Mar 09, 2019
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?
Aug 14, 2019
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 Rupsa R•
Jul 04, 2019
por Nazarii N•
Jun 25, 2019
por S P•
Jun 20, 2019
por Sui X•
May 26, 2019
por ankit k•
Apr 22, 2019
por Ashok R A•
Apr 03, 2019
Aug 16, 2019
por Ruben M•
Aug 28, 2019
por Raman M•
Aug 04, 2019
por Richard H•
Sep 13, 2019
Great introduction to using Tensorflow to implement convolutional networks.
I took the Stanford course by Andrew Ng first, so many of the concepts were very familiar - in some cases, the detail was just a little bit shallow - probably to avoid interfering with getting on with implementation - but this course certainly had references outside the course to some more detailed information on topics like how convolutions help identify features or the learning factor.
The jupiter notebooks were great in that you don't need to worry about the environment much - it's already set up - a big worry for me for many of these types of courses. But there were quirks, and a few times I (and some of the other students) could get tripped up for a little while. If you are a developer like I used to be, then troubleshooting and debugging environment/code issues is a small hurdle though.
Kudos to the instructors and those that set up the course - this is otherwise very hard material to teach and set up good "hands on" evaluation, which they did really well, a couple kinks aside.
Oct 01, 2019
This is a great course with very useful lessons that helps the students feel confident about implementing Deep Learning solutions. It is a perfect follow up for Deep Learning Specialization which lays down the theoretical foundations. The instructor is great, and he talks about real world problems (not just Fashon MNIST but non centered, colored and large images) and explains them very clearly.
There is some amount of lack of attention to details in the course which manifest itself specially in the code (typos, code and code comments not agreeing with each other, and entire lessons which are slotted for 10 minutes or more but dont have any action other than pressing the "mark as complete" button, which makes you feel that you are missing something. Also the discussion board isnt as responsive (especially moderators) as the other Deeplearning.ai courses have been in the past.
por Avinash M•
Sep 06, 2019
I thoroughly enjoyed the course and programming various CNNs on TensorFlow. However, in certain lectures (especially the ones with the horse/human data sets), the instructor could spend some more time explaining the process of downloading and storing the training and validation images. It took me some effort and quite a lot of Googling to figure out those parts of the code. While that might not be directly related to the task at hand (binary classification) it is, in my opinion, necessary to understand some of these ancillary tasks as well. Perhaps these explanations could be included as optional videos for those who wish to understand these features of TF.
por Kaustubh D•
Jul 28, 2019
This is an excellent course to get hands-on. Keeping some tasks as repetitive like those of the callback functions help make the person strongly hands-on and remember them. Just the way, every week's programming assignment involved writing the callback function, if there would be other TF functions/methods that the coder gets to implement and override and other TF abstract classes to extend from, that would have been cherry on top!
Drilling down from the bigger picture of model definition to model.fit seemed extremely useful.
And since there are tons of courses on theory of ML and DL, thank god this one just focusses on coding it out.
por Egor E•
Aug 02, 2019
I like structure and content of this introdactory course. And like the easy and clear way Laurence Moroney told about all this stuff. Particulary, I like clear formulated exercises. During course we got great bulk of working examples in jupiter notebookes, containg full lecture, notes, likns to supporting materials!
What I would improve in course it is the change a litle bit a balance from solving problems to technical implementation. We learn a lot of using CNN for image recognition. However, it would be great to listen in more details about calculating the shape for input and outputs for layers.
por Devansh K•
Feb 11, 2020
I loved the instructors and the content. For the first time, I found a course that actually taught me the practical aspects of deep learning in a fun and interactive way. The content was very good and the right level of difficulty, i.e. not too difficult but also reasonably challenging. One thing I would change about the course to make it better would be to have longer instructional videos that go over all the code in more detail. I did not completely understand some sections of code and I think this would have changed if there were more code explanations.
por João A J d S•
Apr 30, 2019
It's a great course! Very well structured, with an amazing amount of jupyter Notebooks (Colab) to work with, in a real hands on approach.
Just one criticism, which is why I didn't classify it as 5 Star: There isn't much of an evaluation. The tests are a bit easy, and it would be good to have at least one extensive assignment (maybe with other datasets...).
It's just that I feel the contents were really good. But if I can just pass the tests easily, I feel it doesn't really count as much of a "quality stamp" (to have passed this course).
por Bruce B•
Feb 27, 2020
A great starter course. My only suggestions:
In the code completion exercises, a note or two indicating what is expected to be done, would be helpful. You kind-of have to go back and look at the previous problems to guess what is being asked of the student.
A complete slide deck would be very helpful, if only to be able to write notes onto the slides. And it would allow the student to do less scribbling, and more pondering of the problems being discussed.
por Samuel M•
Jan 24, 2020
Nice class, covers some basics of tensorflow and learns how to quickly build a NN. Not too fond of the quizzes: a few unclear question/choices and lots of "learn by heart" questions (like: what is the size of the pictures in this specific dataset, what is that specific param name) which you can easily answer without understanding too much. The assignments are simple enough for an introduction, quite close to the lesson examples but still interesting.
por Ronet S•
Feb 25, 2020
Brilliant Course for getting started with Tensorflow. The only thing I would like the instructor to include are explanation for non -TF stuff, like matplotlib codes. It would really help develop additional skills apart from making TF models. Going online to find the working of each command in a different library like matplotlib really broke my flow and my focus . So, that would be a welcome addition!
por Jim D•
Sep 25, 2019
I really liked that it was very hands-on and made it very quick and easy to get up to speed on using TensorFlow for Machine Learning. That said, there was a lot less content that I expected (I finished the '4-week' course in about 1.5 days), and I was a bit disappointed that the focus was exclusively on image classification. A little variety in terms of the problems being solved would've been nice.
por Elias B•
Aug 07, 2019
Overall a very good course (with knowledge from the deep learning specialization) to get a deeper knowledge in tensorflow. But sometimes in the exercises you feel a little left alone, because of missing information (example Week 4, which folder should you use, what's the resolution of the images, you can find out but that requiered (for me I had to downloaded the files and check what i needed).
por Andrei N•
Aug 03, 2019
The course is quite light even for introductory one. At the same time, I enjoyed examples of NN implementations in colab and elaboration on how the code works. The most interesting for me personaly were hints and techics helping to develop a better understending on how the NN are builing its knowlarge on input data. I look forward to checking other courses of specialization out.
Dec 29, 2019
A really simple and intuitive approach to Neural Networks in TensorFlow. Smart and simple examples to experiment by yourself how to build image classification with a few lines of code in python. For me was useful to recap what I already studied in DeepLearning.ai courses. This course was pretty good to do some practical exercises and an overall recap.
por Kalana A•
Mar 17, 2020
This is way too easy for an intermediate course I believe. But some of the concepts like visualizing the activations of the layers, writing the custome callbacks are really nice. Overall the explanations were really good and the notebooks gives really good insight and playground to play with parameters and learn how these functions (API) work.