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: 0.9365918097754293
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: 0.2033
- Accuracy: 0.9366
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 |
|---|---|---|---|---|
| 0.3125 | 0.9684 | 23 | 0.3341 | 0.8732 |
| 0.2977 | 1.9789 | 47 | 0.2943 | 0.9062 |
| 0.2677 | 2.9895 | 71 | 0.2374 | 0.9168 |
| 0.2483 | 4.0 | 95 | 0.2230 | 0.9207 |
| 0.2331 | 4.9684 | 118 | 0.2198 | 0.9234 |
| 0.2315 | 5.9789 | 142 | 0.2150 | 0.9181 |
| 0.2249 | 6.9895 | 166 | 0.2177 | 0.9234 |
| 0.1683 | 8.0 | 190 | 0.2068 | 0.9326 |
| 0.1725 | 8.9684 | 213 | 0.2040 | 0.9366 |
| 0.1789 | 9.6842 | 230 | 0.2033 | 0.9366 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1