Gil Levi
Gil Levi
Hi @td042 , Thank you for your interest in our work. Indeed the images has to be cropped to the face region (and preferably aligned). Best, Gil
@PawelGD , the code for alignment is given here: https://talhassner.github.io/home/projects/Adience/Adience-code.html#inplanealign The details regarding detection, cropping and alignment are described in the original paper presented the dataset : Eidinger, Eran, Roee...
Hello Punit, Thank you for your interest in our work. See related [issue](https://github.com/GilLevi/AgeGenderDeepLearning/issues/10)
No, it only works on faces.
This is weird, I signed the CLA, but the PR still has the cls:missing label.
Thanks @bottledmind, hope it will get merged then.