pypose.Parameter¶
- class pypose.Parameter(data=None, requires_grad=True)[source]¶
A kind of LieTensor that is to be considered a module parameter.
Parameters are of
LieTensor()
andtorch.nn.Parameter()
, that have a very special property when used with Modules: when they are assigned as Module attributes they are automatically added to the list of its parameters, and will appear, e.g., inparameters()
iterator.- Parameters
data (LieTensor) – parameter LieTensor.
requires_grad (bool, optional) – if the parameter requires gradient. Default:
True
Examples
>>> import torch, pypose as pp >>> x = pp.Parameter(pp.randn_SO3(2)) >>> x.Log().sum().backward() >>> x.grad tensor([[0.8590, 1.4069, 0.6261, 0.0000], [1.2869, 1.0748, 0.5385, 0.0000]])