FacialExpressionRecognition

Deep learning for the facial expression recognition kaggle challenge

Expected results

This solution achieves the same performance among the best results of that completion (around 70%).

Note: You will be able to reproduce this results since no data grooming, augmentation was performed, this result was achived even without MCMC (markov chain monte carlo) wich gives 2-3% free performance.

Instructions on how to execute

First of all, go to the kaggle challenge (https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge) and download the dataset, and then place the file fer2013.csv in this folder.

Execution file: cnn_tensorflow.py

Enjoy!