Some frustrating issues with the week 4 assignments. I would also like some explanation on how to download all the related materials so I can play with the models later on my own machine.

The programming exercises in week 4 have mistakes in them that have been reported over 2 months ago and still not fixed.

I would expect a payed course to exhibit a higher responsiveness.

Content: good! state of the art!Lecture: to many cut mistakes of the videos such that many sentences are repeated.Exercises: content ok but notebook functionality and grader too buggy!

The lectures were pretty good - however, the programming exercises were rather error-prone. Huge thanks to the Discussion Forum where other students had posted trouble-shooting tips.

content was good,Yolo was hard and i still does not suggest,wasted too much time on exercises,when the answer was not match it passed! very bad experience with the exercise part.

Would have liked to learn more about why various architectural choices are made when building deep networks. The nitty-gritty details and Python exercises were a little boring.

The last week (week 4) was not explained in enough detail. I was often frustrated because i was finding myself not fully understanding the concepts because of missing details.

Content was great but the grading issues with the homework assignments made this course very time consuming and frustrating. Will recommend it when grading issues are fixed.

Teaching and questionnaires are good. Programming assignments are low quality and wasting time. For the next module I will probably not bother much with the assignments.

The theory part is outstanding, concepts explanation is great but the programming assignments are not updated to TensorFlow 2.x that's an issue else everything was nice.

I hoped there would have been a more theoretical explanation and also talks about why some nets are done in this way rather than another; it seems like it's all magic.

Liked the concepts overall. The tieing up of basics concepts across different use cases could've been better explained from first principles and for better intuition.

Andrew Sir explanation is awesome, but please do explain concepts in videos also, as some programming assignments contain data, info that we are not having knowledge

I spend 1 week on the last assignment due of one bug. I am disappointed but the content of the course was good. Please next time react faster for correcting bugs

Grader in the last assignment is wrong. It has been reported in the discussion forums several months ago and still hasn't been. Apart from that, great content

The course gives you a good introduction to NN. However, the grading is buggy, and the content rather superficial. It gives you a false sense of achievement.

The homework assignments, compared to the other courses, where pretty low in quality. If these errors get corrected, I'd happily give this course 5/5 stars.

Videos were mostly great!

Expected more of the written material (quizes, assignments, etc.), not the quality I would expect from something I've paid for...

Some issues regarding the submission of assignments and some minute mistake in the videos and assignment. Although great teaching by Andrew as always :)

Issue with triplet loss function shouldn't happen. I had to remove "axis = -1" in order to pass grader even though function had produced wrong answer!!!

There are a lot of issues with programming assignments grader (I've spent one hour to complete assignment and two days to make a grader to get it)

The programming assignments contain bugs. Also the jupyter notebook kept on shutting down thus slowing down the learning process quite a bit :-(

Certain Parts are not that much clear. Specially like in the triplet loss function, until the coding was done the real procedure was not clear.

the assignment setup and graders are not updated after reporting issues several times which caused a great deal of frustration among students.

The last exercise it was a litle annoyng, it took me almost five days to figure out how to solve the face recognition because a grader fault.