The assignment in the last week was very poorly designed. Other than that, I really liked the course, especially the parts about augmenting data and using pre-trained models. Perhaps the course could cover more topics on how to use pre-trained models, the different kinds of pre-trained models available out there, and the specific applications in which they should be used.

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.

Quite good basic overview of image classification in Tensorflow. After the course can implement basic convolutional neural network using data augmentation and transfer learning techniques. The tasks however are very basic and except for the last lab task do not provide enough challenge to be meaningful. One of the labs is a copy paste of the Introduction to AI one...

The material was quite straightforward, but as a side effect of doing course and doing some "extra playing around". I feel like I got a good understanding of tensorflow and some it's internals. The exercises of trying to tune models to increase their performance was relatively difficult and felt like it started to give one a deeper understanding of models.

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.

Solid and accessible instruction. Would be remiss not to mention inconsistency between instruction and current tensorflow codebase. Requires a lot of digging by the student to reconcile the instruction with the exercises, particularly in week 4. However, my intuition for tensorflow architecture is probably deeper because of that digging.

Short of words to describe this fabulous course by Laurence. Every concept is covered. However, would have liked him suggesting some extra resources like Tensoflow Playground, Hub, and stuff. The section on Transfer Learning could have used the newer syntax based on TF Hub. Otherwise, nothing to complain about. Top 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.

Interesting course. I can do the exactly what is being taught - no more no less. It is almost like we are being taught to solve specific problems rather than learn of the subject. Perhaps, it is the nature of the subject itself - there is no systematic learning - it just is. Learn what is done now and works.

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.

It's a good introduction, and the consistency of a well structured course in general is fantastic. Some of the graded pieces are you simply rewriting code that they've already shown you. I would have liked some quizzes on the correct keras function calls to drill it in to my memory.

Everything is fine, detail explanation of concepts, step by step tutorial making me feeling good and learn the tensorflow in a proper speed. This is a great course!

I am not sure but the final assignment in week 4 seems has bug but I couldn't amend other code. regarding the labels.

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.

This course is great for those needing an introduction to convolutional neural networks. It would be truly amazing if there were more tutorials on transfer learning. It is not quite possible to fluently use pre-trained models only with the knowledge offered in this course.

If there is more coverage on the concept behind the augmentation parameters and how to tune the value, then that would be even better. Now I think most of the students just adjust the parameter value with trial and error approach in order to fulfill the accuracy target

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.

This course provided a nice guidance about filtering, cleaning and augmenting the datasets. This will definately help to build the models where the custom dataset needs to be generated and then use it for training with reduced chances of overfitting.

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.