ZZUTK/Face-Aging-CAAE

Test Problem

akakakakakaa opened this issue · 2 comments

akakakakakaa commented

Sorry for about my question but i don't know how to test this. When i was test dataset using only UTKFace, every model looks like similar. is it need more image like FGNET, MORPH, CACD?

input:
input

test_as_male:
test_as_male

test_as_female:
test_as_female

hai046 commented

I have the same problem，but i found use difference [race] in a dataset that is ok

The info at http://aicip.eecs.utk.edu/wiki/UTKFace

Labels
The labels of each face image is embedded in the file name, formated like [age]_[gender]_[race]_[date&time].jpg
[age] is an integer from 0 to 116, indicating the age
[gender] is either 0 (male) or 1 (female)
[race] is an integer from 0 to 4, denoting White, Black, Asian, Indian, and Others (like Hispanic, Latino, Middle Eastern).
[date&time] is in the format of yyyymmddHHMMSSFFF, showing the date and time an image was collected to UTKFace

Saytoanyone commented

When I use the test, the same problem, how to solve this，Hope for you help ， @hai046 thanks