---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
  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: 0.7302889760970389
---

<!-- 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-finetuned-eurosat

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: 0.5574
- Accuracy: 0.7303

## 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: 256
- eval_batch_size: 256
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6271        | 0.99  | 98   | 0.6035          | 0.6926   |
| 0.6156        | 1.99  | 197  | 0.5844          | 0.7006   |
| 0.6148        | 3.0   | 296  | 0.5758          | 0.7104   |
| 0.6055        | 4.0   | 395  | 0.5853          | 0.7015   |
| 0.5938        | 4.99  | 493  | 0.5858          | 0.7104   |
| 0.5878        | 5.99  | 592  | 0.5630          | 0.7210   |
| 0.5873        | 7.0   | 691  | 0.5620          | 0.7236   |
| 0.5947        | 8.0   | 790  | 0.5670          | 0.7196   |
| 0.5866        | 8.99  | 888  | 0.5592          | 0.7265   |
| 0.5807        | 9.99  | 987  | 0.5574          | 0.7254   |
| 0.5764        | 11.0  | 1086 | 0.5655          | 0.7245   |
| 0.5729        | 12.0  | 1185 | 0.5611          | 0.7237   |
| 0.577         | 12.99 | 1283 | 0.5702          | 0.7189   |
| 0.5702        | 13.99 | 1382 | 0.5588          | 0.7259   |
| 0.5717        | 15.0  | 1481 | 0.5565          | 0.7244   |
| 0.5646        | 16.0  | 1580 | 0.5536          | 0.7303   |
| 0.5591        | 16.99 | 1678 | 0.5525          | 0.7345   |
| 0.5586        | 17.99 | 1777 | 0.5565          | 0.7286   |
| 0.5668        | 19.0  | 1876 | 0.5520          | 0.7304   |
| 0.5617        | 20.0  | 1975 | 0.5557          | 0.7289   |
| 0.5546        | 20.99 | 2073 | 0.5561          | 0.7325   |
| 0.5579        | 21.99 | 2172 | 0.5537          | 0.7314   |
| 0.5604        | 23.0  | 2271 | 0.5545          | 0.7290   |
| 0.5563        | 24.0  | 2370 | 0.5591          | 0.7288   |
| 0.5634        | 24.99 | 2468 | 0.5546          | 0.7307   |
| 0.5563        | 25.99 | 2567 | 0.5557          | 0.7303   |
| 0.5563        | 27.0  | 2666 | 0.5571          | 0.7276   |
| 0.5544        | 28.0  | 2765 | 0.5551          | 0.7298   |
| 0.5491        | 28.99 | 2863 | 0.5596          | 0.7282   |
| 0.5461        | 29.77 | 2940 | 0.5574          | 0.7303   |


### Framework versions

- Transformers 4.29.1
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3