# microsoft/Windows-Machine-Learning

Samples and Tools for Windows ML.

Repository: https://github.com/microsoft/Windows-Machine-Learning
Canonical: https://ross.abutalabs.com/products/windows-machine-learning
Homepage: https://docs.microsoft.com/en-us/windows/ai/
Language: C++
License: MIT
License Family: permissive
Topics: machine-learning, ai, ml, deep-learning, neural-network, onnx, windows, keras, tensorflow, coreml, scikit-learn, caffe2, pytorch, winmltools
Last push: 2025-08-07T17:04:54+00:00

## Health v2 (maintenance only)
Score: 39/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 35, release rhythm 8, longevity 100
- inputs: {"age_days": 3107, "days_push": 391, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1123, forks 442 (observed 2026-08-28T04:03:40.180479+00:00)

## What it is
Microsoft's Windows Machine Learning samples and tools repository, providing a high-performance ONNX inference API powered by ONNX Runtime and DirectML for Windows apps. It includes model samples, the WinmlRunner tool, and WinML Dashboard, though the legacy Windows.AI.MachineLearning namespace is superseded by the Windows App SDK APIs.

## Use cases
- run onnx models on windows with gpu acceleration
- integrate machine learning inference into a windows app
- test onnx model performance on windows hardware
- convert tensorflow or pytorch models for windows ml
- learn windows ml api through samples

## When to choose
- you need low-latency on-device inference in a Windows C++/C# application
- you want DirectML hardware acceleration across CPU, GPU, and NPU
- you need sample code and tooling for the Windows ML API

## When to avoid
- you target cross-platform deployment beyond Windows
- you want the newest Windows AI APIs, which live in the Windows App SDK instead
- you need training rather than inference

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, llm-inference, gpu-computing, sdk, developer-tools
- domain: machine-learning, deep-learning, windows, developer-tools
- platform: windows, cpp, c, python
- tags: onnx, directml, winml, inference, samples, nuget, windows-runtime

## Member repositories
- microsoft/Windows-Machine-Learning (main) score 39

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:40.180479+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:40:53.171362+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/Windows-Machine-Learning (fetched 2026-08-28T04:03:40.180479+00:00, sha 08fe924462b2)
  - homepage: https://docs.microsoft.com/en-us/windows/ai/ (fetched 2026-08-29T12:44:18.627918+00:00, sha 5bda90c3b459)
  - site_page: https://learn.microsoft.com/en-us/lifecycle/faq/internet-explorer-microsoft-edge (fetched 2026-08-29T12:44:18.637503+00:00, sha c363b2f43d4b)
  - site_page: https://learn.microsoft.com/en-us/windows/ai/faq (fetched 2026-08-29T12:44:18.639931+00:00, sha 9d06ef5a3275)
- Data as of 2026-08-30T08:39:29.467469+00:00.