A CNN based Tensorflow implementation on facial expression recognition (FER2013 dataset), achieving 66,72% accuracy
- python 3.7
- Keras with TensorFlow as backend
- Streamlit framework for web implementation
- Dataset from https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
- Image Properties: 48 x 48 pixels (2304 bytes)
- Labels:
- 0 - Angry 😠
- 1 - Disgust 😧
- 2 - Fear 😨
- 3 - Happy 😃
- 4 - Sad 😞
- 5 - Surprise 😮
- 6 - Neutral 😐
- The training set consists of 28,708 examples.
- The model is represented as a json file :model.json
The separated dataset is already available to download in the two folders train and test.
- Open Anaconda's command prompt on the project's directory.
- Install virtual environment :
pip install virtualenv
- Create virtual environment :
virutalenv venv
- Activate the virtual environment :
source venv/bin/activate
- Install dependencies in requirements.txt :
pip install -r requirements.txt
- Install Streamlit :
pip install streamlit
- Run the app.py file :
streamlit run app.py"