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


Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804