Make Your First GAN Using PyTorch

Description

In this course, you will :

• Pytorch basics
• Making a neural network with PyTorch
• Refining the neural network output
• Basics of CUDA
• The basic idea of GAN
• Learning a simple 1010 pattern using GAN
• Learning handwritten digits using GAN
• Learning human faces using GAN
• Convolutional GANs
• Conditional GANs
• You will dive into PyTorch and build a simple image classifier to refresh your understanding of neural networks.
• Investigate the concept of adversarial training and build progressively more sophisticated GANs, beginning with a simple 1010 pattern, then moving on to monochrome images of handwritten digits, and finally full-color images of faces.

Syllabus :

1. PyTorch Basics

• Why PyTorch?
• Pytorch Tensors
• Automatic Gradients with PyTorch
• Computation Graphs
• Learning Points in PyTorch Basics

 

2. First PyTorch Neural Network

• MNIST Image Dataset
• Simple Neural Network
• Visualizing Training
• The MNIST Dataset Class
• Training Our Classifier
• Querying Our Neural Network
• Simple Classifier Performance
• Learning Points in First PyTorch Neural Network

 

3. Refinements

• Loss Function
• Activation Function
• Optimisation Function
• Normalisation
• Combined Refinements
• Learning Points in Refinements

 

4. CUDA Basics

• NumPy vs. Python
• Nvidia CUDA
• Using CUDA in Python
• Learning Points in CUDA Basics

 

5. The GAN Idea

• Generating Images
• Adversarial Training
• Training a GAN
• Learning Points in The GAN Idea

 

6. Simple 1010 Pattern

• Generating Real Data
• Building The Discriminator
• Training and Testing The Discriminator
• Building The Generator
• Training The 1010 Pattern GAN
• Learning Points in Simple 1010 Pattern

 

7. Handwritten Digits

• The MNIST Dataset Class
• The MNIST Discriminator
• The MNIST Generator
• Training the MNIST GAN
• Mode Collapse
• Improving GAN Training
• Experimenting with Seeds
• Learning Points in Handwritten Digits

 

8. Human Faces

• The Colour Images
• CelebA Dataset
• The Dataset Class
• The Discriminator
• The Generator
• Training The Human Faces GAN
• Learning Points in Human Faces

 

9. Convolutional GANs

• MNIST CNN
• CelebA CNN
• Experimentation
• Learning Points in Convolutional GANs

 

10. Conditional GANs

• Introduction to Conditional GANs
• The Discriminator
• The Generator
• Training the MNIST cGAN
• Conditional GAN Results
• Learning Points in Conditional GANs

Show more