Returns horse breed given an image with about 91% accuracy.

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

Classification report:

                      precision    recall  f1-score   support

            Friesian     0.8889    1.0000    0.9412        24
             Arabian     0.8571    0.9600    0.9057        25
           Percheron     1.0000    0.6400    0.7805        25
       Orlov Trotter     0.7931    0.9200    0.8519        25
          Akhal-Teke     1.0000    0.9200    0.9583        25
Vladimir Heavy Draft     0.9200    0.9583    0.9388        24
           Appaloosa     1.0000    1.0000    1.0000        25

            accuracy                         0.9133       173
           macro avg     0.9227    0.9140    0.9109       173
        weighted avg     0.9229    0.9133    0.9106       173
Downloads last month
6
Safetensors
Model size
85.8M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for dima806/horse_breeds_image_detection

Finetuned
(2094)
this model