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)

Model ensembling

There could be times when we would need to try to combine multiple models to build a very powerful model. There are many techniques that can be used for building an ensemble model. In this section, we will learn how to combine outputs using the features generated by three different models (ResNet, Inception, and DenseNet) to build a powerful model. We will be using the same dataset that we used for other examples in this chapter.

The architecture for the ensemble model would look like this:

This image shows what we are going to do in the ensemble model, which can be summarized in the following steps:

  1. Create three models
  2. Extract the image features using the created models
  3. Create a custom dataset which returns features of all the three models along with the labels
  4. Create model similar to the architecture in the preceding figure
  5. Train and validate the model