Build GANs and Diffusion Models with TensorFlow and PyTorch

2h 22mAdvanced2022-09-15

Authors

Janani Ravi

Certified Google Cloud Architect and Data Engineer

Course details

If you’re looking for a crash course in generative modeling, this course was made for you. Generative adversarial networks (GANs) and diffusion models are some of the most important components of machine learning infrastructure. Join instructor Janani Ravi to find out more about how to get started building GANs with both dense neural as well as deep convolutional networks. Javani shows you the basics of how to train a deep convolutional GAN on multichannel images. Along the way, she gives you tips on how to get up and running with GANs using TensorFlow and diffusion models using PyTorch.

Skills covered

PulumiKubernetesMachine LearningAdvancedAmazon Web Services (AWS)AmazonGenerative AIArtificial Intelligence FoundationsArtificial Intelligence (AI)Open Source

Concepts

0. Introduction

01 - Overview of generative models
02 - Applications of generative models

1. Getting Started with Generative Adversarial Networks

03 - Introducing GANs and diffusion models
04 - Generator and discriminator
05 - Architectural overview of a GAN
06 - Training the generator and discriminator
07 - Common problems with GANs

2. Building a GAN Using a Dense Neural Network

08 - Getting set up with Google Colab
09 - Loading the fashion MNIST data set
10 - The generator network
11 - The discriminator network
12 - Adversary loss functions
13 - Training the generative adversarial network
14 - Generating images using the GAN

3. Building a GAN Using a Deep Convolutional Network

15 - Overview of CNNs
16 - Transposed convolutional layer
17 - Deep Convolutional GANs
18 - Greyscale images - Generator and discriminator in a Deep Convolutional GAN
19 - Greyscale images - Training a Deep Convolutional GAN

4. Training a Deep Convolutional GAN on Multichannel Images

20 - Color images - Loading multichannel image data
21 - Color images - Generator and discriminator in a Deep Convolutional GAN
22 - Color images - Training a Deep Convolutional GAN

5. Getting Started with Diffusion Models

23 - Generative learning trilemma
24 - Introducing denoising diffusion probabilistic models
25 - How do denoising diffusion probabilistic models work
26 - Forward diffusion process
27 - Reverse diffusion process
28 - Training a diffusion model - Intuition

6. Running a Diffusion Model

29 - Denoising diffusion probabilistic models - Exploring implementation on GitHub
30 - Denoising diffusion probabilistic models - Code overview
31 - Denoising diffusion probabilistic models - Code tweaks
32 - Denoising diffusion probabilistic models - Generating images

Conclusion

33 - Summary and next steps