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-spa_saloon_classification
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: 0.9798083504449008
swin-tiny-patch4-window7-224-spa_saloon_classification
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: 0.0639
- Accuracy: 0.9798
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 |
|---|---|---|---|---|
| 0.337 | 1.0 | 205 | 0.2108 | 0.9175 |
| 0.196 | 2.0 | 411 | 0.1137 | 0.9620 |
| 0.1502 | 3.0 | 616 | 0.1030 | 0.9668 |
| 0.1476 | 4.0 | 822 | 0.0815 | 0.9736 |
| 0.1532 | 5.0 | 1027 | 0.0815 | 0.9760 |
| 0.1311 | 6.0 | 1233 | 0.0667 | 0.9805 |
| 0.1212 | 7.0 | 1438 | 0.0675 | 0.9805 |
| 0.1637 | 8.0 | 1644 | 0.0697 | 0.9798 |
| 0.116 | 9.0 | 1849 | 0.0638 | 0.9812 |
| 0.085 | 9.98 | 2050 | 0.0639 | 0.9798 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1