Edit model card

Returns anime character name given an image with about 98% accuracy.

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

Classification report:

                    precision    recall  f1-score   support

            Killua     1.0000    1.0000    1.0000        57
    Sakata Gintoki     1.0000    0.9655    0.9825        58
       Eren Yeager     0.9649    0.9649    0.9649        57
            Ichigo     0.9825    0.9825    0.9825        57
Lelouch Lamperouge     1.0000    1.0000    1.0000        58
            Naruto     1.0000    1.0000    1.0000        58
              Goku     0.9655    0.9825    0.9739        57
            Vegeta     0.9649    0.9649    0.9649        57
              Zoro     0.9355    1.0000    0.9667        58
    Natsu Dragneel     1.0000    1.0000    1.0000        58
               Gon     1.0000    0.9310    0.9643        58
            Sasuke     0.9333    0.9655    0.9492        58
      Elric Edward     1.0000    0.9825    0.9912        57
      Light Yagami     0.9828    0.9828    0.9828        58
             Luffy     1.0000    1.0000    1.0000        58

          accuracy                         0.9815       864
         macro avg     0.9820    0.9815    0.9815       864
      weighted avg     0.9820    0.9815    0.9815       864
Downloads last month
20
Safetensors
Model size
85.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for dima806/top_15_anime_characters_image_detection

Finetuned
(1681)
this model