Keras Deep Learning and Generative Adversarial Networks (GAN)

Learn deep learning and Generative Adversarial Networks (GAN) using Python with Keras

Created by Abhilash Nelson

Start with the basics of Python programming and gradually move into the world of deep learning and Generative Adversarial Networks. Build a strong foundation in neural networks, then apply your skills to real-world AI projects using Keras. No prior programming experience is needed to get started.

Packt | Sep 2023 | 1036 min

Start Trial

LevelExpert

CategoriesData Science, Deep Learning Architectures and Frameworks, Keras, Python

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

What You Will Learn

You will begin by learning Python fundamentals and essential libraries like NumPy. As you progress, you will explore neural networks and deep learning concepts, then put theory into practice by building and training models. Step-by-step guidance and hands-on exercises help you gain practical experience with Keras and GANs.

Key Features

Master Python essentials and key libraries for deep learning projects
Build and train neural networks and GANs using Keras and real datasets
Apply deep learning techniques to image processing and classification tasks

Target Audience

Ideal for beginners interested in deep learning and AI, especially those aiming for roles like machine learning engineer or data scientist. If you want to start from scratch and develop skills to build and deploy advanced neural networks and GANs, this learning path is a great fit for you.

Related courses

Cover image for Python for Deep Learning — Build Neural Networks in Python

Cover image for Deep Learning Using Keras - A Complete and Compact Guide for Beginners

Pro

Cover image for Modern Deep Learning Foundations

Cover image for AI & Python Development Megaclass

Cover image for AI Engineer Associate Course