Keras Deep Learning And Generative Adversarial Networks (GAN)
Create images and text with GANs in Python and Keras. This deep learning course is perfect for beginners – no coding experience required. Join the AI revolution! Read more.
5.0( 1 REVIEWS )
4 STUDENTS
17h 6m
Course Skill Level
Beginner
Time Estimate
17h 6m
I am a Post Graduate Masters Degree holder in Computer Science and Engineering with experience in Android/iOS Mobile and PHP/Python Web Developer Apps
Access all courses in our library for only $9/month with All Access Pass
Get Started with All Access PassBuy Only This CourseAbout This Course
Who this course is for:
- This deep learning course is perfect for beginners who want to learn about deep learning and Generative Adversarial Networks (GAN).
What you’ll learn:
- Build GANs using Python with Keras.
- Learn deep learning from scratch to expert level.
- Dive into Python and Keras for GAN and deep learning.
Requirements:
- No programming experience is needed; just bring your enthusiasm for GAN and deep learning.
- You might also be interested in taking Complete And Compact Dummies Guide To Deep Learning Using Keras first if you’re a complete beginner.
Course Highlights:
Introduction to Deep Learning Course
- Comprehend the basics of Artificial Intelligence, Machine Learning, and deep learning.
- Set up your coding environment using Anaconda and Jupyter notebook.
- Learn Python basics and essential libraries (Numpy, Matplotlib, and Pandas).
Deep Learning Essentials
- Delve into Theano, TensorFlow, and Keras for deep learning.
- Explore the basic structure of an Artificial Neuron and Neural Network.
- Understand activation functions, loss functions, and optimizers.
Text-Based Deep Learning Models
- Create text-based models for regression, binary classification, and multi-class classification.
- Work on real-world datasets like King County house prices, Heart Disease data, and Red Wine Quality data.
- Train, evaluate, and visualize models using Keras and Matplotlib.
Image-Based Deep Learning Models
- Learn digital image basics and image processing using Keras.
- Implement Convolutional Neural Networks (CNNs) for image classification.
- Work on diverse datasets, including flowers, MNIST, MNIST Fashion, and CIFAR-10.
Advanced Techniques and Transfer Learning
- Explore optimization techniques, dropout regularization, and image augmentation.
- Dive into Hyperparameter tuning for efficient model improvement.
- Harness the power of transfer learning using renowned models like VGG16, VGG19, and ResNet50.
Generative Adversarial Networks (GAN)
- Understand the basics of GANs and their components (Generator and Discriminator).
- Implement a Fully Connected GAN and a deep learning tutorial for a Deep Convolutional GAN (DCGAN).
- Explore image generation with MNIST, MNIST Fashion, and CIFAR-10 datasets.
Conditional Generative Adversarial Networks (CGAN)
- Compare Vanilla GANs with Conditional GAN.
- Implement CGAN with label embedding for MNIST and MNIST Fashion datasets.
- Discover other popular types of GANs and access a valuable git repository for further exploration.
Resources:
- Access a shared folder with code, images, models, and weights used in the course.
Get ready for an exciting deep learning tutorial journey into the realms of Deep Learning and Generative Adversarial Networks. See you in the classroom – happy learning!
Our Promise to You
By the end of this deep learning course, you will have learned GAN using Python with Keras.
10 Day Money Back Guarantee. If you are unsatisfied for any reason, simply contact us and we’ll give you a full refund. No questions asked.
Get started today!
Course Curriculum
| Section 1 - Introduction | |||
| Course Introduction And Table Of Contents | 00:00:00 | ||
| Source Code Links | 00:00:00 | ||
| Introduction To AI And Machine Learning | 00:00:00 | ||
| Introduction To Deep Learning And Neural Networks | 00:00:00 | ||
| Setting Up Computer – Installing Anaconda | 00:00:00 | ||
| Section 2 - Basics | |||
| Python Basics – Flow Control – Part 1 | 00:00:00 | ||
| Python Basics – Flow Control – Part 2 | 00:00:00 | ||
| Python Basics – List And Tuples | 00:00:00 | ||
| Python Basics – Dictionary And Functions – Part 1 | 00:00:00 | ||
| Python Basics – Dictionary And Functions – Part 2 | 00:00:00 | ||
| Numpy Basics – Part 1 | 00:00:00 | ||
| Numpy Basics – Part 2 | 00:00:00 | ||
| Matplotlib Basics – Part 1 | 00:00:00 | ||
| Matplotlib Basics – Part 2 | 00:00:00 | ||
| Pandas Basics – Part 1 | 00:00:00 | ||
| Pandas Basics – Part 2 | 00:00:00 | ||
| Section 3 - Installing Deep Learning Libraries | |||
| Installing Deep Learning Libraries | 00:00:00 | ||
| Section 4 - Basic Structure Of Artificial Neuron And Neural Network | |||
| Basic Structure Of Artificial Neuron And Neural Network | 00:00:00 | ||
| Section 5 - Activation Functions Introduction | |||
| Activation Functions Introduction | 00:00:00 | ||
| Section 6 - Popular Types | |||
| Popular Types Of Activation Functions | 00:00:00 | ||
| Popular Types Of Loss Functions | 00:00:00 | ||
| Popular Optimizers | 00:00:00 | ||
| Popular Neural Network Types | 00:00:00 | ||
| Section 7 - King County House Sales Regression Model | |||
| King County House Sales Regression Model – Step 1 Fetch And Load Dataset | 00:00:00 | ||
| Step 2 And 3 EDA And Data Preparation – Part 1 | 00:00:00 | ||
| Step 2 And 3 EDA And Data Preparation – Part 2 | 00:00:00 | ||
| Step 4 Defining The Keras Model – Part 1 | 00:00:00 | ||
| Step 4 Defining The Keras Model – Part 2 | 00:00:00 | ||
| Step 5 And 6 Compile And Fit Model | 00:00:00 | ||
| Step 7 Visualize Training And Metrics | 00:00:00 | ||
| Step 8 Prediction Using The Model | 00:00:00 | ||
| Section 8 - Heart Disease Binary Classification Model | |||
| Heart Disease Binary Classification Model – Introduction | 00:00:00 | ||
| Step 1 – Fetch And Load Data | 00:00:00 | ||
| Step 2 And 3 – EDA And Data Preparation – Part 1 | 00:00:00 | ||
| Step 2 And 3 – EDA And Data Preparation – Part 2 | 00:00:00 | ||
| Step 4 – Defining The Model | 00:00:00 | ||
| Step 5 – Compile Fit And Plot The Model | 00:00:00 | ||
| Step 5 – Predicting Heart Disease Using Model | 00:00:00 | ||
| Step 6 – Testing And Evaluating Heart Disease Model – Part 1 | 00:00:00 | ||
| Step 6 – Testing And Evaluating Heart Disease Model – Part 2 | 00:00:00 | ||
| Section 9 - Redwine Quality MultiClass Classification Model | |||
| Redwine Quality Multiclass Classification Model – Introduction | 00:00:00 | ||
| Step1 – Fetch And Load Data | 00:00:00 | ||
| Step 2 – EDA And Data Visualization | 00:00:00 | ||
| Step 3 – Defining The Model | 00:00:00 | ||
| Step 4 – Compile Fit And Plot The Model | 00:00:00 | ||
| Step 5 – Predicting Wine Quality Using Model | 00:00:00 | ||
| Serialize And Save Trained Model For Later Usage | 00:00:00 | ||
| Digital Image Basics | 00:00:00 | ||
| Section 10 - Basic Image Processing Using Keras Functions | |||
| Basic Image Processing Using Keras Functions – Part 1 | 00:00:00 | ||
| Basic Image Processing Using Keras Functions – Part 2 | 00:00:00 | ||
| Basic Image Processing Using Keras Functions – Part 3 | 00:00:00 | ||
| Section 11 - Keras Image Augmentation | |||
| Keras Single Image Augmentation – Part 1 | 00:00:00 | ||
| Keras Single Image Augmentation – Part 2 | 00:00:00 | ||
| Keras Directory Image Augmentation | 00:00:00 | ||
| Keras Data Frame Augmentation | 00:00:00 | ||
| Section 12 - CNN Basics | |||
| CNN Basics | 00:00:00 | ||
| Stride Padding And Flattening Concepts Of CNN | 00:00:00 | ||
| Section 13 - Flowers CNN Image Classification Model - Fetch Load And Prepare Data | |||
| Flowers CNN Image Classification Model – Fetch Load And Prepare Data | 00:00:00 | ||
| Flowers Classification CNN – Create Test And Train Folders | 00:00:00 | ||
| Flowers Classification CNN – Defining The Model – Part 1 | 00:00:00 | ||
| Flowers Classification CNN – Defining The Model – Part 2 | 00:00:00 | ||
| Flowers Classification CNN – Defining The Model – Part 3 | 00:00:00 | ||
| Flowers Classification CNN – Training And Visualization | 00:00:00 | ||
| Flowers Classification CNN – Save Model For Later Use | 00:00:00 | ||
| Flowers Classification CNN – Load Saved Model And Predict | 00:00:00 | ||
| Flowers Classification CNN – Optimization Techniques – Introduction | 00:00:00 | ||
| Flowers Classification CNN – Dropout Regularization | 00:00:00 | ||
| Flowers Classification CNN – Padding And Filter Optimization | 00:00:00 | ||
| Flowers Classification CNN – Augmentation Optimization | 00:00:00 | ||
| Section 14 - Hyper Parameter Tuning | |||
| Hyper Parameter Tuning – Part 1 | 00:00:00 | ||
| Hyper Parameter Tuning – Part 2 | 00:00:00 | ||
| Section 15 - Transfer Learning Using Pretrained Models - VGG Introduction | |||
| Transfer Learning Using Pretrained Models – VGG Introduction | 00:00:00 | ||
| VGG16 And VGG19 Prediction – Part 1 | 00:00:00 | ||
| VGG16 And VGG19 Prediction – Part 2 | 00:00:00 | ||
| ResNet50 Prediction | 00:00:00 | ||
| VGG16 Transfer Learning Training Flowers Dataset – Part 1 | 00:00:00 | ||
| VGG16 Transfer Learning Training Flowers Dataset – Part 2 | 00:00:00 | ||
| VGG16 Transfer Learning Flower Prediction | 00:00:00 | ||
| VGG16 Transfer Learning Using Google Colab GPU – Preparing And Uploading Dataset | 00:00:00 | ||
| VGG16 Transfer Learning Using Google Colab GPU – Training And Prediction | 00:00:00 | ||
| VGG19 Transfer Learning Using Google Colab GPU – Training And Prediction | 00:00:00 | ||
| Resnet50 Transfer Learning Using Google Colab GPU – Training And Prediction | 00:00:00 | ||
| Section 16 - Popular Neural Network Types | |||
| Popular Neural Network Types | 00:00:00 | ||
| Section 17 - Generative Adversarial Networks GAN Introduction | |||
| Generative Adversarial Networks GAN Introduction | 00:00:00 | ||
| Section 18 - Simple Transpose Convolution Using A Grayscale Image | |||
| Simple Transpose Convolution Using A Grayscale Image – Part 1 | 00:00:00 | ||
| Simple Transpose Convolution Using A Grayscale Image – Part 2 | 00:00:00 | ||
| Simple Transpose Convolution Using A Grayscale Image – Part 3 | 00:00:00 | ||
| Section 19 - Generator And Discriminator Mechanism Explained | |||
| Generator And Discriminator Mechanism Explained | 00:00:00 | ||
| Section 20 - A Fully Connected Simple GAN Using MNIST Dataset - Introduction | |||
| A Fully Connected Simple GAN Using MNIST Dataset – Introduction | 00:00:00 | ||
| Fully Connected GAN – Loading The Dataset | 00:00:00 | ||
| Fully Connected GAN – Defining The Generator Function – Part 1 | 00:00:00 | ||
| Fully Connected GAN – Defining The Generator Function – Part 2 | 00:00:00 | ||
| Fully Connected GAN – Defining The Discriminator Function – Part 1 | 00:00:00 | ||
| Fully Connected GAN – Defining The Discriminator Function – Part 2 | 00:00:00 | ||
| Fully Connected GAN – Combining Generator And Discriminator Models | 00:00:00 | ||
| Fully Connected GAN – Compiling Discriminator And Combined GAN Models | 00:00:00 | ||
| Fully Connected GAN – Discriminator Training – Part 1 | 00:00:00 | ||
| Fully Connected GAN – Discriminator Training – Part 2 | 00:00:00 | ||
| Fully Connected GAN – Discriminator Training – Part 3 | 00:00:00 | ||
| Fully Connected GAN – Generator Training | 00:00:00 | ||
| Fully Connected GAN – Saving Log At Each Interval | 00:00:00 | ||
| Fully Connected GAN – Plot The Log At Intervals | 00:00:00 | ||
| Fully Connected GAN – Display Generated Images – Part 1 | 00:00:00 | ||
| Fully Connected GAN – Display Generated Images – Part 2 | 00:00:00 | ||
| Saving The Trained Generator For Later Use | 00:00:00 | ||
| Generating Fake Images Using The Saved GAN Model | 00:00:00 | ||
| Fully Connected GAN Vs Deep Convoluted GAN | 00:00:00 | ||
| Section 21 - Deep Convolutional GAN - Loading The MNIST Hand Written Digits Dataset | |||
| Deep Convolutional GAN – Loading The MNIST Hand Written Digits Dataset | 00:00:00 | ||
| Deep Convolutional GAN – Defining The Generator Function – Part 1 | 00:00:00 | ||
| Deep Convolutional GAN – Defining The Generator Function – Part 2 | 00:00:00 | ||
| Deep Convolutional GAN – Defining The Discriminator Function | 00:00:00 | ||
| Deep Convolutional GAN – Combining And Compiling The Model | 00:00:00 | ||
| Deep Convolutional GAN – Training The Model | 00:00:00 | ||
| Deep Convolutional GAN – Training The Model Using Google Colab GPU | 00:00:00 | ||
| Deep Convolutional GAN – Loading The Fashion MNIST Dataset | 00:00:00 | ||
| Deep Convolutional GAN – Training The MNIST Fashion Model Using Google Colab GPU | 00:00:00 | ||
| Deep Convolutional GAN – Loading The CIFAR-10 Dataset And Generator – Part 1 | 00:00:00 | ||
| Loading The CIFAR-10 Dataset And Defining The Generator – Part 2 | 00:00:00 | ||
| Deep Convolutional GAN – Defining The Discriminator | 00:00:00 | ||
| Deep Convolutional GAN CIFAR 10 – Training The Model | 00:00:00 | ||
| Deep Convolutional GAN – Training The CIFAR10 Model Using Google Colab GPU | 00:00:00 | ||
| Section 22 - Vanilla GAN Vs Conditional GAN | |||
| Vanilla GAN Vs Conditional GAN | 00:00:00 | ||
| Conditional GAN – Defining The Basic Generator Function | 00:00:00 | ||
| Conditional GAN – Label Embedding For Generator – Part 1 | 00:00:00 | ||
| Conditional GAN – Label Embedding For Generator – Part 2 | 00:00:00 | ||
| Conditional GAN – Defining The Basic Discriminator Function | 00:00:00 | ||
| Conditional GAN – Label Embedding For Discriminator | 00:00:00 | ||
| Conditional GAN – Combining And Compiling The Model | 00:00:00 | ||
| Conditional GAN – Training The Model – Part 1 | 00:00:00 | ||
| Conditional GAN – Training The Model – Part 2 | 00:00:00 | ||
| Conditional GAN – Display Generated Images | 00:00:00 | ||
| Conditional GAN – Training The MNIST Model Using Google Colab GPU | 00:00:00 | ||
| Conditional GAN – Training The Fashion MNIST Model Using Google Colab GPU | 00:00:00 | ||
| Section 23 - Other Popular GANS - Further Reference | |||
| Other Popular GANs – Further Reference | 00:00:00 | ||