Deep Learning with PyTorch: Guide for Beginners and Intermediate

By Mark Watson

This book is an exploration of deep learning in Python using PyTorch. The author guides you on how to create neural network models using PyTorch in Python. You will know the initial steps of getting started with PyTorch in Python. This involves installing PyTorch and writing your first code. PyTorch works using the concept of graphs. The author helps you know how build neural network graphs in PyTorch. Deep learning in Python with PyTorch simply involves the creation of neural network models. The author helps you understand how to create neural network models with TensorFlow. You are guided on how to train such models with data of various types. Examples of such data include images and text. The process of loading your own data into PyTorch for training neural network models has also been discussed. You will also know how to use the inbuilt data for training your neural network models.

This book will help you to understand:

- Why PyTorch for Deep Learning?

- Getting Started with PyTorch

- Building a Neural Network

- Loading and Processing Data

- Convolutional Neural Networks

- Transfer Learning

- Developing Distributed Applications

- Word Embeddings

- Moving a Model from PyTorch to Caffe2

- Custom C Extensions

- Neural Transfer with PyTorch

Tags: pytorch deep learning, python programming, python, python data science handbook, neural network python, tensorflow python, tensorflow for deep learning, python code programming.

• Format: Paperback
• Language: English
• ISBN: 1795409207
• ISBN13: 9781795409209
• Release Date: January 2019
• Publisher: Independently Published
• Length: 96 Pages
• Weight: 0.31 lbs.
• Dimensions: 0.2" x 6.0" x 9.0"