Avis et commentaires pour d'étudiants pour Apply Generative Adversarial Networks (GANs) par deeplearning.ai
À propos du cours
Meilleurs avis
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!
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!
51 - 75 sur 85 Avis pour Apply Generative Adversarial Networks (GANs)
par Samuel K
•Awesome course! Direct application to my research!
par nghia d
•amazing course! thanks coursea, thanks Instructors
par Евгений Ц
•Easy yet fundamental enough for an eager learner.
par Shams A
•Amazing course. Thanks so much for offering it!
par Ali G
•Very informative and easy-to-understand!
par Gokulakannan S
•Nice course enjoyed it a lot. Thanks!
par James H
•Very thorough and clearly explained.
par Xiaoyu X
•Very good lectures and assignments!
par Jesus A
•Great applications cases of GANs
par Dela C F S
•Full of amazing content! :D
par Manuel R
•It was a nice experience!
par amadou d
•Excellent! Thank You all!
par brightmart
•GREAT COURSE AT COURSERA!
par Cường N N
•This course is very good
par 晋习
•data augment is helpful
par M. H A P
•What a great course
par Diego C N
•An amazing Course
par Tim C
•Incredible! :)
par Vishnu N S
•Great Course
par vignesh m
•Wonderful!
par Kuro N
•Amazing!!
par Raymond B S
•Thank you
par Steven W
•I would have preferred the assignments spent more time on the training loop, and talking about what's going on with the cost function.
One of the interesting things about GANs is that your cost function is different for different parts of the network. This is really really important to the workings of a GAN, but we never touched the training loop after the first assignment in course 1. I feel like we should have spent more time nailing that training loop down.
Also, I don't think any of the classes mentioned the importance of the fact that the cost function is learned, rather than explicit. That's huge! You can do that for any network, not just generative networks, and it seems applicable to all kinds of less-supervised ML. It seems a waste that they didn't draw more attention to that.
par Ernest W
•Overall it was good but the final assignments were very confusing in my opinion because there are so many things going on there I still don't understand. I still think there is a lot to supplement, hours of exploration and reading many research papers to meet my expectations so I can create own generative art. Maybe more similar assignments with more detailed explanations (and more tasks) would make me understand more even at the cost of the specialization duration.
par Harold S
•It was good, I think it covered a lot of material and get you fast to a point where you can start attacking some real problems with this technology, however I do not fully like some of the exercises that get you stuck with some silly things.
Coursera Footer
