Good intro course, but google colab assignments need to be improved. And submitting a jupyter notebook was much more easier, why would I want to login to my google account to be a part of this course?
Great course to get started with building Convolutional Neural Networks in Keras for building Image Classifiers. This is probably the best way to get beginners into Deep Learning for Computer Vision.
por Arif O•
Not at the level of the courses from Andrew Ng. I expected it to be more about TensorFlow API than machine learning concepts. It tries to do both and does not excel in any. Got some stuff out it but you can probably say that by any course.
por Venkata N S H N•
The course was comfortable to handle, explanations were were apt to the contents of the course, resources provided as reference were also really nice and apt, only felt that the course was a bit basic and well suited well for beginners.
por Wenyu Y•
A solid course, but if you have already take the deep learning specialization by Andrew Ng, there won't be too much new stuff for you. Callbacks and ImageDataGenerotor are new things for me, but I think they can be covered very quickly.
por Nitish R D•
The programming assignments are vague and should be improved. The course lacks explanation content. It's more of a 'Don't question, Just follow along' tutorial. However, what is taught is presented neatly and clearly by the instructor.
por STEFANO F P•
I understand that now Keras is inside TF 2.0 but the name of the specialisation is quite confusing. Here you learn how to use the high level API Keras not just the lower level TF. Really easy course, finished in less than a day.
por Mayur K•
it was good but there is scope of providing more thereotical contents along with videos for the concepts beyond the scope of this course so one could get better familiar with the terms (e.g adam. cross entropy)
por Naman B•
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.
por Jose L A C•
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.
por victor K•
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.
por siddharth J•
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.
por Hasan E E•
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.
por Stefano T•
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
por Vic H•
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.)
por Mohamed A T•
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
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.
por Thomas B•
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.
por Roberto F•
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.
por Raffaello B•
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.
por KAUSHAL K•
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.
por Rui P•
Instructors, please take a look at the discussion forum and answer some questions. It would save students a lot of time. The content of the course was overall awesome though.
por Xiangzhen Z•
Each video is a bit too short. And the assingment can't be smoothly finished and submitted due to environment issue. The creator should try to improve the user experience.
por Volodymyr L•
A very basic course, but it doesn't give you any fundamentals - just gives you a chance to recall keras API better. You'll be much better off doing cs231n, which is free!
por Aniket C•
The notebooks do not provide enough information about what block implements what. A simple comment that implement custom callback here would have made things lot easier.
por Ranjan D•
The course was good enough on the high-level perspective but was expecting pure TensorFlow based implementation of the models instead of using the Keras high-level API.
por Roger G A•
The course was very basic but interesting. However, there were some issues when submitting the assignments. And the virtual lab uses tensorflow 1.x instead of 2.x