Chevron Left
Facial Expression Recognition with Keras に戻る

Coursera Project Network による Facial Expression Recognition with Keras の受講者のレビューおよびフィードバック



In this 2-hour long project-based course, you will build and train a convolutional neural network (CNN) in Keras from scratch to recognize facial expressions. The data consists of 48x48 pixel grayscale images of faces. The objective is to classify each face based on the emotion shown in the facial expression into one of seven categories (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral). You will use OpenCV to automatically detect faces in images and draw bounding boxes around them. Once you have trained, saved, and exported the CNN, you will directly serve the trained model to a web interface and perform real-time facial expression recognition on video and image data. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with Python, Jupyter, and Keras pre-installed. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....



Jul 04, 2020

All the concepts are well explained. The project gives a nice insight about how we can integrate different ML frameworks to build a project and also how to deploy the model as a web app by Flask.


Jun 12, 2020

Very easy to follow and the instructor was very informative throughout the project. As a beginner myself, it was easy for me to follow along and understand the project


Facial Expression Recognition with Keras: 101 - 124 / 124 レビュー

by Shivam S

Jun 13, 2020

Good project for applying the concepts of CNN .

by Padmini k

Jun 23, 2020

Good course for new learner's in a short time.

by Md. S I S

May 20, 2020

good one. learned a lot


Jun 28, 2020

Good for beginners.

by Moresh M

Jul 19, 2020

Informative course

by sanjay p

Jun 12, 2020


by Sattenapally s c

Jul 04, 2020

Good course

by Ankit K

Jun 08, 2020

It is nice

by Matapathi S

Jun 14, 2020

Thank you

by Nelson R

Sep 02, 2020


by Estefania T

Jun 16, 2020

The content is good but the platform it still not comfortable to use. We have to code in a tiny screen, flexibility is needed. From a developer point of view, nice job Rhyme people, still work to do.

by Ayush G

Aug 09, 2020

This could be better, the accuracy achieved is not appreciable.

Also, the user interface was bad, rhyme cloud desktop was causing too much of lag collab could be a better option

by Ankit P

Jun 01, 2020

I didn't get the dataset . Sir If You give me the proper link to download the dataset then it is very helpful for me .

by suryanarayana d

Jun 10, 2020

Good one for very beginners in computer vision. Not for intermediate or advanced audience

by Mukul A

Jun 04, 2020

Not enough detail

by Ali E

Apr 13, 2020

Interesting, but at best, I'd say it's still in beta testing. Shouldn't have been released to "paying" customers:

1) I was never able to access the cloud notebook. Kept asking for a token or password. Incidentally, I prefer being able to run stuff locally on my computer, which brings me to (2):

2) The notebooks and auxiliary files were missing the videos and the utils, further making things difficult to reproduce on one's own computer.

3) The presenter makes several mistakes/typos and corrects them in real time or even later. Seriously? You can't check this stuff and re-record it without mistakes? And, is it worth really watching the presenter type the code on the fly?

In conclusion, you get what you pay for. Not even worth asking for my money back.

by Omar M A

May 09, 2020

Thanks for the content, I browsed this course to know how the instructor would deal with class imbalance problem, but he didn't handle it, and dealt with the problem as if the classes were balanced.

Also I noticed when he made the validation generator, he enabled shuffling which I think is wrong as you don't want to shuffle the validation set and each epoch have a different subset of validation set to evaluate your model, you need to make to make sure that the validation set doesn't change per epoch to serve its purpose of had the model improved during this epoch?

by yashika M

Jun 04, 2020

the course is not explainatory as expected.

material provided is just to complete a formality of doing a project and not learning implementation.

if you are an intermediate , i will recommend you to take course until and unless you know about concepts of data vizualisation, opencv, flask, basic of html,CNN using keras.

by Deepak Y V

Jul 19, 2020

Course is a basic one. Take this project only if you are looking for a beginner level introduction into CNN with Keras. Not for people who have already done a course or has decent knowledge/hands on with CNN and Keras.

by Keyur R S

Jul 20, 2020

Rhyme software is too much slow and it is very boaring to work on that and also font is too much small.

by Simon S R

Sep 04, 2020

Still much to improve

by Stanislav M

Jun 07, 2020

This is the worst course I've ever seen anywhere (and I've seen a lot), an absolute useless waste of time and money. No explanations related to the subject whatsoever: nothing about the model architecture, hyperparameters, or even general approach. Just we use X because we use X, and more details are "beyond the scope...". References to Flask and OpenCV are ridiculous (imagine trying to learn a foreign language in 20 minutes). ...And this is not mentioning all the mistakes and errors from the author during the actual explanation.

The ONLY thing you can practice here is typing on your keyboard.

by Rachita P

Jun 05, 2020

not for someone with no background in programming/python etc. They should have mentioned this! Disappointed

by Pranav S

May 15, 2020

i cant use it again and finding difficulty in running the code on my system. worst course ever