Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

A flexible, high-performance serving system for machine learning models

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Caffe: a fast open framework for deep learning.

Future versions with model training module will be maintained through a forked version here: https://github.com/seasalt-ai/snowboy

ONNX-TensorRT: TensorRT backend for ONNX

Embedded Learning Library

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

Benchmarking Deep Learning operations on different hardware

Open source 5G UE and RAN (gNodeB) implementation.

Parameter server framework for distributed machine learning

Pytorch C++ Library

pytrec_eval is an Information Retrieval evaluation tool for Python, based on the popular trec_eval.

This is a sample showing how to do real-time video analytics with NVIDIA DeepStream connected to Azure via Azure IoT Edge. It uses a NVIDIA Jetson Nano device that can process up to 8 real-time vid…

Small utility to check CUDA memory on Mac

Anomaly Detection on Time-Evolving Streams in Real-time. Detecting intrusions (DoS and DDoS attacks), frauds, fake rating anomalies.

This project is a simple deep neural network trained using only TensorFlow C++.

Azure Percept DK advanced topics

This is an example how to run a TensorFlow object detection model as web server in TensorFlow C++ API.

Build an application that alerts you when someone enters a restricted area. Learn how to use models for multiclass object detection.