Instructions to use dima806/attractive_faces_celebs_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dima806/attractive_faces_celebs_detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/attractive_faces_celebs_detection") 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("dima806/attractive_faces_celebs_detection") model = AutoModelForImageClassification.from_pretrained("dima806/attractive_faces_celebs_detection") - Notebooks
- Google Colab
- Kaggle
Returns person celebrity-style attractiveness (0 to 1) based on facial image with about 83% accuracy.
See https://www.kaggle.com/code/dima806/attractive-faces-celebs-detection-vit for more details.
Classification report:
precision recall f1-score support
attractive 0.8297 0.8502 0.8398 5192
not attractive 0.8464 0.8255 0.8358 5192
accuracy 0.8378 10384
macro avg 0.8380 0.8378 0.8378 10384
weighted avg 0.8380 0.8378 0.8378 10384
- Downloads last month
- 816
Model tree for dima806/attractive_faces_celebs_detection
Base model
google/vit-base-patch16-224-in21k