Deep Learning with TensorFlow

Giancarlo Zaccone, Md. Rezaul Karim, Ahmed Menshawy

• Publisher: Packt Publishing
• Year: 2017
• eBook ISBN: 9781786460127
• Edition: 1
• Topic: Computer Science
• Subtopic: Artificial Intelligence (AI) & Semantics
• Index: Computer Science

Delve into neural networks, implement deep learning algorithms, and explore layers of data abstraction with the help of this comprehensive TensorFlow guideAbout This Book• Learn how to implement advanced techniques in deep learning with Google's brainchild, TensorFlow• Explore deep neural networks and layers of data abstraction with the help of this comprehensive guide• Real-world contextualization through some deep learning problems concerning research and application Who This Book Is ForThe book is intended for a general audience of people interested in machine learning and machine intelligence. A rudimentary level of programming in one language is assumed, as is a basic familiarity with computer science techniques and technologies, including a basic awareness of computer hardware and algorithms. Some competence in mathematics is needed to the level of elementary linear algebra and calculus.What You Will Learn• Learn about machine learning landscapes along with the historical development and progress of deep learning• Learn about deep machine intelligence and GPU computing with the latest TensorFlow 1.x• Access public datasets and utilize them using TensorFlow to load, process, and transform data• Use TensorFlow on real-world datasets, including images, text, and more• Learn how to evaluate the performance of your deep learning models• Using deep learning for scalable object detection and mobile computing• Train machines quickly to learn from data by exploring reinforcement learning techniques• Explore active areas of deep learning research and applicationsIn DetailDeep learning is the step that comes after machine learning, and has more advanced implementations. Machine learning is not just for academics anymore, but is becoming a mainstream practice through wide adoption, and deep learning has taken the front seat. As a data scientist, if you want to explore data abstraction layers, this book will be your guide. This book shows how this can be exploited in the real world with complex raw data using TensorFlow 1.x.Throughout the book, you'll learn how to implement deep learning algorithms for machine learning systems and integrate them into your product offerings, including search, image recognition, and language processing. Additionally, you'll learn how to analyze and improve the performance of deep learning models. This can be done by comparing algorithms against benchmarks, along with machine intelligence, to learn from the information and determine ideal behaviors within a specific context.After finishing the book, you will be familiar with machine learning techniques, in particular the use of TensorFlow for deep learning, and will be ready to apply your knowledge to research or commercial projects.Style and approachThis step-by-step guide will explore common, and not so common, deep neural networks and show how these can be exploited in the real world with complex raw data. With the help of practical examples, you will learn how to implement different types of neural nets to build smart applications related to text, speech, and image data processing.

First Look at TensorFlow

TensorFlow is mathematical software and an open-source software library for Machine Intelligence, developed in 2011, by Google Brain Team. The initial target of TensorFlow was to conduct research in machine learning and in deep neural networks. However, the system is general enough to be applicable in a wide variety of other domains as well.

The name is derived from the data model which is represented by tensors and from the data flow graph that stands for the TensorFlow's execution model. In 2015, Google has open-sourced the TensorFlow and all of its reference implementation and made all the source code available on GitHub under the Apache 2.0 license. After that, TensorFlow has achieved wide adaption, form academia and research to industry and following that recently the most stable version 1.0 has been released with a unified API.

Keeping in mind your needs and based on all the latest and exciting features of TensorFlow 1.x, this chapter will give a description of the main TensorFlow's capabilities. The following topics will be discussed in this chapter:

• General overview
• Installing and getting started with TensorFlow
• Computation graph
• The programming model
• Data model
• TensorBoard
• Implementing a single input neuron
• Migrating to TensorFlow 1.x

General overview

TensorFlow is an open source software library for numerical computation using data flow graphs that enables machine learning practitioners to do more data-intensive computing. It provides some robust implementations of widely used deep learning algorithms. Nodes in the flow graph represent mathematical operations. On the other hand, the edges represent multidimensional tensors that ensure communication between edges and nodes. TensorFlow offers you a very flexible architecture that enables you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.

What's new with TensorFlow 1.x?

The APIs in TensorFlow 1.0 have changed in ways that are not all backward-compatible. That is, TensorFlow programs that worked on TensorFlow 0.x won't necessarily work on TensorFlow 1.x. These API changes have been made to ensure an internally-consistent API. In other words, Google does not have any plans to make TensorFlow backwards-breaking changes throughout the 1.x lifecycle.

In the latest TensorFlow 1.x version, Python APIs resemble NumPy more closely. This has made the current version more stable for array-based computation. Two experimental APIs for Java and GO have been introduced too. This is very good news for the Java and GO programmer.

A new tool called TensorFlow Debugger (tfdbg) has been introduced. This is a command-line interface and API for debugging live TensorFlow programs. A new Android demos (https://github.com/tensorflow/tensorflow/tree/r1.0/tensorflow/examples/android) for object detection and localization and camera-based image stylization have been made available.

Now the installation of TensorFlow can be done through an Anaconda and Docker image of TensorFlow. Finally and most importantly, a new domain-specific compiler for TensorFlow graphs targeting CPU and GPU computing has been introduced. This is called Accelerated Linear Algebra (XLA).

How does it change the way people use it?

The main features offered by the latest release of TensorFlow are as follows:

• Faster computing: The major versioning upgrade to TensorFlow 1.0 has made its capability incredibly faster including a 7.3x speedup on 8 GPUs for inception v3 and 58x speedup for distributed Inception (v3 training on 64 GPUs).
• Flexibility: TensorFlow is not just a deep learning or machine learning software library but also great a library full with powerful mathematical functions with which you can solve most different problems. The execution model that uses the data flow graph allows you to build very complex models from simple sub-models. TensorFlow 1.0 introduces high-level APIs for TensorFlow, with tf.layers, tf.metrics, tf.losses and tf.keras modules. These have made TensorFlow very suitable for high-level neural network computing
• Portability: TensorFlow runs on Windows, Linux, and Mac machines and on mobile computing platforms (that is, Android).
• Easy debugging: TensorFlow provides the TensorBoard tool for the analysis of the developed models.
• Unified API: TensorFlow offers you a very flexible architecture that enables you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
• Transparent use of GPU computing: Automating management and optimization of the same memory and the data used. You can now use your machine for large-scale and data-intensive GPU computing with NVIDIA, cuDNN, and CUDA tool kits.
• Easy Use: TensorFlow is for everyone; it's for students, researchers, and deep learning practitioners and also for readers of this book.
• Production ready at scale: Recently it has been evolved as the neural network for machine translation, at production scale. TensorFlow 1.0 promises Python API stability making it easier to choose new features without worrying too much about breaking your existing code.
• Extensibility: TensorFlow is relatively new technology and it's still under active development. However, it is extensible because it was released with the source code available on GitHub (https://github.com/tensorflow/tensorflow). And if you don't see the low-level data operator you need, you can write it in C++ and add it to the framework.
• Supported: There is a large community of developers and users working together to improve TensorFlow both by providing feedback and by actively contributing to the source code.
• Wide adaption: Numerous tech giants are using TensorFlow to increase their business intelligence. For example, ARM, Google, Intel, eBay, Qualcomm, SAM, DropBox, DeepMind, Airbnb, Twitter and so on.

Installing and getting started with TensorFlow

You can install and use TensorFlow on a number of platforms such as Linux, Mac OSX, and Windows. You can also build and install TensorFlow from the latest GitHub source of TensorFlow. Also if you have a Windows machine you can install ...

Table of contents

• Title Page
• Copyright
• Credits
• About the Authors
• About the Reviewers
• www.PacktPub.com
• Customer Feedback
• Preface
• Getting Started with Deep Learning
• First Look at TensorFlow
• Using TensorFlow on a Feed-Forward Neural Network
• TensorFlow on a Convolutional Neural Network
• Optimizing TensorFlow Autoencoders
• Recurrent Neural Networks
• GPU Computing
• Advanced TensorFlow Programming
• Advanced Multimedia Programming with TensorFlow
• Reinforcement Learning