metadata
license: other
base_model: nvidia/segformer-b0-finetuned-ade-512-512
tags:
- generated_from_keras_callback
model-index:
- name: Omar280X/personal_license_card_segmentation_x2
results: []
Omar280X/personal_license_card_segmentation_x2
This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0152
- Validation Loss: 0.0132
- Epoch: 9
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:
- optimizer: {'name': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.1232 | 0.0261 | 0 |
| 0.0387 | 0.0190 | 1 |
| 0.0291 | 0.0162 | 2 |
| 0.0218 | 0.0149 | 3 |
| 0.0188 | 0.0142 | 4 |
| 0.0227 | 0.0149 | 5 |
| 0.0195 | 0.0138 | 6 |
| 0.0160 | 0.0133 | 7 |
| 0.0169 | 0.0131 | 8 |
| 0.0152 | 0.0132 | 9 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.10.0
- Tokenizers 0.15.2