Deploy an ONNX model to a Windows device
| WinML and ONNX on Windows IoT Core | |
|
Windows 10 IoT Core is a version of Windows 10 that is optimized for smaller devices with or without a display that run on both ARM and x86/x64 devices. With Windows ML, developers can use trained ML models in Windows apps that are written in C#, C++, JavaScript, or Python, either locally on a Windows 10 device or on a Windows Server 2019 machine. |
|
| Solution example | |
| This example is based on a lab that was run at //Build conference in 2019. It show cases intelligent edge on Windows IoT Core operating system. In this lab you will download the ONNX model from Custom Vision, add some .NET components and deploy the model in a docker container to a device running Azure IoT Edge on Windows 10 IoT Core. Images will be captured from a camera on our edge device with inferencing happening at the edge using Windows ML and sending our results through Azure IoT Hub. Finally, we will visualize the results using Azure Time Series Insights. | |
|
Do the system setup preparations
Access the lab in GitHub to get started | |
Architecture
| |