Book Image

Xamarin.Forms Projects - Second Edition

By : Daniel Hindrikes, Johan Karlsson
Book Image

Xamarin.Forms Projects - Second Edition

By: Daniel Hindrikes, Johan Karlsson

Overview of this book

Xamarin.Forms is a lightweight cross-platform development toolkit for building apps with a rich user interface. Improved and updated to cover the latest features of Xamarin.Forms, this second edition covers CollectionView and Shell, along with interesting concepts such as augmented reality (AR) and machine learning. Starting with an introduction to Xamarin and how it works, this book shares tips for choosing the type of development environment you should strive for when planning cross-platform mobile apps. You’ll build your first Xamarin.Forms app and learn how to use Shell to implement the app architecture. The book gradually increases the level of complexity of the projects, guiding you through creating apps ranging from a location tracker and weather map to an AR game and face recognition. As you advance, the book will take you through modern mobile development frameworks such as SQLite, .NET Core Mono, ARKit, and ARCore. You’ll be able to customize your apps for both Android and iOS platforms to achieve native-like performance and speed. The book is filled with engaging examples, so you can grasp essential concepts by writing code instead of reading through endless theory. By the end of this book, you’ll be ready to develop your own native apps with Xamarin.Forms and its associated technologies, such as .NET Core, Visual Studio 2019, and C#.
Table of Contents (13 chapters)

Building the Hot Dog or Not Hot Dog application using machine learning

Let's get started! We will first train a model for image classification that we can use later in the chapter to decide whether a photo contains a hot dog.

Training a model

To train a model for image classification, we need to collect photos of hot dogs and photos that aren't of hot dogs. Because most items in the world are not hot dogs, we need more photos that don't contain hot dogs. It's better if the photos of hot dogs cover a lot of different hot-dog scenarios—with bread, with ketchup, or with mustard. This is so the model will be able to recognize hot dogs in different situations. When we are collecting photos that aren't of hot dogs, we also need to have a big variety of photos that are both of items that are similar to hot dogs and that are completely different from hot dogs.

The model that is in the solution on GitHub was trained with 240 photos, 60 of which were of hot dogs...