---
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: 0.9197530864197531
    - name: F1
      type: f1
      value: 0.6365832614322692
    - name: Recall
      type: recall
      value: 0.9931972789115646
    - name: Precision
      type: precision
      value: 0.9240506329113924
---

<!-- 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: 0.5002
- Accuracy: 0.9198
- F1: 0.6366
- Auc: 0.5966
- Recall: 0.9932
- Precision: 0.9241

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:---------:|
| 0.7767        | 1.0   | 47   | 0.3346          | 0.9074   | 0.4757 | 0.5    | 1.0    | 0.9074    |
| 0.7767        | 2.0   | 94   | 0.5513          | 0.8272   | 0.5919 | 0.6204 | 0.8741 | 0.9312    |
| 0.7767        | 3.0   | 141  | 0.4290          | 0.9074   | 0.4757 | 0.5    | 1.0    | 0.9074    |
| 0.7767        | 4.0   | 188  | 0.4333          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |
| 0.7767        | 5.0   | 235  | 0.5041          | 0.9074   | 0.6181 | 0.5898 | 0.9796 | 0.9231    |
| 0.7767        | 6.0   | 282  | 0.4848          | 0.9167   | 0.6317 | 0.5949 | 0.9898 | 0.9238    |
| 0.7767        | 7.0   | 329  | 0.4877          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |
| 0.7767        | 8.0   | 376  | 0.4926          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |
| 0.7767        | 9.0   | 423  | 0.4958          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |
| 0.7767        | 10.0  | 470  | 0.4981          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |
| 0.0381        | 11.0  | 517  | 0.4996          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |
| 0.0381        | 12.0  | 564  | 0.5002          | 0.9198   | 0.6366 | 0.5966 | 0.9932 | 0.9241    |


### Framework versions

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