Skip to content

es65/ADSP

Repository files navigation

MIT Applied Data Science Program (ADSP)

This repository contains materials from the capstone project for the MIT ADSP, 2023

Facial Image Emotion Detection Using Neural Nets (MIT ADSP Capstone Project)

  • Built and trained CNNs and transfer learning models (VGG16, ResNetV2, EfficientNet) to classify facial expressions into four emotion categories
  • Applied data augmentation and preprocessing techniques to enhance model robustness; automated training and evaluation pipelines in TensorFlow/Keras
  • Achieved an F1-score of 0.85 with a fine-tuned VGG model; confusion between 'sad' and 'neutral' reflected labeling ambiguity in the dataset
  • Leveraged A100 GPU for training, enabling extensive model experimentation and hyperparameter tuning

About

MIT Applied Data Science Program Capstone: Facial Emotion Recognition with Neural Nets

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors