The NVIDIA Jetson range of devices are high performance, low power devices that run AI models on the edge using multiple PU cores.
You can compare the different Jetson devices on the Jetson Hardware page.
These devices can run the Azure IoT Edge runtime and host AI models trained in the cloud that do real-time computer vision inference. The results of this inference can then be sent to the cloud.
- Getting started with the Jetson Nano - a getting started guide from NVIDIA to get started with the Jetson Nano
- Intelligent edge hands-on-lab - this lab walks through the process of deploying an IoT Edge module to an Nvidia Jetson device to allow for detection of objects in YouTube videos, RTSP streams, Hololens Mixed Reality Capture, or an attached web cam.
- Intelligent video analytics with NVIDIA Jetson and Microsoft Azure - A repository demonstrating an end-to-end architecture for Intelligent Video Analytics using NVIDIA hardware with Microsoft Azure.
- Azure IoT Edge DeepStream Module with IoT Central - Demonstration using the the Nvidia DeepStream Module from the Azure Marketplace with Azure IoT Central.
- Azure IoT NVIDIA Jetson deepstream plug-and-play - a set of IoT PnP applications (nvidia-jetson-dcs & nvidia-jetson-dps) to enable remote interaction and telemetry for DeepStream on Nvidia Jetson Devices for use with Azure IoT Central.
- Azure IoT Edge Workshop: Visual Anomaly Detection over multiple cameras with NVIDIA Jetson Nano devices - a hands-on workshop showing how to build a solution that can process several real-time video streams with an AI model, how to build your own AI model to detect custom anomalies and finally how to operate it remotely.
- NVIDIA Deepstream + Azure IoT Edge on a NVIDIA Jetson Nano - a sample showing how to do real-time video analytics with NVIDIA Deepstream on a NVIDIA Jetson Nano device connected to Azure via Azure IoT Edge.
- Running a GPU enabled Azure Custom Vision Docker container on a Nvidia Jetson Nano - a guide going through the steps needed to run computer vision containers created with Microsoft Azure Custom Vision on a GPU enabled Nvidia Jetson Nano in a Docker Container.