Retuns tyre quality given a tyre image with about 99.3% accuracy.

See https://www.kaggle.com/code/dima806/tyre-quality-image-detection-vit for more details.

Classification report:

              precision    recall  f1-score   support

   defective     1.0000    0.9854    0.9926       411
        good     0.9856    1.0000    0.9928       412

    accuracy                         0.9927       823
   macro avg     0.9928    0.9927    0.9927       823
weighted avg     0.9928    0.9927    0.9927       823

Downloads last month: 5

Safetensors

Model size

85.8M params

Tensor type

F32

Model tree for dima806/tyre_quality_image_detection

Base model

google/vit-base-patch16-224-in21k

Finetuned

(2526)

this model