Explore

Apply Generative Adversarial Networks (GANs)

Approx. 27 hours to complete

Save Course

Go to Course

Course Summary

Learn how to apply Generative Adversarial Networks (GANs) to create realistic images and videos with this course. You'll explore the theory behind GANs and implement them in Python using TensorFlow and Keras.

Key Learning Points

Understand the theory behind GANs and how they work
Learn to implement GANs in Python using TensorFlow and Keras
Create realistic images and videos using GANs

Learning Outcomes

Understand the theory and implementation of GANs
Gain experience with TensorFlow and Keras
Create realistic images and videos using GANs

Prerequisites or good to have knowledge before taking this course

Familiarity with Python programming
Basic understanding of deep learning

Course Difficulty Level

Intermediate

Course Format

Online
Self-paced

Similar Courses

Introduction to Deep Learning
Convolutional Neural Networks
Generative Adversarial Networks Specialization

Related Education Paths

Notable People in This Field

Ian Goodfellow
Yann LeCun

Related Books

Description

In this course, you will:

- 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 The DeepLearning.AI Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach. It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more. Build a comprehensive knowledge base and gain hands-on experience in GANs. Train your own model using PyTorch, use it to create images, and evaluate a variety of advanced GANs. This Specialization provides an accessible pathway for all levels of learners looking to break into the GANs space or apply GANs to their own projects, even without prior familiarity with advanced math and machine learning research.

Outline

Week 1: GANs for Data Augmentation and Privacy
Welcome to Course 3
Welcome to Week 1
Overview of GAN Applications
Data Augmentation: Methods and Uses
Data Augmentation: Pros & Cons
GANs for Privacy
GANs for Anonymity
Syllabus
Connect with your mentors and fellow learners on Slack!
(Optional) Automated Data Augmentation
(Optional Notebook) Generative Teaching Networks
(Optional) De-identification
(Optional) GAN Fingerprints
Works Cited
GANs Hippocratic Oath

Week 2: Image-to-Image Translation with Pix2Pix
Welcome to Week 2
Image-to-Image Translation
Pix2Pix Overview
Pix2Pix: PatchGAN
Pix2Pix: U-Net
Pix2Pix: Pixel Distance Loss Term
Pix2Pix: Putting It All Together
Pix2Pix Advancements
(Optional) The Pix2Pix Paper
(Optional Notebook) Pix2PixHD
(Optional Notebook) Super-resolution GAN (SRGAN)
(Optional) More Work Using PatchGAN
(Optional Notebook) GauGAN
Works Cited

Week 3: Unpaired Translation with CycleGAN
Welcome to Week 3
Unpaired Image-to-Image Translation
CycleGAN Overview
CycleGAN: Two GANs
CycleGAN: Cycle Consistency
CycleGAN: Least Squares Loss
CycleGAN: Identity Loss
CycleGAN: Putting It All Together
CycleGAN Applications & Variants
(Optional) The CycleGAN Paper
(Optional) CycleGAN for Medical Imaging
(Optional Notebook) MUNIT
Works Cited
Acknowledgements
(Optional) Opportunity to Mentor Other Learners

Summary of User Reviews

Learn about Generative Adversarial Networks (GANs) and their applications in this course on Coursera. Reviews praise the course for its engaging content and thorough explanations.

Key Aspect Users Liked About This Course

The course is well-structured and provides practical examples that help users understand the concepts better.

Pros from User Reviews

Engaging content that keeps users interested
Thorough explanations that make complex topics easy to understand
Practical examples that help users apply the concepts in real-world scenarios
Great instructor who is knowledgeable and responsive to questions
Course materials are well-organized and easy to follow

Cons from User Reviews

Some users found the pace to be too slow
There could be more emphasis on advanced topics
The course could benefit from more hands-on exercises
No certification or credential offered upon completion
Some users found the course to be too basic

Recommended for you

Deep Learning: GANs and Variational Autoencoders

Generative Adversarial Networks and Variational Autoencoders in Python, Theano, and Tensorflow Variational autoencoders and GANs have been 2 of the most interesting developments in deep learning and machine learning recently....

Save Course

Deep Convolutional Generative Adversarial Networks (DCGAN)

Learn to create Generative Adversarial Networks (GAN) & Deep Convolutional Generative Adversarial Networks (DCGAN) Two models are trained simultaneously by an adversarial process....

Save Course

Introduction to Generative Adversarial Networks with PyTorch

A comprehensive course on GANs including state of the art methods, recent techniques, and step-by-step hands-on projects...

Save Course

Build Better Generative Adversarial Networks (GANs)

In this course, you will: - Assess the challenges of evaluating GANs and compare different generative models - Identify sources of bias and the ways to detect it in GANs...

Save Course