Description
Book SynopsisLearn how to use PyTorch to build neural network models using code snippets updated for this second edition. This book includes new chapters covering topics such as distributed PyTorch modeling, deploying PyTorch models in production, and developments around PyTorch with updated code. You'll start by learning how to use tensors to develop and fine-tune neural network models and implement deep learning models such as LSTMs, and RNNs. Next, you'll explore probability distribution concepts using PyTorch, as well as supervised and unsupervised algorithms with PyTorch. This is followed by a deep dive on building models with convolutional neural networks, deep neural networks, and recurrent neural networks using PyTorch. This new edition covers also topics such as Scorch, a compatible module equivalent to the Scikit machine learning library, model quantization to reduce parameter size, and preparing a model for deployment within a production system. Distributed parallel processing for bala
Trade Review“The book covers all important facets of neural network implementation and modeling, and could definitely be useful to students and developers keen for an in-depth look at how to build models using PyTorch, or how to engineer particular neural network features using this platform.” (Mariana Damova, Computing Reviews, July 24, 2023)
Table of ContentsChapter 1: Introduction to PyTorch, Tensors, and Tensor Operations
Chapter Goal: This chapter is to understand what is PyTorch and its basic building blocks.
Chapter 2: Probability Distributions Using PyTorch
Chapter Goal: This chapter aims at covering different distributions compatible with PyTorch for data analysis.
Chapter 3: Neural Networks Using PyTorch
Chapter Goal: This chapter explains the use of PyTorch to develop a neural network model and optimize the model.
Chapter 4: Deep Learning (CNN and RNN) Using PyTorch
Chapter Goal: This chapter explains the use of PyTorch to train deep neural networks for complex datasets.
Chapter 5: Language Modeling Using PyTorch
Chapter Goal: In this chapter, we are going to use torch text for natural language processing, pre-processing, and feature engineering.
Chapter 6: Supervised Learning Using PyTorch
Goal: This chapter explains how supervised learning algorithms implementation with PyTorch.
Chapter 7: Fine Tuning Deep Learning Models using PyTorch
Goal: This chapter explains how to Fine Tuning Deep Learning Models using the PyTorch framework.
Chapter 8: Distributed PyTorch Modeling
Chapter Goal: This chapter explains the use of parallel processing using the PyTorch framework.
Chapter 9: Model Optimization Using Quantization Methods
Chapter Goal: This chapter explains the use of quantization methods to optimize the PyTorch models and hyperparameter tuning with ray tune.
Chapter 10: Deploying PyTorch Models in Production
Chapter Goal: In this chapter we are going to use torch serve, to deploy the PyTorch models into production.
Chapter 11: PyTorch for Audio
Chapter Goal: In this chapter torch audio will be used for audio resampling, data augmentation, features extractions, model training, and pipeline development.
Chapter 12: PyTorch for Image
Chapter Goal: This chapter aims at using Torchvision for image transformations, pre-processing, feature engineering, and model training.
Chapter 13: Model Explainability using Captum
Chapter Goal: In this chapter, we are going to use the captum library for model interpretability to explain the model as if you are explaining the model to a 5-year-old.
Chapter 14: Scikit Learn Model compatibility using Skorch
Chapter Goal: In this chapter, we are going to use skorch which is a high-level library for PyTorch that provides full sci-kit learn compatibility.
