacopaz (2)
ruitaocc (2)

Top Labels

Issue Labels

stat:awaiting response (210) stale (188) type:support (160) platform:python (154) type:build/install (152) type:bug (115) type:feature (84) type:others (74) platform:android (72) platform:javascript (71) os:windows (66) os:linux-non-arm (65) stat:awaiting googler (65) task::all (47) platform:c++ (47) task:LLM inference (47) legacy:hands (42) type:modelmaker (40) task:face landmarker (38) os:macOS (38) task:pose landmarker (33) platform:ios (30) legacy:face mesh (24) legacy:pose (23) gpu (23) task:hand landmarker (21) platform::android (15) task:face detection (14) task:image segmentation (14) task:object detection (14)

Pull Request Labels

dependencies (4) stale (3) platform:python (3) stat:awaiting response (3) type:support (3) type:build/install (2) platform:android (2) type:others (2) type:docs-bug (2) type:bug (1) type:performance (1) task:face landmarker (1) os:linux-non-arm (1) task:holistic landmarker (1) type:feature (1) legacy:hands (1) type:modelmaker (1) task:object detection (1) python (1)

Packages

Total packages: 1
Total downloads: unknown

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 54

proxy.golang.org: github.com/google-ai-edge/mediapipe

Documentation: https://pkg.go.dev/github.com/google-ai-edge/mediapipe#section-documentation
License: apache-2.0
Latest release: v0.10.26
published 8 months ago

Versions: 54
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.1%

Average: 6.3%

Dependent repos count: 6.5%

Last synced: 6 months ago

Dependencies

.github/workflows/stale.yaml actions

actions/stale v7 composite

Dockerfile docker

ubuntu 20.04 build

mediapipe/examples/android/solutions/build.gradle maven

mediapipe/examples/android/solutions/facedetection/build.gradle maven

androidx.appcompat:appcompat 1.3.0 implementation
androidx.constraintlayout:constraintlayout 2.0.4 implementation
androidx.exifinterface:exifinterface 1.3.3 implementation
com.google.android.material:material 1.3.0 implementation
com.google.mediapipe:facedetection latest.release implementation
com.google.mediapipe:solution-core latest.release implementation

mediapipe/examples/android/solutions/facemesh/build.gradle maven

androidx.appcompat:appcompat 1.3.0 implementation
androidx.constraintlayout:constraintlayout 2.0.4 implementation
androidx.exifinterface:exifinterface 1.3.3 implementation
com.google.android.material:material 1.3.0 implementation
com.google.mediapipe:facemesh latest.release implementation
com.google.mediapipe:solution-core latest.release implementation

mediapipe/examples/android/solutions/hands/build.gradle maven

androidx.appcompat:appcompat 1.3.0 implementation
androidx.constraintlayout:constraintlayout 2.0.4 implementation
androidx.exifinterface:exifinterface 1.3.3 implementation
com.google.android.material:material 1.3.0 implementation
com.google.mediapipe:hands latest.release implementation
com.google.mediapipe:solution-core latest.release implementation

mediapipe/tasks/web/package.json npm

package.json npm

@bazel/jasmine ^5.7.2 development
@bazel/rollup ^5.7.1 development
@bazel/typescript ^5.7.1 development
@rollup/plugin-commonjs ^23.0.2 development
@rollup/plugin-node-resolve ^15.0.1 development
@rollup/plugin-terser ^0.1.0 development
@types/google-protobuf ^3.15.6 development
@types/jasmine ^4.3.1 development
@types/node ^18.11.11 development
@types/offscreencanvas ^2019.7.0 development
google-protobuf ^3.21.2 development
jasmine ^4.5.0 development
jasmine-core ^4.5.0 development
protobufjs ^7.1.2 development
protobufjs-cli ^1.0.2 development
rollup ^2.3.0 development
ts-protoc-gen ^0.15.0 development
typescript ^4.8.4 development

yarn.lock npm

180 dependencies

mediapipe/model_maker/requirements.txt pypi

absl-py *
mediapipe >=0.10.0
numpy *
opencv-python *
tensorflow >=2.10
tensorflow-addons *
tensorflow-datasets *
tensorflow-hub *
tensorflow-text *
tf-models-official >=2.13.1

mediapipe/model_maker/setup.py pypi

requirements.txt pypi

absl-py *
attrs >=19.1.0
flatbuffers >=2.0
matplotlib *
numpy *
opencv-contrib-python *
protobuf >=3.11,<4
sounddevice >=0.4.4

setup.py pypi