---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: vit-base-patch16-224-in21k_covid_19_ct_scans
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9765258215962441
    - name: F1
      type: f1
      value: 0.9294374875770225
    - name: Recall
      type: recall
      value: 1.0
    - name: Precision
      type: precision
      value: 0.9744897959183674
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# vit-base-patch16-224-in21k_covid_19_ct_scans

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1064
- Accuracy: 0.9765
- F1: 0.9294
- Auc: 0.8864
- Recall: 1.0
- Precision: 0.9745

## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Auc    | Recall | Precision |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:---------:|
| 0.6804        | 1.0   | 54   | 0.3821          | 0.8967   | 0.4728 | 0.5    | 1.0    | 0.8967    |
| 0.6804        | 2.0   | 108  | 0.4134          | 0.8967   | 0.4728 | 0.5    | 1.0    | 0.8967    |
| 0.6804        | 3.0   | 162  | 0.2708          | 0.9061   | 0.5585 | 0.5455 | 1.0    | 0.9052    |
| 0.6804        | 4.0   | 216  | 0.2405          | 0.9437   | 0.7973 | 0.7273 | 1.0    | 0.9409    |
| 0.6804        | 5.0   | 270  | 0.2193          | 0.9437   | 0.7973 | 0.7273 | 1.0    | 0.9409    |
| 0.6804        | 6.0   | 324  | 0.1719          | 0.9484   | 0.8775 | 0.9310 | 0.9529 | 0.9891    |
| 0.6804        | 7.0   | 378  | 0.0525          | 0.9859   | 0.9612 | 0.9519 | 0.9948 | 0.9896    |
| 0.6804        | 8.0   | 432  | 0.0482          | 0.9906   | 0.9736 | 0.9545 | 1.0    | 0.9896    |
| 0.6804        | 9.0   | 486  | 0.0907          | 0.9765   | 0.9294 | 0.8864 | 1.0    | 0.9745    |
| 0.1258        | 10.0  | 540  | 0.1009          | 0.9765   | 0.9294 | 0.8864 | 1.0    | 0.9745    |
| 0.1258        | 11.0  | 594  | 0.1051          | 0.9765   | 0.9294 | 0.8864 | 1.0    | 0.9745    |
| 0.1258        | 12.0  | 648  | 0.1064          | 0.9765   | 0.9294 | 0.8864 | 1.0    | 0.9745    |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1