Skip to content

Latest commit

 

History

History
33 lines (19 loc) · 1.29 KB

File metadata and controls

33 lines (19 loc) · 1.29 KB

Emotion recognition with CNN

This repository is the out project about mood recognition using convolutional neural network for the course Seminar Neural Networks at TU Delft.

Angry Test

67% Accuracy

Angry Test

Dependencies

Dataset

We use the FER-2013 Faces Database, a set of 28,709 pictures of people displaying 7 emotional expressions (angry, disgusted, fearful, happy, sad, surprised and neutral).

You have to request for access to the dataset or you can get it on Kraggle.

Usage

$ python emotion_recognition.py poc

Paper

Link