Hands-On Generative Adversarial Networks with PyTorch 2.x: Gain hands-on expertise in utilizing robust Generative AI models to tackle a wide array of challenges

Explore the creation of AI-generated images, videos, and audio, and gain proficiency in designing, training, and optimizing various types of generative networks for diverse applications using PyTorch Key Features Implement GAN architectures to generate images, text, audio, 3D models, and more Understand how GANs work and become an active contributor in the open-source community Learn about using GANs in combination with other generative models, such as Transformers and Diffusion Models Book DescriptionGenerative AI is the most spoken of AI direction in media nowadays, and this book is aimed at assisting you in becoming an expert in its most well-established class of models - Generative Adversarial Nets. With the help of this book, you will work your way up from understanding the basic components and architecture of GANs, building your first model from scratch to designing, building, training and optimizing a wide variety of these powerful models. You will go way beyond theoretical knowledge and gain hands-on experience in finding the right type of GAN for each specific problem using PyTorch examples provided in every chapter. You will cover important image-generation and translation architectures such as classic and conditional GANs, DCGANs, StyleGANs, CycleGANs, and pix2pix. Learn to synthesize sequences, text and audio, and generate videos. Finally, we will dive into the state-of-the-art hybrid models of GANs with other generative models. By the end of this book, you will be an expert in practical applications of GANs to real-world problems.What you will learn Use PyTorch's latest features to ensure efficient model design Get to grips with the working mechanisms of GAN models Build and train a range of GANs to perform a variety of image synthesis and editing operations Perform style transfer between unpaired and unpaired image collections with CycleGAN and pix2pix Train GANs for video generation and video-to-video translation Acquire the skills to use GANs for imitation learning and other automation tasks Understand how to use elements of GANs in combination with other generative models Attain a comprehensive understanding of the privacy and ethical considerations Who this book is forThis GAN book is for machine learning practitioners and deep learning researchers looking to get hands-on guidance in implementing GAN models using PyTorch. You'll become familiar with state-of-the-art GAN architecture with the help of real-world examples. Working knowledge of Python programming language is necessary to grasp the concepts covered in this book.

Table of Contents:
Table of Contents Basics of Generative Models Getting Started with PyTorch 2.0 Useful tricks for model designing Building your first GAN with PyTorch Interactively generating images via Conditional GAN Producing Photorealistic images with StyleGAN2/3 Image-to-image translation and its applications Image restoration with GANs Training your GANs to break other people’s models Image generation from description text Sequence synthesis with GANs Video Generation with GANs Reconstructing 3D models with GANs GANs for Imitation Learning and Other Automation Tasks Hybrid models: Using GANs in combination with Transformers or Diffusion Models Where generative models are heading? Commercial Use and Ethical Considerations when deploying generative models

About the Author :
Marija currently holds the position of a Senior Machine Learning Research Scientist at Metaphysic.ai. She has worked in Generative AI research for over 8 years, 5+ of them specifically with GANs. Previous employers and projects include Meta, iCAIRD (NHS Scotland), Seebyte (Batelle Company), and DREAM (EU Horizon2020). Her PhD is in Generative Models Applications to Robotics and Automation, acquired from the University of Edinburgh. She also has an MSc in Computational Statistics and Machine Learning from the University College London. She has authored multiple academic publications in several prestigious peer-reviewed venues in the fields of Machine Learning and Robotics, such as IEEE IROS, ICRA, and TPAMI.