ML: ML.NET: deep dive into dev AI
summary
Live coding shows ML.NET building a sentiment classifier from 40,000 Wikipedia comments using MLContext, text FeaturizeText, an 80/20 train/test split and SDCA logistic regression that reports 94.65% accuracy on the test split; code creates a PredictionEngine and runs sample predictions. A second demo loads a Tiny YOLOv2 ONNX model (416×415 RGB input) to produce bounding boxes for 20 classes in a simple web app, with Netron used to inspect network layers.
AI-written summary · about
chapters (8)
- 0:00Introduction to ML.NET
- 15:26Live coding setup
- 19:44Data structures and setup
- 28:46Building the ML pipeline
- 31:14Training and evaluating model
- 36:16Making predictions
- 40:25Deep learning model demo
- 44:32Q&A and summary
related talks
58mExploring Machine Learning for .Net Developers
59mMachine Learning in .NET (ML.NET)
01h 04mIntroduction to ML.NET
46mMachine Learning for .NET Developers
50mA Pragmatic Deep Dive into ML.NET
57mMachine Learning Made Easy – An Introduction to ML.NET
01h 03mMachine learning for C# developers: Introducing ML
42mStep into Machine Learning .NET