Book Image

Hands-On Convolutional Neural Networks with TensorFlow

By : Iffat Zafar, Giounona Tzanidou, Richard Burton, Nimesh Patel, Leonardo Araujo
Book Image

Hands-On Convolutional Neural Networks with TensorFlow

By: Iffat Zafar, Giounona Tzanidou, Richard Burton, Nimesh Patel, Leonardo Araujo

Overview of this book

Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time! We start with an overview of popular machine learning and deep learning models, and then get you set up with a TensorFlow development environment. This environment is the basis for implementing and training deep learning models in later chapters. Then, you will use Convolutional Neural Networks to work on problems such as image classification, object detection, and semantic segmentation. After that, you will use transfer learning to see how these models can solve other deep learning problems. You will also get a taste of implementing generative models such as autoencoders and generative adversarial networks. Later on, you will see useful tips on machine learning best practices and troubleshooting. Finally, you will learn how to apply your models on large datasets of millions of images.
Table of Contents (17 chapters)
Title Page
Copyright and Credits
Packt Upsell

When data does not fit on one computer

One problem that may occur is that we simply can't store the data on one computer and/or we still need to search for things on this dataset. To solve this kind of problem, we may need distributed Not only SQL (NoSQL) databases, such as Cassandra. Cassandra supports data distribution on multiple systems where availability and performance are critical:

Cassandra tries its best to not have a single point of failure. For example, all nodes will act like a sort of master (there is no actual master) so that all nodes have the responsibility to handle requests and automatically distribute data between nodes, in some sort of high-availability backup.

The advantages of NoSQL systems

NoSQL databases, in contrast with relational databases (such as older versions of MySQL and PostgreSQL), shine when the amount of data becomes too big, and also when we don't need the Features of relational databases (such as triggers or stored procedures).

Before we continue, let's...