|
--- |
|
license: apache-2.0 |
|
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: images |
|
split: train |
|
args: images |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9609375 |
|
--- |
|
|
|
<!-- 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: 0.1211 |
|
- Accuracy: 0.9609 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 40 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 4 | 0.4862 | 0.8516 | |
|
| No log | 2.0 | 8 | 0.4103 | 0.8828 | |
|
| 0.4518 | 3.0 | 12 | 0.3210 | 0.8984 | |
|
| 0.4518 | 4.0 | 16 | 0.2053 | 0.9375 | |
|
| 0.2909 | 5.0 | 20 | 0.1675 | 0.9453 | |
|
| 0.2909 | 6.0 | 24 | 0.1439 | 0.9531 | |
|
| 0.2909 | 7.0 | 28 | 0.1448 | 0.9297 | |
|
| 0.1492 | 8.0 | 32 | 0.1798 | 0.9531 | |
|
| 0.1492 | 9.0 | 36 | 0.1360 | 0.9453 | |
|
| 0.1161 | 10.0 | 40 | 0.1670 | 0.9531 | |
|
| 0.1161 | 11.0 | 44 | 0.1637 | 0.9531 | |
|
| 0.1161 | 12.0 | 48 | 0.1298 | 0.9531 | |
|
| 0.1053 | 13.0 | 52 | 0.1162 | 0.9531 | |
|
| 0.1053 | 14.0 | 56 | 0.1353 | 0.9531 | |
|
| 0.0839 | 15.0 | 60 | 0.1211 | 0.9609 | |
|
| 0.0839 | 16.0 | 64 | 0.1113 | 0.9609 | |
|
| 0.0839 | 17.0 | 68 | 0.1145 | 0.9609 | |
|
| 0.0689 | 18.0 | 72 | 0.1239 | 0.9531 | |
|
| 0.0689 | 19.0 | 76 | 0.1280 | 0.9531 | |
|
| 0.0581 | 20.0 | 80 | 0.1533 | 0.9531 | |
|
| 0.0581 | 21.0 | 84 | 0.1323 | 0.9609 | |
|
| 0.0581 | 22.0 | 88 | 0.1327 | 0.9531 | |
|
| 0.0545 | 23.0 | 92 | 0.1529 | 0.9531 | |
|
| 0.0545 | 24.0 | 96 | 0.1357 | 0.9531 | |
|
| 0.046 | 25.0 | 100 | 0.1333 | 0.9531 | |
|
| 0.046 | 26.0 | 104 | 0.1466 | 0.9531 | |
|
| 0.046 | 27.0 | 108 | 0.1300 | 0.9531 | |
|
| 0.0421 | 28.0 | 112 | 0.1077 | 0.9609 | |
|
| 0.0421 | 29.0 | 116 | 0.0985 | 0.9609 | |
|
| 0.0371 | 30.0 | 120 | 0.1186 | 0.9531 | |
|
| 0.0371 | 31.0 | 124 | 0.1123 | 0.9531 | |
|
| 0.0371 | 32.0 | 128 | 0.1144 | 0.9531 | |
|
| 0.0348 | 33.0 | 132 | 0.1276 | 0.9531 | |
|
| 0.0348 | 34.0 | 136 | 0.1488 | 0.9531 | |
|
| 0.0211 | 35.0 | 140 | 0.1560 | 0.9531 | |
|
| 0.0211 | 36.0 | 144 | 0.1477 | 0.9531 | |
|
| 0.0211 | 37.0 | 148 | 0.1488 | 0.9531 | |
|
| 0.0274 | 38.0 | 152 | 0.1467 | 0.9531 | |
|
| 0.0274 | 39.0 | 156 | 0.1401 | 0.9531 | |
|
| 0.0259 | 40.0 | 160 | 0.1379 | 0.9531 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
