A well taught course with interesting coursework and projects

This is another great course in the specialization. I wish only there were graded exercises like the previous course that we can submit and get a grade for. I understand maybe this is due to the long time of training and that is not possible to do.

A good course for Keras but not for tensoflow.

First, I think the course was great, very instructive. Thanks to Andrew and Laurence for putting this together, is a great source of information to understand more about DL. Some things I think could improve the course.

I found the transfer learning lessons a bit unclear and I struggle generalizing this to other cases. Also, I was a bit confused by the flow of the course. The course starts with a multi classifier (or actually, the previous course), then the lessons focus on binary classifiers and it ends again with multi classifiers, because these should be the more complex ones.

One last technical thing, only on the last lesson of this course it is mentioned that the classifiers output the probabilities on alphabetical order when using ImageDataGenerators (or at least, that's my impresision). I've wondered since the course introduced the ImageDataGenerators, how the probabilities are assigned on the outputs. I could figure out on the sigmoid that the classifier would look for the first class on the directory and output 1 or 0 based on that, but it would be good to have this mentioned at some point on the video when the ImageDataGen is introduced.

Thanks again! Great course

Please transfer the notebook from CoLab to Coursera.

Great insight for the practical aspect of TensorFlow, add value on top of Andrew's DL courses.

I need more coding practice, not just quizzes.

Some overlap with first course.

One challenge i have faced is with deploying the trained models. I find very little coverage on that across courses. It's one thing to save a model.h5 or model.pb. It would be nice if you can add a small piece on deployment of these models using TF Serving or something similar. There is some distance between just getting these files outputted and deploying. TF documentation is confusing about some of these things. Would be nice if you can include a module on that.

Good content, but lacks exercises that forces us to code ourselves to solve the problemas

Excellent course. Would have liked graded coding assignments like in the first course.

The course was fine sometimes I feel too easy. I would like to see more of the available options for the layers, such as padding, stride. filter size, mean average, batch normalization, etc...

the last exercise needed a big upload, made it imposible (for me) to do. This was a problem not related to the subject, should use data downloadable directly from internet.

Instructors are really good, but in my opinion, this course should contain Object Detection and Object Segmentation topis.

The course is really nice. But would be better if the convolutional layers were a bit more detailed. It was a bit difficult for me to understand all the parameters e.g: input/output filter size.

A more advanced course would be highly appreciated.

Good, but expected more, for example object detection.

very practical courses on implementation of CNN in tensorflow. Suggest student also take the deeplearning series with this series.

Loved the course. I would have liked a module on saving your own models and then loading them later. The Inception one is nice, but it comes with some "niceties" that I don't think you have with loading a home grown model.

Good practical course. A bit heavy on visual images, but very informative.

will be nice to have non-third party programming exercises that are graded by Coursera

Maybe a bit repetitive, when you just finished Course 1. We see a lot of lines of codes explained again from course 1 and I think that could be avoided.

However, the new concepts are nicely introduced and very interesting to implement!

quite easy

I think most much of the course conent was same as the first course, this course could have been a little more advanced. But overall a great place to start.

More exercises should be available for students to practice and test their skills.