This is very intensive and wonderful course on CNN. No other course in the MOOC world can be compared to this course's capability of simplifying complex concepts and visualizing them to get intuition.
Great course for kickoff into the world of CNN's. Gives a nice overview of existing architectures and certain applications of CNN's as well as giving some solid background in how they work internally.
by Carol S•
The Neural Style Transfer notebook seems to have makes it difficult in the last panel to access the generated_image global variable.
The assignments need to be reworked as they are quite confusing and the grading system is flawed especially for the last assignment.
by Jnana R D•
More simple lectures with illustrations required and also graders need to fixed. Had a lot of time wasted because of buggy graders
by NEEL V•
It has very less explanation about working of back propagation of convolution network,
plus it can explain YOLO in much better way
by Aoun L•
The course is great but the assessments and grading is terrible, so many particularities and repetition that does not make sense.
by Sudhanshu D•
Week 3, exercise 2 is very buggy. Couldn't have completed it without the discussion forum. Kindly fix it for the future learners
by Ankit R•
Found it really difficult to submit programming assignments, at times the jupyter notebooks were not at all responsive.....
by Gowdhaman S•
Course content was good but lack with hands-on projects. It would be really helpful if the team could add capstone project.
by vishwanathan r•
There should be a way through which folks can download the entire zipped contents of the programming and also the lessons.
by Carmine M•
Very interesting and with high quality material. It could be improved by adding more tutorials about the frameworks used.
by Corbin C•
Poorly edited videos, poorly worded (bordering incorrect) quiz questions, buggy notebook. Good, useful content, though.
by Bence K•
The content of the course was perfect. But the support for the issues and the feedback for the forum threads is awful.
by Siarhei K•
For the YOLO part would be nice to have explanation for how to set up training set and train your own object detector.
by Junchen F•
The homework portion of CNN is underwhelming. We are asked to play around the core algorithm but not the core itself.
by Claudio T•
The content of the course is a lot of fun. I loved this module. But unfortunately the grade engine wasn't work right.
by Martin N•
The exercises are awkward - it is a lot of index juggling and I feel it does not help me understanding the "whys".
by Aditya M•
The audio was not clear ( mostly was of low volume) at moments when the instructor was telling important points.
by Michal S•
some videos weren't properly edited (repeated sentences).
I like the assignments but the machine was too slow.
by Rajib C•
The Algorithms should have been touched in depth, so that we could learn and apply everything from scratch.
by James H•
Great intro to CNNs - would be 5 star but downloading the support files to your own machine is such a pain.
by Tatsunari W•
A great introductory course in CNN
A little too many hints and too much guidance on every coding assignment
by Ajeet M•
I would like for the course to be a little bit more difficult as far as writing the programming exercises.
by Ritvik A•
End of the course was not well structured. But the starting of the course was good and very well planned.
by Ifan W•
Good Lecture overall, but the last assignments contain bugs that students were not supposed to figure out
by Bingcheng L•
Not enough materials about the fundamentals about CNN, just a couple of implementation without details.