awesome

Brutal.

useful

Very good. I love how it refers to the papers in which the algorithms are based. But of course i wish that from here they would go even deeper on some of them. Perhaps with time, space opens up so they will want to dig down further. This is already satisfying and an excellent course though.

This lecture series is really easy to follow and informative. I previously had no experience with distributed training concepts. I think It opened up doors for me to learn more advance concepts regarding distributed training using TensorFlow or any other deep learning frameworks.

Great course! The only downside, but maybe it's just out of the course's scope, is the lack of real projects at the end of it. That is left up to you, which is not a bad thing, but it'd be nice to have it as a great conclusion to a great course.

This course was much more detailed, I liked it. I hope there's a TF course down the road which really gets into all those numpy-like TF functions and APIs and how to use them for complex layers and losses.

For a newbie (me) this course helps me to know something new but it's not much helpful for my current job now

The course provides under-the-hood insights of Keras APIs and gives in-depth review of native TF APIs

Good assignments are too easy

Week 03 Grader is error

couldnt access flowers-public data from gcs, so couldnt practice the week 3 lab .

Many lectures are called "X code walkthrough" meaning that Laurence reads through the Python code. The problem here is that he does exactly that, not bothering to explain anything, even if it was an important new concept, etc. Considering that the only other type of lectures are those in which Laurence shows slides or "explains" something while quite obviously reading from his screen, I think it would be fair to add the "slide/code walkthrough" descriptor to the course title. I would not mind Laurence reading from his screen (how could I, he even acts like he was really giving a lecture, with the intonation and all) if he was systematic in explaining the newly introduced concepts. This way it simply does not make sense to me. Why bother with recording the lecture videos instead of just publishing the text that is being read out? I do not advise taking this course. It has a nice selection of topics for sure, but TensorFlow lines are just shown, not explained. You will learn about them way better if you simply read it from the official TensorFlow documentation. How can a course like this have such a high Coursera rating is beyond me.

nothing here that I can't get from just reading the docs...