Keras Deep Learning and Generative Adversarial Networks (GAN)

Keras Deep Learning and Generative Adversarial Networks (GAN)

by Abhilash Nelson
Released September 2023
Publisher(s): Packt Publishing
ISBN: 9781805125495

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

The course begins with the fundamentals of Python, encompassing concepts such as assignment, flow control, lists, tuples, dictionaries, and functions. We then move on to the Python NumPy library, which supports large arrays and matrices.

Before embarking on the journey of deep learning, a comprehensive theoretical session awaits, expounding upon the essential structure of an artificial neuron and its amalgamation to form an artificial neural network. The exploration then delves into the realm of CNNs, text-based models, binary and multi-class classification, and the intricate world of image processing. The transformation continues with an in-depth exploration of the GAN paradigm, spanning from fundamental principles to advanced strategies. Attendees will have the opportunity to construct models, harness transfer learning techniques, and venture into the realm of conditional GANs.

Once we complete the fully connected GAN, we will then proceed with a more advanced Deep Convoluted GAN, or DCGAN. We will discuss what a DCGAN is and see the difference between a DCGAN and a fully connected GAN. Then we will try to implement the DCGAN. We will define the Generator function and define the Discriminator function.

By the end of the course, you will wield the skills to create, fine-tune, and deploy cutting-edge AI solutions, setting you apart in this evolving landscape.

What You Will Learn

  • Learn about Artificial Intelligence (AI) and machine learning
  • Understand deep learning and neural networks
  • Learn about lists, tuples, dictionaries, and functions in Python
  • Learn Pandas, NumPy, and Matplotlib basics
  • Explore the basic structure of artificial neurons and neural network
  • Understand Stride, Padding, and Flattening concepts of CNNs

Audience

This course is designed for newcomers aiming to excel in deep learning and Generative Adversarial Networks (GANs) starting from the basics. Progress from novice to advanced through immersive learning. Suitable for roles like machine learning engineer, deep learning specialist, AI researcher, data scientist, and GAN developer.

About The Author

Abhilash Nelson: Abhilash Nelson is a pioneering, talented, and security-oriented Android/iOS mobile and PHP/Python web application developer with more than eight years of IT experience involving designing, implementing, integrating, testing, and supporting impactful web and mobile applications. He has a master’s degree in computer science and engineering and has PHP/Python programming experience, which is an added advantage for server-based Android and iOS client applications. Abhilash is currently a senior solution architect managing projects from start to finish to ensure high quality and innovative and functional design.

Table of contents

  1. Chapter 1 : Introduction
    1. Course Introduction and Table of Contents
  2. Chapter 2 : Introduction to AI and Machine Learning
    1. Introduction to AI and Machine Learning
  3. Chapter 3 : Introduction to Deep learning and Neural Networks
    1. Introduction to Deep learning and Neural Networks
  4. Chapter 4 : Setting Up Computer - Installing Anaconda
    1. Setting Up Computer - Installing Anaconda
  5. Chapter 5 : Python Basics - Flow Control
    1. Python Basics - Flow Control - Part 1
    2. Python Basics - Flow Control - Part 2
  6. Chapter 6 : Python Basics - Lists and Tuples
    1. Python Basics - Lists and Tuples
  7. Chapter 7 : Python Basics - Dictionaries and Functions
    1. Python Basics - Dictionaries and Functions - part 1
    2. Python Basics - Dictionary and Functions - part 2
  8. Chapter 8 : NumPy Basics
    1. NumPy Basics - Part 1
    2. NumPy Basics - Part 2
  9. Chapter 9 : Matplotlib Basics
    1. Matplotlib Basics - part 1
    2. Matplotlib Basics - part 2
  10. Chapter 10 : Pandas Basics
    1. Pandas Basics - Part 1
    2. Pandas Basics - Part 2
  11. Chapter 11 : Installing Deep Learning Libraries
    1. Installing Deep Learning Libraries
  12. Chapter 12 : Basic Structure of Artificial Neuron and Neural Network
    1. Basic Structure of Artificial Neuron and Neural Network
  13. Chapter 13 : Activation Functions Introduction
    1. Activation Functions Introduction
  14. Chapter 14 : Popular Types of Activation Functions
    1. Popular Types of Activation Functions
  15. Chapter 15 : Popular Types of Loss Functions
    1. Popular Types of Loss Functions
  16. Chapter 16 : Popular Optimizers
    1. Popular Optimizers
  17. Chapter 17 : Popular Neural Network Types
    1. Popular Neural Network Types
  18. Chapter 18 : King County House Sales Regression Model - Step 1 Fetch and Load Dataset
    1. King County House Sales Regression Model - Step 1 Fetch and Load Dataset
  19. Chapter 19 : Steps 2 and 3 - EDA and Data Preparation
    1. Steps 2 and 3 - EDA and Data Preparation - Part 1
    2. Steps 2 and 3 - EDA and Data Preparation - Part 2
  20. Chapter 20 : Step 4 - Defining the Keras Model
    1. Step 4 Defining the Keras Model - Part 1
    2. Step 4 Defining the Keras Model - Part 2
  21. Chapter 21 : Steps 5 and 6 - Compile and Fit Model
    1. Steps 5 and 6 Compile and Fit Model
  22. Chapter 22 : Step 7 Visualize Training and Metrics
    1. Step 7 Visualize Training and Metrics
  23. Chapter 23 : Step 8 Prediction Using the Model
    1. Step 8 Prediction Using the Model
  24. Chapter 24 : Heart Disease Binary Classification Model - Introduction
    1. Heart Disease Binary Classification Model - Introduction
  25. Chapter 25 : Step 1 - Fetch and Load Data
    1. Step 1 - Fetch and Load Data
  26. Chapter 26 : Steps 2 and 3 - EDA and Data Preparation
    1. Steps 2 and 3 - EDA and Data Preparation - Part 1
    2. Steps 2 and 3 - EDA and Data Preparation - Part 2
  27. Chapter 27 : Step 4 - Defining the Model
    1. Step 4 - Defining the Model
  28. Chapter 28 : Step 5 – Compile, Fit, and Plot the Model
    1. Step 5 – Compile, Fit, and Plot the Model
  29. Chapter 29 : Step 5 - Predicting Heart Disease Using Model
    1. Step 5 - Predicting Heart Disease Using Model
  30. Chapter 30 : Step 6 - Testing and Evaluating Heart Disease Model
    1. Step 6 - Testing and Evaluating Heart Disease Model - Part 1
    2. Step 6 - Testing and Evaluating Heart Disease Model - Part 2
  31. Chapter 31 : Redwine Quality Multiclass Classification Model - Introduction
    1. Redwine Quality Multiclass Classification Model - Introduction
  32. Chapter 32 : Step1 - Fetch and Load Data
    1. Step1 - Fetch and Load Data
  33. Chapter 33 : Step 2 - EDA and Data Visualization
    1. Step 2 - EDA and Data Visualization
  34. Chapter 34 : Step 3 - Defining the Model
    1. Step 3 - Defining the Model
  35. Chapter 35 : Step 4 – Compile, Fit, and Plot the Model
    1. Step 4 – Compile, Fit, and Plot the Model
  36. Chapter 36 : Step 5 - Predicting Wine Quality Using Model
    1. Step 5 - Predicting Wine Quality Using Model
  37. Chapter 37 : Serialize and Save Trained Model for Later Usage
    1. Serialize and Save Trained Model for Later Usage
  38. Chapter 38 : Digital Image Basics
    1. Digital Image Basics
  39. Chapter 39 : Basic Image Processing Using Keras Functions
    1. Basic Image Processing Using Keras Functions - Part 1
    2. Basic Image Processing Using Keras Functions - Part 2
    3. Basic Image Processing using Keras Functions - Part 3
  40. Chapter 40 : Keras Single Image Augmentation
    1. Keras Single Image Augmentation - Part 1
    2. Keras Single Image Augmentation - Part 2
  41. Chapter 41 : Keras Directory Image Augmentation
    1. Keras Directory Image Augmentation
  42. Chapter 42 : Keras Data Frame Augmentation
    1. Keras Data Frame Augmentation
  43. Chapter 43 : CNN Basics
    1. CNN Basics
  44. Chapter 44 : Stride, Padding, and Flattening Concepts of CNN
    1. Stride, Padding, and Flattening Concepts of CNN
  45. Chapter 45 : Flowers CNN Image Classification Model – Fetch, Load, and Prepare Data
    1. Flowers CNN Image Classification Model – Fetch, Load, and Prepare Data
  46. Chapter 46 : Flowers Classification CNN - Create Test and Train Folders
    1. Flowers Classification CNN - Create Test and Train Folders
  47. Chapter 47 : Flowers Classification CNN - Defining the Model
    1. Flowers Classification CNN - Defining the Model - Part 1
    2. Flowers Classification CNN - Defining the Model - Part 2
    3. Flowers Classification CNN - Defining the Model - Part 3
  48. Chapter 48 : Flowers Classification CNN - Training and Visualization
    1. Flowers Classification CNN - Training and Visualization
  49. Chapter 49 : Flowers Classification CNN - Save Model for Later Use
    1. Flowers Classification CNN - Save Model for Later Use
  50. Chapter 50 : Flowers Classification CNN - Load Saved Model and Predict
    1. Flowers Classification CNN - Load Saved Model and Predict
  51. Chapter 51 : Flowers Classification CNN - Optimization Techniques - Introduction
    1. Flowers Classification CNN - Optimization Techniques - Introduction
  52. Chapter 52 : Flowers Classification CNN - Dropout Regularization
    1. Flowers Classification CNN - Dropout Regularization
  53. Chapter 53 : Flowers Classification CNN - Padding and Filter Optimization
    1. Flowers Classification CNN - Padding and Filter Optimization
  54. Chapter 54 : Flowers Classification CNN - Augmentation Optimization
    1. Flowers Classification CNN - Augmentation Optimization
  55. Chapter 55 : Hyperparameter Tuning
    1. Hyperparameter Tuning - Part 1
    2. Hyperparameter Tuning - Part 2
  56. Chapter 56 : Transfer Learning Using Pre-Trained Models - VGG Introduction
    1. Transfer Learning Using Pre-Trained Models - VGG Introduction
  57. Chapter 57 : VGG16 and VGG19 Prediction
    1. VGG16 and VGG19 Prediction- Part 1
    2. VGG16 and VGG19 Prediction- Part 2
  58. Chapter 58 : ResNet50 Prediction
    1. ResNet50 Prediction
  59. Chapter 59 : VGG16 Transfer Learning Training Flowers Dataset
    1. VGG16 Transfer Learning Training Flowers Dataset - part 1
    2. VGG16 Transfer Learning Training Flowers Dataset - Part 2
  60. Chapter 60 : VGG16 Transfer Learning Flower Prediction
    1. VGG16 Transfer Learning Flower Prediction
  61. Chapter 61 : VGG16 Transfer Learning Using Google Colab GPU - Preparing and Uploading Dataset
    1. VGG16 Transfer Learning Using Google Colab GPU - Preparing and Uploading Dataset
  62. Chapter 62 : VGG16 Transfer Learning Using Google Colab GPU - Training and Prediction
    1. VGG16 Transfer Learning Using Google Colab GPU - Training and Prediction
  63. Chapter 63 : VGG19 Transfer Learning Using Google Colab GPU - Training and Prediction
    1. VGG19 Transfer Learning Using Google Colab GPU - Training and Prediction
  64. Chapter 64 : ResNet50 Transfer Learning Using Google Colab GPU - Training and Prediction
    1. ResNet50 Transfer Learning Using Google Colab GPU - Training and Prediction
  65. Chapter 65 : Popular Neural Network Types
    1. Popular Neural Network Types
  66. Chapter 66 : Generative Adversarial Networks GAN Introduction
    1. Generative Adversarial Networks GAN Introduction
  67. Chapter 67 : Simple Transpose Convolution Using a Grayscale Image
    1. Simple Transpose Convolution Using a Grayscale Image - Part 1
    2. Simple Transpose Convolution Using a Grayscale Image - Part 2
    3. Simple Transpose Convolution Using a Grayscale Image - Part 3
  68. Chapter 68 : Generator and Discriminator Mechanism Explained
    1. Generator and Discriminator Mechanism Explained
  69. Chapter 69 : A fully Connected Simple GAN Using MNIST Dataset - Introduction
    1. A Fully Connected Simple GAN Using MNIST Dataset - Introduction
  70. Chapter 70 : Fully Connected GAN - Loading the Dataset
    1. Fully Connected GAN - Loading the Dataset
  71. Chapter 71 : Fully Connected GAN - Defining the Generator Function
    1. Fully Connected GAN - Defining the Generator Function - Part 1
    2. Fully Connected GAN - Defining the Generator Function - Part 2
  72. Chapter 72 : Fully Connected GAN - Defining the Discriminator Function
    1. Fully Connected GAN - Defining the Discriminator Function - Part 1
    2. Fully Connected GAN - Defining the Discriminator Function - Part 2
  73. Chapter 73 : Fully Connected GAN - Combining Generator and Discriminator Models
    1. Fully Connected GAN - Combining Generator and Discriminator Models
  74. Chapter 74 : Fully Connected GAN - Compiling Discriminator and Combined GAN Models
    1. Fully Connected GAN - Compiling Discriminator and Combined GAN Models
  75. Chapter 75 : Fully Connected GAN - Discriminator Training
    1. Fully Connected GAN - Discriminator Training - Part 1
    2. Fully Connected GAN - Discriminator Training - Part 2
    3. Fully Connected GAN - Discriminator Training - Part 3
  76. Chapter 76 : Fully Connected GAN - Generator Training
    1. Fully Connected GAN - Generator Training
  77. Chapter 77 : Fully Connected GAN - Saving Log at Each Interval
    1. Fully Connected GAN - Saving Log at Each Interval
  78. Chapter 78 : Fully Connected GAN - Plot the Log at Intervals
    1. Fully Connected GAN - Plot the Log at Intervals
  79. Chapter 79 : Fully Connected GAN - Display Generated Images
    1. Fully Connected GAN - Display Generated Images - Part 1
    2. Fully Connected GAN - Display Generated Images - Part 2
  80. Chapter 80 : Saving the Trained Generator for Later Use
    1. Saving the Trained Generator for Later Use
  81. Chapter 81 : Generating Fake Images Using the Saved GAN Model
    1. Generating Fake Images Using the Saved GAN Model
  82. Chapter 82 : Fully Connected GAN Versus Deep Convoluted GAN
    1. Fully Connected GAN Versus Deep Convoluted GAN
  83. Chapter 83 : Deep Convolutional GAN - Loading the MNIST Handwritten Digits Dataset
    1. Deep Convolutional GAN - Loading the MNIST Handwritten Digits Dataset
  84. Chapter 84 : Deep Convolutional GAN - Defining the Generator Function
    1. Deep Convolutional GAN - Defining the Generator Function - Part 1
    2. Deep Convolutional GAN - Defining the Generator Function - Part 2
  85. Chapter 85 : Deep Convolutional GAN - Defining the Discriminator Function
    1. Deep Convolutional GAN - Defining the Discriminator Function
  86. Chapter 86 : Deep Convolutional GAN - Combining and Compiling the Model
    1. Deep Convolutional GAN - Combining and Compiling the Model
  87. Chapter 87 : Deep Convolutional GAN - Training the Model
    1. Deep Convolutional GAN - Training the Model
  88. Chapter 88 : Deep Convolutional GAN - Training the Model Using Google Colab GPU
    1. Deep Convolutional GAN - Training the Model Using Google Colab GPU
  89. Chapter 89 : Deep Convolutional GAN - Loading the Fashion MNIST Dataset
    1. Deep Convolutional GAN - Loading the Fashion MNIST Dataset
  90. Chapter 90 : Deep Convolutional GAN - Training the MNIST Fashion Model Using Google Colab GPU
    1. Deep Convolutional GAN - Training the MNIST Fashion Model Using Google Colab GPU
  91. Chapter 91 : Deep Convolutional GAN - Loading the CIFAR-10 Dataset and Defining the Generator
    1. Deep Convolutional GAN - Loading the CIFAR-10 Dataset and Generator - Part 1
    2. Loading the CIFAR-10 Dataset and Defining the Generator - part 2
  92. Chapter 92 : Deep Convolutional GAN - Defining the Discriminator
    1. Deep Convolutional GAN - Defining the Discriminator
  93. Chapter 93 : Deep Convolutional GAN CIFAR-10 - Training the Model
    1. Deep Convolutional GAN CIFAR-10 - Training the Model
  94. Chapter 94 : Deep Convolutional GAN - Training the CIFAR-10 Model Using Google Colab GPU
    1. Deep Convolutional GAN - Training the CIFAR-10 Model Using Google Colab GPU
  95. Chapter 95 : Vanilla GAN Versus Conditional GAN
    1. Vanilla GAN Versus Conditional GAN
  96. Chapter 96 : Conditional GAN - Defining the Basic Generator Function
    1. Conditional GAN - Defining the Basic Generator Function
  97. Chapter 97 : Conditional GAN - Label Embedding for Generator
    1. Conditional GAN - Label Embedding for Generator - Part 1
    2. Conditional GAN - Label Embedding for Generator - Part 2
  98. Chapter 98 : Conditional GAN - Defining the Basic Discriminator Function
    1. Conditional GAN - Defining the Basic Discriminator Function
  99. Chapter 99 : Conditional GAN - Label Embedding for Discriminator
    1. Conditional GAN - Label Embedding for Discriminator
  100. Chapter 100 : Conditional GAN - Combining and Compiling the Model
    1. Conditional GAN - Combining and Compiling the Model
  101. Chapter 101 : Conditional GAN - Training the Model
    1. Conditional GAN - Training the Model - Part 1
    2. Conditional GAN - Training the Model - Part 2
  102. Chapter 102 : Conditional GAN - Display Generated Images
    1. Conditional GAN - Display Generated Images
  103. Chapter 103 : Conditional GAN - Training the MNIST Model Using Google Colab GPU
    1. Conditional GAN - Training the MNIST Model Using Google Colab GPU
  104. Chapter 104 : Conditional GAN - Training the Fashion MNIST Model Using Google Colab GPU
    1. Conditional GAN - Training the Fashion MNIST Model Using Google Colab GPU
  105. Chapter 105 : Other Popular GANs - Further Reference and Source Code Link
    1. Other Popular GANs - Further Reference and Source Code Link

Product information

  • Title: Keras Deep Learning and Generative Adversarial Networks (GAN)
  • Author(s): Abhilash Nelson
  • Release date: September 2023
  • Publisher(s): Packt Publishing
  • ISBN: 9781805125495