search

Kartik-3004 / facexformer

Official implementation of FaceXFormer: A Unified Transformer for Facial Analysis
https://kartik-3004.github.io/facexformer_web/
MIT License
170 stars 17 forks source link

Can you share age/gender/race mapping #5

Closed Podidiving closed 3 months ago

Podidiving commented 3 months ago

:wave:

It'd be super nice if you can share a mapping dictionary from predictions to actual data. For example age_gender_race task outputs 1 for the race but I have no idea what it means

Thx in advance

Kartik-3004 commented 3 months ago

Hi, We shared the mapping in the Appendix of the paper. I am reiterating it here for your convenience.

age: {
    "0": 0-9,
    "1": 10-19,
    "2": 20-29,
    "3": 30-39,
    "4": 40-49,
    "5": 50-59,
    "6": 60-69,
    "7": over 70
}

gender: {
    "0": Male,
    "1": Female
}

race: {
    "0": White,
    "1": Black,
    "2": Indian,
    "3": Asian,
    "4": Others
}