This classifier is used to determine whether the speaker's gender is easily identifiable in the non-verbal behaviors transmitted.
To run these files you would need to add three folders :
- the data folder, which you can create with explanations from this github: FairGenderGen
- the generated data folder: the csv files corresponding to the gaze, head movements and AUs generated by your models. Exemple here: https://drive.google.com/drive/folders/1IfXOXlcB44t9sFjk0yZqFI9zJoUwZiYk?hl=fr
- the saved_models folder containing the trained classifiers, which you can download here: https://drive.google.com/drive/folders/1KlytbvuCfaSSgD35Tlq4QDTQNCuNLXai?hl=fr