Discover millions of ebooks, audiobooks, and so much more with a free trial

Only $11.99/month after trial. Cancel anytime.

Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python
Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python
Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python
Ebook204 pages1 hour

Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python

Rating: 0 out of 5 stars

()

Read preview

About this ebook

Learn how to use TensorFlow 2.0 to build machine learning and deep learning models with complete examples. 
The book begins with introducing TensorFlow 2.0 framework and the major changes from its last release. Next, it focuses on building Supervised Machine Learning models using TensorFlow 2.0. It also demonstrates how to build models using customer estimators. Further, it explains how to use TensorFlow 2.0 API to build machine learning and deep learning models for image classification using the standard as well as custom parameters. 
You'll review sequence predictions, saving, serving, deploying, and standardized datasets, and then deploy these models to production. All the code presented in the book will be available in the form of executable scripts at Github which allows you to try out the examples and extend them in interesting ways.
What You'll Learn
  • Review the new features of TensorFlow 2.0
  • Use TensorFlow 2.0 to build machine learning and deep learning models 
  • Perform sequence predictions using TensorFlow 2.0
  • Deploy TensorFlow 2.0 models with practical examples

Who This Book Is For

Data scientists, machine and deep learning engineers.

LanguageEnglish
PublisherApress
Release dateDec 17, 2019
ISBN9781484255582
Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python

Read more from Pramod Singh

Related to Learn TensorFlow 2.0

Related ebooks

Intelligence (AI) & Semantics For You

View More

Related articles

Reviews for Learn TensorFlow 2.0

Rating: 0 out of 5 stars
0 ratings

0 ratings0 reviews

What did you think?

Tap to rate

Review must be at least 10 words

    Book preview

    Learn TensorFlow 2.0 - Pramod Singh

    © Pramod Singh, Avinash Manure 2020

    P. Singh, A. ManureLearn TensorFlow 2.0https://doi.org/10.1007/978-1-4842-5558-2_1

    1. Introduction to TensorFlow 2.0

    Pramod Singh¹  and Avinash Manure²

    (1)

    Bangalore, Karnataka, India

    (2)

    Bangalore, India

    The intent of this book is to introduce readers to the latest version of the TensorFlow library. Therefore, this first chapter focuses mainly on what has changed in the TensorFlow library since its first version, TensorFlow 1.0. We will cover the various changes, in addition to highlighting the specific parts for which changes are yet to be introduced. This chapter is divided into three sections: the first discusses the internals of TensorFlow; the second focuses on the changes that have been implemented in TensorFlow 2.0 after TensorFlow 1.0; and the final section covers TensorFlow 2.0 installation methods and basic operations.

    You may already be aware that TensorFlow is widely used as a machine learning implementation library. It was created by Google as part of the Google Brain project and was later made available as an open source product, as there were multiple machine learning and deep learning frameworks that were capturing the attention of users. With open source availability, more and more people in the artificial intelligence (AI) and machine learning communities were able to adopt TensorFlow and build features and products on top of it. It not only helped users with implementation of standard machine learning and deep learning algorithms but also allowed them to implement customized and differentiated versions of algorithms for business applications and various research purposes. In fact, it soon became one of the most popular libraries in the machine learning and AI communities—so much so that people have been building a huge number of apps using TensorFlow under the hood. This is principally owing to the fact that Google itself uses TensorFlow in most of its products, whether Google Maps, Gmail, or other apps.

    While TensorFlow had its strengths in certain areas, it also had a few limitations, owing to which developers found it a bit difficult to adopt, compared to such other libraries as PyTorch, Theano, and OpenCV. As Google’s TensorFlow team took the feedback of the TensorFlow community seriously, it went back to the drawing board and started working on most of the changes required to make TensorFlow even more effective and easy to work with, soon launching the TensorFlow 2.0 alpha version this year. TensorFlow 2.0 claims to have removed some of the previous hurdles, in order to allow developers to use TensorFlow even more seamlessly. In this chapter, we will go over those changes one by one, but before covering these, let us spend some time understanding what exactly TensorFlow is and what makes it one of the best available options to perform machine learning and deep learning

    Enjoying the preview?
    Page 1 of 1