ECS174-FinalProject

Due to the large size of the model and dataset, that could not be pushed to git, we set up a system that should allow you to reproduce the data and model we developed for this project.

However, in submitting our final assignment, we are able to zip the data and models with our code.

If you can see v3/src/models/emotion_model.joblib and v3/src/models/label_encoder.joblib, you can skip the steps to prepare the data, and you can skip running python emotion_model.py

Steps to start the project

1. Clone the repository where you want it to be:

git clone https://github.com/hadiafifah/ECS174-FinalProject.git

2. Open the repository
3. Set up your virtual environment

source venv/bin/activate

4. Install required python libraries

pip install -r requirements.txt

5. Run jupyter notebook

jupyter notebook

Steps to prepare the data

1. cd into v3.
2. Create two folders at the same level as src (one for "data" and another for "models")
3. Open:

v3/src/data_processing.ipynb

5. Run all cells to process data from kaggle.

Steps to run the model + demo

1. From root directory, cd into v3/src
2. Then run:

python emotion_model.py

To train the model on your computer

2. Now run

python webcam.py

Doing these steps will bring up a camera window that shows the demo of the project!

----To close the window Press "esc" or "q" key----