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.

I​t'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.

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.

The final project was missing some prompts for additional code. I'm all for research but there should be a heads up that we won't have all the prompts we need, since all the tests before specifically asked for the code needed to pass.

Maybe a bit repetitive, when you just finished Course 1. We see a lot of lines of codes explained again from course 1 and I think that could be avoided.

However, the new concepts are nicely introduced and very interesting to implement!

Sudden spike of difficulty and approach in the final assignment, but overall, the pacing is really nice. You really can't solve the last assignment without reading the discussion forum or looking for things for yourself though.

It was good, but similar to other learners I feel a little light in content. Though in tandem with the deep learning specialization gives a good view on convolutional neural networks as well as its implementation in tensorflow.

Loved the course. I would have liked a module on saving your own models and then loading them later. The Inception one is nice, but it comes with some "niceties" that I don't think you have with loading a home grown model.

It's an great course with simple explanations about the Deep Learning topic. It's a perfect fit for beginners or those who want to have a practical review before starting using Tensorflow 2.0 with keras implemetations.

It was a great course but there wasn't much theory into explaining why and what's happening. A course to get started with the coding without actually needing to require what is happening in the background.

A great course for those who want to start building their AI models using Tensorflow. It explains how to use the required tools for different purposes like data augmentation, transfer learning, etc.

Nice course. Even though I have previously done some projects using CNN and multi-class classification still this course let me to have an insight to how these APIs work. Keep Up The Good Work!!!!!!

This course awesome, but the notebook from coursera "i think" doesn't support any experiment we want, so we have to do it on google colab. But great, limitation is okay as long it's still graded

The course is really nice. But would be better if the convolutional layers were a bit more detailed. It was a bit difficult for me to understand all the parameters e.g: input/output filter size.