This course is more challenging than the previous steps in the deep learning specialization, but it's still a great way to learn how convolutional neural networks work.

Interesting materials. Give a good understanding of the concepts of constitutional networks.

week 4 is the weakest of the 4 weeks especially the programming assignments.

Challenging course but very interesting. It gave the opportunity to understand better what a neural network is doing (from a visual point of view). Thanks Professor Ng.

Create explanations in the vids! The programming exercises felt a little less refined compared to the previous courses, although I've to admit the bar was raised high.

Andrew is an excellent teacher really. Quiz and Programming exercise were helpful to check the understanding on the topic. Overall it is a really good course to take.

This course explains very well how to use convnet, but however, I am a little disappointed because it does not explain why the convnet works and how to make it better.

I believe the coding tasks could be a little more open and require back referencing as I felt I was able to do them without fully udnerstanding the subject at times

A little more explanation on the advanced models like object detection would have been very helpful. Also, semantic segmentation has not been covered in the module.

Nice course, things didn't work out in the Jupiter Notebooks always, lucky we had the forums. Learned about CNNs, I know now how to engineer one from scratch. Cool!

Amazing instructor and lectures. It reached a point after week 1 in the course after which I was no longer able to view feedback after attempting the weekly quizes

it had really good content we could really have a good understanding of the topic after this course.

one thing which can be done better is the programming exercise.

There some problem with the happy house assignment in week 4, specifically in function 'verify', kindly omit that mistake, otherwise, everything is great, loved it

Provides a fairly basic understanding of all the tools and processes used into making a Convolutional neural network along with the necessary background knowledge.

The art generation exercise is not very clear to me. i believe some more explanation on how to use and slice existing models, in the lecture could have helped alot

There were some technical issues with assessment in this one. It seems the motivation in those creating the assessment is dropping as the specialisation goes on

The course was superb, many thanks. The performance of noteboooks is annoying, it's very often I was not able to save changes to the notebook due to an "error".

Transfer learning is extremely important and it would be helpful if we actually learned how pretrained networks are loaded into a new network through Tensorflow

It was an amazing course. Never thought that diving in deep learning would be so amazing. The only problem was regarding update of notebooks to tensorflow 2.0.

Videos are great. The course could use some more imaginative / challenging programming assignments, but overall it's a great way to learn the basics of CNNs.

Content and lectures are great.

In notebooks explanations are great.

Some problems with grader in week 4.

I would also like more open ended harder assignments.

Would be 5 stars if the last programming assignment wasn't broken. But it is a great course, I recommend it to anyone who's passionate about computer vision.

Week 4 could have been a little more detailed, and also faced some issues with the auto-grader. Apart from that, wonderful course. Looking forward to more.

Could use more clarification/direction on the programming assignments. Also would be interested in learning more about how back propagation works with CNNs.

the content of this course was very interesting and practical. however towards the end (week 4), there were a lot of confusions about how TensorFlow works.

Excellent course. My only reason for not giving 5 stars is purely because there was a grading error on the last weeks' assignment which is still not fixed.