tfjs

JavaScript API for face detection and face recognition in the browser and nodejs with tensorflow.js

Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

FaceAPI: AI-powered Face Detection & Rotation Tracking, Face Description & Recognition, Age & Gender & Emotion Prediction for Browser and NodeJS using TensorFlow/JS

Enhance Images with Javascript and AI. Increase resolution, retouch, denoise, and more. Open Source, Browser & Node Compatible, MIT License.

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.

👀 Use machine learning in JavaScript to detect eye movements and build gaze-controlled experiences.

微信小程序运行 TensorFlow 的 Demo

In-Browser Object Detection using Tiny YOLO on Tensorflow.js

Demo on adding virtual background to a live video stream in the browser

Github action that checks the toxicity level of comments and PR reviews to help make repos safe spaces.

Learning to track eye movement in the browser

Node.js module to predict indoor location using machine learning and WiFi information 📶

💫 Parallax effect in javascript using face tracking. An immersive view in 3d with webcam.

TensorFlow JS models for MIRNet for low-light💡 image enhancement

This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC/NCHW) -> TFLite (NHWC/NCHW). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflite and saved_model to .tflite and saved_model to onnx. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support.

Pytorch to Keras/Tensorflow/TFLite conversion made intuitive

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite, ONNX, OpenVINO, Myriad Inference Engine blob and .pb from .tflite. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support. Supports inverse quantization of INT8 quantization model.

tensorflowJS implementation of EfficientNet 🚀