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: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7722370456736698

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: 0.4877
Accuracy: 0.7722

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
0.5611	1.0	392	0.5374	0.7341
0.5299	2.0	784	0.5180	0.7486
0.5289	3.0	1176	0.5049	0.7568
0.5208	4.0	1568	0.4980	0.7622
0.5051	5.0	1960	0.4996	0.7621
0.5035	6.0	2352	0.4890	0.7672
0.5028	7.0	2744	0.4880	0.7685
0.5129	8.0	3136	0.4966	0.7644
0.5014	9.0	3528	0.4895	0.7669
0.4923	10.0	3920	0.4880	0.7702
0.496	11.0	4312	0.4932	0.7673
0.4978	12.0	4704	0.4868	0.7718
0.4993	13.0	5096	0.4827	0.7723
0.4928	14.0	5488	0.4826	0.7724
0.4883	15.0	5880	0.4826	0.7729
0.4951	16.0	6272	0.4815	0.7717
0.4955	17.0	6664	0.4879	0.7700
0.4931	18.0	7056	0.4837	0.7720
0.4803	19.0	7448	0.4841	0.7732
0.4906	20.0	7840	0.4812	0.7737
0.4718	21.0	8232	0.4880	0.7731
0.479	22.0	8624	0.4826	0.7733
0.483	23.0	9016	0.4825	0.7719
0.4748	24.0	9408	0.4828	0.7738
0.4708	25.0	9800	0.4877	0.7722
0.4746	26.0	10192	0.4856	0.7734
0.4659	27.0	10584	0.4879	0.7725
0.4732	28.0	10976	0.4864	0.7721
0.4672	29.0	11368	0.4866	0.7725
0.4677	30.0	11760	0.4877	0.7722

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3