Practical Deep Learning for Cloud, Mobile, and Edge: Real-World AI & Computer-Vision Projects Using Python, Keras & TensorFlow 1st Edition, Kindle Edition
Use the Amazon App to scan ISBNs and compare prices.
The Amazon Book Review
Book recommendations, author interviews, editors' picks, and more. Read it now.
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
From the Author
Nearly every chapter begins with a motivating example, establishes the questions upfront that one might ask through the process of building a solution, and discusses multiple approaches to solve the problem, each with varying levels of complexity and effort involved. If you are seeking a quick solution, you might end up just reading a few pages of a chapter and be done. Someone wanting to gain a deeper understanding of the subject should read the entire chapter. Of course, everyone should peruse the case studies at the end of each chapter for two reasons--they are fun to read and they showcase how people in the industry are using the concepts discussed in the chapter to build real products (over 40 discussed).
We also discuss many of the practical concerns faced by deep learning practitioners and industry professionals in building real-world applications using the cloud, browsers, mobile, and edge devices. We compiled a number of practical "tips and tricks", as well as life-lessons in this book to encourage our readers to build applications that can make someone's day just a little bit better.
To the Backend/Frontend/Mobile Software DeveloperYou are quite likely a proficient programmer already. Even if Python is an unfamiliar language to you, we expect that you will be able to pick it up easily and get started in no time. Best of all, we don't expect you to have any background in machine learning and AI; that's what we are here for! We believe that you will gain value from the book's focus in the following areas:
- How to build user-facing AI products.
- How to train models quickly.
- How to minimize the code and effort required in prototyping.
- How to make models more performant and energy-efficient.
- How to operationalize and scale, and estimate the costs involved.
- Discover how AI is applied in the industry with 40+ case studies.
- Develop a broad-spectrum knowledge of deep learning.
- Develop a generalized skill set that can be applied on new frameworks (e.g., PyTorch), domains (e.g., healthcare, robotics), input modalities (e.g., video, audio, text), and tasks (e.g., image segmentation, one-shot learning).
- Speed up your training, including on multi-node clusters.
- Build an intuition for developing and debugging models, including hyperparameter tuning, thus dramatically improving model accuracy.
- Understand how your model works, uncover bias in the data, and automatically determine the best hyperparameters as well as model architecture using AutoML.
- Learn tips and tricks used by other data scientists, including gathering data quickly, tracking your experiments in an organized manner, sharing your models with the world, and being up to date on the best available models for your task.
- Use tools to deploy and scale your best model to real users, and even automatically (without involving a dev-ops team).
- Aspire to a career in AI by developing a portfolio of interesting projects.
- Learn from industry practices to help prepare for internships and job opportunities.
- Unleash your creativity by building fun applications like an autonomous car.
- Prepare for interviews for jobs in the AI field.
- Become an AI for Good champion by using your creativity to solve the most pressing problems faced by humanity.
To the Robotics EnthusiastRobotics is exciting. If you're a robotics enthusiast, we don't really need to convince you that adding intelligence to robots is the way to go. Increasingly capable hardware platforms such as Raspberry Pi, NVIDIA Jetson Nano, Google Coral, Intel Movidius, PYNQ-Z2, and others are helping drive innovation in the robotics space. As we grow towards Industry 4.0, (some of) these platforms will become more and more relevant and ubiquitous. With this book, you will:
- Learn how to build and train AI, and then bring it to the edge.
- Benchmarking and compare edge devices on performance, size, power, battery and costs.
- Understand how to choose the optimal AI algorithm and device for a given scenario.
- Learn on how other makers are building creative robots and machines.
- Learn how to further progress in the field and showcase your work.
- Publication Date : October 14, 2019
- File Size : 102494 KB
- Print Length : 620 pages
- Word Wise : Not Enabled
- Publisher : O'Reilly Media; 1st Edition (October 14, 2019)
- Language: : English
- ASIN : B07Z7957PL
- Text-to-Speech : Enabled
- Simultaneous Device Usage : Unlimited
- X-Ray : Not Enabled
- Enhanced Typesetting : Enabled
- Lending : Not Enabled
- Best Sellers Rank: #248,017 in Kindle Store (See Top 100 in Kindle Store)
- Customer Reviews:
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
EDIT: Having spent a bit more time with the book, I can update the review with a bit more detail. This book is quite witty with many funny examples. Kudos to the authors for taking the time to be so inventive with their practical deep learning examples. This book has mentions of many interesting applications of machine learning on mobile and in other places. Some nice CoreML and python examples which came in quite handy.
The authors did a great job explaining the important concepts of deep learning. I remembered it took me a while to understand and remember the concept of backpropagation when I first learned NN at school. The way they explained it, particularly the diagrams, was so clear and spot-on. Wish I had this book when I was a student.
After reading the first four chapters, I was able to follow the simple steps and make an image classifier with high accuracy, which was what I needed for the project at work. I went a step further and also tried out the image recommendation system from chapter 4, which helped me in understanding image features in greater detail and how to scale it up for large datasets.
I used to think it would take a long time for me to be able to apply deep learning at work because I was overwhelmed by questions like the framework I should use, the programming language, and where I can start collecting training data.. This book answered all my questions and provided just what I needed for me to get my work done. I highly recommend this book to anyone who wants to be familiarized with deep learning and be able to start coding and shipping production-ready machine learning projects.
The writing style is a bit off but could be due to the use of Grammerly (mentioned in Personal Acknowledgements).
The lack of a digital standalone book is also a minus. You'd think in this age O'Reilly would try to reduce the costs associated with printing books rather than try to make what they can on (subscription) profits.
Top reviews from other countries
The concept of machine learning does not need to be intimidating. It can be fun, rewarding and motivating. And, this book just does the job right!
Es el tercer libro de esta compañía (O'REILLY) que compro, y el segundo que me sale mal.
La calidad de impresión es muy mala, acartonada y el papel parece que se va a rasgar en cualquier momento, pero eso no es lo peor, sino que está impreso en blanco y negro, lo cual dificulta mucho entender ciertas imágenes. Esto, para un libro enfocado en redes neuronales, y más en concreto aplicadas a vision artificial, es algo pésimo, ya que se pierde muchísima información al no poder ver el color en las imágenes y los gráficos.
Adjunto imágenes donde pueda apreciarse la razón de mi queja.
Practical examples, latest frameworks, supported by GitHub code snippets/examples.