The course is very easy for anyone who has taken other deeplearning.ai courses. The course do has good and polished material but it is very small to be called as a course. Also there should be code based exams.

The theoretical concepts are too basic, the sample code to learn tensorflow are quite repetitive. I think the course should be much more dense both in DNN theory and in programming to worth the money.

A nice intro but very basic. Would have liked not using the keras api to have fewer things abstracted away. Then keras is a nice convenience once you fully understand what it is doing under the hood.

I felt the instructor is going too fast without covering the concepts of Neural networks, CNN and basics. Or maybe i need to take a supplement course for statistics and Neural networks by Andrew NG.

A very good introductory course, however the algorithms working under Tensorflow was omitted heavily. Some technical background on how these algorithms work would enhance the quality of the course.

content and teacher are great!

google collab and the submit process is tedious because of the hidden restrictions (memory space, computation power) and the bugs of the exercise submission tool

Oveall, a good course. Very good program examples. One area for improvement: fuker, more detailed explanations for ech line of code (both in the videos and the comment lines within the code.)

I was expecting an intermediate level course in which we learn how to create complex deep learning models using Tensorflow (and not keras).

the course is still great for beginners... I guess

Didn't like the exercises too much. There was just 1 massive function where both model building and fitting was happening. Difficult to test. It's like - everything works or nothing works.

It was very difficult to learn anything from this course. I had to go through several TensorFlow tutorials https://www.tensorflow.org/tutorials before anything in this course made sense.

This was a very basic course entirely solvable in a few hours. It gives you some insight how to use Keras in TensorFlow, and why convolution is a good idea. It was far too basic for me.

Es un curso bastante práctico, se hace muy ameno y te engancha a seguir aprendiendo. Para ser un curso introductorio está bastante bien, aunque te quedas con ganas de profundizar más.

This course is great for begineer who wants to get hands on with tensorflow. But I feel that this course lacks a little bit of exploratory data analysis. Other than that great course

It's not easy to complete all weekly exam for a lot of kernel errors.

It is as a good starting point for TensorFlow, but is not newbie course in Machine Learning and Computer vision.

Prior knowledge of CNNs is required, instructor just walks through the modules, you shoild be prepared to learn stuff from the documentations on internet amd the sample modules.

Great course to start learning about Tensorflow. However, I consider some quizzez may not contain specific technical questions like the "size"of the fashion MNST dataset.

One needs to have prior understanding to grasp the information in this course. This course does not provide full information about all the topics.

After finishing the amazing Machine Learning course, this felt little underwhelming. Hopefully the next courses will be more in depth.

The examples almost show you how to complete every labs. It would help me more if you increase the difficulty in the exercises.

Too basic for someone with a maths and Machine Learning background. Probably better to upgrade to the Advanced classes offered.

Good beginner course on Tensorflow, but many errors in example codes and tests that do not seem to be fixed for years now.

This Course is only useful if and only if u have prior knowledge about neural networks, and if previously used Tensorflow

It was a well-formatted course for someone just starting out with tensorflow as their choice of deep-learning framework.

Very good course to start with TensorFlow but a lot of problems on coursera's servers, the exercises are crashing a lot

It was annoying to keep writing the callbacks when we could use the inbuilt callbacks already provided. twas alright.