This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

Deep learning gateway on Raspberry Pi and other edge devices

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

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

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

LFD is a big update upon LFFD. Generally, LFD is a multi-class object detector characterized by lightweight, low inference latency and superior precision. It is for real-world appilcations.

Helmut Hoffer von Ankershoffen experimenting with arm64 based NVIDIA Jetson (Nano and AGX Xavier) edge devices running Kubernetes (K8s) for machine learning (ML) including Jupyter Notebooks, TensorFlow Training and TensorFlow Serving using CUDA for smart IoT.

FedERA is a modular and fully customizable open-source FL framework, aiming to address these issues by offering comprehensive support for heterogeneous edge devices and incorporating both standalone and distributed computing. It includes new software modules to enhance usability and promote environ- mental sustainability.

The core runtime engine for Ambianic Edge devices.

Real-time speech enhancement mobile app using Nested U-Net

Automatic Over the Air Deployment of Improved Machine Learning Models to IoT Devices for Edge Processing

Python library for serverless Federated Learning experiments.

Code for paper "EdgeKE: An On-Demand Deep Learning IoT System for Cognitive Big Data on Industrial Edge Devices"

This repository is a PyTorch implementation of NIPS 2019 Paper "Shallow RNNs: A Method for Accurate Time-series Classification on Tiny Devices"

Yocto Project meta layer for EdgeX Foundry Services

Home Climate Control ESP32 based edge device firmware

Edge Computing using Tensorflow Lite

A list of production-ready models for resource-constrained devices.

Hub for the Radlet IOT ecosystem