swin-tiny-patch4-window7-224-plant-doctor
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0043
- Accuracy: 0.9983
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0643 | 1.0 | 3954 | 0.0218 | 0.9933 |
| 0.0536 | 2.0 | 7908 | 0.0103 | 0.9966 |
| 0.018 | 3.0 | 11862 | 0.0043 | 0.9983 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu115
- Datasets 2.1.0
- Tokenizers 0.12.1