Open blackmrb opened 1 month ago
Good catch! It seems that when slicing a TensorDataclass
it will init a new TensorDataclass
with the default init params. For your application, the easiest thing will likely be to change the default. But I'll look at a more general solution
The default value of
asseme_ego_compensated
isTrue
, but my laser point cloud does not have motion compensation, so I set asseme_ego_compensated to false.However,
asseme_ego_compensated
in _generaterarys'from_points() is still true.the callback stack is below:![image](https://github.com/georghess/neurad-studio/assets/165770555/1b45bf39-98af-48b2-9150-e867ebdbcc8c)
I think it's the
class Lidar
base classTensorDataclass
problem, but I don't konw how to fix it. I temporarily set the default value ofasseme_ego_compensated
to false.