Chevron Left
Back to Apply Generative Adversarial Networks (GANs)

Learner Reviews & Feedback for Apply Generative Adversarial Networks (GANs) by DeepLearning.AI

4.8
stars
505 ratings

About the Course

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....

Top reviews

UD

Dec 5, 2020

I really liked the exposure to preparing various loss functions in paired and non-paired GANs, introduction to other applications, and many great changes to improve the quality of the networks!

AM

Jan 23, 2021

GANs are awesome, solving many real-world problems. Especially unsupervised things are cool. Instructors are great and to the point regarding theoretical and practical aspects. Thankyou!

Filter by:

26 - 50 of 99 Reviews for Apply Generative Adversarial Networks (GANs)

By Pang C H J

Sep 26, 2021

A timely review of GANs and all that is related to GANs, and very well explained with diagrams and appropriate slides. Very easy to understand. Reference to some 2020 material (I don't think I saw 2021 material), so material is up to date.

By Rishav S

Nov 7, 2020

This Course was fun to do and was also very much helpful for my knowledge. Mainly the reading part was very good and had so much to study and gain from which I think was best and also the video lectures and Assignment notebook off course.

By Pavel K

Feb 3, 2021

I really enjoyed the content of the 3rd course in this specialisation. The only wish I have for the future courses is for them to be in HD, it's 2021, come on, apply some SuperRes GANs already ;)

By Ian O

Jun 30, 2023

I loved this course,super informative.Now I have the foundational knowledge to learn about the latest GANs and understand how they work and probably try to build them from scratch

By Mikhail P

Nov 20, 2020

Great course and the specialization! It gives a clear explanation of quite difficult concepts, after which it becomes much easier to look for more details in original papers.

By José A C C

Jan 17, 2021

It is a great course that you need to take time to understand fully, particularly the optional materials and readings are super valuable to extend understanding.

By Rushirajsinh P

Apr 16, 2021

Perfect course for GANs!! I've never seen such a perfect curriculum before! A blend of state-of-the-art approaches and their practical implementation!

By Lambertus d G

Feb 18, 2021

Great to put the GANs to practice and see what you can achieve. This was the icing on the cake for me. Thanks Sharon for your clear explanations!

By 大内竜馬

Mar 10, 2021

The content is very nice. But, as a non-native English speaker, I would have been happier if you would speak more slowly, like prof. Andrew Ng.

By Yiqiao Y

Jan 5, 2021

It's a great specialization and I deeply enjoyed it! I want to thank Sharon and her team of developing this material! I highly recommend it!

By Vishal Y

May 17, 2023

Thank you very much to the whole team, the videos, the examples, and the notebooks all are literally amazing.

Thank you very much again

By Angelos K

Oct 31, 2020

Great course, it provides an excellent explanation on concepts and provides useful practical exercises on main applications of GANs.

By Andrey R

Dec 7, 2020

It was fun to learn, especially cycle gan part. I only hope the authors will keep creating new courses. Looking forward to them.

By Vaseekaran V

Dec 24, 2021

A brilliant third course in the specialization. Really enjoyed doing this, and learned quite a lot. Thank you DeepLearning.AI

By 昭輝江

Jan 24, 2022

The courses in this tutorial is awesome, very recommend for those who interested in GAN, so glad I enroll this course!!!

By Moustafa S

Oct 31, 2020

great course and great material really, keep the great work and hopefully seeing more of your courses again Zho <3

By Jaekoo K

Apr 11, 2021

I really enjoyed this course. It was easy to follow and clear in terms of content organizations. Thank you!

By Paul J L I

Jan 31, 2021

This was a really great course, and the lectures presented really well. I learned a lot from this course.

By Akshai S

Jan 17, 2021

The applications of GANs were very well illustrated in the course. I thank the coursera team for this :-)

By Stefan S

Oct 30, 2020

Very good and interesting course where you learn how state of the art GAN's is constructed.

By Anri L

Dec 24, 2021

Sharon Zhou, her sister and the rest of the Deeplearning.Ai team is a gift to the world!

By Arkady A

Feb 8, 2021

Awesome course, with well explained material that makes state of the art new models easy!

By Dhritiman S

Dec 8, 2020

The course did a great job of conveying complex material very succinctly and clearly.

By Serge T

Nov 18, 2020

Great course and a fantastic Specialisation! Would recommend to everyone interested!

By Antoreep J

Apr 24, 2021

Course 3 was better than Course 2. Course 2's assignments were bit confusing.