nice

good

gj

I think I might say this for every course of this specialisation:

Great content all around!

It has some great colab examples explaining how to put these models into action on TensorFlow, which I'm know I'm going to revisit time and again.

There's only one thing that I think it might not be quite so good: the evaluation of the course. There isn't one, apart from the quizes. A bit more evaluation steps, as per in Andrew's Deep Learning Specialisation, would require more commitment from students.

One challenge i have faced is with deploying the trained models. I find very little coverage on that across courses. It's one thing to save a model.h5 or model.pb. It would be nice if you can add a small piece on deployment of these models using TF Serving or something similar. There is some distance between just getting these files outputted and deploying. TF documentation is confusing about some of these things. Would be nice if you can include a module on that.

Great course! Builds on the concepts of Course 1 in this Specialization although the course can be taken without having completed Course 1. Concepts are explained in a super clear and engaging way and the hands-on exercises give you the experience you need to become proficient. The course covers plenty of practical concepts including some pitfalls for practitioners to avoid, but the theoretical concepts are covered less than I expected.

Content was clear building upon each topic however the lab submissions need work. Most of the "write your own code" complexities and issues where around data wrangling, directories, and memory efficient code which was not too relevant to the main learning objectives. I spent 90% of the coding exercises fixing or waiting for the data prep functions instead of experimenting with the different layers, dropouts, augmentation values.

The course is well-paced and the instructor provides good coverage on the main topics on Convolutional Neural Networks. I'd recommend watching Andrew Ng videos from the Deep Learning specialization for a better understanding of topics like dropout, transfer learning, and optimization methods. The final exam is quite difficult as you need a lot of trial and error to get things to work properly - just like the real messy world.

Whilst I very much enjoyed playing around with convolutional neural networks, transfer learning and using image transformation to augment standard convolution, this course lacked an proper introduction in how to use python and will require a course into python or a good python language reference book which should help you build the necessary functions for completing the tasks required. Otherwise, this was a great course!

As another reviewer mentioned, this course is much simpler than Andrew Ng's deep learning specialisation but even so it has it's uses. I'm taking it to prepare for the Google TensorFlow certificate and it's forcing me to learn more of the api.

Andrew Ng's course was how to implement

the theory from papers, whereas this course is how to use TensorFlow. Each has it's place, although the former is probably more valuable.

Overall very helpful. I wish debugging on the jupyter notebook assignments was better and that it gave pop text descriptions, etc. Google collab is much better that way. I wish the assignments could use that environment instead. Also, the assignments us model.fit_generator which is now deprecated in TF 2.2. Would be good if the assignments were updated to use model.fit instead.

The course is very good, but coming from the Deep Learning Specialization, also offered by deeplearning.ai, it feels somewhat like a downgrade having 15 minutes of video for each week, while the other specialization had real extense and complete explanations with over 2h of video. I feel like 10min more of explanations going through the code would make a huge difference.

The grader memory availability does not match the one available to us during the exercise. as a result insufficient memory is shown as grader remarks whereas we do not face such a problem. This becomes hard to debug and is more of analysis, trial and error. Can be avoided if we also get the same type of warning when we create/update our notebook

Course material was good. The only issue I found was that the graded exercises are graded by automated systems that have different requirements to the notebook environment used for development. This 'black box' strategy by Coursera makes some of the exercises difficult. If you don't have debugging skills with Python, don't attempt this course.

Exellent tutorial for using Tensorflow and convolutional networks. Useful usage examples, interesting and challenging exercises. A few minor mistakes prevent five star grading. But please note that mistakes happen and we have to live with this :-). Nice work, looking forward for the next course of the specialization.

What I feel in this course is that, a lot of the exercises are much about file handling operations instead of CNN implementation. Also, in the exercises there are missing task allotments/comments.

I liked the explanation and implementation part of Transfer Learning, I think it's the best part of this course.

The course gives you an eagle eye view of how to use keras tensorflow for convnets. While they lectures are good, they are very short. I would have loved to hear more about training and storing your own networks for transfer learning and a bit more on regularization. A bit too shallow and easy for my taste.

I really did enjoy learning and playing around with the workbooks, however the exercise problems needed more explanation as how to go about since sometimes some of the concepts are not very obvious unless we dig into the documentation of the tensor flow and keras libraries which can be a good thing.

Good coverage of practical stuff in image recognition but it only covers the basic introductory stuff. There is a lot more to image recognition than what Is covered in this course. This will give a foundation to a novice user to learn more advanced deep learning techniques.

This course explores the topics of the first course for image classification with neural networks. All the tests are multiple choice questions. There are some code examples to work with as well as extra exercises but it would have been good to have a programming test as well.

Generally a really good course, but the last assignment is out of nothing very badly explained in terms of data processing, which causes the grader to fail or run out of memory and therefore passing it is quite a challenge. Besides that, a very good intro to CNNs.

Course was quite good, but the last assignment was a little challenging,Well..that's what i really liked!. Also, i felt like more concepts in computer vision had to be covered like Object detection, segmentation. Fairly basic concepts were emphasized here.

I think some parts of the assignments are not really the main objective of the course, they focus more on methods that involve just creating folders and copying files, which is not what I was there for. Aside from that, great ML content right here :)

Excelente curso, casi no necesitas saber programar los conceptos super actuales y las actividades te permiten ejecutar procesos de inteligencia artificial y lograr resultados interesantes con un conocimiento tecnico minimo....super recomandable!!!!!

This is another great course in the specialization. I wish only there were graded exercises like the previous course that we can submit and get a grade for. I understand maybe this is due to the long time of training and that is not possible to do.