783 Open source projects that are alternatives of or similar to Awesome Edge Machine Learning

Awesome machine learning model compression research papers, tools, and learning material.

Apache StreamPipes - A self-service (Industrial) IoT toolbox to enable non-technical users to connect, analyze and explore IoT data streams.

Azure IoT Edge

Extend cloud computing, data and service seamlessly to edge devices.

macchina.io IoT Edge Device SDK is a powerful C++ and JavaScript SDK for edge devices, IoT gateways and connected embedded systems.

Embedded and mobile deep learning research resources

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

Software to automate the management and configuration of any infrastructure or application at scale. Get access to the Salt software package repository here:

[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

A lightweight IoT edge analytics software

PaddleSlim is an open-source library for deep model compression and architecture search.

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

A CNCF Project to Bootstrap & Maintain Trust on the Edge / Cloud and IoT

Infrastructures™ for Machine Learning Training/Inference in Production.

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint

reference pytorch code for named entity tagging

Pruning and quantization for SSD. Model compression.

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

EVE is Edge Virtualization Engine

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

SDK for TEE AI Stick (includes model training script, inference library, examples)

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference

Industrial IoT Messaging and Device Management Platform

PyTorch Model Compression

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Simple document db made for infinitely scalable globally distributed reads.

Project Flogo is an open source ecosystem of opinionated event-driven capabilities to simplify building efficient & modern serverless functions, microservices & edge apps.

Secure sensor and gateway platform based on ESP8266 and ESP32

Android串口通信：抱歉，学会它真的可以为所欲为 ! ! !

The Firmware Security Testing Methodology (FSTM) is composed of nine stages tailored to enable security researchers, software developers, consultants, hobbyists, and Information Security professionals with conducting firmware security assessments.

Graph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow

揭秘 Zephyr OS

Collections of model quantization algorithms

Floorplan for Home Assistant

1btn (one button) uses the internet to complete a task with the simple, satisfying click of a single button. It connects to the internet over Wi-Fi to trigger whatever action you have assigned to it using a simple, online interface. One click, one task. It’s that simple. Unlike many other “Internet of Things” devices, 1btn does not maintain a continuous connection to the internet. Instead, it sleeps until it is pressed, then it connects to the internet, performs the assigned task, tells you the outcome via its multi-colored LEDs, and then returns to rest.

Vert.x MQTT

Open-source IoT Platform

A lightweight, embeddable scripting language

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Swifitch is ESP8266 based relay board that could be used to turn any light or any wall socket into smart one!

Open Source Lightweight Microservices Architecture for the Internet of Things. For developers.

🎨OpenIoTHub Server[内网穿透和物联网设备管理服务器]

Deep learning gateway on Raspberry Pi and other edge devices

Extraction tool for LG, Hisense, Sharp, Philips/TPV, Thompson and similar TVs/Embedded Devices

My Home Assistant Configuration 🏡🏡

🎁GateWay Client for OpenIoTHub[云易连访问内网端口和设备的网关]

oh~~

C implementation of the client-side OMA LwM2M protocol

《Zephyr OS 文档 - 中文版》

Interact with the browser using the Freedrum sensors in JavaScript

[NeurIPS 2020] Code release for paper "Deep Multimodal Fusion by Channel Exchanging" (In PyTorch)

All open source file and project for OpenFPGAduino project

AT component porting or samples for different devices

Official Docker Image for ioBroker

An open-source time-series SQL database optimized for fast ingest and complex queries. Packaged as a PostgreSQL extension.

Arduino Sketches that use ThingSpeak Web Services and API