---
license: apache-2.0
metrics:
- accuracy
- f1
---
Returns facial emotion based on facial human image.

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

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6449300e3adf50d864095b90/LptXA-4SRuOqWf2-ZAcm-.png)

```
Classification report:

              precision    recall  f1-score   support

         sad     0.8406    0.8699    0.8550      3596
     disgust     0.9895    1.0000    0.9947      3596
       angry     0.9120    0.8996    0.9058      3596
     neutral     0.8736    0.8709    0.8723      3595
        fear     0.8851    0.8531    0.8688      3595
    surprise     0.9419    0.9516    0.9467      3596
       happy     0.9347    0.9321    0.9334      3596

    accuracy                         0.9110     25170
   macro avg     0.9111    0.9110    0.9110     25170
weighted avg     0.9111    0.9110    0.9110     25170
```