dima806's picture
Update README.md
efdaa94 verified
|
raw
history blame
769 Bytes
metadata
license: apache-2.0
metrics:
  - accuracy
  - f1
base_model:
  - google/vit-base-patch16-224-in21k

Returns with about 99.2% accuracy whether the face belongs to man or woman based on face image.

See https://www.kaggle.com/code/dima806/man-woman-face-image-detection-vit for more details.

image/png

Classification report:

              precision    recall  f1-score   support

         man     0.9919    0.9921    0.9920      7071
       woman     0.9921    0.9919    0.9920      7072

    accuracy                         0.9920     14143
   macro avg     0.9920    0.9920    0.9920     14143
weighted avg     0.9920    0.9920    0.9920     14143