tf-lite

Open-Source AI Camera. Empower any camera/CCTV with state-of-the-art AI, including facial recognition, person recognition(RE-ID) car detection, fall detection and more

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

This repository contains the trained models and some audio samples for the tPLCnet.

Iranian debit card (credit card) real-time scanner using Deep Learning and TensorFlow Lite for Android.

TensorFlow Quantization Example, for TensorFlow Lite

Parse TF-Lite Model File in C++

This repository, "Autonomous Driving System On Various Platforms", details the exploration and implementation of autonomous driving systems across platforms such as AirSim, Android, Raspberry Pi 4, and Nvidia's Jetson Nano, utilizing Lidar, image processing, and machine learning technologies.

A real-time object detection model on Raspberry Pi 4

Vite, TypeScript, UniCli, Vue3. RealTime Human body posture detection in the WeChat MiniProgram, supporting PoseNet, MoveNet, BlazePose models. Support WeChat front and rear camera switching, FPS callback, frame-by-frame detection result callback

In this repository, you will receive information (notebooks) of TensorFlow model optimization using TensorRT and TF-Lite. You will be able to: Understand the fundamentals of optimization using TF-TRT and TF-Lite, deploy deep learning models by reduced precision (FP32, FP16 and INT8) on the inference stage and calibrate the weights

Smart Trunk Opener based on radar data using time series predection AI

Tomato leaf disease prediction

Android sms spam detection app

Android application for Herbalens, Bangkit Acadey 2023 Product Based Capstone Project

Third Submission in Dicoding Machine Learning Path

A Scalable CAPTCHA solving Solution using CNN's

Face Mask Detection App using CameraX & Tensorflow Lite

This is a Machine Learning (Deep Learning) project that aims to classify satellite pictures into classes of lands

TF lite is for ML inside android with no loss in accuracy.