metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: ZachBeesley/food-classifier
results: []
datasets:
- food101
ZachBeesley/food-classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3376
- Validation Loss: 0.3213
- Train Accuracy: 0.921
- Epoch: 4
Model description
Image-classification model that can identify foods based on pictures
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 20000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 2.6919 | 1.5372 | 0.848 | 0 |
| 1.1404 | 0.8059 | 0.881 | 1 |
| 0.6375 | 0.6164 | 0.865 | 2 |
| 0.4379 | 0.3822 | 0.915 | 3 |
| 0.3376 | 0.3213 | 0.921 | 4 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3