Hands-On Deep Learning for Images with TensorFlow

Build intelligent computer vision applications using TensorFlow and Keras

Will Ballard

• Publisher: Packt Publishing
• Year: 2018
• Print ISBN: 9781789538670
• eBook ISBN: 9781789532517
• Edition: 1
• Topic: Computer Science
• Subtopic: Artificial Intelligence (AI) & Semantics
• Index: Computer Science

Explore TensorFlow's capabilities to perform efficient deep learning on images

Key Features

• Discover image processing for machine vision
• Build an effective image classification system using the power of CNNs
• Leverage TensorFlow's capabilities to perform efficient deep learning

Book Description

TensorFlow is Google's popular offering for machine learning and deep learning, quickly becoming a favorite tool for performing fast, efficient, and accurate deep learning tasks.

Hands-On Deep Learning for Images with TensorFlow shows you the practical implementations of real-world projects, teaching you how to leverage TensorFlow's capabilities to perform efficient image processing using the power of deep learning. With the help of this book, you will get to grips with the different paradigms of performing deep learning such as deep neural nets and convolutional neural networks, followed by understanding how they can be implemented using TensorFlow.

By the end of this book, you will have mastered all the concepts of deep learning and their implementation with TensorFlow and Keras.

What you will learn

• Build machine learning models particularly focused on the MNIST digits
• Work with Docker and Keras to build an image classifier
• Understand natural language models to process text and images
• Prepare your dataset for machine learning
• Create classical, convolutional, and deep neural networks
• Create a RESTful image classification server

Who this book is for

Hands-On Deep Learning for Images with TensorFlow is for you if you are an application developer, data scientist, or machine learning practitioner looking to integrate machine learning into application software and master deep learning by implementing practical projects in TensorFlow. Knowledge of Python programming and basics of deep learning are required to get the best out of this book.

Machine Learning Toolkit

In this chapter, we're going to look at the following topics:

• Installing Docker
• Building a machine learning Docker file
• Sharing data back and forth between your host computer and your Docker container
• Building a REST service that uses the machine learning infrastructure run inside of your Docker container

Installing Docker

We'll need to download Docker to get it installed, and in this section, you'll see how we install Docker on Windows and use a script that's suitable for installation on Linux.

Let's install Docker from https://www.docker.com/. The quickest way to get this done is to head up to the menu. Here, we'll choose to download the version for Windows. Give it a click, which will take you right over to the Docker store, where you can download the specific installer for your platform, as shown in the following screenshot:

Docker installer window

All the platforms are available here. We'll just download the MSI for Windows. It downloads relatively quickly, and once it's on your PC, you can just click the MSI installer and it will quickly continue.

Installing on Ubuntu is best done with a script. So, I've provided a sample installation script (install-docker.sh) that will update your local package manager pointing to the official Docker distribution repositories, and then simply use apps to get the installation completed.

Getting Docker installed on Linux is pretty straightforward: you just run the install-docker shell script I've provided. The packages will update, download, and then install. When you get to the end of it, you just have to type docker --help to make sure that everything is installed:

Output—docker --help command

Now, for GPU support, which will make your Keras and TensorFlow models run faster, there is a special version called nvidia-docker, which exposes devices on Ubuntu to your Docker containers to allow GPU acceleration. There's an install script for this as well (install-nvidia-docker.sh). Now, assuming that you do have an actual NVIDIA graphics card, you can use NVIDIA Docker in place of Docker.

Here, we're running a test command that uses the NVIDIA SMI, which is really the status program that shows you the GPU status on your machine:

GPU status

And you can see, our TITAN X is fully exposed to Docker. Getting Docker installed is a relatively easy operation.

In the next section, we're going to take a look at authoring a Docker file to set up a complete machine learning environment.

The machine learning Docker file

Now, let's dive into preparing a machine learning Docker file. In this section, we will take a look at cloning the source files, the base images that are needed for Docker, installing additional required packages, exposing a volume so that you can share your work, and exposing ports so that you'll be able to see Jupyter Notebooks, which is the tool that we'll be using to explore machine learning.

Now, you'll need to get the source code that goes with these sections. Head on over to https://github.com/wballard/kerasvideo/tree/2018, where you can quickly clone the repository. Here, we're just using GitHub for Windows as a relatively quick way in order to make that repository cloned, but you can use Git in any fashion you're comfortable with. It doesn't matter what directory you put these files in; we're just downloading them into our local work directory. Then, we're going to use this location as the place to begin the build of the actual Docker container.

In the clone repository, take a look at the Docker file:

Docker file code

This is what we'll be using to create our environment. We're starting off with the base NVIDIA image that has the CUDA and cuDNN drivers, which will enable GPU support in the future. Now, in this next section, we're updating the package manager that will be on the container to make sure that we have git and wget updated graphics packages so that we'll be able to draw charts in our notebooks:

Docker file code

Now, we're going to be installing Anaconda Python. We're downloading it from the internet, and then running it as a shell script, which will place Python on the machine. We'll clean up after we're done:

Docker file code

Anaconda is a convenient Python distribution to use for machine learning and data science tasks because it comes with pre-built math libraries, particularly Pandas, NumPy, SciPy, and scikit-learn, which are built with optimized Intel Math Kernal Libraries. This is because, even if you don't have a GPU, you can generally get better performance by using Anaconda. It also has the advantage of installing, not as a root or globally underneath your system, but in your home directory. Therefore, you can add it on to an existing system without worrying about breaking system components that might rely on Python, say, in the user's bin or whats been installed by your global package manager.

Now, we're going to be setting up a user on our container called Keras:

Docker file code

When we're running notebooks, they're going to be running as this user, so you'll know who owns the files at all times. Creating a specific user in order to set up your container isn't strictly necessary, but it is convenient...

Table of contents

• Title Page
• Copyright and Credits
• Packt Upsell
• Contributors
• Preface
• Machine Learning Toolkit
• Image Data
• Classical Neural Network
• A Convolutional Neural Network
• An Image Classification Server
• Other Books You May Enjoy