Intelligent Mobile Projects with TensorFlow: Build 10 Wide-Ranging Apps with TensorFlow Mobile and Lite for iOS, Android, and Raspberry Pi

✍ Scribed by Jeff Tang

• Publisher: Packt Publishing
• Year: 2018
• Tongue: English
• Leaves: 396
• Category: Library

✦ Synopsis

Create Deep Learning and Reinforcement Learning apps for multiple platforms with TensorFlow

Key Features

• Build TensorFlow-powered AI applications for mobile and embedded devices
• Learn modern AI topics such as computer vision, NLP, and deep reinforcement learning
• Get practical insights and exclusive working code not available in the TensorFlow documentation

Book Description

As a developer, you always need to keep an eye out and be ready for what will be trending soon, while also focusing on what's trending currently. So, what's better than learning about the integration of the best of both worlds, the present and the future? Artificial Intelligence (AI) is widely regarded as the next big thing after mobile, and Google's TensorFlow is the leading open source machine learning framework, the hottest branch of AI. This book covers more than 10 complete iOS, Android, and Raspberry Pi apps powered by TensorFlow and built from scratch, running all kinds of cool TensorFlow models offline on-device: from computer vision, speech and language processing to generative adversarial networks and AlphaZero-like deep reinforcement learning. You’ll learn how to use or retrain existing TensorFlow models, build your own models, and develop intelligent mobile apps running those TensorFlow models. You'll learn how to quickly build such apps with step-by-step tutorials and how to avoid many pitfalls in the process with lots of hard-earned troubleshooting tips.

What you will learn

• Classify images with transfer learning
• Detect objects and their locations
• Transform pictures with amazing art styles
• Understand simple speech commands
• Describe images in natural language
• Recognize drawing with Convolutional Neural Network and Long Short-Term Memory
• Predict stock price with Recurrent Neural Network in TensorFlow and Keras
• Generate and enhance images with generative adversarial networks
• Build AlphaZero-like mobile game app in TensorFlow and Keras
• Use TensorFlow Lite and Core ML on mobile
• Develop TensorFlow apps on Raspberry Pi that can move, see, listen, speak, and learn

Who This Book Is For

If you're an iOS/Android developer interested in building and retraining others' TensorFlow models and running them in your mobile apps, or if you're a TensorFlow developer and want to run your new and amazing TensorFlow models on mobile devices, this book is for you. You'll also benefit from this book if you're interested in TensorFlow Lite, Core ML, or TensorFlow on Raspberry Pi.

Table of Contents

1. Getting Started with Mobile TensorFlow
2. Recognizing Dog Breed or Flower Type
3. Detecting Objects and their Locations
4. Transforming Pictures with Amazing Art Styles
5. Understanding Simple Speech Commands
6. Describing Images in Natural Language
7. Generating Natural Sounding Speech
8. Classifying and Summarizing Text
9. Performing Machine Translation from English to French
10. Predicting House and Stock Prices
11. Building AlphaGo-like Chess App
12. Seeing, Listening, Speaking and Learning on Raspberry Pi

✦ Table of Contents

Cover
Copyright and Credits
Dedication
Packt Upsell
Foreword
Contributors
Table of Contents
Preface
Chapter 1: Getting Started with Mobile TensorFlow
Setting up TensorFlow
Setting up TensorFlow on MacOS
Setting up TensorFlow on GPU-powered Ubuntu
Setting up Xcode
Setting up Android Studio
TensorFlow Mobile vs TensorFlow Lite
Running sample TensorFlow iOS apps
Running sample TensorFlow Android apps
Summary
Chapter 2: Classifying Images with Transfer Learning
Transfer learning – what and why
Retraining using the Inception v3 model
Retraining using MobileNet models
Using the retrained models in the sample iOS app
Using the retrained models in the sample Android app
Adding TensorFlow to your own iOS app
Adding TensorFlow to your Objective-C iOS app
Adding TensorFlow to your Swift iOS app
Adding TensorFlow to your own Android app
Summary
Chapter 3: Detecting Objects and Their Locations
Object detection–a quick overview
Setting up the TensorFlow Object Detection API
Quick installation and example 
Using pre-trained models
Retraining SSD-MobileNet and Faster RCNN models
Using object detection models in iOS
Building TensorFlow iOS libraries manually
Using TensorFlow iOS libraries in an app
Adding an object detection feature to an iOS app
Using YOLO2–another object-detection model
Summary
Chapter 4: Transforming Pictures with Amazing Art Styles
Neural Style Transfer – a quick overview
Training fast neural-style transfer models
Using fast neural-style transfer models in iOS
Adding and testing with fast neural transfer models
Looking back at the iOS code using fast neural transfer models
Using fast neural-style transfer models in Android
Using the TensorFlow Magenta multi-style model in iOS
Using the TensorFlow Magenta multi-style model in Android
Summary
Chapter 5: Understanding Simple Speech Commands
Speech recognition – a quick overview
Training a simple commands recognition model
Using a simple speech recognition model in Android
Building a new app using the model
Showing model-powered recognition results
Using a simple speech recognition model in iOS with Objective-C
Building a new app using the model
Fixing model-loading errors with tf_op_files.txt
Using a simple speech recognition model in iOS with Swift
Summary
Chapter 6: Describing Images in Natural Language
Image captioning – how it works
Training and freezing an image captioning model
Training and testing caption generation
Freezing the image captioning model
Transforming and optimizing the image captioning model
Fixing errors with transformed models
Optimizing the transformed model
Using the image captioning model in iOS
Using the image captioning model in Android
Summary
Chapter 7: Recognizing Drawing with CNN and LSTM
Drawing classification – how it works
Training, predicting, and preparing the drawing classification model
Training the drawing classification model
Predicting with the drawing classification model
Preparing the drawing classification model
Using the drawing classification model in iOS
Building custom TensorFlow library for iOS
Developing an iOS app to use the model
Using the drawing classification model in Android
Building custom TensorFlow library for Android
Developing an Android app to use the model
Summary
Chapter 8: Predicting Stock Price with RNN
RNN and stock price prediction – what and how
Using the TensorFlow RNN API for stock price prediction
Training an RNN model in TensorFlow
Testing the TensorFlow RNN model 
Using the Keras RNN LSTM API for stock price prediction
Training an RNN model in Keras
Testing the Keras RNN model 
Running the TensorFlow and Keras models on iOS
Running the TensorFlow and Keras models on Android
Summary
Chapter 9: Generating and Enhancing Images with GAN
GAN – what and why
Building and training GAN models with TensorFlow
Basic GAN model of generating handwritten digits
Advanced GAN model of enhancing image resolution
Using the GAN models in iOS
Using the basic GAN model
Using the advanced GAN model
Using the GAN models in Android
Using the basic GAN model
Using the advanced GAN model
Summary
Chapter 10: Building an AlphaZero-like Mobile Game App
AlphaZero – how does it work?
Training and testing an AlphaZero-like model for Connect 4
Training the model
Testing the model
Looking into the model-building code
Freezing the model
Using the model in iOS to play Connect 4
Using the model in Android to play Connect 4
Summary
Chapter 11: Using TensorFlow Lite and Core ML on Mobile
TensorFlow Lite – an overview
Using TensorFlow Lite in iOS
Running the example TensorFlow Lite iOS apps
Using a prebuilt TensorFlow Lite model in iOS
Using a retrained TensorFlow model for TensorFlow Lite in iOS
Using a custom TensorFlow Lite model in iOS
Using TensorFlow Lite in Android
Core ML for iOS – an overview
Using Core ML with Scikit-Learn machine learning 
Building and converting the Scikit Learn models
Using the converted Core ML models in iOS
Using Core ML with Keras and TensorFlow
Summary
Chapter 12: Developing TensorFlow Apps on Raspberry Pi
Setting up Raspberry Pi and making it move
Setting up Raspberry Pi 
Making Raspberry Pi move
Setting up TensorFlow on Raspberry Pi
Image recognition and text to speech
Audio recognition and robot movement
Reinforcement learning on Raspberry Pi
Understanding the CartPole simulated environment
Starting with basic intuitive policy 
Using neural networks to build a better policy
Summary
Final words
Other Books You May Enjoy
Index

✦ Subjects

Computers, Intelligence (AI) & Semantics, COM060180 - COMPUTERS / Web / Web Services & APIs, COM074000 - COMPUTERS / Hardware / Mobile Devices, COM004000 - COMPUTERS / Intelligence (AI) and Semantics