---
license: apache-2.0
metrics:
- accuracy
- f1
base_model:
- google/vit-base-patch16-224-in21k
pipeline_tag: image-classification
library_name: transformers
---
Returns a hand gesture type for smart TV given an image.

See https://www.kaggle.com/code/dima806/smart-tv-hand-gestures-image-detection-vit for details.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6449300e3adf50d864095b90/YQKXqTq3L3TJEFGuOt-Ko.png)

```
Classification report:

              precision    recall  f1-score   support

        Down     1.0000    1.0000    1.0000      1350
  Left Swipe     1.0000    1.0000    1.0000      1350
 Right Swipe     1.0000    1.0000    1.0000      1350
        Stop     0.9912    1.0000    0.9956      1350
Stop Gesture     1.0000    1.0000    1.0000      1350
       Swipe     1.0000    0.9948    0.9974      1350
 Thumbs Down     1.0000    1.0000    1.0000      1350
   Thumbs Up     1.0000    1.0000    1.0000      1350
          Up     1.0000    0.9963    0.9981      1350

    accuracy                         0.9990     12150
   macro avg     0.9990    0.9990    0.9990     12150
weighted avg     0.9990    0.9990    0.9990     12150
```