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-Kuzushiji
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: 0.9718236819360415
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: 0.1356
- Accuracy: 0.9718
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 |
|---|---|---|---|---|
| 0.5595 | 1.0 | 406 | 0.1957 | 0.9628 |
| 0.6314 | 2.0 | 813 | 0.1814 | 0.9654 |
| 0.5433 | 3.0 | 1220 | 0.1723 | 0.9658 |
| 0.488 | 4.0 | 1627 | 0.1588 | 0.9677 |
| 0.5789 | 5.0 | 2033 | 0.1572 | 0.9689 |
| 0.4526 | 6.0 | 2440 | 0.1496 | 0.9701 |
| 0.4538 | 7.0 | 2847 | 0.1447 | 0.9708 |
| 0.447 | 8.0 | 3254 | 0.1414 | 0.9710 |
| 0.3809 | 9.0 | 3660 | 0.1385 | 0.9715 |
| 0.4515 | 9.98 | 4060 | 0.1356 | 0.9718 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0