metadata
license: apache-2.0
metrics:
- accuracy
- f1
Returns age bin based on a facial image.
See https://www.kaggle.com/code/dima806/facial-age-years-detection-vit for more details.
Classification report:
precision recall f1-score support
01 0.7163 0.9079 0.8008 445
02 0.4423 0.6292 0.5195 445
03 0.6935 0.2899 0.4089 445
04 0.8133 0.1371 0.2346 445
05 0.5684 0.9798 0.7195 445
06-07 0.7367 0.6239 0.6756 444
08-09 0.6605 0.8000 0.7236 445
10-12 0.7435 0.7101 0.7264 445
13-15 0.8118 0.7753 0.7931 445
16-20 0.6673 0.7573 0.7095 445
21-25 0.6951 0.6404 0.6667 445
26-30 0.4435 0.6194 0.5169 444
31-35 0.5123 0.2342 0.3215 444
36-40 0.4799 0.3483 0.4036 445
41-45 0.5131 0.7483 0.6088 445
46-50 0.4832 0.5820 0.5280 445
51-55 0.5176 0.5281 0.5228 445
56-60 0.4545 0.3146 0.3718 445
61-65 0.6567 0.1978 0.3040 445
66-70 0.4918 0.8108 0.6122 444
71-80 0.8024 0.7483 0.7744 445
81-90 0.8792 0.9978 0.9347 445
90+ 0.9955 1.0000 0.9978 445
accuracy 0.6253 10231
macro avg 0.6426 0.6252 0.6032 10231
weighted avg 0.6426 0.6253 0.6033 10231