Chevron Left
Retour à Convolutional Neural Networks

Avis et commentaires pour d'étudiants pour Convolutional Neural Networks par deeplearning.ai

4.9
étoiles
28,572 évaluations
3,452 avis

À propos du cours

This course will teach you how to build convolutional neural networks and apply it to image data. Thanks to deep learning, computer vision is working far better than just two years ago, and this is enabling numerous exciting applications ranging from safe autonomous driving, to accurate face recognition, to automatic reading of radiology images. You will: - Understand how to build a convolutional neural network, including recent variations such as residual networks. - Know how to apply convolutional networks to visual detection and recognition tasks. - Know to use neural style transfer to generate art. - Be able to apply these algorithms to a variety of image, video, and other 2D or 3D data. This is the fourth course of the Deep Learning Specialization....

Meilleurs avis

RK

Sep 02, 2019

This is very intensive and wonderful course on CNN. No other course in the MOOC world can be compared to this course's capability of simplifying complex concepts and visualizing them to get intuition.

RS

Dec 12, 2019

Great Course Overall\n\nOne thing is that some videos are not edited properly so Andrew repeats the same thing, again and again, other than that great and simple explanation of such complicated tasks.

Filtrer par :

2851 - 2875 sur 3,414 Avis pour Convolutional Neural Networks

par Radu I

Dec 08, 2017

Nice course, things didn't work out in the Jupiter Notebooks always, lucky we had the forums. Learned about CNNs, I know now how to engineer one from scratch. Cool!

par Arshdeep K

Jul 26, 2019

There some problem with the happy house assignment in week 4, specifically in function 'verify', kindly omit that mistake, otherwise, everything is great, loved it

par Piyush M

Jan 24, 2019

Provides a fairly basic understanding of all the tools and processes used into making a Convolutional neural network along with the necessary background knowledge.

par Parth J P

Mar 14, 2018

The art generation exercise is not very clear to me. i believe some more explanation on how to use and slice existing models, in the lecture could have helped alot

par Vladimir F

Jun 18, 2018

The course was superb, many thanks. The performance of noteboooks is annoying, it's very often I was not able to save changes to the notebook due to an "error".

par Arnav D

Jun 15, 2018

Transfer learning is extremely important and it would be helpful if we actually learned how pretrained networks are loaded into a new network through Tensorflow

par Alexandra M

May 13, 2019

Videos are great. The course could use some more imaginative / challenging programming assignments, but overall it's a great way to learn the basics of CNNs.

par Howard S

Jan 05, 2018

Content and lectures are great.

In notebooks explanations are great.

Some problems with grader in week 4.

I would also like more open ended harder assignments.

par Allan A D

Dec 31, 2017

Would be 5 stars if the last programming assignment wasn't broken. But it is a great course, I recommend it to anyone who's passionate about computer vision.

par Collin J

Sep 15, 2018

Could use more clarification/direction on the programming assignments. Also would be interested in learning more about how back propagation works with CNNs.

par Tianqi T

Jun 19, 2019

the content of this course was very interesting and practical. however towards the end (week 4), there were a lot of confusions about how TensorFlow works.

par Pieter N

Jan 15, 2018

Excellent course. My only reason for not giving 5 stars is purely because there was a grading error on the last weeks' assignment which is still not fixed.

par mihai.ionut.aurel@gmail.com

Dec 04, 2017

Really insightful. I did the course on Udacity and didnt understand much about the CNN but now I feel I have a better understand. I can't wait to apply it!

par Hao Z

Dec 02, 2017

The bugs in the grading system make me uncomfortable. People have to submit the answer which is obviously wrong but favored by the grader to pass the test.

par Hamlet B

Nov 20, 2017

The content was fun and very useful. The last programming assignment had some incorrect guidance and made the grading experience unnecessarily frustrating.

par Jose-Luis L

Nov 26, 2019

The course is great. There is only one minor downside: sometimes the notebooks' connection is lost and you lose the latest modifications of your homework.

par Matthew J

Jul 03, 2019

A good introduction to CNN's if you haven't seen them before. Strong on concepts and motivations. Kinda vague on mathematical details and implementations.

par Preethi G

May 06, 2018

The course structure is really good. But please do fix the bugs in the assignments. Thanks to the discussion forum, it helped me a lot in fixing the bugs.

par Sudipto C

Jan 01, 2018

Excellent content delivered very honestly by Prof. Andrew Ng. The course has some broken grader issues which need to be fixed to make this course awesome.

par Jonatan K

Jan 06, 2020

explained very well

very interesting with andrew

the main problem with this course is bug fixing on assignments.. i lost alot of hours just because of this

par kenji m

Sep 13, 2019

the last programming assingment has a lot of bugs as of 9/13/19 and was verry difficult to pass even though the actual code was very simple ti implement.

par Ameya G

Dec 21, 2017

Course content was good and well structured. Some videos still need editing and grader for 2 assignments is faulty. Otherwise a very interesting course.

par Nazmus s

Aug 04, 2019

ipython notebook fails often. It was a frustrating experience. There are many bugs to be fixed to run the homework problem submission process smoothly.

par itay k

Dec 21, 2017

A great course! I would have gladly given it 5 stars, but currently, the assignment of week four have bugs and the notebooks tend to stuck or run slow.

par Venkat K

Dec 06, 2017

A bit dense and fast-paced even for Prof Ng's usual standards - this course is drinking from a firehose, but a great hands-on introduction to ConvNets