Introduction to Machine Learning Systems

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

A curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.

Unofficial implementation of MobileNetV3 architecture described in paper Searching for MobileNetV3.

Soft Threshold Weight Reparameterization for Learnable Sparsity

Workshop showcasing how to run defect detection using computer vision at the edge with Amazon SageMaker

Identification of handwritten digit from images taken by a  OV7670 camera module connected to a Raspberry Pi Pico and a 120x160 TFT LCD display. The Pi Pico running CircuitPython handles everything from image acquisition to post-processing and inference. This code is somewhat experimental, but it is fun to play with. For more information, please…

A tool to support using classification models in low-power and microcontroller-based embedded systems.

Android application recognizing digits using quantized 8-bit MobileNetV3.

Realtime image classification in Unity Engine.

PyTorch Mobile starter kit.

Measure the speed of your machine learning models on real devices!

Protect your Machine Learning model in your Flutter application.

Modified inference engine for quantized convolution using product quantization

Running VAEs on mobile and IOT devices using TFLite.