chbh7051's picture
update model card README.md
d8c5f3c
metadata
license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - uta_rldd
metrics:
  - accuracy
model-index:
  - name: vit-driver-drowsiness-detection
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: chbh7051/driver-drowsiness-detection
          type: uta_rldd
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9930477264186396

vit-driver-drowsiness-detection

This model is a fine-tuned version of google/vit-base-patch16-224 on the chbh7051/driver-drowsiness-detection dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0159
  • Accuracy: 0.9930

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.1504 0.17 500 0.1178 0.9540
0.0581 0.33 1000 0.1022 0.9579
0.0415 0.5 1500 0.0877 0.9746
0.0487 0.67 2000 0.0650 0.9775
0.0555 0.84 2500 0.0537 0.9786
0.0279 1.0 3000 0.0472 0.9827
0.0139 1.17 3500 0.0452 0.9855
0.0282 1.34 4000 0.0358 0.9878
0.0077 1.5 4500 0.0397 0.9876
0.0143 1.67 5000 0.0159 0.9930
0.0439 1.84 5500 0.0162 0.9930

Framework versions

  • Transformers 4.27.4
  • Pytorch 1.13.0
  • Datasets 2.1.0
  • Tokenizers 0.13.2