|
--- |
|
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: 0.5917085427135679 |
|
--- |
|
|
|
<!-- 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 was trained from scratch on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0104 |
|
- Accuracy: 0.5917 |
|
|
|
## 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: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 512 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.0339 | 1.0 | 28 | 1.0541 | 0.5641 | |
|
| 1.0193 | 2.0 | 56 | 1.0464 | 0.5622 | |
|
| 1.0348 | 3.0 | 84 | 1.0331 | 0.5691 | |
|
| 1.0072 | 4.0 | 112 | 1.0254 | 0.5848 | |
|
| 0.9892 | 5.0 | 140 | 1.0121 | 0.5754 | |
|
| 0.9379 | 6.0 | 168 | 1.0175 | 0.5810 | |
|
| 0.9123 | 7.0 | 196 | 1.0120 | 0.5867 | |
|
| 0.8865 | 8.0 | 224 | 1.0104 | 0.5917 | |
|
| 0.8668 | 9.0 | 252 | 1.0236 | 0.5873 | |
|
| 0.8189 | 10.0 | 280 | 1.0360 | 0.5829 | |
|
| 0.7933 | 11.0 | 308 | 1.0395 | 0.5835 | |
|
| 0.7765 | 12.0 | 336 | 1.0594 | 0.5729 | |
|
| 0.7538 | 13.0 | 364 | 1.0552 | 0.5879 | |
|
| 0.7146 | 14.0 | 392 | 1.0620 | 0.5829 | |
|
| 0.6885 | 15.0 | 420 | 1.0783 | 0.5842 | |
|
| 0.6556 | 16.0 | 448 | 1.1010 | 0.5817 | |
|
| 0.6453 | 17.0 | 476 | 1.1131 | 0.5735 | |
|
| 0.6175 | 18.0 | 504 | 1.1074 | 0.5892 | |
|
| 0.5993 | 19.0 | 532 | 1.1328 | 0.5741 | |
|
| 0.5683 | 20.0 | 560 | 1.1423 | 0.5791 | |
|
| 0.5524 | 21.0 | 588 | 1.1517 | 0.5873 | |
|
| 0.5151 | 22.0 | 616 | 1.1673 | 0.5766 | |
|
| 0.5096 | 23.0 | 644 | 1.1760 | 0.5798 | |
|
| 0.4937 | 24.0 | 672 | 1.1931 | 0.5817 | |
|
| 0.487 | 25.0 | 700 | 1.2084 | 0.5735 | |
|
| 0.4597 | 26.0 | 728 | 1.2270 | 0.5716 | |
|
| 0.4482 | 27.0 | 756 | 1.2389 | 0.5829 | |
|
| 0.4183 | 28.0 | 784 | 1.2430 | 0.5773 | |
|
| 0.4228 | 29.0 | 812 | 1.2637 | 0.5741 | |
|
| 0.4116 | 30.0 | 840 | 1.2688 | 0.5779 | |
|
| 0.3942 | 31.0 | 868 | 1.2986 | 0.5879 | |
|
| 0.3815 | 32.0 | 896 | 1.2911 | 0.5766 | |
|
| 0.3828 | 33.0 | 924 | 1.3113 | 0.5773 | |
|
| 0.3791 | 34.0 | 952 | 1.3317 | 0.5766 | |
|
| 0.3701 | 35.0 | 980 | 1.3384 | 0.5773 | |
|
| 0.3566 | 36.0 | 1008 | 1.3406 | 0.5754 | |
|
| 0.3551 | 37.0 | 1036 | 1.3410 | 0.5766 | |
|
| 0.3487 | 38.0 | 1064 | 1.3364 | 0.5867 | |
|
| 0.3463 | 39.0 | 1092 | 1.3496 | 0.5810 | |
|
| 0.3242 | 40.0 | 1120 | 1.3640 | 0.5747 | |
|
| 0.3308 | 41.0 | 1148 | 1.3627 | 0.5716 | |
|
| 0.3255 | 42.0 | 1176 | 1.3795 | 0.5804 | |
|
| 0.3295 | 43.0 | 1204 | 1.3747 | 0.5798 | |
|
| 0.3147 | 44.0 | 1232 | 1.3747 | 0.5861 | |
|
| 0.3125 | 45.0 | 1260 | 1.3839 | 0.5817 | |
|
| 0.3276 | 46.0 | 1288 | 1.3806 | 0.5842 | |
|
| 0.2989 | 47.0 | 1316 | 1.3906 | 0.5886 | |
|
| 0.2941 | 48.0 | 1344 | 1.3876 | 0.5867 | |
|
| 0.3131 | 49.0 | 1372 | 1.3896 | 0.5823 | |
|
| 0.2975 | 50.0 | 1400 | 1.3906 | 0.5835 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|