Deep Learning on Windows
Deep Learning on Windows
Minimum price
Suggested price
Deep Learning on Windows

This book is 35% complete

Last updated on 2020-06-05

About the Book

Do you wish to learn to build practical Deep Learning and Computer Vision Systems, but are reluctant to switch to Linux for the development? Do you feel like you're more familiar with Windows, and wish that you could build everything on Windows?

Well, you don't need to worry anymore. The latest deep learning and computer vision libraries have matured to the point that almost everything now can be made to work seamlessly on Windows as well. This book will show you how.

Deep Learning on Windows will help you learn to build Deep Learning and Computer Vision Systems, using Python, TensorFlow, Keras, OpenCV and more, right within the familiar elements of Microsoft Windows.

The goal of this book is to get as many of you interested in the field of Deep Learning and have the OS you build upon a non-barrier to start learning.

Along the way, we will learn what deep learning is, and how it came to be. We’ll clarify some misconceptions and confusion surrounding deep learning, and look at some of the major milestones it has achieved throughout the years. We will dive into coding while learning how the concepts apply as you build.

In this book, you will learn how to set up all the tools and technologies you will need to start coding deep learning systems on a Windows system. It will guide you from building and running your first ‘hello world’ convolutional neural network, to building practical computer vision systems from scratch, while exploring how each of the components works as we build them.

The target completion of the book will be in June 2020.

A total of 12 chapters are planned for the book, covering topics from setting up your tools on Windows, building your first models, to some advanced topics like transfer learning, deploying your models, computer vision, generative adversarial networks, and reinforcement learning.

The price of the book will increase over time as new chapters gets added, so purchasing early gives you the best value.

  • Share this book

  • Feedback

    You must own a copy of this Book to access the forums

    Email the Author(s)

About the Author

Thimira Amaratunga
Thimira Amaratunga

Software Architect at Pearson | AI Practitioner | Inventor | Author

An inventor. A software architect with over 10 years of industry experience. A practitioner and a researcher in AI & machine learning in education and computer vision domains.

Has a Masters in Computer Science with a Bachelors in IT. Has filed 3 patents to date, in the fields of dynamic neural networks and semantics for online learning platforms. Author of 2 books in deep learning & AI.

Table of Contents

  • Preface
    • What this book covers
    • Who this book is for
    • What you need in order to follow this book
    • Conventions used in this book
    • Questions and feedback
  • 1 Chapter 1: What is Deep Learning?
    • 1.1 Intelligent Machines
    • 1.2 Artificial Intelligence
    • 1.3 Machine Learning
    • 1.4 Deep Learning
    • 1.5 Convolutional Neural Networks
    • 1.6 How Deep?
    • 1.7 Is Deep Learning Just CNNs?
    • 1.8 Why Computer Vision?
    • 1.9 How Does It All Come Together?
    • 1.10 Is ‘Artificial Intelligence’ Possible?
  • 2 Chapter 2: Where to Start Your Deep Learning
    • 2.1 Can We Build Deep Learning Models on Windows?
      • Advantages of Using Windows
      • Limitations of Using Windows
    • 2.2 Programming Language – Python
    • 2.3 Package and Environment Management – Anaconda
    • 2.4 Python Utility Libraries for Deep Learning and Computer Vision
    • 2.5 Deep Learning Frameworks
      • TensorFlow
      • Keras
      • Other Frameworks
    • 2.6 Computer Vision Libraries
      • OpenCV
      • Dlib
    • 2.7 Optimizers and Accelerators
      • NVIDIA CUDA and cuDNN
      • OpenBLAS
    • 2.8 What About Hardware?
    • 2.9 Recommended PC Hardware Configurations
  • 3 Chapter 3: Setting Up Your Tools
    • 3.1 Step 1: Install Visual Studio with C++ Support
    • 3.2 Step 2: Install CMake
    • 3.3 Step 3: Install Anaconda Python
    • 3.4 Step 4: Setup the Conda Environment and the Python Libraries
    • 3.5 Step 5: Install TensorFlow
    • 3.6 Step 6: (Optional) Install Keras multi-backend version
    • 3.7 Step 7: Install OpenCV
    • 3.8 Step 8: Install Dlib
    • 3.9 Step 9: Verify Installations
    • 3.10 Optional Steps
      • Manually Installing CUDA Toolkit and cuDNN
      • Installing OpenBLAS for Theano
    • 3.11 Troubleshooting
      • Matplotlib Pyplot Error
      • Not Getting the Latest Versions
      • Not Using the Latest Version of OpenCV
      • Dlib Build Errors
    • 3.12 Summary
  • 4 Chapter 4: Building Your First Deep Learning Model
    • 4.1 What is the MNIST Dataset?
    • 4.2 The LeNet Model
    • 4.3 Let’s Build Our First Model
    • 4.4 Running Our Model
    • 4.5 What Can You Do Next?
  • 5 Chapter 5: Understanding What We Built
    • 5.1 Digital Images
    • 5.2 Convolutions
    • 5.3 Non-Linearity Function
    • 5.4 Pooling
    • 5.5 Classifier (Fully Connected Layer)
    • 5.6 How Does This All Come Together?
  • 6 Chapter 6: Visualizing Models
    • 6.1 Using the plot_model Function of Keras
    • 6.2 Using Netron
    • 6.3 Coming Soon…
  • 7 Chapter 7: Transfer Learning
    • 7.1 Coming Soon…
  • 8 Chapter 8: Starting, Stopping. and Resuming Learning
    • 8.1 Coming Soon…
  • 9 Chapter 9: Deploying Your Application as a Web Service
    • 9.1 Coming Soon…
  • 10 Chapter 10: Having Fun with Computer Vision
    • 10.1 Coming Soon…
  • 11 Chapter 11: Introduction to Generative Adversarial Networks
    • 11.1 The Story of the Artist and the Art Critic
    • 11.2 Generative Adversarial Networks
    • 11.3 Generating Handwritten Digits with DCGAN
    • 11.4 Coming Soon…
  • 12 Chapter 12: Basics of Reinforcement Learning
    • 12.1 Coming Soon…
  • References and Useful Links
  • Appendix 1: A History Lesson - Milestones of Deep Learning
    • What is the ImageNet Challenge (a.k.a. The ILSVRC)?
    • AlexNet – 2012
    • ZF Net – 2013
    • VGG Net – 2014
    • GoogLeNet/Inception – 2014/2015
    • Microsoft ResNet – 2015
    • DenseNet – 2015
    • Why Simply Going Deeper Does Not Work?
    • AlphaGo from DeepMind
    • Dota 2 Bot from OpenAI
  • Appendix 2: Switching the Backend in Multi-Backend Keras
  • Appendix 3: Code Samples
    • Chapter 4: Building Your First Deep Learning Model
      • Let’s Build Our First Model
  • About the Author
  • Notes

Authors have earned$9,196,652writing, publishing and selling on Leanpub,
earning 80% royalties while saving up to 25 million pounds of CO2 and up to 46,000 trees.

Learn more about writing on Leanpub

The Leanpub 45-day 100% Happiness Guarantee

Within 45 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers), EPUB (for phones and tablets) and MOBI (for Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses! Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks. Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. It really is that easy.

Learn more about writing on Leanpub