We approach deep learning projects from a very practical point of view. In thinking about how to share what we know, our experiences, the strategies that we've learned, and the tactics we employ, it was natural for us to format this book as if you (the reader) were a member of our Applied AI Engineering team here at The Intelligence Factory.

To get the most out of these projects, you should have at least an average working knowledge of Python and some familiarity with deep learning concepts. This Python Deep Learning Projects book is primarily a technical instruction book with content related to the intuition side of deep learning as required in order to learn the code that will produce functioning models. It is outside the scope of this book to dive deep into the calculus that is the foundation for these technologies.

Each chapter is like participating in the AI team's weekly standup. As you engage with the material, you will hopefully do the following:

• See the big picture
  • What's the real-world use case and the goal of the project?
  • What's the impact of success?
  • What's our strategy to achieve the goal?
• Get focused and into the code!
  • Identify specific tactics to achieve the project goal
  • Why is this the right approach?
  • Loop through executing the tactics
    • What are the inputs or establishing context?
    • Code examples
    • Outputs and success criteria
  • Questions and answers
    • What questions did we have?
    • What questions might you have?
• Expand back out to the big picture
  • Let's confirm that we have achieved our goal
  • What intuition can we gain from the experience?
  • How to generalize this successful experience in relation to new use cases?

Explaining Python deep learning is as easy as 1-2-3! But talking about deep learning isn't the same thing as doing, and that's what this book is about. What follows are a few thought provoking and exciting experiences. We will be using the most sophisticated Python libraries and advanced technologies available to empower you (our newest Applied AI Engineering team member) to contribute in your career using the projects we've created in this book. We're happy to have you in our weekly AI team standup.

Now let's learn a bunch, have some fun, and do great work in these Python deep learning projects!

You can download the example code files for this book from your account at www.packt.com. If you purchased this book elsewhere, you can visit www.packt.com/support and register to have the files emailed directly to you.

You can download the code files by following these steps:

1. Log in or register at www.packt.com.
2. Select the SUPPORT tab.
3. Click on Code Downloads & Errata.
4. Enter the name of the book in the Search box and follow the onscreen instructions.

Once the file is downloaded, please make sure that you unzip or extract the folder using the latest version of:

• WinRAR/7-Zip for Windows
• Zipeg/iZip/UnRarX for Mac
• 7-Zip/PeaZip for Linux

The code bundle for the book is also hosted on GitHub at https://github.com/PacktPublishing/Python-Deep-Learning-Projects. In case there's an update to the code, it will be updated on the existing GitHub repository.

We also have other code bundles from our rich catalog of books and videos available at https://github.com/PacktPublishing/. Check them out!

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. You can download it here: http://www.packtpub.com/sites/default/files/downloads/9781788997096_ColorImages.pdf.

There are a number of text conventions used throughout this book.

CodeInText: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. Here is an example: "Once you have Docker installed, you should be able to use the docker command in Terminal."

A block of code is set as follows:

import sys
import dlib
from skimage import io

When we wish to draw your attention to a particular part of a code block, the relevant lines or items are set in bold:

# Create a HOG face detector using the built-in dlib class
face_detector = dlib.get_frontal_face_detector()

Any command-line input or output is written as follows:

curl https://get.docker.com | sh