Skip to content

Emotion Recognition model using Convolution Neural Network . Model accurarcy is not upto mark. I dont have powerful GPUs . So I am unable to built complex model. If can then you are most welcom.

Notifications You must be signed in to change notification settings

NupurMunda/Emotion_Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Emotion_Recognition

Emotion Recognition model using Convolution Neural Network . Model accurarcy is not upto the mark. I dont have powerful GPUs . So I am unable to built complex model. If can then you are most welcome.

Dataset

FER-2013 Faces Database

Number of images for training= 28,709

Number of images for Testing= 3,589

Image format=(48x48) in grayscale

No of Emotions=7 (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral)

Training

file name- ER_model_train.py

library used- keras, tensorflow

Model

file name- ER_model_training12ep.h5

no of hidden layer= 3

pooling used- Max and Average

dropout=0.5

Activation -

model accuracy= 57.17

Prediction

file name- ER_model_predict.py

to predict enter the image file name along with its location

About

Emotion Recognition model using Convolution Neural Network . Model accurarcy is not upto mark. I dont have powerful GPUs . So I am unable to built complex model. If can then you are most welcom.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages