Instructions to use dima806/coffee_bean_roast_image_detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dima806/coffee_bean_roast_image_detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dima806/coffee_bean_roast_image_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/coffee_bean_roast_image_detection") model = AutoModelForImageClassification.from_pretrained("dima806/coffee_bean_roast_image_detection") - Notebooks
- Google Colab
- Kaggle
Returns coffee roast type given bean image.
See https://www.kaggle.com/code/dima806/roasted-coffee-bean-image-detection-vit for more details.
Classification report:
precision recall f1-score support
Dark 1.0000 1.0000 1.0000 160
Light 1.0000 1.0000 1.0000 160
Green 1.0000 1.0000 1.0000 160
Medium 1.0000 1.0000 1.0000 160
accuracy 1.0000 640
macro avg 1.0000 1.0000 1.0000 640
weighted avg 1.0000 1.0000 1.0000 640
- Downloads last month
- 6
Model tree for dima806/coffee_bean_roast_image_detection
Base model
google/vit-base-patch16-224-in21k