Web components for making creative tools more accessible.

PoseNet Sketchbook is a collection of open source, interactive web experiments designed to allude to the artistic possibilities of using PoseNet (running on tensorflow.js) to create a relationship between movement and machine.

Play a Beat Saber clone with hand movements using Tensorflow.js & PoseNet

BlazePose - Super fast human pose detection on Tensorflow 2.x

Microsoft Engage 2021 - Video Conferencing Application

A personalized yoga trainer app based on Flutter and TensorFlow Lite.

Virtual walks in Google Street View using PoseNet and applying Deep Learning models to recognize actions.

I checked the performance by running PoseNet on CoreML

The baseline project for inferencing various Pose Estimation tflite models with TFLiteSwift on iOS

微信小程序下运行最新TensorFlowJS的解决方案

Virtual Try On site using HR-VITON. Anyone can try it using their own Image with clothes image.

Python ML library for people fall detection

📹🤸‍♂️🤾‍♀️🤺 PoseNet + OSC: send realtime human pose estimation data to your apps

Examples of Tensorflow Lite on Android

在微信小程序中运行TensorFlow模型

Flutter App real-time object detection with Tensorflow Lite

AI Exercise Rep Counter based on Google's Human Pose Estimation Library (Posenet)

Controlling Three.js 3D model over websockets with Tensorflow.js Posenet and SocketIO

[JS/TensorFlow] JavaScript library that implements machine learning-based models for human pose estimation and human movement analysis. It allows you to easily implement three neural network models for human pose estimation: MoveNet, PoseNet, and BlazePose. No Node.js is required. TensorFlowJS was used, and an example app is included.

AI在前端领域应用的Demo集合