Practical Machine Learning for Computer Vision: End-to-End Machine Learning for Images

by Valliappa Lakshmanan, Martin Görner, Ryan Gillard

This practical book shows you how to employ machine learning models to extract information from images. ML engineers and data scientists will learn how to solve a variety of image problems including classification, object detection, autoencoders, image generation, counting, and captioning with proven ML techniques. This book provides a great introduction to end-to-end deep dataset creation, data preprocessing, model design, model training, evaluation, deployment, and interpretability. Google engineers Valliappa Lakshmanan, Martin Görner, and Ryan Gillard show you how to develop accurate and explainable computer vision ML models and put them into large-scale production using robust ML architecture in a flexible and maintainable way. You'll learn how to design, train, evaluate, and predict with models written in TensorFlow or Keras. You'll learn how

Genres: Artificial Intelligence

480 pages, Paperback

Published August 24, 2021

Reviews

[Minh Nguyen · Rating 5 out of 5]

I have been using no-code computer vision like Google Cloud AutoML Vision, and it works very well. However, in the new project, I may need to develop an end-to-end ML pipeline for Computer Vision, so I am reading this book. It is very well written and practical. Lak is a great tutor! I have bought some books from him and am very satisfied with them.

In this book, Lak starts from a simple image classification tutorial to more sophisticated object detection with R-CNN. The best part of this book is from Chapter 5 to Chapter 10, where he provides a step-by-step tutorial on how to develop ML Ops for Computer Vision. Highly recommended for Computer Vision practitioners, also for those interested in developing end-to-end ML pipelines on Google Cloud.

One cautionary note: running the tutorials requires heavy GPU computing resources. I am running this on GCP VM instances and it has already cost me a few hundred dollars. Be careful with your computing resources.

[Shreyas · Rating 5 out of 5]

What makes this book good is the way the chapters are organised and the intuitive way different architectures are explained. It covers many neural network architectures related to computer vision and explains the developments that have taken place in the field in a step by step manner.

[Matthew Mechtly · Rating 5 out of 5]

A fantastically thorough introduction to getting started on NN-related computer vision tasks. I haven't played with many of the code snippets yet, but assuming those work relatively well, this really is a fantastic resource.

[Mayada · Rating 4 out of 5]

I found this book really helpful. It helped me get started with machine learning for computer vision, which I needed for my final year project in university.
I recommend it!