Название: Learn Generative AI with PyTorch (MEAP v2)
Автор: Mark Liu
Издательство: Manning Publications
Год: 2024
Страниц: 298
Язык: английский
Формат: pdf, epub
Размер: 52.8 MB

Create your own generative AI models for text, images, music, and more!

Generative AI tools like ChatGPT, Bard, and DALL-E have transformed the way we work. Learn Generative AI with PyTorch takes you on an incredible hands-on journey through creating and training AI models using Python, the free PyTorch framework and the hardware you already have in your office. Along the way, you’ll master the fundamentals of General Adversarial Networks (GANs), Transformers, Large Language Models (LLMs), variational autoencoders, diffusion models, LangChain, and more!

All generative models in this book are deep neural networks. The book starts with a comprehensive Deep Learning project in PyTorch, ideal for those new to the field. Each chapter is carefully structured to build upon the previous one, especially beneficial for readers new to Deep Learning in PyTorch. You'll start by creating basic content like shapes, numbers, and images using Generative Adversarial Networks (GANs) with straightforward architectures. As you progress, the complexity increases, culminating in building advanced models like Transformers.

In Learn Generative AI with PyTorch you’ll build these amazing models:

A simple English-to-French translator
A text-generating model as powerful as GPT-2
A diffusion model that produces realistic flower images
Music generators using GANs and Transformers
An image style transfer model
A zero-shot know-it-all agent

All you need is Python and the fundamentals of Machine Learning to get started. You’ll learn the rest as you go!

about the book
Learn Generative AI with PyTorch teaches the underlying mechanics of generative AI by building working AI models from scratch. Every model you’ll create is fun and fascinating, with projects that include generating color images of anime faces, changing photograph’s hair color, training a model to write like Hemingway, and generating music in the style of Mozart.

Throughout, you’ll use the intuitive PyTorch framework that’s instantly familiar to anyone who’s worked with Python data tools. You’ll begin by creating simple content like shapes, numbers, and images using Generative Adversarial Networks (GANs). Then, each chapter introduces a new project as you work towards building your own LLMs.

about the reader
For Python programmers who know the basics of machine learning. No knowledge of PyTorch or generative AI required.

about the author
Dr. Mark Liu is a tenured finance professor and the founding director of the Master of Science in Finance program at the University of Kentucky. He has more than 20 years of coding experience, a Ph.D. in finance from Boston College.