Integral-Human-Pose-Regression-for-3D-Human-Pose-Estimation icon indicating copy to clipboard operation
Integral-Human-Pose-Regression-for-3D-Human-Pose-Estimation copied to clipboard

Published 20 hours ago • verified publisher icon mks0601

loss proplem

Open wangm-word opened this issue 3 years ago • 2 comments

thank you very much ! what is the gt_vis and gt_have_depth？ image

wangm-word avatar Aug 16 '21 09:08 wangm-word

gt_vis: 1 if the joint is annotated. 0 else gt_have_depth: 1 if the dataset has depth annotations. 0 else.

mks0601 avatar Aug 16 '21 13:08 mks0601

gt_vis: 1 if the joint is annotated. 0 else gt_have_depth: 1 if the dataset has depth annotations. 0 else.

thank you for your replay! Can you tell me how to visual a img by useing the train results ?

wangm-word avatar Aug 18 '21 09:08 wangm-word