Reader small image

You're reading from  Hands-On Neural Networks with TensorFlow 2.0

Product typeBook
Published inSep 2019
Reading LevelExpert
PublisherPackt
ISBN-139781789615555
Edition1st Edition
Languages
Right arrow
Author (1)
Paolo Galeone
Paolo Galeone
author image
Paolo Galeone

Paolo Galeone is a computer engineer with strong practical experience. After getting his MSc degree, he joined the Computer Vision Laboratory at the University of Bologna, Italy, as a research fellow, where he improved his computer vision and machine learning knowledge working on a broad range of research topics. Currently, he leads the Computer Vision and Machine Learning laboratory at ZURU Tech, Italy. In 2019, Google recognized his expertise by awarding him the title of Google Developer Expert (GDE) in Machine Learning. As a GDE, he shares his passion for machine learning and the TensorFlow framework by blogging, speaking at conferences, contributing to open-source projects, and answering questions on Stack Overflow.
Read more about Paolo Galeone

Right arrow

Object localization

Convolutional neural networks (CNNs) are extremely flexible objects—so far, we have used them to solve classification problems, making them learn to extract features specific to the task. As shown in Chapter 6, Image Classification Using TensorFlow Hub, the standard architecture of CNNs designed to classify images is made of two parts—the feature extractor, which produces a feature vector, and a set of fully connected layers that classifies the feature vector in the (hopefully) correct class:

The classifier placed on top of the feature vector can also be seen as the head of the network

The fact that, so far, CNNs have only been used to solve classification problems should not mislead us. These types of networks are extremely powerful, and, especially in their multilayer setting, they can be used to solve many different kinds of problems, extracting...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Neural Networks with TensorFlow 2.0
Published in: Sep 2019Publisher: PacktISBN-13: 9781789615555

Author (1)

author image
Paolo Galeone

Paolo Galeone is a computer engineer with strong practical experience. After getting his MSc degree, he joined the Computer Vision Laboratory at the University of Bologna, Italy, as a research fellow, where he improved his computer vision and machine learning knowledge working on a broad range of research topics. Currently, he leads the Computer Vision and Machine Learning laboratory at ZURU Tech, Italy. In 2019, Google recognized his expertise by awarding him the title of Google Developer Expert (GDE) in Machine Learning. As a GDE, he shares his passion for machine learning and the TensorFlow framework by blogging, speaking at conferences, contributing to open-source projects, and answering questions on Stack Overflow.
Read more about Paolo Galeone