Edit model card

Returns weather type given an image with about 96% accuracy.

See https://www.kaggle.com/code/dima806/weather-types-image-prediction-vit for more details.

Classification report:

              precision    recall  f1-score   support

         dew     0.9795    0.9897    0.9846       290
     fogsmog     0.9715    0.9414    0.9562       290
       frost     0.9674    0.9207    0.9435       290
       glaze     0.8855    0.9069    0.8961       290
        hail     0.9966    0.9966    0.9966       290
   lightning     1.0000    1.0000    1.0000       290
        rain     0.9561    0.9759    0.9659       290
     rainbow     1.0000    1.0000    1.0000       290
        rime     0.9078    0.8828    0.8951       290
   sandstorm     0.9759    0.9759    0.9759       290
        snow     0.9049    0.9517    0.9277       290

    accuracy                         0.9583      3190
   macro avg     0.9587    0.9583    0.9583      3190
weighted avg     0.9587    0.9583    0.9583      3190
Downloads last month
46
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/weather_types_image_detection

Finetuned
(1692)
this model