|
--- |
|
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 |
|
--- |
|
|
|
<!-- 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: 0.4877 |
|
- 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 |
|
|
