---
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: 0.76
    - name: Precision
      type: precision
      value: 0.7692631578947368
    - name: Recall
      type: recall
      value: 0.76
---

<!-- 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: 0.5138
- Accuracy: 0.76
- Precision: 0.7693
- Recall: 0.76
- F1 Score: 0.6932

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 | Precision | Recall | F1 Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
| No log        | 1.0   | 8    | 0.5844          | 0.7333   | 0.5378    | 0.7333 | 0.6205   |
| 0.6556        | 2.0   | 16   | 0.5703          | 0.7333   | 0.5378    | 0.7333 | 0.6205   |
| 0.5707        | 3.0   | 24   | 0.5585          | 0.7417   | 0.8090    | 0.7417 | 0.6397   |
| 0.5383        | 4.0   | 32   | 0.6247          | 0.7333   | 0.5378    | 0.7333 | 0.6205   |
| 0.5149        | 5.0   | 40   | 0.5308          | 0.7792   | 0.7885    | 0.7792 | 0.7281   |
| 0.5149        | 6.0   | 48   | 0.5445          | 0.7833   | 0.8155    | 0.7833 | 0.7274   |
| 0.4879        | 7.0   | 56   | 0.5620          | 0.7667   | 0.7709    | 0.7667 | 0.7064   |
| 0.453         | 8.0   | 64   | 0.5384          | 0.7708   | 0.7695    | 0.7708 | 0.7178   |
| 0.4249        | 9.0   | 72   | 0.5377          | 0.7542   | 0.7276    | 0.7542 | 0.7054   |
| 0.4001        | 10.0  | 80   | 0.5417          | 0.7667   | 0.7575    | 0.7667 | 0.7147   |


### Framework versions

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