Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Generative Adversarial Networks (GANs) Specialization

  • up to 3 months
  • Intermediate

The Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques. Gain hands-on experience in building and evaluating GANs using PyTorch, and explore their applications in data augmentation and privacy preservation.

  • GAN components
  • Basic GANs using PyTorch
  • Advanced DCGANs
  • Conditional GANs
  • FID method for GAN evaluation

Overview

In this specialization, you will learn to understand GAN components, build basic and advanced GANs using PyTorch, and control your GAN to build conditional GANs. You will compare generative models, use the FID method to assess GAN fidelity and diversity, and learn to detect bias in GANs. Additionally, you will explore GAN applications in data augmentation and privacy preservation, and implement Pix2Pix and CycleGAN for image translation.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Professional Certification
    upon course completion
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

Data Scientists

Professionals looking to enhance their skills in generative models and image generation.

Machine Learning Engineers

Engineers aiming to implement advanced GAN techniques in their projects.

AI Enthusiasts

Individuals interested in understanding and applying GANs for various applications.

This specialization offers a comprehensive introduction to GANs, covering both foundational concepts and advanced techniques. It is ideal for data scientists, machine learning engineers, and AI enthusiasts looking to enhance their skills in generative models and image generation. By completing this course, learners will gain hands-on experience in building and evaluating GANs, and explore their applications in data augmentation and privacy preservation.

Pre-Requisites

1 / 3

  • Basic knowledge of machine learning and deep learning concepts

  • Familiarity with Python programming

  • Understanding of neural networks and PyTorch

What will you learn?

Course 1: Build Basic Generative Adversarial Networks (GANs)
Learn about GANs and their applications; Understand the intuition behind the fundamental components of GANs; Explore and implement multiple GAN architectures; Build conditional GANs capable of generating examples from determined categories.
Week 1: Intro to GANs
Learn about GANs and their applications, understand the intuition behind the basic components of GANs, and build your very own GAN using PyTorch.
Week 2: Deep Convolutional GAN
Build a more sophisticated GAN using convolutional layers. Learn about useful activation functions, batch normalization, and transposed convolutions to tune your GAN architecture and apply them to build an advanced DCGAN specifically for processing images.
Week 3: Wasserstein GANs with Normalization
Reduce instances of GANs failure due to imbalances between the generator and discriminator by learning advanced techniques such as WGANs to mitigate unstable training and mode collapse with a W-Loss and an understanding of Lipschitz Continuity.
Week 4: Conditional and Controllable GANs
Understand how to effectively control your GAN, modify the features in a generated image, and build conditional GANs capable of generating examples from determined categories.
Course 2: Build Better Generative Adversarial Networks (GANs)
Assess the challenges of evaluating GANs and compare different generative models; Use the Fréchet Inception Distance (FID) method to evaluate the fidelity and diversity of GANs; Identify sources of bias and the ways to detect it in GANs; Learn and implement the techniques associated with the state-of-the-art StyleGANs.
Week 1: GAN Evaluation
Understand the challenges of evaluating GANs, learn about the advantages and disadvantages of different GAN performance measures, and implement the Fréchet Inception Distance (FID) method using embeddings to assess the accuracy of GANs.
Week 2: GAN Disadvantages and Bias
Find out the disadvantages of GANs when compared to other generative models, discover the pros/cons of these models — plus, learn about the many places where bias in machine learning can come from, why it’s important, and an approach to identify it in GANs.
Week 3: StyleGAN and Advancements
Understand how StyleGAN improves upon previous models and implement the components and the techniques associated with StyleGAN, currently the most state-of-the-art GAN with powerful capabilities.
Course 3: Apply Generative Adversarial Networks (GANs)
Explore the applications of GANs and examine them wrt data augmentation, privacy, and anonymity; Leverage the image-to-image translation framework and identify applications to modalities beyond images; Implement Pix2Pix, a paired image-to-image translation GAN, to adapt satellite images into map routes (and vice versa); Compare paired image-to-image translation to unpaired image-to-image translation and identify how their key difference necessitates different GAN architectures; Implement CycleGAN, an unpaired image-to-image translation model, to adapt horses to zebras (and vice versa) with two GANs in one.
Week 1: GANs for Data Augmentation and Privacy Preservation
Explore the applications of GANs and examine them wrt data augmentation, privacy, and anonymity. Improve your downstream AI models with GAN-generated data.
Week 2: Image-to-Image Translation
Leverage the image-to-image translation framework and identify extensions, generalizations, and applications of this framework to modalities beyond images. Implement Pix2Pix, a paired image-to-image translation GAN, to adapt satellite images to map routes (and vice versa) with advanced U-Net generator and PatchGAN discriminator architectures.
Week 3: Image-to-Image Unpaired Translation
Compare paired image-to-image translation to unpaired image-to-image translation and identify how their key difference necessitates different GAN architectures. Implement CycleGAN, an unpaired image-to-image translation model, to adapt horses to zebras (and vice versa) with two GANs in one.

Meet your instructors

  • Sharon Zhou

    Cofounder & CEO, Lamini

    Sharon Zhou is the Cofounder & CEO of Lamini, an LLM startup based on both her PhD dissertation in generative AI and her love for building delightful products as a product manager.

  • Eda Zhou

    Full Stack Engineer, Lamini

    Eda Zhou is a passionate and curious graduate from Worcester Polytechnic Institute who enjoys the possibilities computer science has to offer. She is always eager to try something new.

  • Eric Zelikman

    CS PhD Student @ Stanford, DeepLearning.AI

    Eric Zelikman is a student researcher at Blueshift at Google. He is currently pursuing a PhD in Computer Science at Stanford University.

Upcoming cohorts

  • Dates

    start now

Free