The content is excellent, but there were technical problems with the final homework assignment that were not addressed by staff in a timely manner.

Content was interestind and provided good theoretical overview. Exercices where you just have to fill in some line of codes are not usefull.

Some of the code was incorrect and the guidance was often confusing. Visibly worse than the other courses in the specialization,

Don't feel like I understand these models much better than before. Still don't see the logic of the identity layers

Lots of problem with the grader. Wasted a lot of time grappling with grader issues. Very disappointed.

The quality of some of the graders e.g. IOU is poor. One cannot make out what exactly is it checking

Disappointed by the quality of notebooks, which often disconnect and lose all the code you wrote.

The course assignment parts have many errors, I have to fix it myself. That's silly.

Good content, but quite a bit of technical work is needed to present this better.

for goodness sake "your didn't pass the test" isn't feedback for notebook grades

Dificultades en la hoja de tareas de Face Recognition que deberían solucionar

The content was good, as usual, but week 4's quiz was pretty buggy.

Good course but lots of technical issues with the assignments.

The notebooks were too simple. And the grader was not working.

Videos are good, but exercises are really confusing

content good, but assignment is in poor quality

The structure of the assignments is not good

Programming exercises have bugs

unclear content...I'm sorry

Numerous technical issues

Assignement: Face recognition for happy house was not happy at all

it took me 4 attempts to pass.

triplet_loss function you need to submit incorrect answer to pass. to get correct answer you need to have axis=-1. Bu to pass you have to take it out.

I hope you guys fix to stop more people to waste there time.

Not happy at all.

I took the basic ML course and now am taking all the Deep Learning courses. This is by far the worse course so far. Assignments are very unclear. Even explanations are less linear than in previous courses. Support is now on a different platform and not directly on Coursera. I would give it a negative grade if I could.

The content covered was good; however, the code used ancient versions of Python, Tensorflow, etc., which made it very difficult to replicate on my hardware. The course would get a 10/10 if they updated the code to make the learning more transferable. I expected this to be 100% current and feel disappointed.

Lectures were good, but the assignments have major problems with the grading. On several problems, you have to put in an incorrect solution in order for the grader to accept it. This have been reported by a number of students in the forum. It needs to be cleaned up.

This course is much poorer than the previous courses in this series. Much of the content was at a very high level without sufficient detail. More explanation to make a concept clear was lacking. Hope for some improvement to the content for future learners.