Get started with ONNX Runtime for Windows

The ONNX Runtime Nuget package provides the ability to use the full WinML API. This allows scenarios such as passing a Windows.Media.VideoFrame from your connected camera directly into the runtime for realtime inference.

The WinML API is a WinRT API that shipped inside the Windows OS starting with build 1809 (RS5) in the Windows.AI.MachineLearning namespace. It embedded a version of the ONNX Runtime.

In addition to using the in-box version of WinML, WinML can also be installed as an application re-distributable package (see Direct ML Windows for technical details).

Contents

Windows OS integration

ONNX Runtime is available in Windows 10 versions >= 1809 and all versions of Windows 11. It is embedded inside Windows.AI.MachineLearning.dll and exposed via the WinRT API (WinML for short). It includes the CPU execution provider and the DirectML execution provider for GPU support.

The high level design looks like this:

ONNX + WinML layered architecture

API choice

You can choose to use either the WinRT API or the C API.

  WinRT C API
Type system Integration with Windows RT types Platform neutral types
Language support Language support via WinRT Projections Language support via per language projections
Tensorization Accepts VideoFrames and converts to tensors (support for CPU and GPU) Accepts tensors

Using the NuGet WinRT API with other C-API distributions

The WinRT API NuGet package is distributed with a specific version of ONNX Runtime, but apps can include their own version of ONNX Runtime (either a released version or a custom build). You may wish to do this to use non-default execution providers. To use your own version of ONNX Runtime, replace onnxruntime.dll with your desired version.

Back to top

Supported Versions

Windows 8.1+

Back to top

Builds

Artifact Description Supported Platforms
Microsoft.AI.MachineLearning WinRT - CPU, GPU (DirectML) Windows 8.1+

API Reference

Windows.AI.MachineLearning

Samples

Any code already written for the Windows.AI.MachineLearning API can be easily modified to run against the Microsoft.ML.OnnxRuntime package. All types originally referenced by inbox customers via the Windows namespace will need to be updated to now use the Microsoft namespace.

Should I use the in-box vs NuGet WinML version?

For a comparison, see Windows Machine Learning: In-box vs NuGet WinML solutions.

To detect if a particular OS version of Windows has the WinML APIs, use the IsApiContractPresent method. This can be called from either UWP or native apps.

If the OS does not have the runtime you need you can switch to use the redist binaries instead.

Release API contract version
Windows OS 1809 1
Windows OS 1903 2
Windows OS 1909 2
ORT release 1.2 3
ORT release 1.3 3
ORT release 1.4 3

See here for more about opsets and ONNX version details in Windows OS distributions.

Back to top