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

Get a head start in the world of AI and deep learning by developing your skills with PyTorch Key Features * Learn how to define your own network architecture in deep learning * Implement helpful methods to create and train a model using PyTorch syntax * Discover how intelligent applications using fe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Saleh, Hyatt
Format: E-Book
Sprache:Englisch
Veröffentlicht: Birmingham Packt Publishing 2020
Packt Publishing, Limited
Ausgabe:1
ISBN:9781838981846, 1838981845, 1838989218, 9781838989217
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • 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