Hello! This is my final project for ECE 176. My project focuses on using Convolutional Neural Networks (CNNs) for Facial Expression Recognition (FER). Specifically, I built and trained a few different models of varying complexity to compare their performance on two different datasets (FER-2013 and RAF-DB). Two of these models incorporate Squeeze-and-Excite blocks as an attentional mechanism to improve accuracy.

In order to use, download the dataset zip files from the following links:

• https://www.kaggle.com/datasets/msambare/fer2013
• https://www.kaggle.com/datasets/shuvoalok/raf-db-dataset

My video is available at: https://www.youtube.com/watch?v=vLezI-tQ-Y0