|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224 |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: 5class224_b_p_c_u_n |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# 5class224_b_p_c_u_n |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.0113 |
|
- Train Accuracy: 0.9459 |
|
- Train Top-3-accuracy: 0.9925 |
|
- Validation Loss: 0.1326 |
|
- Validation Accuracy: 0.9504 |
|
- Validation Top-3-accuracy: 0.9932 |
|
- Epoch: 4 |
|
|
|
## 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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 585, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch | |
|
|:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:| |
|
| 0.6186 | 0.6303 | 0.9043 | 0.2809 | 0.8026 | 0.9654 | 0 | |
|
| 0.1012 | 0.8565 | 0.9767 | 0.1746 | 0.8901 | 0.9832 | 1 | |
|
| 0.0296 | 0.9093 | 0.9865 | 0.1447 | 0.9234 | 0.9888 | 2 | |
|
| 0.0137 | 0.9329 | 0.9904 | 0.1352 | 0.9404 | 0.9915 | 3 | |
|
| 0.0113 | 0.9459 | 0.9925 | 0.1326 | 0.9504 | 0.9932 | 4 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
