|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: facebook/convnext-tiny-224 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- imagefolder |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: convnext-tiny-224-driverbox |
|
|
results: |
|
|
- task: |
|
|
name: Image Classification |
|
|
type: image-classification |
|
|
dataset: |
|
|
name: imagefolder |
|
|
type: imagefolder |
|
|
config: default |
|
|
split: train |
|
|
args: default |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.9879688605803255 |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# convnext-tiny-224-driverbox |
|
|
|
|
|
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0497 |
|
|
- Accuracy: 0.9880 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 128 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 30 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
|
| 0.3349 | 0.9950 | 99 | 0.2700 | 0.9328 | |
|
|
| 0.2393 | 2.0 | 199 | 0.1932 | 0.9540 | |
|
|
| 0.1831 | 2.9950 | 298 | 0.1403 | 0.9618 | |
|
|
| 0.1397 | 4.0 | 398 | 0.1055 | 0.9689 | |
|
|
| 0.0795 | 4.9950 | 497 | 0.1030 | 0.9731 | |
|
|
| 0.0915 | 6.0 | 597 | 0.0966 | 0.9703 | |
|
|
| 0.0718 | 6.9950 | 696 | 0.0779 | 0.9745 | |
|
|
| 0.0502 | 8.0 | 796 | 0.0729 | 0.9788 | |
|
|
| 0.0314 | 8.9950 | 895 | 0.0621 | 0.9802 | |
|
|
| 0.0408 | 10.0 | 995 | 0.0758 | 0.9752 | |
|
|
| 0.0335 | 10.9950 | 1094 | 0.0598 | 0.9823 | |
|
|
| 0.0228 | 12.0 | 1194 | 0.0573 | 0.9823 | |
|
|
| 0.0229 | 12.9950 | 1293 | 0.0473 | 0.9844 | |
|
|
| 0.0119 | 14.0 | 1393 | 0.0642 | 0.9844 | |
|
|
| 0.028 | 14.9950 | 1492 | 0.0526 | 0.9851 | |
|
|
| 0.0117 | 16.0 | 1592 | 0.0594 | 0.9837 | |
|
|
| 0.0187 | 16.9950 | 1691 | 0.0497 | 0.9880 | |
|
|
| 0.0131 | 18.0 | 1791 | 0.0663 | 0.9837 | |
|
|
| 0.0132 | 18.9950 | 1890 | 0.0478 | 0.9866 | |
|
|
| 0.014 | 20.0 | 1990 | 0.0465 | 0.9880 | |
|
|
| 0.0039 | 20.9950 | 2089 | 0.0496 | 0.9851 | |
|
|
| 0.0102 | 22.0 | 2189 | 0.0468 | 0.9880 | |
|
|
| 0.0035 | 22.9950 | 2288 | 0.0581 | 0.9866 | |
|
|
| 0.0071 | 24.0 | 2388 | 0.0519 | 0.9866 | |
|
|
| 0.0032 | 24.9950 | 2487 | 0.0510 | 0.9880 | |
|
|
| 0.0049 | 26.0 | 2587 | 0.0575 | 0.9858 | |
|
|
| 0.0037 | 26.9950 | 2686 | 0.0511 | 0.9880 | |
|
|
| 0.0029 | 28.0 | 2786 | 0.0484 | 0.9880 | |
|
|
| 0.0019 | 28.9950 | 2885 | 0.0523 | 0.9866 | |
|
|
| 0.0058 | 29.8492 | 2970 | 0.0532 | 0.9866 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.40.1 |
|
|
- Pytorch 2.3.0+cu118 |
|
|
- Datasets 2.19.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
