metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
results: []
swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the ASL_Isolated_Swin_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0558
- Accuracy: 0.9846
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6758 | 1.09 | 100 | 1.3206 | 0.5769 |
| 1.0717 | 2.17 | 200 | 0.6482 | 0.8154 |
| 0.627 | 3.26 | 300 | 0.4486 | 0.8654 |
| 0.5397 | 4.35 | 400 | 0.2978 | 0.8923 |
| 0.537 | 5.43 | 500 | 0.1513 | 0.9423 |
| 0.3766 | 6.52 | 600 | 0.4737 | 0.8846 |
| 0.3994 | 7.61 | 700 | 0.3060 | 0.9115 |
| 0.2139 | 8.7 | 800 | 0.1345 | 0.9577 |
| 0.2995 | 9.78 | 900 | 0.1558 | 0.95 |
| 0.2835 | 10.87 | 1000 | 0.0943 | 0.9731 |
| 0.3089 | 11.96 | 1100 | 0.0913 | 0.9577 |
| 0.3632 | 13.04 | 1200 | 0.0888 | 0.9692 |
| 0.327 | 14.13 | 1300 | 0.1038 | 0.9808 |
| 0.313 | 15.22 | 1400 | 0.0976 | 0.9731 |
| 0.1752 | 16.3 | 1500 | 0.0504 | 0.9808 |
| 0.2397 | 17.39 | 1600 | 0.0612 | 0.9808 |
| 0.1348 | 18.48 | 1700 | 0.0558 | 0.9846 |
| 0.2842 | 19.57 | 1800 | 0.0504 | 0.9769 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1