What do you think?
Rate this book
Make Your First GAN With PyTorch
A gentle introduction to Generative Adversarial Networks, and a practical step-by-step tutorial on making your own with PyTorch.
This beginner-friendly guide will give you hands-on It will introduce GANs, one of the most exciting areas of machine Beyond the very basics, readers can explore more sophisticated The appendices will be useful for students of machine learning as they explain themes often skipped over in many All code is available publicly as open source on github.
This beginner-friendly guide will give you hands-on It will introduce GANs, one of the most exciting areas of machine Beyond the very basics, readers can explore more sophisticated The appendices will be useful for students of machine learning as they explain themes often skipped over in many All code is available publicly as open source on github.
207 pages, Paperback
Published March 14, 2020
3 people are currently reading
38 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 2 of 2 reviews
July 5, 2021
I Can't buy the kindle edition of this book from amazon !!!
Where i can buy a kindle edition of this book ???
Where i can buy a kindle edition of this book ???
March 22, 2020
GANs are one of the hottest topics in machine learning at the moment.
Yes, there are lots of blogs, papers, textbooks and YouTube videos explaining what they are. What this book does, that many can't, is explain GANs in a way that almost anyone with school maths can understand.
If you've read the author's previous book Make Your Own Neural Network, you'll know why it is an Amazon #1 Bestseller. The author really has thought carefully about what to teach and also what not to cover, to ensure as many people as possible can work through the guide without feeling discouraged. His talent is not that he knows everything, but that he can explain concepts in a way that any curious reader with school maths can understand. He's not precious about using friendly language, and I can tell he chooses words that are simple, when others would have chosen jargon or longer cleverer words. His diagrams and visualisations really help people like me who learn and think visually.
The book is a hands on tutorial. So don't but this if you're looking for a reference on the theory. The book "holds your hand" as you journey from zero to understanding intuitively how GAN's work. As you work through the book you develop simple, then intermediate, then more complex networks. And this works well because you learn the important ideas with simple examples, so you're ready for the more complex ones.
I myself really appreciated the appendix with worked examples of convolutions. I spent hours reading blogs and watching videos and none managed to explain them. Now they're easy!
Even though the book isn't a specific guide to PyTorch, it is probably one of the best introductions I have ever read. It starts from python and numpy examples that we're familiar with, and then gently develops the pytorch equivalents, just to show how easy it is to use pytorch. The computation graph idea made sense for the first time, to me at least.
This book isn't advanced. It's not meant to be. If you're already experienced in machine learning, this won't be for you. If you're looking for a primer, or struggling with the recommended texts, this book will help. you get started.
The author promises genuine experience, and I do feel I have some now. I have now actually built several neural networks and GANs with pytorch. And I've seen some of the things that can go wrong, and have a rough plan for how to fix them.
If you liked Make Your Own Neural Network - this is the one for you!
Yes, there are lots of blogs, papers, textbooks and YouTube videos explaining what they are. What this book does, that many can't, is explain GANs in a way that almost anyone with school maths can understand.
If you've read the author's previous book Make Your Own Neural Network, you'll know why it is an Amazon #1 Bestseller. The author really has thought carefully about what to teach and also what not to cover, to ensure as many people as possible can work through the guide without feeling discouraged. His talent is not that he knows everything, but that he can explain concepts in a way that any curious reader with school maths can understand. He's not precious about using friendly language, and I can tell he chooses words that are simple, when others would have chosen jargon or longer cleverer words. His diagrams and visualisations really help people like me who learn and think visually.
The book is a hands on tutorial. So don't but this if you're looking for a reference on the theory. The book "holds your hand" as you journey from zero to understanding intuitively how GAN's work. As you work through the book you develop simple, then intermediate, then more complex networks. And this works well because you learn the important ideas with simple examples, so you're ready for the more complex ones.
I myself really appreciated the appendix with worked examples of convolutions. I spent hours reading blogs and watching videos and none managed to explain them. Now they're easy!
Even though the book isn't a specific guide to PyTorch, it is probably one of the best introductions I have ever read. It starts from python and numpy examples that we're familiar with, and then gently develops the pytorch equivalents, just to show how easy it is to use pytorch. The computation graph idea made sense for the first time, to me at least.
This book isn't advanced. It's not meant to be. If you're already experienced in machine learning, this won't be for you. If you're looking for a primer, or struggling with the recommended texts, this book will help. you get started.
The author promises genuine experience, and I do feel I have some now. I have now actually built several neural networks and GANs with pytorch. And I've seen some of the things that can go wrong, and have a rough plan for how to fix them.
If you liked Make Your Own Neural Network - this is the one for you!
Displaying 1 - 2 of 2 reviews