Book Image

Deep Learning with PyTorch

By : Vishnu Subramanian
Book Image

Deep Learning with PyTorch

By: Vishnu Subramanian

Overview of this book

Deep learning powers the most intelligent systems in the world, such as Google Voice, Siri, and Alexa. Advancements in powerful hardware, such as GPUs, software frameworks such as PyTorch, Keras, TensorFlow, and CNTK along with the availability of big data have made it easier to implement solutions to problems in the areas of text, vision, and advanced analytics. This book will get you up and running with one of the most cutting-edge deep learning libraries—PyTorch. PyTorch is grabbing the attention of deep learning researchers and data science professionals due to its accessibility, efficiency and being more native to Python way of development. You'll start off by installing PyTorch, then quickly move on to learn various fundamental blocks that power modern deep learning. You will also learn how to use CNN, RNN, LSTM and other networks to solve real-world problems. This book explains the concepts of various state-of-the-art deep learning architectures, such as ResNet, DenseNet, Inception, and Seq2Seq, without diving deep into the math behind them. You will also learn about GPU computing during the course of the book. You will see how to train a model with PyTorch and dive into complex neural networks such as generative networks for producing text and images. By the end of the book, you'll be able to implement deep learning applications in PyTorch with ease.
Table of Contents (11 chapters)

Data preprocessing and feature engineering

We have looked at different ways to split our datasets to build our evaluation strategy. In most cases, the data that we receive may not be in a format that can be readily used by us for training our algorithms. In this section, we will cover some of the preprocessing techniques and feature engineering techniques. Though most of the feature engineering techniques are domain-specific, particularly in the areas of computer vision and text, there are some common feature engineering techniques that are common across the board, which we will discuss in this chapter.

Data preprocessing for neural networks is a process in which we make the data more suitable for the deep learning algorithms to train on. The following are some of the commonly-used data preprocessing steps:

  • Vectorization
  • Normalization
  • Missing values
  • Feature extraction
...