How to run the code

Download Fer2013 dataset if training of the model is being executed and create a folder with the name data in the main folder and place the fer2013 folder in the data folder-

- [Kaggle Fer2013 challenge](https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data)

#For SVM

Download model, unzip and place in the SVM folder
- Dlib Shape Predictor model

Install dependencies

pip install numpy
pip install argparse
pip install sklearn
pip install scikit-image
pip install pandas
pip install hyperopt
pip install dlib

Convert the dataset to extract Face Landmarks and HOG Features
```
python convert_fer2013_to_images_and_landmarks.py
```
Train the model
```
python train.py --train=yes
```
Evaluate the model
```
python train.py --evaluate=yes
```

Train and evaluate [instead of step 5 and 6]

python train.py --train=yes --evaluate=yes

Customize the training parameters:

Feel free to change the values of the parameters in the parameters.py file accordingly.
Find the best hyperparameters (using hyperopt):
```
python optimize_parameters.py --max_evals=15
```

For CNN

Install Dependencies
- TensorFlow (latest version) Installation
- OpenCV (python3-version) Installation
To run the demo, just type:
```
python3 main.py
```

Then the program will creat a window to display the scene capture by webcamera. You need press SPACE key to capture face in current frame and recognize the facial expression.

To train models Modifying the MODE(in main.py) from demo to train before you start training. Then type:
```
python3 main.py
```

chusri/Facial-Expression-Recognition-1

How to run the code

For CNN