Some lectures aren't clearly structured. The homework assignments have downstream dependencies (week 5 depends on earlier weeks) which is not the best format IMO.

Overall:

This is an advanced course. Most of the time it would be difficult. In general, this course looks like the whole educational system in Russia - the given task is much harder then you can solve right now. But if you had a strong motivation you became much smarter. Support for this course doesn't even exist, but sometimes it is very useful to read the discussion to week practice.

Lectures and quizzes:

Teachers try to give a LOT of information in a very short time. But this theme is really not as simple to be told quickly. So as a result, you can understand just nothing:) Additionally, a heavy accent and kind of advanced vocabulary can make you feel frustrated.

BUT you can look at this that some keywords to google it was given) So generally, to understand I spend a lot of hours of reading about approaches in Computer Vision, mentioned here. The course was very useful from this point of view.

Quizzes sometimes look like crap. For some tasks, I still don't know to answer correctly.

Practice:

This is a part which could you a reason for you to finish this course. Tasks here really hard and requires from you a lot of time (about 20h, including the time to understand the task itself). I highly recommend all this practice carefully, it could be helpful for you in the future;) As a result, I knew a lot of tricks on how to prepare a model for find, recognize and even create faces.

The content was good, but there are several drawbacks too

1 Content not explained well

2 Assignments had mistakes (like broken links, wrong descriptions)

3 Minimal or Non-Existing support from the staff.

The task is really practical and useful, but the courses content is too general and I hope for the future it could include some papers reading assignment

Not clear. And just focus on papers, not on basic structure or models.

pretty good mooc wtih very exciting and hard assignments, I highly recommend it. The main issue I faced it was that the lectures are not well explained, so you need to look for documents and other lectures by yourself.

Course homework is actually not well designed for Coursera platform, some homework is not quite relevant to Deep Learning (i.e., HW1 and HW2) and some is very hard to complete (i.e., the last one, I tried on CPU for about 2 weeks). Also, the slides are not shared for this course in the series.

no lecture slides, the lecturer cannot elaborate his point clearly (or he doesn't want to), the projects seems ok, but they also are in lack of hints for me to gain progress

This isn't a good course, difficult to understand and don't maintain by authors.

Some lectures are just reading the teleprompter！

not clearly content

Zero passion from instructors. A lot of stupid questions, some of them with errors. Interesting programming assignments, but with dozen of typos. Don't expect to finish any of those programming assignments in two hours.

Course is poorly mantained. Time is spent to understand what it is to be done rather than learning. Some bugs in notebooks are not fixed. Not a good experience.

Worst course in the specialization.

Poor English pronunciation, strange tone makes this course very difficult to understand

This is not a course,it is just a man giving his presentation.

There is too much content stuffed into every week. The quizzes and assignments are very difficult with zero moderator help/guidance. Even the discussion forums are filled with people asking others to review their assignments. No guidance posts are available. I haven't seen any posts by mentors in any discussion forums.