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.

Related Content you might be interested in

Current Title:

Small book image
Deep Learning with PyTorch
Vishnu Subramanian
Feb, 2018 | 262 pages
Small book image
PyTorch Deep Learning Hands-On
Sherin Chacko Thomas | Sudhanshu Passi
Apr, 2019 | 250 pages
Small book image
Mastering PyTorch
Ashish Ranjan Jha
Feb, 2021 | 450 pages
Small book image
PyTorch Artificial Intelligence Fundamentals
Jibin Mathew
Feb, 2020 | 200 pages
Table of Contents (11 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Getting Started with Deep Learning Using PyTorch
Getting Started with Deep Learning Using PyTorch
Artificial intelligence
Machine learning
Deep learning
Summary
2
Building Blocks of Neural Networks
Building Blocks of Neural Networks
Installing PyTorch
Our first neural network
Summary
3
Diving Deep into Neural Networks
Diving Deep into Neural Networks
Deep dive into the building blocks of neural networks
Summary
4
Fundamentals of Machine Learning
Fundamentals of Machine Learning
Three kinds of machine learning problems
Machine learning glossary
Evaluating machine learning models
Data preprocessing and feature engineering
Overfitting and underfitting
Workflow of a machine learning project
Summary
5
Deep Learning for Computer Vision
Deep Learning for Computer Vision
Introduction to neural networks
Building a CNN model from scratch
Creating and exploring a VGG16 model
Calculating pre-convoluted features
Understanding what a CNN model learns
Visualizing weights of the CNN layer
Summary
6
Deep Learning with Sequence Data and Text
Deep Learning with Sequence Data and Text
Working with text data
Training word embedding by building a sentiment classifier
Using pretrained word embeddings
Recursive neural networks
LSTM
Convolutional network on sequence data
Summary
7
Generative Networks
Generative Networks
Neural style transfer
Generative adversarial networks
Deep convolutional GAN
Language modeling
Summary
8
Modern Network Architectures
Modern Network Architectures
Modern network architectures
Densely connected convolutional networks – DenseNet
Model ensembling
Encoder-decoder architecture
Summary
9
What Next?
What Next?
What next?
Overview
Interesting ideas to explore
How to keep yourself updated
Summary
10
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Deep convolutional GAN

In this section, we will implement different parts of training a GAN architecture, based on the DCGAN paper I mentioned in the preceding information box. Some of the important parts of training a DCGAN include:

  • A generator network, which maps a latent vector (list of numbers) of some fixed dimension to images of some shape. In our implementation, the shape is (3, 64, 64).
  • A discriminator network, which takes as input an image generated by the generator or from the actual dataset, and maps to that a score estimating if the input image is real or fake.
  • Defining loss functions for generator and discriminator.
  • Defining an optimizer.
  • Training a GAN.

Let's explore each of these sections in detail. The implementation is based on the code, which is available in the PyTorch examples at:

https://github.com/pytorch/examples/tree/master/dcgan

...
Previous Section
End of Section 4
Next Section