A minimalist Deep Learning framework for embedded Computer Vision

Acoustic features (MFSCs and MFCCs) for edge AI

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

The Hailo PCIe driver is required for interacting with a Hailo device over the PCIe interface

Speech Recognition using STM32 and Machine Learning

Epsilon is a library with functions for machine learning and statistics written in plain C. It is intended to run on microcontrollers.

Mobilenet v1 (3,160,160, alpha=0.25, and 3,192,192, alpha=0.5) on STM32H7 using X-CUBE-AI v4.1.0

AutoEntangle (SmartTrap_V03) is an insect trap using FOMO (Edge Impulse) model, equipped with advanced features and minimal resources on the ESP-EYE, achieves an impressive 97% F1 Score in validation dataset, with an efficient mean processing time of 6 seconds per image and peak RAM usage of 2.4Mb per task!

Open source Python library for deploying deep learning model on Edge devices

Arduino TinyML project that uses a ML model to recognize digits in the camera feed, the model was trained using the MNIST dataset

Example Standalone for STM32F4 Nucleo boards using CMSIS toolbox

The official Edge Impulse firmware for PSoC63 (CY8CKIT-062-BLE)

Classifying workout exercises on an Arduino Nano 33 BLE Sense board.

A mnist classifier trained with Tinygrad running on $1 of compute (Raspberry Pi Pico | ArduCAM Pico4ML)

TinyMaix is a tiny inference library for microcontrollers (TinyML).