Book Image

Intelligent Mobile Projects with TensorFlow

By : Jeff Tang

Book Image

Intelligent Mobile Projects with TensorFlow

By: Jeff Tang

Overview of this book

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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Getting Started with Mobile TensorFlow

Getting Started with Mobile TensorFlow

Setting up TensorFlow

Setting up Xcode

Setting up Android Studio

TensorFlow Mobile vs TensorFlow Lite

Running sample TensorFlow iOS apps

Running sample TensorFlow Android apps

Classifying Images with Transfer Learning

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 own Android app

Detecting Objects and Their Locations

Detecting Objects and Their Locations

Object detection–a quick overview

Setting up the TensorFlow Object Detection API

Retraining SSD-MobileNet and Faster RCNN models

Using object detection models in iOS

Using YOLO2–another object-detection model

Transforming Pictures with Amazing Art Styles

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

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

Understanding Simple Speech Commands

Understanding Simple Speech Commands

Speech recognition – a quick overview

Training a simple commands recognition model

Using a simple speech recognition model in Android

Using a simple speech recognition model in iOS with Objective-C

Using a simple speech recognition model in iOS with Swift

Describing Images in Natural Language

Describing Images in Natural Language

Image captioning – how it works

Training and freezing an image captioning model

Transforming and optimizing the image captioning model

Using the image captioning model in iOS

Using the image captioning model in Android

Recognizing Drawing with CNN and LSTM

Recognizing Drawing with CNN and LSTM

Drawing classification – how it works

Training, predicting, and preparing the drawing classification model

Using the drawing classification model in iOS

Using the drawing classification model in Android

Predicting Stock Price with RNN

Predicting Stock Price with RNN

RNN and stock price prediction – what and how

Using the TensorFlow RNN API for stock price prediction

Using the Keras RNN LSTM API for stock price prediction

Running the TensorFlow and Keras models on iOS

Running the TensorFlow and Keras models on Android

Generating and Enhancing Images with GAN

Generating and Enhancing Images with GAN

GAN – what and why

Building and training GAN models with TensorFlow

Using the GAN models in iOS

Using the GAN models in Android

Building an AlphaZero-like Mobile Game App

Building an AlphaZero-like Mobile Game App

AlphaZero – how does it work?

Training and testing an AlphaZero-like model for Connect 4

Using the model in iOS to play Connect 4

Using the model in Android to play Connect 4

Using TensorFlow Lite and Core ML on Mobile

Using TensorFlow Lite and Core ML on Mobile

TensorFlow Lite – an overview

Using TensorFlow Lite in iOS

Using TensorFlow Lite in Android

Core ML for iOS – an overview

Using Core ML with Scikit-Learn machine learning

Using Core ML with Keras and TensorFlow

Developing TensorFlow Apps on Raspberry Pi

Developing TensorFlow Apps on Raspberry Pi

Setting up Raspberry Pi and making it move

Setting up TensorFlow on Raspberry Pi

Image recognition and text to speech

Audio recognition and robot movement

Reinforcement learning on Raspberry Pi

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Building and training GAN models with TensorFlow

In general, a GAN model has two neural networks: G for the generator and D for the discriminator. x is some real data input from the training set, and z is random input noise. During the training, D(x) is the probability of x being real and D tries to make D(x) close to 1; G(z) is the generated output with the random input z, and D tries to make D(G(z)) close to 0, but at the same time, G tries to make D(G(z)) close to 1. Now, let's first see how we can build a basic GAN model in TensorFlow and Python that can write or generate handwritten digits.

Basic GAN model of generating handwritten digits

The training model for handwritten digits is based on the repo https://github...