Concepts and Programming in PyTorch

  • 1h 42m
  • Chitra Vasudevan
  • BPB Publications
  • 2018

The book has been written in such a way that the concepts are explained in detail, giving adequate emphasis on examples. To make clarity of the programming examples, logic is explained properly as well as discussed by using comments in the program itself. The book covers the topics right from the start of the software by using coding in software and writing programs into it. The book features more on practical approach with more examples covering topics from simple to complex one addressing many of the core concepts and advanced topics also.

Key Features

  • Basics concepts of PyTorch like CNN architecture, RNN architecture are discussed in a detailed manner.
  • Each and every chapter consists of Points to Remember, Interview questions, Exercise and Case studies wherever applicable.
  • In fact, the worked out case studies are also dealt in a detailed manner.
  • At the end of chapters, the observations of this PyTorch is also given for the better understanding of the topic.
  • Many worked out coding examples are also given.
  • The Book was highly self-explanatory as well as user-friendly.

This book will “need to have”:

  • Gaining Customers by adopting and implementing PyTorch in / projects/programs and in Research Departments.
  • Help in sustaining Customer Relationships as the core of all successful working relationships are two essential characteristics: trust and commitment. To demonstrate their trustworthiness and commitment to customers, progressive suppliers periodically provide evidence to customers of their accomplishments.
  • Help in delivering “Superior Value and Getting an Equitable Return” as the understanding value in business markets and doing business based on value delivered gives suppliers the means to get an equitable return for their efforts.

In this Book

  • Introduction to PyTorch
  • Linear Regression
  • Convolution Neural Network (CNN)
  • Recurrent Neural Networks (RNN)
  • PyTorch Datasets
  • Observations in PyTorch