GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition by Jakub Langr (PDF)

Description

Summary GANs in Action teaches you how to build and train your own Generative Adversarial Networks, one of the most important innovations in deep learning. In this book, you’ll learn how to start building your own simple adversarial system as you explore the foundation of GAN architecture: the generator and discriminator networks. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the Technology Generative Adversarial Networks, GANs, are an incredible AI technology capable of creating images, sound, and videos that are indistinguishable from the “real thing.” By pitting two neural networks against each other–one to generate fakes and one to spot them–GANs rapidly learn to produce photo-realistic faces and other media objects. With the potential to produce stunningly realistic animations or shocking deepfakes, GANs are a huge step forward in deep learning systems. About the Book GANs in Action teaches you to build and train your own Generative Adversarial Networks. You’ll start by creating simple generator and discriminator networks that are the foundation of GAN architecture. Then, following numerous hands-on examples, you’ll train GANs to generate high-resolution images, image-to-image translation, and targeted data generation. Along the way, you’ll find pro tips for making your system smart, effective, and fast. What’s inside Building your first GANHandling the progressive growing of GANsPractical applications of GANsTroubleshooting your systemAbout the Reader For data professionals with intermediate Python skills, and the basics of deep learning-based image processing. About the Author Jakub Langr is working on ML tooling and was a Computer Vision Lead at Founders Factory. Vladimir Bok is a Senior Product Manager overseeing machine learning infrastructure and research teams at a New York-based startup. Table of Contents PART 1 – INTRODUCTION TO GANS AND GENERATIVE MODELINGIntroduction to GANs Intro to generative modeling with autoencoders Your first GAN: Generating handwritten digits Deep Convolutional GAN PART 2 – ADVANCED TOPICS IN GANSTraining and common challenges: GANing for success Progressing with GANs Semi-Supervised GAN Conditional GAN CycleGANPART 3 – WHERE TO GO FROM HERE Adversarial examples Practical applications of GANsLooking ahead

User’s Reviews

Editorial Reviews: Review Editorial Reviews: “Strikes that rare balance between an applied programming book, an academic book heavy on theory, and a conversational blog post on machine learning techniques.” –Dr. Erik Sapper, California Polytechnic State University “Comprehensive and in-depth coverage of the future of AI.” –Simeon Leyzerzon, Excelsior Software “An incredibly useful mix of practical and academic information.” –Dana Robinson, The HDF Group “A great systematization of the rapidly evolving and vast GAN landscape.” –Grigory V. Sapunov, Intento “Excellent writing combined with easy-to-grasp mathematical explanations.” –Bachir Chihani, C3 About the Author Jakub Langr graduated from Oxford University where he also taught at OU Computing Services. He has worked in data science since 2013, most recently as a data science Tech Lead at Filtered.com and as a data science consultant at Mudano. Jakub also designed and teaches Data Science courses at the University of Birmingham and is a fellow of the Royal Statistical Society.Vladimir Bok is a Senior Product Manager at Intent Media, a data science company for leading travel sites, where he helps oversee the company’s Machine Learning research and infrastructure teams. Prior to that, he was a Program Manager at Microsoft. Vladimir graduated Cum Laude with a degree in Computer Science from Harvard University. He has worked as a software engineer at early stage FinTech companies, including one founded by PayPal co-founder Max Levchin, and as a Data Scientist at a Y Combinator startup.

Reviews from Amazon users which were colected at the time this book was published on the website:

⭐Yes the book addresses GANs. However, it is more heavily focused on computer vision applications with less discussion about text related generative modeling and hardly any discussion related to structured data and/or time series applications. It is definitely a solid text, but would be even better if it addressed broader applications of GAN.

⭐5/5. Very impressed by the mix of technical detail and real world application of an emergent area in deep learning.

⭐I’m currently reviewing a couple books in the space. Some are better than others. This, like most, uses the usual data sets with examples to highlight the key aspects of design. I found the parts of the book that dived into the theory a bit frustrating… the authors clearly understand the theory behind e.g. latent space structures but the explanatory math was too minimalist to actually support the explanations. Which was too bad because their enthusiasm for the science behind the code was enticing. Ultimately, I had to switch to other material to really understand what the authors were excited about. Great subject, however, and I am ultimately happy that I read this book as part of the bigger picture.

⭐The book is too vague and does not explain in the real mathematical idea behind the constructions. A lot of time it just writes the model layers without real mathematical motivation. Also, the quality of the book got progressively worse as you go into later chapters. I usually get a book to get insights that do not exists online and in the case of this book, it does not really have insights–all it has is a collection of codes without any real explanation for the meaning behind it.

⭐The authors did give enough explanation of codes and algorithms. For example, when it comes to KL divergency, the authors didn’t give formula. When it comes to variational autoencoder, it didn’t give prediction based on testing dataset. Avoid as you can.

⭐This book is quite dry to read, lack good explanation on the theory. The models and examples use toy dataset which aren’t very useful at all.The first few chapters introducing the basics GANs are okay but you can find similar materials freely available on internet. Most of the code are taken from somebody else’s Github repo, perhaps why there lacks in-depth explanation on why the models were constructed in such a way. As already mentioned by others, the later chapters get worse. There wasn’t even model implementation for ProgressiveGAN but simply call APIs from TensorFlow Hub.I found Foster’s “Generative Deep Learning” to be easier to read. It is good for simple models up to CycleGAN but it too is lacking in advanced GANs as it dedicates only about half of the book to GANs and the rest are RNN and RL. The best and most complete book on GANs on market now is Cheong’s “Hands-on Image Generation with TensorFlow”. Not only it is easy to read but also cover all the important techniques leading to state-of-the-art models like StyleGAN to generate photorealistic faces. This is the book if you are serious about learning GANs for practical datasets.

⭐Muito bom

⭐

Keywords

Free Download GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition in PDF format
GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition PDF Free Download
Download GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition 2019 PDF Free
GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition 2019 PDF Free Download
Download GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition PDF
Free Download Ebook GANs in Action: Deep learning with Generative Adversarial Networks 1st Edition