Machine learning isn’t only for the cloud. With Windows ML, you can integrate trained machine learning models in your Windows apps.
Overview
Windows ML allows you to use trained machine learning models in your Windows apps (C#, C++, and JavaScript). 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.

Develop

To build apps with Windows ML, you’ll:
- Get a trained ONNX model, or convert models trained in other ML frameworks into ONNX with WinMLTools.
- Add the ONNX model file to your app.
- Integrate the model into your app’s code.
- Run on any Windows device!
To see Windows ML in action, you can try out the sample apps in the Windows-Machine-Learning repo on Github. To learn more about using Windows ML, take a look through our documentation.
Ref
https://docs.microsoft.com