|
|
|
--- |
|
language: en |
|
license: mit |
|
tags: |
|
- VIT |
|
- image-classification |
|
- drowsiness-detection |
|
--- |
|
|
|
# VIT_Drowsiness_2 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) for drowsiness detection. |
|
|
|
## Model description |
|
|
|
This model is a Vision Transformer (ViT) fine-tuned for drowsiness detection. It classifies images into two categories: drowsy and not drowsy. |
|
|
|
## Intended uses & limitations |
|
|
|
This model is intended for drowsiness detection in images. It should be used on facial images similar to those in the training dataset. |
|
|
|
## Training data |
|
|
|
The model was trained on a custom dataset located at /kaggle/input/nthuddd2/train_data. The dataset was split into 70% training, 15% validation, and 15% test sets. |
|
|
|
## Training procedure |
|
|
|
The model was trained for 10 epochs using the Lion optimizer with a learning rate of 0.0001 and weight decay of 0.01. A cosine learning rate scheduler with 0.1 warmup ratio was used. |
|
|
|
## Evaluation results |
|
|
|
[Add your evaluation results here after training] |
|
|
