metadata
license: mit
base_model: google/vit-large-patch16-224-in21k
datasets:
- ahmed-ai/skin-lesions-classification-dataset
metrics:
- accuracy
pipeline_tag: image-classification
ahmed-ai/slc-2
Skin Lesions Classifier
Important Warning
This model is currently undergoing development and, as such, cannot be considered reliable for real-world applications at this time.
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.08
- Validation Loss: 0.27
- Train Accuracy: 0.92
- Number of Epochs: 8
Training results
| Train Loss | Validation Loss | Accuracy | Epoch |
|---|---|---|---|
| 0.628000 | 0.593520 | 0.785519 | 0 |
| 0.437800 | 0.481456 | 0.827322 | 1 |
| 0.398300 | 0.418967 | 0.853825 | 2 |
| 0.224900 | 0.363181 | 0.874590 | 3 |
| 0.192100 | 0.372062 | 0.886339 | 4 |
| 0.167800 | 0.321268 | 0.898361 | 5 |
| 0.083000 | 0.283219 | 0.914754 | 6 |
| 0.084300 | 0.273708 | 0.921585 | 7 |