Excellent set of videos and practice assignments!

This is a very nice introduction to Tensorflow.

Thanks for awesome lectures.

Good Course but too short!

Another Amazing Course :)

Brief and interesting.

Enplaned very nicely

excellent course

Great content

Very good!

Some of the material is a little confusing: sometimes the exercises will open on Google Collab, others in a classic Jupyter Notebook; instructions sometimes seem to lack revision to make them more organized and less convoluted. Also, references in videos should be always made into links (e.g. Andrew's videos are usually referenced as links in the class video and they are not clickable. Since the graded course is paid (and is not cheap for most third world countries) it seems that a little more care and polish should be applied. The contents are excellent, but they lack the organization and quality of the original course from Professor Andrew Ng, which was, by the way, 100% free and didn't have exercise grading locked by payment, for example.

The course offers a great introduction to TensorFlow methods for handling data, training models, and inferring results. Two things could be enhanced, in my opinion:

1) A better estimate of the time required to read the materials and do the exercises (the course takes less time than stated).

2) More in-depth explanations for certain parameters (although it could be argued that you should just follow the other deeplearning.ai specialisation for that).

Overall, though, a great crash-course for getting started with Tensorflow!

I took this course after taking deep learning ai CNN course. I found this course complement the other course really well.On itself, it is a little thin on theory size, but if you have already taken the other course, then this is a great consolidation of the material.

It take some time to change the code and run examples from this course with TensorFlow 2.0 locally on my computer. Today TF 2.0 is state of the art and required in practice. Please rewrite code for TensorFlow 2.0

More or less the course takes on Tensorflow's implementation of Keras rather than Tensorflow native env. It also only focuses on computer vision domain. Kind of misleading course title.

Ce cours balaye les fonctions de bases de la librairie d'abstraction Keras et permet de construire rapidement des réseaux de neurones complexes.

When each layer visualization was taught, I didnt get that part nor in the program. Else its a great starter course

It's relatively simple course if you've already finished Andrew Ng's deep learning specialization

The assignments need to be polished. They were very lackluster and non-rewarding.

Great introductory course to learn the application of TensorFlow with Keras.

Great course, but can be completed shortly instead of many weeks session

Amazing way of putting all the stuff together

Useful start for practitioner.

Good practice for coding on tf

I think this is a great way to introduce NN to people that have never seen one.

But there was very little depth in this course. I finished the 4 weeks in an afternoon. The external references were at times way too advanced, while the exercise code was way too simple. That being said, the Jupyter notebooks were a great material and helped me start with NN really quickly. The MNIST dataset is brilliant and hank you for showing how to do it.

The reason why I gave 3 stars is because the MOOCs aI have done in the past were much more extensive and gave plenty of theoretical background. Some people might think that the lack of theory lowers the entry bar for students, but in my book that's a tutorial not a course.

Save yourself the $40 price tag and buy a book on the topic, there are plenty out there.