Book Image

Java Machine Learning for Computer Vision [Video]

By : Klevis Ramo
Book Image

Java Machine Learning for Computer Vision [Video]

By: Klevis Ramo

Overview of this book

<p>&nbsp;Although Machine Learning is an exciting world to explore, you may feel confused by all the theory and math out there. As a Java developer, you are used to telling the computer exactly what to do instead of being shown how data is generated; this makes many developers struggle to adapt to this new world of Machine Learning.</p> <p>The goal of this course is to walk you through the process of efficiently training Deep Neural Networks for Computer Vision using the most modern techniques. The course is designed to get you familiar with Deep Neural Networks in order to be able to train them efficiently, customize existing state-of-the-art architectures, build real world Java applications, and get great results in a short time. You will build real-world Computer Vision applications, ranging from simple Java handwritten digit recognition to real-time Java autonomous car driving systems and face recognition.</p> <p>By the end of the course you will have mastered the best practices and most modern techniques to build advanced Computer Vision Java applications and achieve production-grade accuracy.</p> <p>The code bundle for this video course is available at:&nbsp;<a href="https://github.com/PacktPublishing/Java-Machine-Learning-for-Computer-Vision" target="_blank">https://github.com/PacktPublishing/Java-Machine-Learning-for-Computer-Vision</a></p> <h1>Style and Approach</h1> <p>This course will teach you how to build advanced Machine Learning applications with intuitive and detailed explanations of topics, with no math background requirements. It adopts a practical approach by applying the theory to build real-world Java applications using modern practices and techniques in the Computer Vision world.</p>
Table of Contents (6 chapters)
Chapter 4
Real Time Object Detection
Content Locked
Section 4
Detecting Objects with YOLO Algorithm
The aim of this video is to present how the YOLO algorithm solves the object detection problem efficiently. - Present the problem of having not flexible and accurate bounding boxes - Explore how YOLO overcome the problem efficiently during the training phase - See how the bounding box is specified generally and how YOLO specifies it internally