vit-base-brain-xray / README.md
abdulelahagr's picture
initial commit
c99ba2d verified
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-base-brain-xray
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: sartajbhuvaji/Brain-Tumor-Classification
          type: imagefolder
          config: default
          split: Testing
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6903553299492385

vit-base-brain-xray

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the sartajbhuvaji/Brain-Tumor-Classification dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9079
  • Accuracy: 0.6904

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: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2478 0.5556 100 0.9079 0.6904
0.1499 1.1111 200 1.1543 0.7183
0.0872 1.6667 300 1.1469 0.7614
0.0118 2.2222 400 1.2361 0.7259
0.0077 2.7778 500 1.2023 0.7665
0.0057 3.3333 600 1.2470 0.7640
0.0053 3.8889 700 1.2096 0.7766

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1