Dev Inspiration Roundup: Your one stop shop to Windows Machine Learning
Need some app inspiration? Check out our roundup of #DevInspiration links to help you start developing for #Windows10. This week we’re highlighting resources and materials to help get you started with Windows Machine Learning (Windows ML). Let’s jump in!
Getting Started
Windows Machine Learning allows you to use trained machine learning models in your applications. The platform evaluates trained models locally on Windows 10 devices, providing hardware-accelerated performance by leveraging the device’s CPU or GPU, and computes evaluations for both classical ML algorithms and Deep Learning.
Need a refresher? Check out this link containing an intro to machine learning and how to start developing with Windows ML.
- Get started — Create your first Windows ML app with this step-by-step tutorial.
- How to train a model — Train a model for Windows ML using Visual Studio Tools for AI.
- Convert existing ML models to ONNX— To use Windows ML, you’ll need a pre-trained machine learning model in the Open Neural Network Exchange (ONNX) format.
- Integrate a model into your app— Integrate a model into your app by following the load, bind, and evaluate pattern.
Windows ML Samples on GitHub
The following sample UWP apps demonstrate how to use Windows ML. The best part? They’re available to download from the Windows-Machine-Learning repo on GitHub!
- MNIST Multilayer Perceptron — This simple UWP application uses MNIST, a trained machine learning model, to recognize a numeric digit drawn by the user. For step-by-step instructions on how to create this sample, see the Get Started with Windows ML tutorial.
- SqueezeNet Image Classifier — This UWP application uses SqueezeNet, a pre-trained machine learning model, to detect the predominant object in an image selected by the user from a file. This sample demonstrates the use of the Windows.AI.MachineLearning.Preview API to load a model, bind an input image and an output tensor, and evaluate a binding.
- Windows Machine Learning Explorer — Windows ML Explorer is a sample app that you can use to bootstrap ML models to be evaluated with Windows ML. Currently, the app includes a circuit board defect detection model that can detect defects on images and a real-time camera feed of a printed circuit board.
*Bonus Content*
Want an overview of what Windows ML can do for you? Take a look at this blog post, showing you how three lines of code and Windows Machine Learning empower .NET developers to run AI locally on Windows 10 devices.
Speaking of AI, Visual Studio Tools for AI is an extension that supports deep learning frameworks, including:
You can also use additional deep learning frameworks via the open architecture. Visual Studio Tools for AI use existing code support for Python, C/C++/C#, and supplies additional support for Cognitive Toolkit BrainScript!
To learn more about developing for Windows 10, see more here!
