Windows ML allows you to use trained machine learning models in your Windows apps. The Windows ML inference engine evaluates trained models locally on Windows devices, removing concerns of connectivity, bandwidth, and data privacy. Hardware optimizations for CPU and GPU additionally enable high performance for quick evaluation results.
This extension is to help you get started using WinML APIs on UWP apps in VS2017 by generating a template code when you add a trained ONNX file of version up to 1.5 into the UWP project. From the template code you can load a model, create a session, bind inputs, and evaluate with wrapper codes. Note that using the template code is entirely optional and may not be the most optimal way to utilize WinML APIs, but it's there to help you get started.