On-Device ML using Flutter and TensorFlow Lite (pt.2): Consume your trained model in Flutter

This article is the second part of a two-part series on On-Device ML using Flutter. In this article, we focus on building the Flutter app that consumes the trained model. We create custom widgets such as TempSlideDetector, TempSlider, TempInfoDisplay, and TempMLDisplay to handle sliding events, display temperature values, and show the ML model's output. We also use Riverpod to manage state and broadcast updates to listening widgets. The article provides code examples and explanations for each widget.