swin-tiny-patch4-window7-224-finetuned-plant-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: 0.6592
- Accuracy: 0.7557
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8257 | 1.0 | 268 | 0.7941 | 0.6695 |
| 0.7235 | 2.0 | 537 | 0.7696 | 0.6695 |
| 0.6939 | 3.0 | 806 | 0.7428 | 0.6724 |
| 0.665 | 4.0 | 1075 | 0.6884 | 0.7328 |
| 0.6846 | 5.0 | 1343 | 0.7144 | 0.6954 |
| 0.6391 | 6.0 | 1612 | 0.6854 | 0.7155 |
| 0.6172 | 7.0 | 1881 | 0.6698 | 0.7011 |
| 0.6332 | 8.0 | 2150 | 0.6510 | 0.7126 |
| 0.5679 | 9.0 | 2418 | 0.6323 | 0.7299 |
| 0.5109 | 10.0 | 2687 | 0.6629 | 0.7098 |
| 0.5594 | 11.0 | 2956 | 0.6556 | 0.7270 |
| 0.4874 | 12.0 | 3225 | 0.6627 | 0.7155 |
| 0.4687 | 13.0 | 3493 | 0.6645 | 0.7299 |
| 0.4686 | 14.0 | 3762 | 0.6469 | 0.7213 |
| 0.4862 | 15.0 | 4031 | 0.6602 | 0.7356 |
| 0.4432 | 16.0 | 4300 | 0.6550 | 0.7270 |
| 0.4368 | 17.0 | 4568 | 0.6472 | 0.7385 |
| 0.3815 | 18.0 | 4837 | 0.6557 | 0.7557 |
| 0.3674 | 19.0 | 5106 | 0.6638 | 0.7529 |
| 0.4224 | 19.94 | 5360 | 0.6592 | 0.7557 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1