Great Course Overall\n\nOne thing is that some videos are not edited properly so Andrew repeats the same thing, again and again, other than that great and simple explanation of such complicated tasks.
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 Daniel M•
Good insights on the YOLO algorithm as well as in Siamese networks and triplet loss. Miss some more deeper understanding both in the lectures and the assignments, but I totally recommend the course anyway.
By ashwin m•
very good topics discussed ,facial recognition and facial verification assignments do not do justice to the complexity involved.practical knowledge gained is less compared to other modules prior to this.
By Carlos V•
The knowledge is good, and the techniques taught are valuable; however, having to use a deprecated version of TensorFlow is annoying and a lot of this will have to be re-learned to be put into practice.
By Hagay G•
Course is very informative.
Unfortunately, unlike other courses in the spec, there were quite a few bugs in the notebooks and they took quite a while to load due to the sheer weight of the models loaded.
By David v L•
Face recognition is a bit oversimplified, there is more to it that a simple accuracy metric. Priors are involved, which are included in the NN training, but should really be disassociated in evaluation.
By João G V•
In contrast to course 1 and 2, I've found the videos to be rather shallow (no pun intended), in the sense that, in my opinion, they haven't explained thoroughly the techniques' underlying mathematics.
By Ramon S•
The information in the lectures was brilliant. However, the coding assignments don't really test your understanding of the course, rather your ability to piece together the authors previous code.
By Joscha O•
This is a very interesting and well structured but the assignments in week 4 got alot of bugs, grading gives zero points for the right ouput (according to the notebook) and ten for a wrong one...
By Swaraj L•
The course starts normal but suddenly gets very confusing from the start of week 2. Also it gets a bit difficult to understand things later on. Otherwise its very good course and i enjoyed it
By Marcela H B•
Overall the specialization this course is the more complex, not only regarding the main concepts I think that the assignments are hard and will be usefull have more context about tensorflow
By Martin S•
So far I was very enthusiastic about the courses but this one is rather disappointing. Unfortunately, the video editing is very poor, if done at all, which make listening somewhat annoying.
By George C•
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.
By Michael A•
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.
By Mario S•
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!
By Bashyam A•
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.
By Roya K•
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.
By Till R•
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.
By Mostafa M•
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.
By Claire L•
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.
By Jes T B K•
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.
By Aditya K•
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.
By Marco L S•
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.
By Arjun V•
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.
By Amit A•
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
By Sebastien M•
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