Chevron Left
Вернуться к Deep Neural Networks with PyTorch

Отзывы учащихся о курсе Deep Neural Networks with PyTorch от партнера IBM

Оценки: 1,131
Рецензии: 250

О курсе

The course will teach you how to develop deep learning models using Pytorch. The course will start with Pytorch's tensors and Automatic differentiation package. Then each section will cover different models starting off with fundamentals such as Linear Regression, and logistic/softmax regression. Followed by Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers. Then Convolutional Neural Networks and Transfer learning will be covered. Finally, several other Deep learning methods will be covered. Learning Outcomes: After completing this course, learners will be able to: • explain and apply their knowledge of Deep Neural Networks and related machine learning methods • know how to use Python libraries such as PyTorch for Deep Learning applications • build Deep Neural Networks using PyTorch...

Лучшие рецензии


29 апр. 2020 г.

An extremely good course for anyone starting to build deep learning models. I am very satisfied at the end of this course as i was able to code models easily using pytorch. Definitely recomended!!


15 мая 2020 г.

This is not a bad course at all. One feedback, however, is making the quizzes longer, and adding difficult questions especially concept-based one in the quiz will be more rewarding and valuable.

Фильтр по:

76–100 из 252 отзывов о курсе Deep Neural Networks with PyTorch

автор: Juho H

6 мая 2020 г.

This course is difficult to rate as a learning experience. There are some very good parts yet there is also some very poor material. I would say that if you are already very familiar with machine learning and Python BEFORE taking this course, you can still draw some useful learnings on how PyTorch can be applied to various problems, and how to create convolutional neural networks with it; but if you are uncertain about some of the key concepts, this course may only end up making things worse for you.

To give an idea of the problems, there are issues like:

- When explaining the train/validation/test data logic and how validation data can be used to prevent overfitting, the videos keep calling training data test data.

- Pytorch is used for some really fancy stuff like defining functions and datasets, but then those functions are not parametrized in any sensible way – meaning if you want to compare loss functions from two different initialisations of the model weights, you are expected to define a new function so you can just change the variable “LOSS” to “LOSS2”, rather than just passing the loss function as a parameter or just initializing or returning it. Given the Pytorch logic is not your regular Python stuff, a best practice should be provided – it is definitely not writing a new function every time.

So be warned: if you know what you are doing, and simply want to learn how to do it with Pytorch, this may still be a decent course for you, just ignore all the stuff where the instructors make mistakes (and they are plenty, also in incorrect quiz answers). But if you feel at all uncertain, I suggest you hone your machine learning skills elsewhere, because otherwise this course will leave you totally confounded on even the very basics of machine learning.

On the upside then, you learn Pytorch through repetition. In the beginning, the logic appears very intimidating, but then you gradually learn the logic and you can do some very impressive stuff quite easily in the end. Be prepared for the amount of repetition, however - first the stuff is shown on a video, then you run the exactly same stuff in a lab, and unfortunately the Skills Lab is not at all efficient for some of the stuff - I ended up downloading the notebooks and using them on my Watson Studio account for much faster performance.

автор: Daan S

18 нояб. 2021 г.

To be honest I am severely disappointed by the quality of the course. Nearly every single video contained typos and the example code often lacked consistency through weeks. For example, one week batch normalization was applied before activation, while the next week it was applied after activation. Without even elaborating on such changes, this threw me off as I am now unsure how to apply it. Furthermore, the labs barely presented any actual practice. In 9/10 cases I could just run all the code without implementing anything myself, this definitely decreased the learning experience. In addition, the quizzes don't provide any challenge at all. You can easily complete most quizzes without even watching the lectures as the answer is often already provided in the question itself. The last thing I would like to mention is that the staff in the discussion forums, although friendly, is clearly lacking fluency in English. They often don't seem to grasp the question and provide a copy-paste solution to most cases. Whether it's Deep Learning or PyTorch you want to learn, you're much better off following a course by a different provider on Coursera.

автор: Lennart F

28 сент. 2021 г.

T​he video's are voiced by a robot. There is alot of information, but the quiz questions are so simple that you get the feeling they are aimed at 6-year olds (e.g. most times you just have to repeat what the robot voice has JUST said). The peer review system for the honors assignment is retarded: I failed this assignment while answering everything correctly, just because some dude accidentaly misgraded a question. Coursera now expects me to pay another 40 euros to resubmit the assignment just because someone else messed this up, lol. Take your courses elsewhere.

автор: Ben A

5 авг. 2020 г.

Awful quality content that fails to teach or test you properly.

The videos are exceptionally poor using a text-to-speech narrator that makes you want to quit after only one video. Additionally, the quizzes are buggy with awful wording, typos, invisible options, and useless content. The biggest shame is that they don't use notebooks to test your learning with real examples that would reinforce both the theory & practical elements.

This course has no effort put into it & is clearly a money grab. Avoid this and instead try a or course.

автор: Gopal I

10 апр. 2022 г.

One of the worst courses on coursera. A very complex subject is treated in an off-hand manner. Course instructions have not been updated since 2019. Labs are different from instructions. There is no lab to opne in Week 7 - I wanted the honors content.

The Watson instructions are completely outdated.

There are so many spelling errors in the quizes including misspelling simple works like "does" - looks like no one checked these materials ever.

автор: Oussama B

26 февр. 2020 г.

Bad !!!!! Many mistakes, questions too easy !!! I am really disapointed

автор: Zaheer U R

12 июля 2020 г.

Amazing course with brilliant explanation

автор: Farhad A

16 июня 2020 г.

It was well structured . Thank you

автор: Krishna H

28 апр. 2020 г.


автор: Ali A

14 сент. 2020 г.

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.

автор: Fabrizio D

30 июля 2020 г.


-A lot of codes for practicing and learning

-The quizzes are short and focused


-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

автор: Miele W

16 февр. 2020 г.

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.

автор: Philippe G

10 мар. 2020 г.

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.

автор: Luca R

29 мар. 2020 г.

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.

автор: Eric

20 янв. 2020 г.

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

автор: Mateo P

10 июля 2020 г.

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

автор: Andrey G

17 июня 2020 г.

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.

автор: Vitalii S

15 апр. 2020 г.


Good intro to PyTorch, great work.


1) typos along the course.

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

автор: Paranjape A J

12 февр. 2020 г.

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

автор: Simon P

17 окт. 2020 г.

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.

автор: Olivier C

8 мая 2020 г.

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.

автор: Abdus S

5 мая 2020 г.

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.

автор: Geir D

8 мар. 2020 г.

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

автор: Dr. C C

11 мар. 2020 г.

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.

автор: Ozan G

20 янв. 2021 г.

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.