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 0.7299 0.8989 0.8056 445
02 0.4438 0.6652 0.5324 445
03 0.7118 0.2719 0.3935 445
04 0.8765 0.1596 0.2700 445
05 0.5623 0.9730 0.7128 445
06-07 0.6980 0.6180 0.6555 445
08-09 0.6569 0.8090 0.7251 445
10-12 0.7109 0.6742 0.6920 445
13-15 0.7874 0.7573 0.7721 445
16-20 0.6786 0.7275 0.7022 444
21-25 0.6824 0.5843 0.6295 445
26-30 0.4281 0.6090 0.5028 445
31-35 0.5309 0.2315 0.3224 445
36-40 0.4583 0.3461 0.3944 445
41-45 0.5253 0.7236 0.6087 445
46-50 0.4965 0.6315 0.5559 445
51-55 0.4936 0.5180 0.5055 444
56-60 0.4984 0.3416 0.4053 445
61-65 0.7132 0.2067 0.3206 445
66-70 0.4953 0.8266 0.6194 444
71-80 0.8048 0.7523 0.7776 444
81-90 0.8725 0.9843 0.9250 445
90+ 0.9978 1.0000 0.9989 445
accuracy 0.6221 10231
macro avg 0.6458 0.6222 0.6012 10231
weighted avg 0.6458 0.6221 0.6012 10231