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)

Creating and exploring a VGG16 model

PyTorch provides a set of trained models in its torchvision library. Most of them accept an argument called pretrained when True, which downloads the weights tuned for the ImageNet classification problem. Let's look at the code snippet that creates a VGG16 model:

from torchvision import models
vgg = models.vgg16(pretrained=True)

Now we have our VGG16 model with all the pre-trained weights ready to be used. When the code is run for the first time, it could take several minutes, depending on your internet speed. The size of the weights could be around 500 MB. We can take a quick look at the VGG16 model by printing it. Understanding how these networks are implemented turns out to be very useful when we use modern architectures. Let's take a look at the model:

VGG (
  (features): Sequential (
    (0): Conv2d(3, 64, kernel_size=(3, 3)...