ueh-vdr-vit
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on UEH Visual Dish Recognition (UEH-VDR) dataset. It achieves the following results on the evaluation set:
- Loss: 0.4856
- Accuracy: 0.9296
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 197 | 0.8112 | 0.8943 |
| No log | 2.0 | 394 | 0.5428 | 0.9220 |
| 0.9 | 3.0 | 591 | 0.4856 | 0.9296 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1