Book Image

Hands-On Deep Learning for Computer Vision [Video]

By : Jakub Konczyk
Book Image

Hands-On Deep Learning for Computer Vision [Video]

By: Jakub Konczyk

Overview of this book

<p>Machine Learning, and Deep learning techniques in particular, are changing the way computers see and interact with the World. From augmented and mixed-reality applications to just gathering data, these new techniques are revolutionizing a lot of industries This course is designed to give you a hands-on learning experience by going from the basic concepts to the most current in-depth Deep Learning methods for Computer Vision in use today.</p> <p>In this course, you will be introduced to the concept of deep learning and a variety of popular and effective techniques for image classification, detection, segmentation and generation. You will learn to build your own neural network and classify images accordingly. You will be taken through popular techniques such as Deep Dream (to generate psychedelic, surreal images), Style Transfer (to transfer styles between images), and Neural Doodle, to generate an image that matches a doodled sketch.</p> <p>By the end of this course, you will be able to use computer vision and deep learning to encode, classify, detect, and style images for the real world.</p> <p>The code bundle for this video course is available at -&nbsp;<a href="https://github.com/PacktPublishing/Hands-On-Deep-Learning-for-Computer-Vision" target="_blank">https://github.com/PacktPublishing/Hands-On-Deep-Learning-for-Computer-Vision</a></p> <h1>Style and Approach</h1> <p>This video course offers a project-based approach to teach you the skills required to develop computer vision applications using Deep Learning and Python.</p>
Table of Contents (5 chapters)
Chapter 5
Generating Images with Neural Style
Content Locked
Section 1
An Introduction to Neural Style Transfer
Discover the main ideas behind neural style transfer - Learn how it’s possible to extract “content” and “style” from a CNN network - Learn the characteristics of “content” and “style” and where in CNN you can find them - Learn which pre-trained CNN model to choose for neural transfer and which optimizer to use for best results