|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: SWIN-AI-Image-Detector |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# SWIN-AI-Image-Detector |
|
|
|
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on CIFAKE dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0342 |
|
- Accuracy: 0.9874 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.2432 | 1.0 | 703 | 0.1859 | 0.9267 | |
|
| 0.1665 | 2.0 | 1406 | 0.1229 | 0.9514 | |
|
| 0.1427 | 3.0 | 2109 | 0.0604 | 0.9761 | |
|
| 0.143 | 4.0 | 2813 | 0.0807 | 0.97 | |
|
| 0.1008 | 5.0 | 3516 | 0.0444 | 0.9824 | |
|
| 0.1189 | 6.0 | 4219 | 0.0635 | 0.977 | |
|
| 0.0936 | 7.0 | 4922 | 0.0535 | 0.9789 | |
|
| 0.1201 | 8.0 | 5626 | 0.0376 | 0.9854 | |
|
| 0.076 | 9.0 | 6329 | 0.0342 | 0.9874 | |
|
| 0.0887 | 10.0 | 7030 | 0.0413 | 0.9844 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.13.3 |
|
|
