# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("dima806/skin_types_image_detection")
model = AutoModelForImageClassification.from_pretrained("dima806/skin_types_image_detection")Quick Links
Detects the skin type (dry, normal, oily) based on facial image.
See https://www.kaggle.com/code/dima806/skin-types-image-detection-vit for details.
Classification report:
precision recall f1-score support
dry 0.6829 0.6346 0.6578 509
normal 0.6414 0.6314 0.6364 510
oily 0.6390 0.6941 0.6654 510
accuracy 0.6534 1529
macro avg 0.6544 0.6534 0.6532 1529
weighted avg 0.6544 0.6534 0.6532 1529
- Downloads last month
- 624
Model tree for dima806/skin_types_image_detection
Base model
google/vit-base-patch16-224-in21k
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/skin_types_image_detection") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")