weeds_swin_balanced
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1356
- Accuracy: 0.9667
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5298 | 1.0 | 150 | 0.3729 | 0.8633 |
| 0.4204 | 2.0 | 300 | 0.2560 | 0.8933 |
| 0.3229 | 3.0 | 450 | 0.3213 | 0.88 |
| 0.2347 | 4.0 | 600 | 0.2031 | 0.9233 |
| 0.3342 | 5.0 | 750 | 0.1912 | 0.9367 |
| 0.2106 | 6.0 | 900 | 0.1365 | 0.9467 |
| 0.1891 | 7.0 | 1050 | 0.1927 | 0.97 |
| 0.0629 | 8.0 | 1200 | 0.1726 | 0.9467 |
| 0.1169 | 9.0 | 1350 | 0.1363 | 0.9633 |
| 0.0426 | 10.0 | 1500 | 0.1356 | 0.9667 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2