metadata
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.
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