AI Workshop: Hands-on with GANs with Deep Convolutional Networks

Course details

If you’re looking for hands-on AI practice, this workshop-style coding course was designed for you. Join instructor Janani Ravi as she shows you how to build and train deep convolutional generative adversarial networks (DCGANs). Explore the core components of convolutional and pooling layers, including setting up Google Colab cloud-hosted notebooks, transforming multichannel images to tensors, applying layers, and viewing filter effects. Janani covers the basics of training a discriminator as a classification model and training a deep convolutional GAN like a pro, from setting up data for GAN training, setting up the generator and discriminator, and outputting from an untrained generator and discriminator to creating a training loop, viewing and evaluating results, and more.

Concepts

0. Introduction

01 - A quick overview of GANs

1. Understanding Convolutional and Pooling Layers

02 - Course outline and prerequisites
03 - Setting up Google Colab cloud-hosted notebooks
04 - Understanding convolutional neural networks
05 - Transforming a multichannel image to tensor
06 - Applying convolutional and pooling layers
07 - Viewing the effect of different filters

3. Training a Discriminator as a Classification Model

08 - Types of convolutional layers
09 - Training data for discriminator bad fakes and real images
10 - Loading and transforming training image data
11 - Understanding the discriminator architecture
12 - Training a discriminator on bad fakes
13 - Training data for discriminator good fakes and real images
14 - Training a discriminator on good fakes

3. Training a Deep Convolutional GAN

15 - Generator and discriminator
16 - Deep convolutional GANs (DCGANs)
17 - Setting up data for GAN training
18 - Setting up the generator and discriminator
19 - Output from an untrained generator and discriminator
20 - Setting up the GAN training loop
21 - Viewing GAN training results

Conclusion

22 - Summary and next steps