Skip to content

README.md

Latest commit

 

History

History
45 lines (27 loc) · 1.62 KB

README.md

File metadata and controls

45 lines (27 loc) · 1.62 KB

Emotion recognition CNN based approach using TensorFlow

This repository is the out project about Face emotion recognition using convolutional neural network.

video_screenshot_16 02 2018

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.

Download per-trained model and data in numpy format from this link.

  • Step 1: Download data.zip file.
  • Step 2: Unzip the files.
  • Step 3: Paste all the files into the data folder of the repository

Train

$ python emotion_recognition.py train

Test

$ python emotion_recognition.py poc

Paper

Link

Credit

This code credit goes to Enrique Correa. I've merely created a wrapper to get people started.