Microsoft announces ML.NET 0.6 improved prediction performance

Microsoft announces ML.NET 0.6 Machine Learning .NET improved prediction performance

Today Microsoft announce latest monthly release: ML.NET 0.6! ML.NET is a cross-platform, open source machine learning framework for .NET developers. We want to enable every .NET developer to train and use machine learning models in their applications and services. If you haven’t tried ML.NET yet, here’s how you can get started!

What’s new in ML.NET 0.6 (Machine Learning .NET)

• New API for building and using machine learning models: Our main focus was releasing the first iteration of new ML.NET APIs for building and consuming models. These new, more flexible, APIs enable new tasks and code workflow that weren’t possible with the previous LearningPipeline API. We are starting to deprecate the current LearningPipeline API.

• Ability to score pre-trained ONNX Models: Many scenarios like Image Classification, Speech to Text, and translation benefit from using predictions from deep learning models. In ML.NET 0.5 we added support for using TensorFlow models. Now in ML.NET 0.6 we’ve added support for getting predictions from ONNX models.
• Significant performance improvements for model prediction, .NET type system consistency, and more: We know that application performance is critical. In this release, we’ve increased getting model predictions performance 100x or more.
  • Additional enhancements include:
    • improvements to ML.NET TensorFlow scoring
    • more consistency with the .NET type-system
    • having a model deployment suitable for serverless workloads like Azure Functions