need to watch Andrew Ng's course on deep learning before watching this one

Solid content, but it feels like it's not *very* much on top of the first course in this specialization. I think these two courses could be combined into one.

Useful but too easy

The concepts are not as clear as in other courses.

Dissapointed a little bit

Lacks depth and complexity. The course is geared more towards complete newbies or high school graduates.

I wish it had real assignments

A lot of boilerplate code with few new concepts

I wish it used TF2.

Actually a great course. Only not getting more stars due to the issue encountered with the last exercise where there is an issue in loading the data files. The workbook keeps on crashing and there is no solution provided to resolve that.

The course is taught excellently. However, there are overfull file stream operations in Python that the course does not cover.

Google colab system for tasks is pretty bad, no control on the tasks plus it erases and u can't prove you did the work unless you save it

A good course, but again, not nearly as in depth as the original deeplearning.ai set of classes. The material feels introductory and at times superficial, with no real work required of the student to complete the class. At best a very early start to using convolutional networks with the keras apis in tensorflow.

Please make the "Ungraded assignment" Graded and add more comments/directive in them to make sure we understand each steps.

Not solid enough and the exercise could be more organised. For example: some of the data downloading links didn't work.

to much shallow

complex ideas in very basic tasks that you can easily accomplish by copy-pasting from provided notebooks.

Coding exercises should be made compulsory and for the grade

It is a good course for a fast overview on this topic. Be aware that it is not an introduction on ConvNN (but there are several courses of deeplearning.ai on this topic). If you are looking for a detailed course on Tf for ConvNN, I suggest you a book, the official documentation.

Expected a lot more in this course from the Tensorflow specialization. Something that'd take us beyond tf.keras.

Clear explanations. Good sample codes. Too easy. Doesn't go deep enough in terms of theory. Exercises should be mandatory.

The course is good for beginners as it is very basic. It needs more advance topics like Detection using TensorFlow. Have a lot of scope for improvement.

too easy! not much to learn actually. all the videos could be one lesson only

If you have taken the first course of the specialization this class was repetitive at some points. I also did not like that there have not been graded coding problems. I still got some practice and learned some new techniques.

Good but too basic.

Specialization's first course already covered the basic of tensorlfow. This course is suppose to expose to sota topics in computer vision using cnns. The content in this course can be easily fetched from many online forums. Thus the curators need to put some advance topic like attention, spatial transformer etc etc

The content could have been covered in 15 min. Moreover, I thought you guys will teach tensorflow low level API and estimators etc. atleast in course 2. Also, what happened to the graded assignments ? I finished this course in 40 min.