Explore

Build Better Generative Adversarial Networks (GANs)

Approx. 29 hours to complete

Save Course

Go to Course

Course Summary

This course is designed for those who want to build better generative adversarial networks (GANs). You will learn the key techniques for building better GANs, including improving training stability, reducing mode collapse, and improving generated image quality.

Key Learning Points

Learn how to improve the stability of GAN training
Discover techniques for reducing mode collapse
Explore methods for improving the quality of generated images

Learning Outcomes

Understand the key concepts of GANs
Implement techniques for improving GAN stability and reducing mode collapse
Improve the quality of generated images

Prerequisites or good to have knowledge before taking this course

Basic knowledge of Python and machine learning
Familiarity with TensorFlow or PyTorch

Course Difficulty Level

Intermediate

Course Format

Online self-paced course
Video lectures
Assignments and quizzes

Similar Courses

Generative Adversarial Networks (GANs)
Advanced Generative Adversarial Networks (GANs)
Deep Learning

Related Education Paths

Notable People in This Field

Ian Goodfellow
Yann LeCun

Related Books

Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play

Description

In this course, you will:

- 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 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: Evaluation of GANs
Welcome to Course 2
Welcome to Week 1
Evaluation
Comparing Images
Feature Extraction
Inception-v3 and Embeddings
Fréchet Inception Distance (FID)
Inception Score
Sampling and Truncation
Precision and Recall
Syllabus
Connect with your mentors and fellow learners on Slack!
(Optional) A Closer Look at Inception Score
(Optional) HYPE!!
(Optional) More on Precision and Recall
(Optional) Recap of FID and IS
Works Cited

Week 2: GAN Disadvantages and Bias
Welcome to Week 2
Disadvantages of GANs
Alternatives to GANs
Intro to Machine Bias
Defining Fairness
Ways Bias is Introduced
(Optional Notebook) Score-based Generative Modeling
Machine Bias
Fairness Definitions
A Survey on Bias and Fairness in Machine Learning
Finding Bias
(Optional Notebook) GAN Debiasing
Works Cited
Analyzing Bias

Week 3: StyleGAN and Advancements
Welcome to Week 3
GAN Improvements
StyleGAN Overview
Progressive Growing
Noise Mapping Network
Adaptive Instance Normalization (AdaIN)
Style and Stochastic Variation
Putting It All Together
Conclusion of Course 2
(Optional) The StyleGAN Paper
(Optional) StyleGAN Walkthrough and Beyond
(Optional Notebook) Finetuning Notebook: FreezeD
Works Cited
Acknowledgments

Summary of User Reviews

Build Better Generative Adversarial Networks (GANs) is a highly recommended course for anyone interested in improving their skills in creating GANs. The course provides a comprehensive overview of GANs and their applications with hands-on experience in building GANs. Many users appreciated the practical nature of the course.

Key Aspect Users Liked About This Course

The hands-on experience in building GANs

Pros from User Reviews

Practical and hands-on learning experience
Great for beginners and intermediate learners
In-depth coverage of GANs and their applications
Engaging and knowledgeable instructors
Well-structured course materials

Cons from User Reviews

The course may be too basic for advanced learners
Some users found the course to be too slow-paced
The course may require prior knowledge in machine learning
Limited interaction with instructors and peers
The course may not cover the latest advancements in GANs

Recommended for you

Tensorflow 2.0: Deep Learning and Artificial Intelligence

Neural Networks for Computer Vision, Time Series Forecasting, NLP, GANs, Reinforcement Learning, and More! Welcome to Tensorflow 2. 0! What an exciting time....

Save Course

Complete Tensorflow 2 and Keras Deep Learning Bootcamp

Learn to use Python for Deep Learning with Google's latest Tensorflow 2 library and Keras! 0's official API) to quickly and easily build models....

Save Course

Deep Learning: Advanced Computer Vision (GANs, SSD, +More!)

VGG, ResNet, Inception, SSD, RetinaNet, Neural Style Transfer, GANs +More in Tensorflow, Keras, and Python Let me give you a quick rundown of what this course is all about:...

Save Course