# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("dima806/surface_crack_image_detection")
model = AutoModelForImageClassification.from_pretrained("dima806/surface_crack_image_detection")Quick Links
Check whether there is a surface crack given surface image.
See https://www.kaggle.com/code/dima806/surface-crack-image-detection-vit for more details.
Classification report:
precision recall f1-score support
Positive 0.9988 0.9995 0.9991 4000
Negative 0.9995 0.9988 0.9991 4000
accuracy 0.9991 8000
macro avg 0.9991 0.9991 0.9991 8000
weighted avg 0.9991 0.9991 0.9991 8000
- Downloads last month
- 6
Model tree for dima806/surface_crack_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/surface_crack_image_detection") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")