Build GANs and Diffusion Models with TensorFlow and PyTorch

Contents

• Introduction Introduction

  • Overview of generative models

    3m 53s
  • Applications of generative models

    3m 41s
• 1. Getting Started with Generative Adversarial Networks 1. Getting Started with Generative Adversarial Networks

  • Introducing GANs and diffusion models

    3m 8s
  • (Locked)
    Generator and discriminator

    5m 36s
  • (Locked)
    Architectural overview of a GAN

    1m 45s
  • (Locked)
    Training the generator and discriminator

    4m 58s
  • (Locked)
    Common problems with GANs

    4m 58s
• 2. Building a GAN Using a Dense Neural Network 2. Building a GAN Using a Dense Neural Network

  • Getting set up with Google Colab

    3m 56s
  • (Locked)
    Loading the fashion MNIST data set

    3m 58s
  • (Locked)
    The generator network

    3m 43s
  • (Locked)
    The discriminator network

    3m 34s
  • (Locked)
    Adversary loss functions

    4m 18s
  • (Locked)
    Training the generative adversarial network

    6m 17s
  • (Locked)
    Generating images using the GAN

    3m 50s
• 3. Building a GAN Using a Deep Convolutional Network 3. Building a GAN Using a Deep Convolutional Network

  • Overview of CNNs

    4m 18s
  • (Locked)
    Transposed convolutional layer

    4m 22s
  • (Locked)
    Deep Convolutional GANs

    4m 28s
  • (Locked)
    Greyscale images: Generator and discriminator in a Deep Convolutional GAN

    6m 33s
  • (Locked)
    Greyscale images: Training a Deep Convolutional GAN

    6m 19s
• 4. Training a Deep Convolutional GAN on Multichannel Images 4. Training a Deep Convolutional GAN on Multichannel Images

  • (Locked)
    Color images: Loading multichannel image data

    6m 22s
  • (Locked)
    Color images: Generator and discriminator in a Deep Convolutional GAN

    4m 58s
  • (Locked)
    Color images: Training a Deep Convolutional GAN

    2m 35s
• 5. Getting Started with Diffusion Models 5. Getting Started with Diffusion Models

  • (Locked)
    Generative learning trilemma

    4m 30s
  • (Locked)
    Introducing denoising diffusion probabilistic models

    2m 29s
  • (Locked)
    How do denoising diffusion probabilistic models work?

    5m 23s
  • (Locked)
    Forward diffusion process

    5m 8s
  • (Locked)
    Reverse diffusion process

    2m 51s
  • (Locked)
    Training a diffusion model: Intuition

    7m 20s
• 6. Running a Diffusion Model 6. Running a Diffusion Model

  • (Locked)
    Denoising diffusion probabilistic models: Exploring implementation on GitHub

    2m 25s
  • (Locked)
    Denoising diffusion probabilistic models: Code overview

    4m 34s
  • (Locked)
    Denoising diffusion probabilistic models: Code tweaks

    2m 22s
  • (Locked)
    Denoising diffusion probabilistic models: Generating images

    5m 53s
• Conclusion Conclusion

  • (Locked)
    Summary and next steps

    1m 49s