---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
model-index:
- name: swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_10
  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: 0.9375490966221524
    - name: Precision
      type: precision
      value: 0.9451238954076366
---

<!-- 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. -->

# swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_10

This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2175
- Accuracy: 0.9375
- F1 Score: 0.9383
- Precision: 0.9451
- Sensitivity: 0.9381
- Specificity: 0.9843

## 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: 0.0001
- train_batch_size: 100
- eval_batch_size: 100
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 400
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Precision | Sensitivity | Specificity |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:-----------:|:-----------:|
| 1.3428        | 0.99  | 19   | 0.7059          | 0.7467   | 0.7535   | 0.7951    | 0.7464      | 0.9332      |
| 0.3308        | 1.97  | 38   | 0.2314          | 0.9183   | 0.9194   | 0.9239    | 0.9191      | 0.9792      |
| 0.1601        | 2.96  | 57   | 0.2024          | 0.9305   | 0.9314   | 0.9349    | 0.9306      | 0.9824      |
| 0.0976        | 4.0   | 77   | 0.3376          | 0.8904   | 0.8943   | 0.9126    | 0.8930      | 0.9724      |
| 0.0585        | 4.99  | 96   | 0.3893          | 0.8830   | 0.8853   | 0.9115    | 0.8854      | 0.9706      |
| 0.0432        | 5.97  | 115  | 0.2559          | 0.9214   | 0.9239   | 0.9330    | 0.9237      | 0.9802      |
| 0.0313        | 6.96  | 134  | 0.2175          | 0.9375   | 0.9383   | 0.9451    | 0.9381      | 0.9843      |
| 0.0176        | 8.0   | 154  | 0.2309          | 0.9313   | 0.9326   | 0.9386    | 0.9320      | 0.9827      |
| 0.0152        | 8.99  | 173  | 0.2358          | 0.9328   | 0.9339   | 0.9416    | 0.9336      | 0.9831      |
| 0.0089        | 9.87  | 190  | 0.2116          | 0.9360   | 0.9374   | 0.9437    | 0.9372      | 0.9839      |


### Framework versions

- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3