All Projects → vignetteapp → Akihabara

vignetteapp / Akihabara

Licence: MIT license
A pure .NET port for Google Mediapipe, inspired of MediaPipeUnity.

Programming Languages

C#
18002 projects
C++
36643 projects - #6 most used programming language
Starlark
911 projects
c
50402 projects - #5 most used programming language
java
68154 projects - #9 most used programming language
python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to Akihabara

ue4-mediapipe-plugin
UE4 MediaPipe plugin
Stars: ✭ 159 (+657.14%)
Mutual labels:  mediapipe
Face-Mask
Real time webcam face detection, protect yourself from COVID19 with a virtual mask
Stars: ✭ 64 (+204.76%)
Mutual labels:  mediapipe
mediapipe-osc
MediaPipe examples which stream their detections over OSC.
Stars: ✭ 26 (+23.81%)
Mutual labels:  mediapipe
Streamlit-Applications
Deep Learning and Computer Vision Applications using Streamlit
Stars: ✭ 55 (+161.9%)
Mutual labels:  mediapipe
modelbox
A high performance, high expansion, easy to use framework for AI application. 为AI应用的开发者提供一套统一的高性能、易用的编程框架,快速基于AI全栈服务、开发跨端边云的AI行业应用。
Stars: ✭ 48 (+128.57%)
Mutual labels:  mediapipe
Sport-With-AI
The human body is detected with the help of the Mediapipe library. Then, using the mathematical methods applied, it is determined how much the exercise count is done.
Stars: ✭ 85 (+304.76%)
Mutual labels:  mediapipe
EyeCommander
An open source computer vision interface that tracks eye movements for individuals with severely-limited mobility.
Stars: ✭ 41 (+95.24%)
Mutual labels:  mediapipe
mediapipe plus
The purpose of this project is to apply mediapipe to more AI chips.
Stars: ✭ 38 (+80.95%)
Mutual labels:  mediapipe
backscrub
Virtual Video Device for Background Replacement with Deep Semantic Segmentation
Stars: ✭ 691 (+3190.48%)
Mutual labels:  mediapipe
SignLanguageRecognition
Real-time Recognition of german sign language (DGS) with MediaPipe
Stars: ✭ 77 (+266.67%)
Mutual labels:  mediapipe
depthai hand tracker
Running Google Mediapipe Hand Tracking models on Luxonis DepthAI hardware (OAK-D-lite, OAK-D, OAK-1,...)
Stars: ✭ 284 (+1252.38%)
Mutual labels:  mediapipe
yeelight-hand-controller
With Yeelight Hand Controller you can turn on and off your Yeelight just with a finger snap and change the brightness intensity raising or lowering your hand.
Stars: ✭ 41 (+95.24%)
Mutual labels:  mediapipe
BlazePoseBarracuda
BlazePoseBarracuda is a human 2D/3D pose estimation neural network that runs the Mediapipe Pose (BlazePose) pipeline on the Unity Barracuda with GPU.
Stars: ✭ 131 (+523.81%)
Mutual labels:  mediapipe
Mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
Stars: ✭ 15,338 (+72938.1%)
Mutual labels:  mediapipe
gestop
A tool to navigate the desktop with hand gestures. Builds on mediapipe.
Stars: ✭ 20 (-4.76%)
Mutual labels:  mediapipe
UnityHandTrackingWithMediapipe
Realtime hand tracking and finger tracking in Unity using Mediapipe
Stars: ✭ 129 (+514.29%)
Mutual labels:  mediapipe
ai-virtual-mouse
Developed an AI-based system to control the mouse cursor using Python and OpenCV with the real-time camera. Fingertip location is mapped to RGB images to control the mouse cursor.
Stars: ✭ 59 (+180.95%)
Mutual labels:  mediapipe

Deprecation Note

This library has been superseded by MediaPipe.NET, which has a more cleaner take to the library. As such, MediaPipe.NET is a natural evolution from Akihabara's codebase and is much more predictable and maintainable. We will no longer provide maintenance to Akihabara.

Akihabara

Akihabara is Vignette's pure .NET port of Mediapipe, based on Junrou Nishida's MediaPipeUnity project.

Getting Started

Almost everything is done via the build.py script, so run this first. This will fetch the Mediapipe source, apply patches and finally compile the glue library + Mediapipe itself in one nifty small library. However, you will still need to do the dotnet side, which is just a matter of dotnet build after getting setup.py done.

Keep in mind Mediapipe supports both CPU and GPU so you will need to compile as such based on what you need:

If you want CPU (Recommended)

python3 build.py build --desktop cpu -vv

If you want GPU (Experimental, doesn't work yet!)

python3 build.py build --desktop gpu --vv

Prerequisites

  • Python 3.9 (We tried it with 3.8 but for some odd reason things were broken for this build. PRs welcome to fix this though!)
  • .NET 5.0 or .NET 6.0 LTS
  • GCC-9 (GCC-10 also works but not guranteed to work since Mediapipe uses a lot of deprecated syntax).
  • Bazel
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].