A possible bug in fittingop

[lzhyu]

SAGA/WholeGraspPose/models/fittingop.py

Lines 183 to 184 in ecaed33

	o2h_marker, h2o_signed_marker, o2h_idx_marker, _ = point2point_signed(body_markers_rec, verts_object.float(), normal_object.float())
	o2h_signed, h2o_signed, o2h_idx, _ = point2point_signed(rhand_verts_rec, verts_object.float(), rh_normals, normal_object.float())

In line 183, it seems that the third positional argument should be the normals of markers.

[DonlynLee]

Hi, have you encountered the problem that "TypeError: init() takes 1 positional argument but 3 were given", when running opt_grasppose.py ?

[lzhyu]

Hi, have you encountered the problem that "TypeError: init() takes 1 positional argument but 3 were given", when running opt_grasppose.py ?

Sorry. I have not.

[DonlynLee]

Thanks for your reply. Could you tell me your pytorch version? By the way, you proposed a possible bug in fittingop, so should we change the third positional argument to normals of markers? Thank you so much.