The Deep Learning with PyTorch Workshop: Build deep neural networks and artificial intelligence applications with PyTorch

Description

Get a head start in the world of AI and deep learning by developing your skills with PyTorch Key FeaturesLearn how to define your own network architecture in deep learningImplement helpful methods to create and train a model using PyTorch syntaxDiscover how intelligent applications using features like image recognition and speech recognition really process your dataBook Description Want to get to grips with one of the most popular machine learning libraries for deep learning? The Deep Learning with PyTorch Workshop will help you do just that, jumpstarting your knowledge of using PyTorch for deep learning even if you're starting from scratch. It's no surprise that deep learning's popularity has risen steeply in the past few years, thanks to intelligent applications such as self-driving vehicles, chatbots, and voice-activated assistants that are making our lives easier. This book will take you inside the world of deep learning, where you'll use PyTorch to understand the complexity of neural network architectures. The Deep Learning with PyTorch Workshop starts with an introduction to deep learning and its applications. You'll explore the syntax of PyTorch and learn how to define a network architecture and train a model. Next, you'll learn about three main neural network architectures - convolutional, artificial, and recurrent - and even solve real-world data problems using these networks. Later chapters will show you how to create a style transfer model to develop a new image from two images, before finally taking you through how RNNs store memory to solve key data issues. By the end of this book, you'll have mastered the essential concepts, tools, and libraries of PyTorch to develop your own deep neural networks and intelligent apps. What you will learnExplore the different applications of deep learningUnderstand the PyTorch approach to building neural networksCreate and train your very own perceptron using PyTorchSolve regression problems using artificial neural networks (ANNs)Handle computer vision problems with convolutional neural networks (CNNs)Perform language translation tasks using recurrent neural networks (RNNs)Who this book is for This deep learning book is ideal for anyone who wants to create and train deep learning models using PyTorch. A solid understanding of the Python programming language and its packages will help you grasp the topics covered in the book more quickly. Table of ContentsIntroduction to Deep Learning and PyTorchBuilding Blocks of Neural NetworksA Classification Problem Using DNNsConvolutional Neural NetworksStyle TransferAnalyzing the Sequence of Data with RNNs Cover FM Copyright Table of Contents Preface Chapter 1: Introduction to Deep Learning and PyTorch Introduction Why Deep Learning? Applications of Deep Learning Introduction to PyTorch GPUs in PyTorch What Are Tensors? Exercise 1.01: Creating Tensors of Different Ranks Using PyTorch Advantages of Using PyTorch Disadvantages of Using PyTorch Key Elements of PyTorch The PyTorch autograd Library The PyTorch nn Module Exercise 1.02: Defining a Single-Layer Architecture The PyTorch optim Package Exercise 1.03: Training a Neural Network Activity 1.01: Creating a Single-Layer Neural Network Summary Chapter 2: Building Blocks of Neural Networks Introduction Introduction to Neural Networks What Are Neural Networks? Exercise 2.01: Performing the Calculations of a Perceptron Multi-Layer Perceptron The Learning Process of a Neural Network Forward Propagation The Calculation of Loss Functions Backward Propagation Gradient Descent Advantages and Disadvantages Advantages Disadvantages Introduction to Artificial Neural Networks Introduction to Convolutional Neural Networks Introduction to Recurrent Neural Networks Data Preparation Dealing with Messy Data Exercise 2.02: Dealing with Messy Data Data Rescaling Exercise 2.03: Rescaling Data Splitting the Data Exercise 2.04: Splitting a Dataset Disadvantages of Failing to Prepare Your Data Activity 2.01: Performing Data Preparation Building a Deep Neural Network Exercise 2.05: Building a Deep Neural Network Using PyTorch Activity 2.02: Developing a Deep Learning Solution for a Regression Problem Summary Chapter 3: A Classification Problem Using DNN Introduction Problem Definition Deep Learning in Banking Exploring the Dataset Data Preparation Building the Model ANNs for Classification Tasks A Good Architecture PyTorch Custom Modules Exercise 3.01: Defining a Model's Architecture Using Custom Modules Defining the Loss Function and Training the Model Activity 3.01: Building an ANN Dealing with an Underfitted or Overfitted Model Error Analysis Exercise 3.02: Performing Error Analysis Activity 3.02: Improving a Model's Performance Deploying Your Model Saving and Loading Your Model PyTorch for Production in C++ Building an API Exercise 3.03: Creating a Web API Activity 3.03: Making Use of Your Model Summary Chapter 4: Convolutional Neural Networks Introduction Building a CNN Why Are CNNs Used for Image Processing? The Image as Input Applications of CNNs Classification Localization Detection Segmentation The Building Blocks of CNNs Convolutional Layers Exercise 4.01: Calculating the Output Shape of a Convolutional Layer Pooling Layers Exercise 4.02: Calculating the Output Shape of a Set of Convolutional and Pooling Layers Fully Connected Layers Side Note – Downloading Datasets from PyTorch Activity 4.01: Building a CNN for an Image Classification Problem Data Augmentation Data Augmentation with PyTorch Activity 4.02: Implementing Data Augmentation Batch Normalization Batch Normalization with PyTorch Activity 4.03: Implementing Batch Normalization Summary Chapter 5: Style Transfer Introduction Style Transfer How Does It Work? Implementation of Style Transfer Using the VGG-19 Network Architecture Inputs – Loading and Displaying Exercise 5.01: Loading and Displaying Images Loading the Model Exercise 5.02: Loading a Pre-Trained Model in PyTorch Extracting the Features Exercise 5.03: Setting Up the Feature Extraction Process The Optimization Algorithm, Losses, and Parameter Update Content Loss Style Loss Total Loss Exercise 5.04: Creating the Target Image Activity 5.01: Performing Style Transfer Summary Chapter 6: Analyzing the Sequence of Data with RNNs Introduction Recurrent Neural Networks Applications of RNNs How Do RNNs Work? Input and Targets for Sequenced Data Exercise 6.01: Creating the Input and Target Variables for a Sequenced Data Problem RNNs in PyTorch Activity 6.01: Using a Simple RNN for a Time Series Prediction Long Short-Term Memory Networks Applications of LSTM Networks How Do LSTM Networks Work? LSTM Networks in PyTorch Preprocessing the Input Data Numbered Labels Generating the Batches One-Hot Encoding Exercise 6.02: Preprocessing the Input Data and Creating a One-Hot Matrix Building the Architecture Training the Model Performing Predictions Activity 6.02: Text Generation with LSTM Networks Natural Language Processing Sentiment Analysis Sentiment Analysis in PyTorch Preprocessing the Input Data Building the Architecture Training the Model Activity 6.03: Performing NLP for Sentiment Analysis Summary Appendix Index