tinyml

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

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.

The Fastest Deep Reinforcement Learning Library

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

[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)