Search icon CANCEL
Subscription
0
Cart icon
Cart
Close icon
You have no products in your basket yet
Save more on your purchases!
Savings automatically calculated. No voucher code required
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
The Deep Learning with PyTorch Workshop

You're reading from  The Deep Learning with PyTorch Workshop

Product type Book
Published in Jul 2020
Publisher Packt
ISBN-13 9781838989217
Pages 330 pages
Edition 1st Edition
Languages
Author (1):
Hyatt Saleh Hyatt Saleh
Profile icon Hyatt Saleh
Toc

Implementation of Style Transfer Using the VGG-19 Network Architecture

VGG-19 is a CNN consisting of 19 layers. It was trained using millions of images from the ImageNet database. The network is capable of classifying images into 1,000 different class labels, including a vast number of animals and different tools.

Note

To explore the ImageNet database, go to the following URL: http://www.image-net.org/.

Considering its depth, the network is able to identify complex features from a wide variety of images, which makes it particularly good for style transfer problems, where feature extraction is crucial at different stages and for different purposes.

This section will focus on how to use the pretrained VGG-19 model to perform style transfer. The end goal of this chapter will be to take an image of an animal or a landscape (as the content image) and one of a painting from a well-known artist (as the style image) to create a new image of a regular object with an artistic...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime