mansikataria/facialexpressionrecognition

Facial Expression Recognition using ResNet18 model implemented in Pytorch

Facial Expression Recognition

This repository is to do facial expression prediction by fine-tuning ResNet-18 with FER-2013 Faces Database.

(Image source: www.kaggle.com)

Notebooks

FERResNet.ipynb

Pytorch is used to create ResNet18 model. RandomCrop and HorizontalFlip are applied on data before training. The model is trained for 200 epochs with batch size 32.

Private Test Accuracy: 73%

Loss Graph:

Accuracy Graph:

Confusion Matrix:

FacialExpressionRecognition.ipynb

Keras is used to create and train a CNN model with BatchNorm. Data is augmented using random rotation, width/height shift, zoom, horizontal flip before training. Model is trained for 50 epochs with batch size 64. More accuracy can be achieved by training for more epochs.

**Private Test Accuracy: 65.45% **

Loss & Accuracy Graph: