You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
for i in range(kpts1.shape[0]):
k2d = keypoints[i, :nJoints]
if k2d[:, -1].sum() < nJoints / 2:
mywarn('[{}] No valid keypoints in frame {}'.format(self.__class__.__name__, i))
params['Th'][i] = params['Th'][i-1]
continue
Why do you use k2d[:, -1].sum()? How do you handle cases where negative and positive values offset each other in the sum?
What is the rationale behind the threshold nJoints / 2?
Thank you for your assistance.
The text was updated successfully, but these errors were encountered:
Hi,
I have some questions about the class
InitTranslation
used for SMPL refinement, specifically regarding the check for valid keypoints –https://github.com/zju3dv/EasyMocap/blob/206c95065f0da64581804528d9e182fd35de5e88/myeasymocap/operations/init.py#L44C1-L45C1
k2d[:, -1].sum()
? How do you handle cases where negative and positive values offset each other in the sum?nJoints / 2
?Thank you for your assistance.
The text was updated successfully, but these errors were encountered: