Deep Learning for Computer Vision: Expert techniques to train advanced neural networks using TensorFlow and Keras

by Rajalingappaa Shanmugamani

Key Features Train efficient deep learning models to solve different problems in Computer Vision with the help of this comprehensive guide Perform object detection, image classification and more, by combining the power of Python, Keras and Tensorflow Contains practical examples using real-world datasets to apply the concepts of deep learning to various computer vision algorithms Book Description

This book will not teach you what you already know – it directly jumps on to readying the environment required to train efficient deep learning models for a plethora of computer vision tasks such as object recognition, image classification and feature detection. In the process, you will leverage the power of Python, popular Deep Learning frameworks such as Keras and Tensorflow. You will implement the common architectures of deep learning such as convolutional neural networks, recurrent neural networks to work on your image data, with this book.

By the end of the book, you will be confident to develop and train your own deep learning models and use them to solve your Computer Vision problems.

What you will learn Setup up the environment for keras and tensorflow Train a pet classification problem while training the first deep learning model Use a pre-trained model for image retrieval problem by understanding the deeper layers of a model Learn about the solutions available of object detection and train a pedestrian detection to understand the nuances Learn about losses for similarity learning and a train a model for face recognition Train a model that can caption images by training image along with text Advance the knowledge by learning Generative Adversarial Networks and train a model that can generate images Explore video classification problem and relate video to images Learn how to deploy the trained models across platforms About the Author

Rajalingappaa is currently working as a Machine Learning Expert at SAP Innovation Center Network. Previously, he has worked/ consulted at various startups for developing computer vision products. He has a Masters from Indian Institute of Technology – Madras where his thesis was based on applications of computer vision in industry. He has published few papers in the same area.

Genres: Artificial Intelligence, Programming, Computer Science

520 pages, Kindle Edition

Published January 23, 2018

Reviews

[Keyo Çalî · Rating 3 out of 5]

if you want to implement deep learning models, this is not a good book.
this book shows you what can be done in deep learning on computer vision. you can see lots of algorithms and models used in computer vision with different datasets. however, it has a weakness in the implementation of algorithms and models.

it used lots of pre-trained and ready models, and you can't discover and get what you need to be learned.

[Carter · Rating 3 out of 5]

The content in this book seems to be more in outline form than truly a book. What is there is generally good but it needs fleshing out. Currently it's a bit too succinct but the general references are reasonable if you want to dig a bit deeper. I find it a bit hard to believe a publisher would accept something like this for publication though.

[RISHIKESAN V · Rating 5 out of 5]

Useful for interdisciplinary engineers..

This book covers all the fundamental concepts in machine learning and image processing. More practical problems were discussed. It is very useful for engineers who want to excel in the interdisciplinary area.

[Prof. Dr. · Rating 4 out of 5]

This book demonstrates the potential of deep learning and gives pointer to useful resources. But, it lacks detail