# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("dima806/lemon_quality_image_detection")
model = AutoModelForImageClassification.from_pretrained("dima806/lemon_quality_image_detection")Quick Links
Returns lemon quality given an image.
See https://www.kaggle.com/code/dima806/lemon-quality-image-detection-vit for more details.
Classification report:
precision recall f1-score support
good_quality 1.0000 1.0000 1.0000 450
empty_background 1.0000 1.0000 1.0000 450
bad_quality 1.0000 1.0000 1.0000 450
accuracy 1.0000 1350
macro avg 1.0000 1.0000 1.0000 1350
weighted avg 1.0000 1.0000 1.0000 1350
- Downloads last month
- 9
Model tree for dima806/lemon_quality_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/lemon_quality_image_detection") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")