swin-tiny-patch4_eurosat
This model is a fine-tuned version of suredream/swin-tiny-patch4-window7-224-finetuned-eurosat on the timm/eurosat-rgb dataset. It achieves the following results on the evaluation set:
- Loss: 0.0610
- Accuracy: 0.9863
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3004 | 1.0 | 2025 | 0.1180 | 0.9678 |
| 0.539 | 2.0 | 4050 | 0.0834 | 0.9798 |
| 0.024 | 3.0 | 6075 | 0.0700 | 0.9831 |
| 0.2674 | 4.0 | 8100 | 0.0685 | 0.9833 |
| 0.2086 | 5.0 | 10125 | 0.0610 | 0.9863 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for suredream/swin-tiny-patch4_eurosat
Base model
microsoft/swin-tiny-patch4-window7-224