---
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
model-index:
- name: swin-tiny-patch4-window7-224
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8933333333333333
    - name: Precision
      type: precision
      value: 0.8772576832151301
    - name: Recall
      type: recall
      value: 0.8933333333333333
---

<!-- 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-tiny-patch4-window7-224

This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co./microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2912
- Accuracy: 0.8933
- Precision: 0.8773
- Recall: 0.8933
- F1 Score: 0.8762

## 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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| No log        | 1.0   | 4    | 0.4588          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| No log        | 2.0   | 8    | 0.3854          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| No log        | 3.0   | 12   | 0.4070          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| 0.4953        | 4.0   | 16   | 0.3890          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| 0.4953        | 5.0   | 20   | 0.3688          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| 0.4953        | 6.0   | 24   | 0.3549          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| 0.4953        | 7.0   | 28   | 0.3138          | 0.8708   | 0.7584    | 0.8708 | 0.8107   |
| 0.4217        | 8.0   | 32   | 0.3330          | 0.8708   | 0.8312    | 0.8708 | 0.8308   |
| 0.4217        | 9.0   | 36   | 0.2946          | 0.9      | 0.8881    | 0.9    | 0.8845   |
| 0.4217        | 10.0  | 40   | 0.2753          | 0.9042   | 0.8938    | 0.9042 | 0.8905   |
| 0.4217        | 11.0  | 44   | 0.2996          | 0.9      | 0.8909    | 0.9    | 0.8935   |
| 0.3747        | 12.0  | 48   | 0.2684          | 0.9      | 0.8883    | 0.9    | 0.8894   |
| 0.3747        | 13.0  | 52   | 0.2670          | 0.9      | 0.8883    | 0.9    | 0.8894   |
| 0.3747        | 14.0  | 56   | 0.2722          | 0.9042   | 0.8940    | 0.9042 | 0.8951   |
| 0.3579        | 15.0  | 60   | 0.2718          | 0.9042   | 0.8940    | 0.9042 | 0.8951   |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3