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

Finding the best neural architectures with AutoML

One way to think of machine learning algorithms is that they automate the process of learning relationships between given inputs and outputs. In traditional software engineering, we would have to explicitly write/code these relationships in the form of functions that take in input and return output. In the machine learning world, machine learning models find such functions for us. Although this automation speeds the process up, there is still a lot to be done. Besides mining and cleaning data, here are a few routine tasks to be performed to get those functions:

  • Choosing a machine learning model (or a model family and then a model)
  • Deciding on the model architecture (especially in the case of deep learning)
  • Choosing hyperparameters
  • Adjusting hyperparameters based on validation set performance
  • Trying different models (or model families)

These are the kinds of tasks that justify the requirement...