Very good course! Helpful to understand evaluation metrics and details of Style GAN. It was also super cool to have the bias section that is not as well known as the others. Loved it!
Great material...but the stylegan code implementation requires more video material. Instead adding one more week for ProGan part before stylegan would be helpful for the learners.
by Karan S•
Too fast speaking, some mathematical concepts difficult to clear
by Michael K•
by Shounak D•
The second course was easily the low point of the curriculum. At the end, I wasnt fully able to implement Style GANs, the thing which this course sets off to do. This led to frustration and didnt feel like anything was accomplished compared to Course 1 and Course 3 where we were able to implement the whole GAN architecture. The argument: 'We have left that as assignment for students' OR 'based on the information, the students can implement the GAN' is flawed because If we students were that smart and good at it, we would have just read the papers, or watched YouTube video and implemented the paper ourselves. We wouldnt have bought a course then. But apart from that, Course 1 and Course 3 were pretty decent. We felt like we accomplished something and learnt new.
by Daniil K•
The material is great; however, after the completion you lose the access to assignments and the only way to restore it is to subscribe again.
by Злобин Я Н•
This course will have a minimum of mathematics explaining the work of GAN
by Bedrich P•
I want to learn GANs not "fairness in ML"