https://github.com/sayakpaul/emotion-detection-using-deep-learning

This project demonstrates the use of Deep Learning to detect emotion (sad, angry, happy etc) from the images of faces.
https://github.com/sayakpaul/emotion-detection-using-deep-learning

computer-vision deep-learning tensorflow

Last synced: 5 months ago
JSON representation

This project demonstrates the use of Deep Learning to detect emotion (sad, angry, happy etc) from the images of faces.

• Host: GitHub
• URL: https://github.com/sayakpaul/emotion-detection-using-deep-learning
• Owner: sayakpaul
• Created: 2020-02-01T04:03:19.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-02-14T15:29:43.000Z (over 5 years ago)
• Last Synced: 2025-03-31T11:01:42.514Z (6 months ago)
• Topics: computer-vision, deep-learning, tensorflow
• Language: Jupyter Notebook
• Size: 238 KB
• Stars: 10
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Emotion-Detection-using-Deep-Learning

This project demonstrates the use of Deep Learning to detect emotion (sad, angry, happy etc) from the images of  faces. 

## Dataset used: 

[Challenges in Representation Learning: Facial Expression Recognition Challenge](https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/)

![](https://i.ibb.co/gMPnd28/Screen-Shot-2020-02-01-at-2-36-22-PM.png)

## Network architectures/techniques tried:

- Shallow fully connected network

- Mini VGG16

- Mini GoogLeNet

- Shallow CNN with progressively increasing channels

- Mini VGG16 with LSUV

The combination of VGG16, SGD, a bit of data augmentation, and Label Smoothing yielded the best generalization. 

![](https://i.ibb.co/92nQjFC/W-B-Chart-2-14-2020-7-22-52-PM.png)

Experimentation report available here: https://app.wandb.ai/sayakpaul/emotion-detection

I happily welcome any feedback :)