tinyml

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

Header-only library for using Keras models in C++.

Machine Learning inference engine for Microcontrollers and Embedded devices

This is a list of interesting papers and projects about TinyML.

TensorFlow Lite models for MIRNet for low-light image enhancement.

Spying on Microcontrollers using Current Sensing and embedded TinyML models

This is the TinyML programs for ESP32 according to BlackWalnut Labs Tutorials. (黑胡桃实验室的TinyML教程中的程序集合)

This repository shows how to train a custom detection model with the TFOD API, optimize it with TFLite, and perform inference with the optimized model.

CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices

Launched in March 2020 in response to the coronavirus disease 2019 (COVID-19) pandemic, COVID-Net is a global open source, open access initiative dedicated to accelerating advancement in machine learning to aid front-line healthcare workers and clinical institutions around the world fighting the continuing pandemic. Towards this goal, our global multi-disciplinary team of researchers, developers, and clinicians have made publicly available a suite of tailored deep neural network models for tackling different challenges ranging from screening to risk stratification to treatment planning for patients with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Furthermore, we have made available fully curated, open access benchmark datasets comprised of some of the largest, most diverse patient cohorts from around the world.

Repo and code of the paper: Train++: An Incremental ML Model Training Algorithm to Create Self-Learning IoT Devices (paper under review)

Containerization for TinyML Applications on Tiny devices.

A tinyML system using a Raspberry Pi Pico and TensorFlow Lite for Microcontrollers to detect loud talking. It can be utilized to encourage people to eat quietly to prevent the spread of the coronavirus and help in the fight against COVID

A tool to support using classification models in low-power and microcontroller-based embedded systems.

Code for paper: 'ML-MCU: A Framework to Train ML Classifiers on MCU-based IoT Edge Devices' (paper under review)

Magic Wand using ESPectro32 or other ESP32 boards, powered by TensorFlow Lite for Microcontrollers and PlatformIO

The EEMBC EnergyRunner application framework for the MLPerf Tiny benchmark.

MicroSpeech Wake Word example on the Raspberry Pi Pico. This is a port of the example on the TensorFlow repository.

Tiny Trainable Instruments is a collection of media arts instruments using tiny machine learning, and based on microcontrollers.

The TinyML "Hello World" sine wave model on Arduino Uno v3

TinyML for STM32F407 using different frameworks in C and C++ with Keil uVision IDE.

Repo of the demo paper: TinyML Benchmark: Executing Fully Connected Neural Networks on Commodity Microcontrollers

TensorFlow Lite C/C++ library for microcontrollers.

Recognize spoken words on device using an Adafruit EdgeBadge and a TinyML model

Motor Activity Detection using TensorFlow Lite on Arduino Nano 33 BLE board

Car state detection (normal, accident, idle) for RP2040/Pico board, using TinyML and Edge Impulse

A scheme for privacy-preserving learning on Tiny Devices.

Final Project for Harvard's Tiny Machine Learning Course (CS249R).

Embedded playground base on nrf52840-customer-board. Zephyr, tensorflow lite micro, and so on.