--- 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-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: 0.9966577540106952 - name: Precision type: precision value: 0.9966586895563994 - name: Recall type: recall value: 0.9966577540106952 --- # 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: 0.0154 - Accuracy: 0.9967 - Precision: 0.9967 - Recall: 0.9967 - Confusion Matrix: [[1506, 6], [4, 1476]] ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Confusion Matrix | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:-----------------------:| | 0.0568 | 1.0 | 374 | 0.0186 | 0.9940 | 0.9940 | 0.9940 | [[1500, 12], [6, 1474]] | | 0.0516 | 2.0 | 748 | 0.0191 | 0.9960 | 0.9960 | 0.9960 | [[1504, 8], [4, 1476]] | | 0.0719 | 3.0 | 1122 | 0.0154 | 0.9967 | 0.9967 | 0.9967 | [[1506, 6], [4, 1476]] | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0