RECTnet
Emotion detection AI model developed by Rain, Evan, Cassie and Tim (RECT).
Getting Started
Web-app is available at: HERE
Face detection is also available in this application.
Prerequisites
Database required: Affectnet
Available at: HERE
Citation: Ali Mollahosseini, Behzad Hasani, and Mohammad H. Mahoor, “AffectNet: A New Database for Facial Expression, Valence, and Arousal Computation in the Wild”, IEEE Transactions on Affective Computing, 2017.
Deployment
You could deploy it to Jupyter Notebook or Google Colab (Small changes such as folder path needs to be made).
Versioning
We have two versions.
Primary model (first version) - transfer learning with AlexNet.
Final model (second version) - transfer learning with concatenation of different models.
Authors
Rain (Yucan Wu), Evan (Yifan Cui), Cassie (Kexin Li), and Tim Fei.
See also the list of contributors who participated in this project.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Sample codes provided by APS360 Introduction to Machine Learning at the University of Toronto.
- Everyone who contributed to this project.