PyTorch Recipes : A Problem-Solution Approach to Build, Train and Deploy Neural Network Models

Mishra, Pradeepta

ISBN 10: 1484289269 / ISBN 13: 9781484289266

Published by Apress 2022-12, 2022

About this Item

Seller Inventory # 6666-IUK-9781484289266

Bibliographic Details

• Title: PyTorch Recipes : A Problem-Solution Approach to Build, Train and Deploy Neural Network Models
• Publisher: Apress 2022-12
• Publication Date: 2022
• Language: English
• ISBN 10: 1484289269
• ISBN 13: 9781484289266
• Binding: PF
• Condition: New

About this title

Synopsis

Chapter 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.