|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: microsoft/swin-small-patch4-window7-224 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- imagefolder |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: swin-small-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: 0.8471810089020771 |
|
|
--- |
|
|
|
|
|
<!-- 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-small-patch4-window7-224-finetuned-eurosat |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/swin-small-patch4-window7-224](https://huggingface.co/microsoft/swin-small-patch4-window7-224) on the imagefolder dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5541 |
|
|
- Accuracy: 0.8472 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 128 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 30 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
|
| 2.8572 | 1.0 | 48 | 2.6775 | 0.2226 | |
|
|
| 1.6357 | 2.0 | 96 | 1.3411 | 0.5519 | |
|
|
| 1.076 | 3.0 | 144 | 0.9200 | 0.6973 | |
|
|
| 1.0091 | 4.0 | 192 | 0.8266 | 0.7062 | |
|
|
| 0.777 | 5.0 | 240 | 0.6904 | 0.7685 | |
|
|
| 0.6453 | 6.0 | 288 | 0.6149 | 0.7864 | |
|
|
| 0.6124 | 7.0 | 336 | 0.6207 | 0.7923 | |
|
|
| 0.5204 | 8.0 | 384 | 0.6130 | 0.7908 | |
|
|
| 0.529 | 9.0 | 432 | 0.6334 | 0.8042 | |
|
|
| 0.4394 | 10.0 | 480 | 0.5370 | 0.8249 | |
|
|
| 0.4398 | 11.0 | 528 | 0.5589 | 0.8249 | |
|
|
| 0.3996 | 12.0 | 576 | 0.5391 | 0.8501 | |
|
|
| 0.3585 | 13.0 | 624 | 0.5796 | 0.8205 | |
|
|
| 0.3276 | 14.0 | 672 | 0.5851 | 0.8338 | |
|
|
| 0.3382 | 15.0 | 720 | 0.5508 | 0.8457 | |
|
|
| 0.3212 | 16.0 | 768 | 0.5279 | 0.8605 | |
|
|
| 0.3226 | 17.0 | 816 | 0.5769 | 0.8338 | |
|
|
| 0.2836 | 18.0 | 864 | 0.5942 | 0.8294 | |
|
|
| 0.2743 | 19.0 | 912 | 0.5862 | 0.8309 | |
|
|
| 0.2637 | 20.0 | 960 | 0.5586 | 0.8234 | |
|
|
| 0.2567 | 21.0 | 1008 | 0.5335 | 0.8427 | |
|
|
| 0.2932 | 22.0 | 1056 | 0.5653 | 0.8383 | |
|
|
| 0.2532 | 23.0 | 1104 | 0.5493 | 0.8368 | |
|
|
| 0.2286 | 24.0 | 1152 | 0.5798 | 0.8383 | |
|
|
| 0.206 | 25.0 | 1200 | 0.5623 | 0.8487 | |
|
|
| 0.2288 | 26.0 | 1248 | 0.5566 | 0.8442 | |
|
|
| 0.2059 | 27.0 | 1296 | 0.5437 | 0.8457 | |
|
|
| 0.1904 | 28.0 | 1344 | 0.5500 | 0.8338 | |
|
|
| 0.2416 | 29.0 | 1392 | 0.5563 | 0.8487 | |
|
|
| 0.1967 | 29.3789 | 1410 | 0.5541 | 0.8472 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.50.0 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
