awesome

AWESOME

good!

Coll!

Good.

The labs are simply taking so much time. I am sure the is a better way to teach students than to make them wait 1 hour. Some people would want to run them locally, but this is not a solution, just a bypass. I learning a lot in this course and would reccomend. The best thing is that it taught me that CNNs are not super tough and with proper techniques can be handled.

Positive

-A lot of codes for practicing and learning

-The quizzes are short and focused

Negative

-The videos are too impersonal: it seems that the speaker is just reading the part, after a while I got tired of listening to him.

-Please review the texts: there are too many misspelled words

-Add more line of comments in the codes provided in lab

Well, as there are no sort of exams or real questions to answer in order to pass, it strictly depends on how much attention you put in following this course. IMHO if well studied, it gives you a solid foundation, in order to let you explore the pytorch module.

Very interesting course. Gives a good introduction to pytorch. My only concern is the quality of the quizzes: It is often limited to 2 very simple questions. This does not allow you to validate that you had a good understanding of the said topic.

At the beginning, PyTorch framework seems very hard to understand. At the half of course you begin to have a clear vision of the problems. A negative point is the notebook for every topic. I would suggest one for week with everything inside.

Good, thorough course. Does not hold the student to any kind of standard or accountability and quizzes are ridiculously easy to pass.

The amount of material was surprisingly extensive and the labs were very useful. The tests were not very good. The videos were OK.

The quizzes are way too easy. The videos are OK (read by computer voice except one). The labs, on the other hand, a really nice.

Pros:

Good intro to PyTorch, great work.

Cons:

1) typos along the course.

2) lab is working too slow - better run locally.

More graded coding assignments would have been better, but content is good!

Videos are sometimes too repetitive, e.g. when we move from 1 variable to many, or from 1 output to many, or from 1 hidden layer to many, all formulas and flows are repeated from scratch. Some parts are so briefly covered that they are too hard to understand if you didn't learn the context before (e.g. CNN). Too easy assignments (quizzes): 2-3 questions that often can be answered without watching the videos. Overall, if you are already familiar with deep learning, this course is a good overview over Pytorch API, although I think one could learn it much faster elsewhere.

The awful text-to-speech voice in the videos and the "We do this.... we do this... we do this..." information dump is poor from a didactic point of view.

The redeeming feature of the course are the labs, but like many of these little courses there's little encouragement to play around with the code.

Useful if you are already comfortable with deep learning and you want to learn how to use the (great) pytorch package. If you want to learn about deep learning from scratch, the explanations are not very intuitive and skip over some very interesting features.

This course provides a good amount of knowledge of PyTorch. However, the explanation and presentation are really bad. The monotonous voice and the quick changing of slides forces learners to watch the videos again and again.

Presenter is a synthesized computer voice. Slides and exercises are full of spelling errors. Contents is OK, but presentation is not very inspiring.

Quizes are either way too easy, almost impossible to fail, or the questions are too unclearly phrased.

Another issue with the quizes is that a lot of them consist of only 2 (multiple choice) questions, with a necessary passing grade of 50%. So, essentially, you don't need to know a lot about the material to pass.

Regarding the classes, the concepts are explained extremely swiftly, leaving no time to think it through.

Also some random guy was hired to read the script of the videos, or perhaps they used text-to-speech software. So don't expect to be engaged much by the classes. They were extremely boring to watch. Overall it felt like the creator of this course just wanted to quickly churn out this thing and get it over with and receive that precious money. There's no love in it :(

Honestly not the quality I expect from a Coursera course that I pay good money for.

If executed properly, this course should have been great, covering a good set of topics necessary to start working on DNN using PyTorch. Unfortunately, there are several issues that lowers the quality of this course.

Slides switch too fast after showing the last element, which is often an element or statement that is most important on the page. Too many typos on slides and notebooks. Labs often fail to launch due to a 500 error and when they do, notebooks often don't work due to outdated libraries. Most of the quizzes are too trivial that can be answered without understanding the important concepts covered in the videos (but some quiz answers are wrong as discussed in the forum; they are not fixed after years).

Personally I don't think it's worth $50 and so I've finished it in the first week before paying.

The general content of the course is good. However, I was experiencing a lot of problem accessing the lab platform. Also, there are typos and grammatical mistake everywhere in the quizzes. The audio of the video are done using computer generate voice over, instead of a real person speaking. I think the instructor of the course doesn't speak fluent English, which is understandable why computer voice over is used instead, but the non-stopping speech makes me a bit hard to concentrate sometimes.

I hated the robotic sound in all of the lecture recordings. It made it impossible to stay focused. The homework was ridiculously easy (including the Honors assignment). In most of the quizzes, anyone from the street could answer correctly just by reading. The lab environment on the IBM cloud was really slow towards the end for training DNNs. I had to skip most of the labs before they finished executing.

The text to speech videos are not very motivating. There could be put more efford in the training notbooks and slides. Questions and assignments are too easy compared to the topics covered in the videos.