Chevron Left
Retour à Convolutional Neural Networks

Avis et commentaires pour d'étudiants pour Convolutional Neural Networks par

36,530 évaluations
4,731 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


Jul 12, 2020

I really enjoyed this course, it would be awesome to see al least one training example using GPU (maybe in Google Colab since not everyone owns one) so we could train the deepest networks from scratch


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.

Filtrer par :

3951 - 3975 sur 4,686 Avis pour Convolutional Neural Networks

par henrik s

May 03, 2020

Very good and well structured lectures. The assignments make you work through some very interesting problems, but there is not a lot room for creativity in the solutions.

par Francisco S

Feb 23, 2020

I learned a lot. The tensorflow methods are not explained well enough (even if you did the previous courses of this specialization), and it still uses tf1 instead of tf2.

par Sven K

Jun 07, 2019

All good, but something is amiss with the submission of the last week's Face recognition notebook. Use manual "Create submission" under "My submission" and then it works.

par Dmitry

May 16, 2019

Great content. 2 hw exercises have some technical issues. E.g. hw4 Face Recognition doesn't teach much content but has a lot of bugs wasting time on it more than needed.

par vishnu v

Dec 10, 2017

Great course, I would have liked it better if assignments were bit more difficult and also could have dig deeper into fewer CNN techniques rather than skimming over many.

par Shilin G

Jul 27, 2019

Great course. Kind of getting difficult at week 3-4, especially week 4. Probably needs to be more familiar with TensorFlow in order to handle the programming assignment.

par Haim K

Aug 07, 2020

Interesting materials. Give a good understanding of the concepts of constitutional networks.

week 4 is the weakest of the 4 weeks especially the programming assignments.

par Rocco I

May 16, 2020

Challenging course but very interesting. It gave the opportunity to understand better what a neural network is doing (from a visual point of view). Thanks Professor Ng.

par Andres A

Mar 24, 2020

Andrew is an excellent teacher really. Quiz and Programming exercise were helpful to check the understanding on the topic. Overall it is a really good course to take.

par Zhan S

Jan 16, 2018

This course explains very well how to use convnet, but however, I am a little disappointed because it does not explain why the convnet works and how to make it better.

par Bishwarup B

Jun 28, 2018

A little more explanation on the advanced models like object detection would have been very helpful. Also, semantic segmentation has not been covered in the module.

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 Dhruvin S

Aug 05, 2020

it had really good content we could really have a good understanding of the topic after this course.

one thing which can be done better is the programming exercise.

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 Clint S

Mar 31, 2020

There were some technical issues with assessment in this one. It seems the motivation in those creating the assessment is dropping as the specialisation goes on

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 Shivank S

May 17, 2020

It was an amazing course. Never thought that diving in deep learning would be so amazing. The only problem was regarding update of notebooks to tensorflow 2.0.

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 Sandheep

May 10, 2020

Week 4 could have been a little more detailed, and also faced some issues with the auto-grader. Apart from that, wonderful course. Looking forward to more.

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.