Machine Learning Systems

Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK. Python, C# and JS(WASM) bindings available.

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

A lightweight header-only library for using Keras (TensorFlow) models in C++.

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.

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

The Fastest Deep Reinforcement Learning Library

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

Machine Learning inference engine for Microcontrollers and Embedded devices

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

vendor independent TinyML deep learning library, compiler and inference framework microcomputers and micro-controllers

Seeed SenseCraft Model Assistant is an open-source project focused on embedded AI. 🔥🔥🔥

Zant simplifies the deployment and optimization of neural networks on microprocessors

Instructions, source code, and misc. resources needed for building a Tiny ML-powered artificial nose.

Neural Networks with low bit weights on low end 32 bit microcontrollers such as the CH32V003 RISC-V Microcontroller and others

Notes on Machine Learning on edge for embedded/sensor/IoT uses

Code for MobiCom paper 'TinyML-CAM: 80 FPS Image Recognition in 1 Kb RAM'

In this repository you will find TinyML course syllabi, assignments/labs, code walkthroughs, links to student projects, and lecture videos (where applicable).

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)

A robust and efficient TinyML inference engine.

A research library for pytorch-based neural network pruning, compression, and more.

Machine Learning and Digital Signal Processing for MicroPython

Rune provides containers to encapsulate and deploy edgeML pipelines and applications

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

This repository holds the Google Colabs for the EdX TinyML Specialization

Building Simple versions of AI (ML, DL, NN) models from scratch to help grasp the concepts

在ESP32上实现基于红外热成像阵列传感器的手势识别

Spying on Microcontrollers using Current Sensing and embedded TinyML models

A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on TinyML — the intersection of machine learning and ultra-low-power embedded systems.

Neural-Kalman GNSS/INS Navigation for Precision Agriculture