YOLO_tensorflow icon indicating copy to clipboard operation
YOLO_tensorflow copied to clipboard

YOLO_face unable to detect faces.

Open ayush-jha opened this issue 6 years ago • 3 comments

The weights seem to be off. Also, usually when a graph s saved, there are either three files or just one '*.ckpt' file. For the face network the weights have only two files. Nevertheless, it doesn't show an error on restoring form those files. But it is unable to detect even one face.

ayush-jha avatar Apr 04 '18 18:04 ayush-jha

I see the same problem, have you solved that?

ZhenyF avatar Aug 29 '18 10:08 ZhenyF

I wasn't able to solve the problem. Since I had limited time, I instead used MT-CNN. You can look into it.

On Wed, Aug 29, 2018 at 4:09 PM ZhenyF [email protected] wrote:

I see the same problem, have you solved that?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/gliese581gg/YOLO_tensorflow/issues/42#issuecomment-416907596, or mute the thread https://github.com/notifications/unsubscribe-auth/AYNFOnENjnHx040IRCmTkht9d2-evONaks5uVm9qgaJpZM4THUHV .

ayush-jha avatar Aug 29 '18 11:08 ayush-jha

@ayush-jha Thanks for the advice! Is that paper called "Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks"

ZhenyF avatar Sep 12 '18 09:09 ZhenyF