aminehorseman / facial-expression-recognition-svm Goto Github PK
View Code? Open in Web Editor NEWTraining SVM classifier to recognize people expressions (emotions) on Fer2013 dataset
License: GNU General Public License v3.0
Training SVM classifier to recognize people expressions (emotions) on Fer2013 dataset
License: GNU General Public License v3.0
Hello, I am a newcomer to research expression recognition.I want to know what sliding window is doing with the data.Why can IT improve the accuracy? Thank you in advance for your reply.
I would like run and see the implementation but the 2013Landmarks+hog file with hog features are not found. It would be great if you could upload the file. Thank you.
Can you please suggest how to fix this?
[jalal@goku facial-expression-recognition-svm]$ python convert_fer2013_to_images_and_landmarks.py --landmarks=yes --hog=yes --jpg=no --onehot=yes
preparing
importing csv file
converting set: Training...
/scratch/sjn/anaconda/lib/python3.6/site-packages/skimage/feature/_hog.py:119: skimage_deprecation: Default value of `block_norm`==`L1` is deprecated and will be changed to `L2-Hys` in v0.15
'be changed to `L2-Hys` in v0.15', skimage_deprecation)
converting set: PublicTest...
converting set: PrivateTest...
[jalal@goku facial-expression-recognition-svm]$ python train.py --train=yes
loading dataset Fer2013...
building model...
start training...
--
kernel: rbf
decision function: ovr
max epochs: 10000
--
Training samples: 28709
Validation samples: 3589
--
Traceback (most recent call last):
File "train.py", line 84, in <module>
train()
File "train.py", line 35, in train
model.fit(data['X'], data['Y'])
File "/scratch/sjn/anaconda/lib/python3.6/site-packages/sklearn/svm/base.py", line 149, in fit
X, y = check_X_y(X, y, dtype=np.float64, order='C', accept_sparse='csr')
File "/scratch/sjn/anaconda/lib/python3.6/site-packages/sklearn/utils/validation.py", line 547, in check_X_y
y = column_or_1d(y, warn=True)
File "/scratch/sjn/anaconda/lib/python3.6/site-packages/sklearn/utils/validation.py", line 583, in column_or_1d
raise ValueError("bad input shape {0}".format(shape))
ValueError: bad input shape (28709, 7)
I want to know about how you ae feeding your network with landmarks? are you appending landmarks on image or just using as a label?
I trained the classifier as explained in your post, and got a trained model. I'm now trying to put together a script that can take a grayscale image from the RPi Camera V2, then return a value from 0-6 depending on the emotion it detected using the trained model. However, I don't know how to feed the landmarks I extracted from the image to the model. I tried replicating some snippets of your code in order to get the desired results, but always ended up feeding incompatible data to the "predict()" function. How could this be done?
hello , thank you for your excellent work how do you test the model ?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.