ahmed-ai/skin-lesions-classification-dataset
Viewer • Updated • 36.7k • 485 • 6
How to use ahmed-ai/SkinLesionsTransformer with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-classification", model="ahmed-ai/SkinLesionsTransformer")
pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png") # Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ahmed-ai/SkinLesionsTransformer")
model = AutoModelForImageClassification.from_pretrained("ahmed-ai/SkinLesionsTransformer")This model is currently undergoing development; as such, it should not be used for clinical diagnosis or relied upon for medical decision-making at this stage.
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 | 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 |
Base model
google/vit-large-patch16-224-in21k