Chevron Left
返回到 Deep Learning in Computer Vision

學生對 国立高等经济大学 提供的 Deep Learning in Computer Vision 的評價和反饋

3.8
263 個評分
65 條評論

課程概述

Deep learning added a huge boost to the already rapidly developing field of computer vision. With deep learning, a lot of new applications of computer vision techniques have been introduced and are now becoming parts of our everyday lives. These include face recognition and indexing, photo stylization or machine vision in self-driving cars. The goal of this course is to introduce students to computer vision, starting from basics and then turning to more modern deep learning models. We will cover both image and video recognition, including image classification and annotation, object recognition and image search, various object detection techniques, motion estimation, object tracking in video, human action recognition, and finally image stylization, editing and new image generation. In course project, students will learn how to build face recognition and manipulation system to understand the internal mechanics of this technology, probably the most renown and often demonstrated in movies and TV-shows example of computer vision and AI. Do you have technical problems? Write to us: coursera@hse.ru...

熱門審閱

SJ

Jun 12, 2018

Excellent course! Quiz questions are conceptual and challenging and assignments are pretty rigorous and 100% practical application oriented.

RR

Apr 19, 2019

Don't just read what's written on the projector. Try explaining it. And explain with code.

篩選依據:

26 - Deep Learning in Computer Vision 的 50 個評論(共 63 個)

創建者 ABHILASH N

Jul 18, 2020

Won't recommend. Concepts are not explained at all. The points mentioned in the slides are simply read out. Quizzes have no relevance to the topics covered in videos. Assignments are very badly structured. Notebooks have no documentation and are outdated (old versions of python lib, tensorflow, etc. - makes it quite frustrating at times). Only good thing about the course - a lot of CV topics covered and assignments are challenging (build from scratch - but no technical support )

創建者 khalid w

Oct 21, 2019

There is too much content stuffed into every week. The quizzes and assignments are very difficult with zero moderator help/guidance. Even the discussion forums are filled with people asking others to review their assignments. No guidance posts are available. I haven't seen any posts by mentors in any discussion forums.

創建者 111qqz

Jun 30, 2019

Poor English pronunciation, strange tone makes this course very difficult to understand

創建者 ALAN J P

Sep 08, 2020

An interesting view of topic with really talented instructors .

thank you

創建者 Edgar I

May 17, 2020

Very good course!

創建者 Anwesha S

Sep 17, 2020

lovedddddd it

創建者 MD A R A

Sep 02, 2020

Excellent !!!

創建者 Nandini

Apr 19, 2019

It was good

創建者 Atrayee C

Sep 06, 2020

good

創建者 Souvik P

Aug 27, 2020

Good

創建者 Roman

Oct 23, 2019

Overall:

This is an advanced course. Most of the time it would be difficult. In general, this course looks like the whole educational system in Russia - the given task is much harder then you can solve right now. But if you had a strong motivation you became much smarter. Support for this course doesn't even exist, but sometimes it is very useful to read the discussion to week practice.

Lectures and quizzes:

Teachers try to give a LOT of information in a very short time. But this theme is really not as simple to be told quickly. So as a result, you can understand just nothing:) Additionally, a heavy accent and kind of advanced vocabulary can make you feel frustrated.

BUT you can look at this that some keywords to google it was given) So generally, to understand I spend a lot of hours of reading about approaches in Computer Vision, mentioned here. The course was very useful from this point of view.

Quizzes sometimes look like crap. For some tasks, I still don't know to answer correctly.

Practice:

This is a part which could you a reason for you to finish this course. Tasks here really hard and requires from you a lot of time (about 20h, including the time to understand the task itself). I highly recommend all this practice carefully, it could be helpful for you in the future;) As a result, I knew a lot of tricks on how to prepare a model for find, recognize and even create faces.

創建者 Harshit R

Jun 26, 2020

The course assignments are not updated. Many libraries have updated and so have their syntax. And its nightmare getting the exact working version of those libraries.

Otherwise the course is good.

創建者 Erik G

Jun 07, 2019

Some lectures aren't clearly structured. The homework assignments have downstream dependencies (week 5 depends on earlier weeks) which is not the best format IMO.

創建者 Eric M

Sep 10, 2020

I would like to have more support from the instructors, because on many occasions I had doubts and the only way to receive help was the forum with my colleagues.

創建者 Wei X

Aug 31, 2018

Nice introductory course. It include many background knowledge of computer vision before deeplearning and is important to know.

創建者 Mallikarjuna R Y

May 08, 2020

good

創建者 Saptashwa B

Apr 20, 2020

I'm usually very kind and upbeat so, writing this review gonna be hard. But let's start with the positives

Pros :

1. Fantastic real-life assignments, which require knowledge and coding ability to build and fine tune realistic deep learning models.

2. Rather new concepts are being presented (or at least shown on the slides) which will give a non-computer vision engineer a glimpse where we are currently now beyond cat-dog classification. So to understand the new stuffs it is necessary to take steps on your own.

Cons:

1. The forum is dead! No instructor, no one from the university/department takes part in it to help answer some basic queries. I'm not so sure what's the point of having instructor or a discussion forum when they are of no use.

2. I feel for the students who take the courses offered by the instructors! It's so boring, they just read from the slides and no clear cut concepts that are necessary for the assignments are discussed. The instructors talking is just as useless as my exes when they used to argue with me. Useless!

3. I kinda feel scammed paying for this course because of the two aforementioned reasons.

4. Sometimes the length of the videos are long and concepts presented are so unclear that, searching and learning by myself would take way longer than estimated time of 1 week. So if you really want to learn all things taught and solve the assignments by yourself, you are in for a hard ride.

So that's all! I have already finished two of the other courses in this specialization (Intro and Bayes), and they are way better so, hopefully the experience with the next course in this specialization won't be as horrendous as this one. Fingers crossed!

創建者 Jiachen L

May 05, 2019

Course homework is actually not well designed for Coursera platform, some homework is not quite relevant to Deep Learning (i.e., HW1 and HW2) and some is very hard to complete (i.e., the last one, I tried on CPU for about 2 weeks). Also, the slides are not shared for this course in the series.

創建者 IMAD E M

Jul 10, 2019

pretty good mooc wtih very exciting and hard assignments, I highly recommend it. The main issue I faced it was that the lectures are not well explained, so you need to look for documents and other lectures by yourself.

創建者 Anmol G

May 02, 2019

The content was good, but there are several drawbacks too

1 Content not explained well

2 Assignments had mistakes (like broken links, wrong descriptions)

3 Minimal or Non-Existing support from the staff.

創建者 William

Apr 22, 2019

The task is really practical and useful, but the courses content is too general and I hope for the future it could include some papers reading assignment

創建者 Igor P

Mar 25, 2020

Overall it's a good course, but needs some improvements to make tasks clearer and provide a fair evaluation.

創建者 Gary

May 27, 2019

Not clear. And just focus on papers, not on basic structure or models.

創建者 Marian L

Aug 08, 2019

Zero passion from instructors. A lot of stupid questions, some of them with errors. Interesting programming assignments, but with dozen of typos. Don't expect to finish any of those programming assignments in two hours.

創建者 Erick D G H

Sep 02, 2020

Course out of date and speakers just read, don't explain. As for homework, they are not very intuitive so they lack explanation and the exams sometimes do not have much to do with the classes.