Book Image

Mastering PyTorch - Second Edition

By : Ashish Ranjan Jha
4 (1)
Book Image

Mastering PyTorch - Second Edition

4 (1)
By: Ashish Ranjan Jha

Overview of this book

PyTorch is making it easier than ever before for anyone to build deep learning applications. This PyTorch deep learning book will help you uncover expert techniques to get the most out of your data and build complex neural network models. You’ll build convolutional neural networks for image classification and recurrent neural networks and transformers for sentiment analysis. As you advance, you'll apply deep learning across different domains, such as music, text, and image generation, using generative models, including diffusion models. You'll not only build and train your own deep reinforcement learning models in PyTorch but also learn to optimize model training using multiple CPUs, GPUs, and mixed-precision training. You’ll deploy PyTorch models to production, including mobile devices. Finally, you’ll discover the PyTorch ecosystem and its rich set of libraries. These libraries will add another set of tools to your deep learning toolbelt, teaching you how to use fastai to prototype models and PyTorch Lightning to train models. You’ll discover libraries for AutoML and explainable AI (XAI), create recommendation systems, and build language and vision transformers with Hugging Face. By the end of this book, you'll be able to perform complex deep learning tasks using PyTorch to build smart artificial intelligence models.
Table of Contents (21 chapters)
20
Index

Understanding image generation using diffusion

Does Figure 10.1 seem normal to you?

Figure 10.1: AI-generated image using diffusion showing the Taj Mahal, India, right next to the Eiffel Tower, France

The Eiffel Tower and the Taj Mahal are situated in two different countries. However, this AI-generated image places them next to each other in a parallel world. This image was generated starting from random noise using a process called diffusion, as shown in Figure 10.2.

Figure 10.2: Generating a realistic image from pure noise using diffusion

Diffusion in the context of generative AI consists of a step-by-step process where simple noise is transformed multiple times to create diverse realistic data, resulting in high-quality sample generation by refining noise iteratively until it resembles the desired data, as demonstrated in Figure 10.3.

Figure 10.3: Diffusion as a step-by-step process of denoising an initial noisy image into a photo-realistic image...