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: 0.9918293236495688
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: 0.0520
- Accuracy: 0.9918
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: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- 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 |
|---|---|---|---|---|
| 0.0765 | 1.0 | 428 | 0.1101 | 0.9773 |
| 0.1014 | 2.0 | 857 | 0.0692 | 0.9825 |
| 0.0425 | 3.0 | 1285 | 0.0766 | 0.9814 |
| 0.1229 | 4.0 | 1714 | 0.0515 | 0.9873 |
| 0.074 | 5.0 | 2142 | 0.0497 | 0.9891 |
| 0.0133 | 6.0 | 2571 | 0.0537 | 0.9882 |
| 0.0753 | 7.0 | 2999 | 0.0490 | 0.9911 |
| 0.0263 | 8.0 | 3428 | 0.0520 | 0.9918 |
| 0.0423 | 9.0 | 3856 | 0.0513 | 0.9914 |
| 0.0266 | 9.99 | 4280 | 0.0485 | 0.9916 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu117
- Datasets 2.16.0
- Tokenizers 0.13.3