Face_Attention_Network icon indicating copy to clipboard operation
Face_Attention_Network copied to clipboard

About Label encoding file?

Open abcdvzz opened this issue 6 years ago • 3 comments

As above, what can label encoding file do? Take Widerface as an example, what's the label and ID?

abcdvzz avatar Jan 08 '19 07:01 abcdvzz

You can detect more types. E.g. men and women faces so set ID 0 for men faces and ID 1 for women faces. Of course you need proper dataset. For WIDER I used only one label "face" with ID 0.

ehp avatar Jan 12 '19 17:01 ehp

You can detect more types. E.g. men and women faces so set ID 0 for men faces and ID 1 for women faces. Of course you need proper dataset. For WIDER I used only one label "face" with ID 0.

if an image has more than a bounding box what is the correct formate is it: 12--Group/12_Group_Group_12_Group_Group_12_285.jpg 912 239 37 38 face 864 268 34 43 face

or 12--Group/12_Group_Group_12_Group_Group_12_285.jpg 912 239 37 38 face 12--Group/12_Group_Group_12_Group_Group_12_285.jpg 864 268 34 43 face

please help

sosha90 avatar Nov 13 '19 01:11 sosha90

Second option - see https://github.com/rainofmine/Face_Attention_Network/blob/68393da155da02d365e50e4118ca428eb9d24eb7/dataloader.py#L50

ehp avatar Nov 18 '19 19:11 ehp