dima806's picture
Update README.md
a127b22 verified
metadata
license: apache-2.0
metrics:
  - accuracy
  - f1
base_model:
  - google/vit-base-patch16-224-in21k

Returns whether the Japanese food or beverage is in an image with about 89% accuracy.

See https://www.kaggle.com/code/dima806/food-beverages-japan-image-detection-vit for more details.

Classification report:

              precision    recall  f1-score   support

        food     0.8898    0.8879    0.8889       473
    beverage     0.8882    0.8901    0.8891       473

    accuracy                         0.8890       946
   macro avg     0.8890    0.8890    0.8890       946
weighted avg     0.8890    0.8890    0.8890       946