Preface

Deep learning techniques can be used to develop intelligent web apps. Over the last few years, tremendous growth in the number of companies adopting deep learning techniques in their products and businesses has been observed. There has been a significant surge in the number of start-ups providing AI and deep learning-based solutions for niche problems. This book introduces numerous tools and technological practices used to implement deep learning in web development using Python.

To start with, you will learn about the fundamentals of machine learning, with a focus on deep learning and the basics of neural networks, along with their common variants, such as convolutional neural networks, and how you can integrate them into websites with frontends built with different standard web tech stacks. You will create your deep learning-enabled web application using Python libraries such as Django and Flask by creating REST APIs for custom models. You will set up a cloud environment for deep learning-based web deployments on Google Cloud and AWS, and get guidance on how to use their battle-tested deep learning APIs. Further, you will use Microsoft's Intelligent Emotion API, which can detect human emotions from a picture of a face. You will also get to grips with deploying real-world websites, and you will get great insights into securing those websites using reCaptcha and Cloudflare for a robust experience. Finally, you will use natural language processing to recommend restaurants from user reviews and to integrate a voice UX on your web pages through Dialogflow.

By the end of this book, you'll be able to deploy your intelligent web apps and websites with the help of the best tools and practices.

Who this book is for

This book is for data scientists, machine learning practitioners, and deep learning engineers who are looking to perform deep learning techniques and methodologies on the web. This book will also be ideal for web developers who want to use smart techniques in the browser to make it more interactive. You will gain deep insights into browser data using this handy guide.

Having a working knowledge of the Python programming language and fundamental machine learning techniques (as covered in the Machine Learning Crash Course by Google, available at https://developers.google.com/machine-learning/crash-course) will be beneficial for reading this book.

What this book covers

Chapter 1, Demystifying Artificial Intelligence and Fundamentals of Machine Learning, briefly introduces machine learning, deep learning, and other forms of artificial intelligence methodologies related to web development. This chapter quickly goes over fundamental topics of the machine learning pipeline, such as exploratory data analysis, data preprocessing, feature engineering, training and testing, models of evaluation, and more. Toward the end, a comparison between the interactivity and user experience offered by websites before AI became popular and how they are in the modern day is presented. We also study the usage of AI on the web by some of the biggest firms and how AI has revolutionized their products.

Chapter 2, Getting Started with Deep Learning Using Python, introduces basic concepts and terminologies related to deep learning and how to use deep learning to build a simple web app with different deep learning libraries in Python.

Chapter 3, Creating Your First Deep Learning Web Application, discusses several important concepts regarding the structure of web applications specifically for leveraging deep learning. It then proceeds to discuss the approaches to understanding a dataset. The chapter also shows how to implement and improve a simple neural network and how it can be wrapped into an API for the development of a simple web application. We then proceed to showcase how the API can be implemented using different standard web tech stacks.

Chapter 4, Getting Started with TensorFlow.js, introduces the most popular JavaScript library for deep learning—TensorFlow.js (Tf.js). It gives a brief overview of what TensorFlow.js is and the things it is capable of doing in a browser. Furthermore, this chapter shows how you can use pre-trained models using TensorFlow.js and build a simple web application with it.

Chapter 5, Deep Learning through APIs, introduces the concept of APIs and their importance in software development. Further, the chapter proceeds to show examples of different deep learning APIs. Toward the very end, the chapter presents an approach to choosing deep learning API providers to suit particular use cases. The deep learning APIs covered are the Vision API, the Text API, and others.

Chapter 6, Deep Learning on Google Cloud Platform Using Python, introduces the offerings by Google Cloud Platform for web developers to integrate into their websites. The focus is on Dialogflow, which can be used to make chatbots and conversational AIs; the Cloud Inference API, which can be used to build a good recommendation system; and also the Translation API, which is used to provide users in different locales with website content in their languages. The chapter discusses their applications at length and also demonstrates a basic how-to for using them with Python.

Chapter 7, DL on AWS Using Python: Object Detection and Home Automation, introduces Amazon Web Services and talks briefly about the various offerings, including the Alexa API and the Rekognition API. The Alexa API can be used to build home automation web apps and other interactive interfaces, while the Rekognition API can be used to detect people and objects in photos and videos.

Chapter 8, Deep Learning on Microsoft Azure Using Python, introduces Microsoft Azure Cloud Services, focusing on the Cognitive Toolkit, which is Microsoft's alternative to TensorFlow's Emotion API, which can be used to determine the emotion of a person from a photograph of their face, and the Text-to-Speech API, which can be used to generate natural-sounding voice from text.

Chapter 9, A General Production Framework for Deep Learning-Enabled Websites, introduces the general framework to be set up for the efficient deployment of deep learning on the web in a production environment. Strategies for reducing computing resources, converting raw datasets to datasets for training deep learning models, and how to make models available for usage on the web in a minimally resource-intensive way are covered.

Chapter 10, Securing Web Apps with Deep Learning, discusses several tricks and techniques for securing websites with deep learning with Python. We present reCaptcha and Cloudflare and discuss how they are used to enhance the security of websites. We also show how to implement security mechanisms to detect malicious users on websites using deep learning on the Python backend.

Chapter 11, DIY – A Web DL Production Environment, discusses the methods by which we update models in production and how we can choose the right method according to requirements. We begin with a brief overview and then demonstrate some famous tools for creating deep learning data flows. Finally, we implement a demo of online learning, or incremental learning, to establish a method of model update in production.

Chapter 12, Creating an E2E Web App Using DL APIs and Customer Support Chatbot, introduces natural language processing and discusses how to create a chatbot for resolving general customer support queries using Dialogflow and integrate it into a Django and Flask website. We explore ways of implementing bot personalities and how to make such system resources effective. We also introduce a method for implementing a text-to-speech and speech-to-text-based user interface with Python.

Appendix, Success Stories and Emerging Areas in Deep Learning on the Web, illustrates some of the most famous websites whose products are based heavily upon leveraging the power of deep learning. This chapter also discusses some key research areas in web development that could be enhanced using deep learning. This will help you to delve even deeper into the fusion of web technologies and deep learning and will motivate you to come up with your own intelligent web applications.

To get the most out of this book

This book assumes an understanding of the Python language, specifically Python 3.6 and above. It is strongly recommended to have the Anaconda distribution of Python installed on your local systems. Any Anaconda distribution with support for Python 3.6 and above is good for running the examples in this book. 

In terms of hardware, this book assumes the availability of a microphone, speaker, and webcam on your computer. 

Software/Hardware covered in the book	OS Requirements
Anaconda distribution of Python and other Python packages	1 GB RAM minimum, 8 GB recommended 15 GB disk space
Code editor of your choice (Sublime Text 3 recommended)	2 GB RAM

 

If you are using the digital version of this book, we advise you to type the code yourself or access the code via the GitHub repository (link available in the next section). Doing so will help you avoid any potential errors related to the copying and pasting of code.

It is expected that you will try to implement the samples present in this book by yourself. In case you run into problems, you can reach out to us by emailing the authors – Sayak Paul ([e-mail]) and Anubhav Singh ([e-mail]). In case you are unable to run the samples provided in the code repo of the book, you can raise issues on the repo and we'll get back to you there!

Download the example code files

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.packtpub.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.
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/Hands-On-Python-Deep-Learning-for-Web. 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!

Download the color images

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/9781789956085_ColorImages.pdf.

Conventions used

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: "We now need to import the saved model and weights from the model training step. Once we do so, we need to recompile the model and make its predict function using the make_predict_fuction() method."

A block of code is set as follows:

def remove_digits(s: str) -> str:
    remove_digits = str.maketrans('', '', digits)
    res = s.translate(remove_digits)
    return res

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

python main.py

Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "Fill up the entries and click on Continue."

Warnings or important notes appear like this.

Tips and tricks appear like this.

Get in touch

Feedback from our readers is always welcome.

General feedback: If you have questions about any aspect of this book, mention the book title in the subject of your message and email us at [e-mail].

Errata: Although we have taken every care to ensure the accuracy of our content, mistakes do happen. If you have found a mistake in this book, we would be grateful if you would report this to us. Please visit www.packtpub.com/support/errata, selecting your book, clicking on the Errata Submission Form link, and entering the details.

Piracy: If you come across any illegal copies of our works in any form on the Internet, we would be grateful if you would provide us with the location address or website name. Please contact us at [e-mail] with a link to the material.

If you are interested in becoming an author: If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, please visit authors.packtpub.com.

Reviews

Please leave a review. Once you have read and used this book, why not leave a review on the site that you purchased it from? Potential readers can then see and use your unbiased opinion to make purchase decisions, we at Packt can understand what you think about our products, and our authors can see your feedback on their book. Thank you!

For more information about Packt, please visit packt.com.