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: 0.9826023921710765
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: 0.0492
- Accuracy: 0.9826
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 |
|---|---|---|---|---|
| 0.2851 | 1.0 | 194 | 0.1485 | 0.9507 |
| 0.2143 | 2.0 | 388 | 0.0938 | 0.9677 |
| 0.152 | 3.0 | 582 | 0.0833 | 0.9710 |
| 0.1469 | 4.0 | 776 | 0.0692 | 0.9754 |
| 0.1663 | 5.0 | 970 | 0.0611 | 0.9797 |
| 0.1135 | 6.0 | 1164 | 0.0649 | 0.9783 |
| 0.1155 | 7.0 | 1358 | 0.0525 | 0.9859 |
| 0.1356 | 8.0 | 1552 | 0.0496 | 0.9851 |
| 0.0895 | 9.0 | 1746 | 0.0497 | 0.9830 |
| 0.1136 | 10.0 | 1940 | 0.0492 | 0.9826 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0