Microsoft Windows Machine Learning* (WINML)

Published: 05/22/2019  

Last Updated: 05/22/2019


Use this high-performance, reliable API to run machine learning inferences on Windows devices and trained machine models in Windows apps that are written in C#, C++, or JavaScript*. WinML is the broad ecosystem AI solution for PCs. Applications are power efficient and high performing using hardware optimizations for Intel® processors (CPU) with Intel® Graphics Technology (GPU) and accelerators, such as the Intel® Movidius™ Vision Processing Unit (VPU).

Learn More

Work with Open Neural Network Exchange (ONNX*)

WinML evaluates models in the ONNX* format—an open format for machine learning models. It allows you to interchange models between various machine learning frameworks and tools.

ONNX Information

Supported Tools

Get the Models

WinMLTools (an extension of ONNXMLTools and TF2ONNX) enables you to convert machine learning models created with different training frameworks into the ONNX format.

Convert Models


Create a Machine Learning Application (C#)

Learn to build a simple Universal Windows Platform application that uses a trained machine learning model to recognize a numeric digit drawn by the user.

Tutorial: Windows Machine Learning for the Desktop (C++)

Create a simplified version of the SqueezeNet object detection sample.


Product and Performance Information


Performance varies by use, configuration and other factors. Learn more at