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 0.7948 0.7948 0.7948 1798
disgust 0.9923 0.9983 0.9953 1798
angry 0.8390 0.8576 0.8482 1798
neutral 0.8141 0.8381 0.8259 1797
fear 0.8134 0.7953 0.8043 1798
surprise 0.9421 0.9227 0.9323 1798
happy 0.9272 0.9132 0.9201 1798
accuracy 0.8743 12585
macro avg 0.8747 0.8743 0.8744 12585
weighted avg 0.8747 0.8743 0.8744 12585