metadata
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: 0.7272727272727273
swin-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6322
- Accuracy: 0.7273
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.97 | 9 | 1.0291 | 0.4621 |
| 1.0954 | 1.95 | 18 | 0.8322 | 0.6136 |
| 0.8859 | 2.92 | 27 | 0.7934 | 0.6364 |
| 0.7328 | 4.0 | 37 | 0.7151 | 0.6742 |
| 0.6285 | 4.97 | 46 | 0.7614 | 0.6061 |
| 0.5817 | 5.95 | 55 | 0.7581 | 0.6439 |
| 0.5145 | 6.92 | 64 | 0.6608 | 0.7121 |
| 0.4899 | 8.0 | 74 | 0.6711 | 0.6894 |
| 0.4372 | 8.97 | 83 | 0.6322 | 0.7273 |
| 0.4452 | 9.73 | 90 | 0.6399 | 0.7121 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1