The course is an introduction to GANs. You won't build anything particularly powerful but it provides a springboard to the future courses in the series. This course is light on video and instruction and relies more on exercises. This is fine and possibly better since presumably you already understand neural networks well and are just looking to understand how to build GANs. If you do not have a good foundation in deep learning, you should check out Andrew Ng's courses on deep learning first.

The exercises can be easier than they should, if you will. Sometimes, the setup of the code that they give you "for free" includes critical insights. Make sure to carefully read over and understand the code outside of the few lines that you need to code for each assignment.

Also, if you are interested, I encourage you to read some of the works cited, each of which made important contributions. Focus on those that are most relevant to your work. Personally, I found "Interpreting the Latent Space of GANs for Semantic Face Editing" the most compelling.

Good class, it actually touches on mathematical aspects, and the text comprises contemporary work in the field. The programming assignments are well-designed so that, while there are usually only 10-20 lines of code to fill in (at most), one must actually think carefully about what the algorithms are doing, read the pytorch manual, and try some test scripts to make sure tensors are being handled correctly.

This is my first experience with PyTorch, and so far I like working with it better in this context than I have working with TF in other classes and books - pytorch seems to be more of a straightforward extension to the numpy / pandas / sklearn paradigm. The focus is on "what the algorithm does" rather than on "the mechanics of the framework" - although part of that may be due to instructional styles as well.

Sharon Zhou is one of the best teachers I've ever had. She (1) reaches and almost surpasses Andrew's standards, (2) has a great history of being a great learning herself (similar to Andrew) and (3) is overall infectuously enthusiastic. As an incoming softmore in University, I could say this course is likely the best resource to start learning GANS I've come accross, and I've scoured the internet.

For students that completed Andrew Ng's deep learning course or had a similar course in University, this course only builds on it and most difficult concepts are easy to grasp with the background.

I cannot speak for experts and if this course will benefit you. I'll hazard a prediction and say "yes" or "try the programming assignments and see if you could breeze through or need to learn some".

I would like to dive deeper into the GANs math more deeply, because in modern research it matters to understand ideas lying behind these methods through math. I saw some great examples of that while I was completing cs231n course from Stanford University. Would like to see more here! And also, I think that there is too little programming. I think, usually you would expect people with kind of strong (by that I mean stronger than beginner) background in DL and probably experienced in PyTorch, so in next courses I would like to see more of "hand work" with coding, because it is so important to do stuff yourself to actually learn it. Thank you guys for the great course!

This is the best course ever.

Before this course I don't know anything about GAN, but now I can understand the GAN.

In week -1 I have learned about Basics of the GAN and other Generative model and their components.

In week -2 I have learned Deep convolution GAN which is now a days used in many applications.

In week -3 I have learned about wasserstein loss and it's important to GAN.

In week -4 I have learned about Controllable generation using GAN, where we can control any of the feature of the GAN.

This course was best for me, I have learned a lot from this course,

I want to thank prof. Andrew for this Amazing Course.

While much of the basic GAN theory should be well known to people in the DL community, not many have actually had relevant hands on experience. Therefore the exercises in this course are priceless. Not only they let you avoid A LOT of boilerplate code, they also set your expectations as to what the GAN can ACTUALLY produce (often pretty bad results). Also, the course did a great job providing intuition for some of the more mathematically perplexing sections (e.g. Wasserstein GAN). Overall I would probably recommend it to a colleague.

Great course. Only thing I don't like is your try to increase level of challenging in assignments. I know that some people in reviews complain about too easy assignments with just one-line code changes. But in my opinion it's not that bad, if an assignment is well designed with emphasis on important things. In the evening after a long day at work, it can be very exhausting to spend time figuring out what params I have to pass in torch.norm to make test working. I think at least hints could be done more helpful.

En general, es un curso básico que brinda los elementos necesarios para entender el funcionamiento de las GAN. Requiere conocimientos de Python para un avance más rápido, ya que las actividades a realizar son 100% programación usando Pytorch. Al contenido le hace falta más rigor matemático, aunque se complementa con los artículos que se citan para mayor profundidad en los temas tratados. Aún así, creo que podría mejorar si se desarrollan más los puntos teóricos (en el sentido matemático).

I want to congratulate all the staff who helped to prepare the course, especially the instructor "Sharon Zhou," for her remarkable teaching expertise. When I started this course, I did not have any knowledge of generative AI, and even though I was not confident enough that I would be able to complete this course. Now, I am knowledgeable about GANs, and I have completely understood the basic concepts of GANs. It was all possible because the instructors delivered the concepts effectively.

The "Build Basic Generative Adversarial Networks (GANs)" course by DeepLearning.AI is an excellent introduction to GANs. The content is well-structured, covering essential concepts and advanced architectures. The hands-on projects using PyTorch were particularly valuable, allowing me to apply what I learned. The instructors are knowledgeable and engaging, making complex topics accessible. I highly recommend this course to anyone interested in machine learning and image generation!

Really amazing course (as expected from deeplearning.ai), I especially liked the detail description of almost everything in notebook assignments, Also the cool reference and advance topic. The simplified explanation of maths formula.

Also, I think infoGan paper and notebook should be moved after disentanglement video since these concept discussed in the paper are relevant to those videos.

Thank you for such an amazing course 🙂

This course is great, it presents GANs in an understandable way. The way how things are explained in each video gives a good delivery that encourages to further pursue the topic. Additional resources are included for more advanced explanations. Before choosing to start the course I've read some comments that it's too basic, maybe assignments are simple but it's not a course for someone with computer science or AI degree.

A Concise introduction to GANs! A good balance between theoretical explanations and practical implementation. Helped a lot to reach learning outcomes swiftly. Interactive jupyter notebooks are a great tool to familiarize on putting everything to work. The citations and links to respective research papers is a good approach to introduce the research practices to the pupils. Thank you for passing on the knowledge!

This course helped deepen understanding of deep neural networks. I definitely felt more command over manipulating pytorch code after this course. Course provided many helpful introduction to some widely used pytorch functions which I found really useful. And finally I actually understood basics about GAN. Thanks for this amazing course.

This is one of my favorite courses. I really like the way the instructor explained the material and thought everything was just the way I would have wanted it to be (e.g., videos, notebooks, assignments, etc...). I also really appreciate including the papers along the way so I can dig deeper as I go along. Great job on this course!

Very good introduction to generative networks. The professors explanations are really clear allow a good understanding of the theory. Notebooks provided are very simplified with lots of details for the new learner. This is not a Pytorch tutorial, but plenty of examples are provided to explore on our own.

The course was great and the slack community too. One issue was, some important topics were not introduced (vaguely introduced) in the video lectures and were asked to implement in the notebooks. Mainly, in Week 4 (for eg: regularization part). Also, the notebooks had more prewritten helping code.

This seems like the way to go. Most of the more interesting content is optional but this is for a good reason. I really enjoy that every week, each topic is complemented with papers where they originate from and more. Some of these papers are even broken down during the lectures. Quality stuff

I found this course well paced and interesting. I didn't lose any interest in the course at any point at all. Although I only knew Tensorflow and Keras when starting the course, I was able to catch up with Pytorch framework. I recommend this course to everyone interested in GANs.

I am really glad that I learned this Magical topic GANS. Thanks to all the mentors who taught this difficult topics with great ease and also to those mentors who promptly reply in the forum. Highly appreciate the Coursera community for spreading the knowledge across the world.

This is a fantastic course. It is a lot of theory to come to terms with. I appreciated the papers referenced, the clear lectures and challenging labs. It is evident that this is great jump-start, and will require substantial additional effort to ensure practical application.

I very much enjoyed this course. There are three points that I want to point out about this course:

1) The lecture is simple, but well organized.

2) The code examples/assignments are simple, but provoking more thoughts.

3) The Slack channel is really useful when you struggle.

Sharon Zhou is a great instructor and manages to keep the flow of ideas always understandable and engaging. The assignments are also perfectly crafted with helpful unit tests to make the learning experience unhindered by confusing hiccups. This is the perfect way to learn.

As a beginner to GANs, this course offers a lot of new insights that I never came across before. It helped me understand a lot of the key terms used in current state of the art research papers and helped me understand a lot of the underlying working principles of GANs.

Thank you so much for providing this wonderful course. I've learned a lot from your wonderful lectures. Specifically, I really like the way you give your lecture, very concise and interesting. Thanks again, and hopefully a lot of people can enjoy the course as well.