README.md

metadata

license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
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: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9546181527389045

swin-tiny-patch4-window7-224-finetuned-eurosat

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.1631
• Accuracy: 0.9546

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4463	1.0	51	0.3232	0.9166
0.2061	2.0	102	0.1659	0.9398
0.1795	3.0	153	0.2043	0.9192
0.1356	4.0	204	0.1204	0.9542
0.1193	5.0	255	0.1357	0.9454
0.1054	6.0	306	0.1197	0.9516
0.0974	7.0	357	0.1081	0.9586
0.092	8.0	408	0.1220	0.9532
0.0601	9.0	459	0.1587	0.9466
0.0639	10.0	510	0.1676	0.9440
0.072	11.0	561	0.1058	0.9618
0.0606	12.0	612	0.1061	0.9634
0.0572	13.0	663	0.1375	0.9552
0.0563	14.0	714	0.1377	0.9548
0.0413	15.0	765	0.1823	0.9470
0.0361	16.0	816	0.0992	0.9674
0.0471	17.0	867	0.1508	0.9550
0.04	18.0	918	0.1700	0.9506
0.0417	19.0	969	0.1760	0.9454
0.0238	20.0	1020	0.1311	0.9600
0.0319	21.0	1071	0.1502	0.9562
0.0328	22.0	1122	0.1843	0.9484
0.0363	23.0	1173	0.1473	0.9558
0.0385	24.0	1224	0.1625	0.9516
0.0198	25.0	1275	0.1749	0.9490
0.0349	26.0	1326	0.1586	0.9528
0.0337	27.0	1377	0.1343	0.9614
0.0261	28.0	1428	0.1624	0.9542
0.0253	29.0	1479	0.1727	0.9532
0.0271	30.0	1530	0.1631	0.9546

Framework versions

• Transformers 4.37.2
• Pytorch 1.13.1
• Datasets 2.16.1
• Tokenizers 0.15.1