Introduction to Generative Adversarial Networks with PyTorch

Introduction to Generative Adversarial Networks with PyTorch, available at $59.99, has an average rating of 4.05, with 34 lectures, 27 quizzes, based on 98 reviews, and has 960 subscribers.

You will learn about How Generative Adversarial Networks work internally How to implement state of the art GANs techniques and methods using PyTorch How to improve the training stability of GANs This course is ideal for individuals who are Data scientists willing to take their skills to the next level in the area of GANs or Research / Postgraduate Students willing to get a comprehensive overview of recent advancement made in the area of GANs or Deep Learning practitioners willing to apply GANs at work in production environments or Enthusiasts willing to stay up to date on GANs research and development or Deep learning beginners willing to master the building blocks of modern GANs It is particularly useful for Data scientists willing to take their skills to the next level in the area of GANs or Research / Postgraduate Students willing to get a comprehensive overview of recent advancement made in the area of GANs or Deep Learning practitioners willing to apply GANs at work in production environments or Enthusiasts willing to stay up to date on GANs research and development or Deep learning beginners willing to master the building blocks of modern GANs.

Enroll now: Introduction to Generative Adversarial Networks with PyTorch

Summary

Title: Introduction to Generative Adversarial Networks with PyTorch

Price: $59.99

Average Rating: 4.05

Number of Lectures: 34

Number of Quizzes: 27

Number of Published Lectures: 34

Number of Published Quizzes: 27

Number of Curriculum Items: 61

Number of Published Curriculum Objects: 61

Original Price: $22.99

Quality Status: approved

Status: Live

What You Will Learn

How Generative Adversarial Networks work internally
How to implement state of the art GANs techniques and methods using PyTorch
How to improve the training stability of GANs

Who Should Attend

Data scientists willing to take their skills to the next level in the area of GANs
Research / Postgraduate Students willing to get a comprehensive overview of recent advancement made in the area of GANs
Deep Learning practitioners willing to apply GANs at work in production environments
Enthusiasts willing to stay up to date on GANs research and development
Deep learning beginners willing to master the building blocks of modern GANs

Target Audiences

Data scientists willing to take their skills to the next level in the area of GANs
Research / Postgraduate Students willing to get a comprehensive overview of recent advancement made in the area of GANs
Deep Learning practitioners willing to apply GANs at work in production environments
Enthusiasts willing to stay up to date on GANs research and development
Deep learning beginners willing to master the building blocks of modern GANs

Master the basic building blocks of modern generative adversarial networks with a unique course that reviews the most recent research papers in GANs and at the same time gives the learner a very detailed hands-on experience in the topic. Start by learning the very basics of how GANs work and incrementally learn more cleverly crafted techniques that enhance your models from the basic GANs towards the more advanced Progressive Growing of GANs. On the journey, you shall learn a fair amount of deep learning concepts with an adequate discussion of the mathematics behind the modern models.

Course Curriculum

Chapter 1: Course Agenda

Lecture 1: Course Agenda

Chapter 2: Introduction to PyTorch for GANs

Lecture 1: Notebook Versioning Notice

Lecture 2: PyTorch Forward and Backward Propagation

Lecture 3: PyTorch Autograd Mechanism

Lecture 4: PyTorch Custom Loss Function

Chapter 3: Generate Handwritten Digits with Vanilla GAN

Lecture 1: Introduction to GANs

Lecture 2: Working of GAN Loss Function

Lecture 3: Implementing GAN Training Methodology

Lecture 4: Implement Vanilla GAN on MNIST Dataset to Generate Digits

Lecture 5: [Coding Exercise] GAN Evaluation Metrics: Inception Score

Lecture 6: [Coding Exercise] GAN Evaluation Metrics: FID Score

Chapter 4: Generate Specific Digits with Conditional GAN

Lecture 1: Introduction to Conditional GANs

Lecture 2: Implement Conditional GAN on MNIST Dataset

Lecture 3: Working of Wasserstein Loss Function

Lecture 4: Implement Wasserstein Loss Function

Lecture 5: [Coding Exercise] Gradient Penalty Wasserstein GAN – GP-WGAN

Chapter 5: Diving Deeper with a Deep Convolutional GAN

Lecture 1: Introduction to DC-GANs

Lecture 2: Implement DC-GAN on UC Birds Dataset

Lecture 3: Working of Multi-way Loss Function

Lecture 4: Implement multi-way loss with Auxiliary-GAN on UC Birds Dataset

Chapter 6: Generate Realistic Human Faces with Progressive GAN

Lecture 1: Introduction to Progressive GANs

Lecture 2: Implement Progressive GANs on Celebs Dataset

Lecture 3: Hints, Tips, and Tricks for GAN Training

Chapter 7: Generate Videos from Other Videos

Lecture 1: Introduction to U-NET Architecture

Lecture 2: Working of Pix2Pix GAN and CycleGAN

Lecture 3: [Coding Exercise] Hands-on Pix2Pix GAN

Lecture 4: [Coding Exercise] Hands-on CycleGAN

Lecture 5: Working of Vid2Vid GAN

Lecture 6: Diving Deeper into Vid2Vid GAN using YouTube Dance Video Dataset

Lecture 7: Conclusion, Next Steps, and Future Directions

Chapter 8: Appendix: Interesting Readings

Lecture 1: LeakGAN: Long Text Generation via Adversarial Training with Leaked Information

Lecture 2: MaskGAN: Towards Diverse and Interactive Facial Image Manipulation

Lecture 3: MGAN: Markovian Generative Adversarial Networks

Lecture 4: GraphGAN: Graph Representation Learning with Generative Adversarial Nets

Instructors

Mustafa Qamaruddin
Software Architect

Rating Distribution

1 stars: 6 votes
2 stars: 6 votes
3 stars: 19 votes
4 stars: 28 votes
5 stars: 39 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu