This project is to classify images into drowsiness and normal condition.
The ones used for image preprocessing are haar cascade and mediapipe.
WideResnet tried to create a more accurate classification model by expanding the range of models.
- NVIDIA Titan XP (CUDA 10.2)
- Python 3.8.10
- Tensorflow-gpu 2.10.0
- Mediapipe 0.9.0.1
- Keras 2.10.0
Check the code for the detailed structure of the model.
The model with WideResnet did not achieve the desired level of learning results due to a lack of epochs.