Book Image

Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter

By : Anubhav Singh, Rimjhim Bhadani
Book Image

Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter

By: Anubhav Singh, Rimjhim Bhadani

Overview of this book

Deep learning is rapidly becoming the most popular topic in the mobile app industry. This book introduces trending deep learning concepts and their use cases with an industrial and application-focused approach. You will cover a range of projects covering tasks such as mobile vision, facial recognition, smart artificial intelligence assistant, augmented reality, and more. With the help of eight projects, you will learn how to integrate deep learning processes into mobile platforms, iOS, and Android. This will help you to transform deep learning features into robust mobile apps efficiently. You’ll get hands-on experience of selecting the right deep learning architectures and optimizing mobile deep learning models while following an application oriented-approach to deep learning on native mobile apps. We will later cover various pre-trained and custom-built deep learning model-based APIs such as machine learning (ML) Kit through Firebase. Further on, the book will take you through examples of creating custom deep learning models with TensorFlow Lite. Each project will demonstrate how to integrate deep learning libraries into your mobile apps, right from preparing the model through to deployment. By the end of this book, you’ll have mastered the skills to build and deploy deep learning mobile applications on both iOS and Android.

Related Content you might be interested in

Current Title:

Small book image
Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter
Anubhav Singh | Rimjhim Bhadani
Apr, 2020 | 380 pages
Small book image
Hands-On Python Deep Learning for the Web
Anubhav Singh | Sayak Paul
May, 2020 | 404 pages
Small book image
Google Flutter Mobile Development Quick Start Guide
Salvatore Giordano | Prajyot Mainkar
Mar, 2019 | 152 pages
Small book image
Flutter Cookbook
Simone Alessandria | Brian Kayfitz
Jun, 2021 | 646 pages
Table of Contents (13 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
1
Introduction to Deep Learning for Mobile
Introduction to Deep Learning for Mobile
Growth of AI-powered mobile devices
Understanding machine learning and deep learning
Introducing some common deep learning architectures
Introducing reinforcement learning and NLP
Methods of integrating AI on Android and iOS
Summary
Free Chapter
2
Mobile Vision - Face Detection Using On-Device Models
Mobile Vision - Face Detection Using On-Device Models
Technical requirements
Introduction to image processing
Developing a face detection application using Flutter
Summary
3
Chatbot Using Actions on Google
Chatbot Using Actions on Google
Technical requirements
Understanding the tools available for creating chatbots
Creating a Dialogflow account
Creating a Dialogflow agent
Understanding the Dialogflow Console
Creating your first action on Google
Creating Actions on a Google project
Implementing a Webhook
Deploying a webhook to Cloud Functions for Firebase
Creating an Action on Google release
Creating the UI for the conversational application
Integrating the Dialogflow agent
Adding audio interactions with the assistant
Summary
4
Recognizing Plant Species
Recognizing Plant Species
Technical requirements
Introducing image classification
Understanding the project architecture
Introducing the Cloud Vision API
Configuring the Cloud Vision API for image recognition
Using an SDK/tools to build a model
Creating a custom TensorFlow Lite model for image recognition
Creating a Flutter application
Running image recognition
Summary
5
Generating Live Captions from a Camera Feed
Generating Live Captions from a Camera Feed
Designing the project architecture
Understanding an image caption generator
Understanding the camera plugin
Creating a camera application
Generating image captions from the camera feed
Creating the material app
Summary
6
Building an Artificial Intelligence Authentication System
Building an Artificial Intelligence Authentication System
Technical requirements
A simple login application
Adding Firebase authentication
Understanding anomaly detection for authentication
A custom model for authenticating users
Implementing ReCaptcha for spam protection
Deploying the model in Flutter
Summary
7
Speech/Multimedia Processing - Generating Music Using AI
Speech/Multimedia Processing - Generating Music Using AI
Designing the project's architecture
Understanding multimedia processing
Developing RNN-based models for music generation
Deploying an audio generation API on Android and iOS
Summary
8
Reinforced Neural Network-Based Chess Engine
Reinforced Neural Network-Based Chess Engine
Introduction to reinforcement learning
Reinforcement learning in mobile games
Exploring Google's DeepMind
Alpha Zero-like AI for Connect 4
Underlying project architecture
Developing a GCP-hosted REST API for the chess engine
Creating a simple chess UI on Android
Integrating the chess engine API with a UI
Summary
9
Building an Image Super-Resolution Application
Building an Image Super-Resolution Application
Basic project architecture
Understanding GANs
Understanding how image super-resolution works
Creating a TensorFlow model for super-resolution
Building the UI for the application
Getting pictures from the device's local storage
Hosting a TensorFlow model on DigitalOcean
Integrating a hosted custom model on Flutter
Creating the Material app
Summary
10
Road Ahead
Road Ahead
Understanding recent trends in DL on mobile applications
Exploring the latest developments in DL on mobile devices
Exploring current research areas for DL in mobile apps
Summary
11
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
Appendix
Appendix
Setting up a deep learning environment on Cloud VM
Installing Dart SDK
Installing Flutter SDK
Configuring Firebase
Setting up VS Code

Designing the project's architecture

This project has a slightly different architecture to a regular deep learning project deployed as an app. We will have two different sets of samples of music. The first set of samples will be used to train an LSTM model that can generate music. The other set of samples will be used as a random input to the LSTM model, which will output the generated music samples. The LSTM-based model that we'll be developing and using later will be deployed on Google Cloud Platform (GCP). You can, however, deploy it on AWS or any other hosting of your choice.

The interaction between the different components that will be used in this project have been summarized in the following diagram:

The mobile application asks the model deployed on the server to generate a new music sample. The model uses a random music sample as input to...

Previous Section
End of Section 2
Next Section