Book Image

TensorFlow 2.0 Quick Start Guide

By : Tony Holdroyd
Book Image

TensorFlow 2.0 Quick Start Guide

By: Tony Holdroyd

Overview of this book

TensorFlow is one of the most popular machine learning frameworks in Python. With this book, you will improve your knowledge of some of the latest TensorFlow features and will be able to perform supervised and unsupervised machine learning and also train neural networks. After giving you an overview of what's new in TensorFlow 2.0 Alpha, the book moves on to setting up your machine learning environment using the TensorFlow library. You will perform popular supervised machine learning tasks using techniques such as linear regression, logistic regression, and clustering. You will get familiar with unsupervised learning for autoencoder applications. The book will also show you how to train effective neural networks using straightforward examples in a variety of different domains. By the end of the book, you will have been exposed to a large variety of machine learning and neural network TensorFlow techniques.
Table of Contents (15 chapters)
Free Chapter
1
Section 1: Introduction to TensorFlow 2.00 Alpha
5
Section 2: Supervised and Unsupervised Learning in TensorFlow 2.00 Alpha
7
Unsupervised Learning Using TensorFlow 2
8
Section 3: Neural Network Applications of TensorFlow 2.00 Alpha
13
Converting from tf1.12 to tf2

Converting from tf1.12 to tf2

Google supplies a command-line script called tf_upgrade_v2, which converts version 1.12 files (both .py and .ipynb files) into TensorFlow 2 compatible files.

The syntax for this conversion is as follows:

 tf_upgrade_v2   --infile  file_to_convert --outfile  converted_file

There is a demonstration of this upgrade script in action at https://www.youtube.com/watch?v=JmSNUeBG-PQ&list=PLQY2H8rRoyvzoUYI26kHmKSJBedn3SQuB&index=32&t=71s, and more detailed information regarding it is available at https://github.com/tensorflow/docs/blob/master/site/en/r2/guide/upgrade.md.

It is important to note that you should not update parts of your code manually before running this script.

The script will not fix all of the issues, but the report it produces will identify those issues that must be fixed manually.

In particular, tf.contrib has been removed from...