pypose.optim.strategy.Constant

class pypose.optim.strategy.Constant(damping=1e-06)

Constant damping strategy used in the Levenberg-Marquardt (LM) algorithm.

Parameters

damping (float, optional) – damping factor of LM optimizer. Default: 1e-6.

Example

>>> class PoseInv(nn.Module):
...     def __init__(self, *dim):
...         super().__init__()
...         self.pose = pp.Parameter(pp.randn_SE3(*dim))
...
...     def forward(self, inputs):
...         return (self.pose @ inputs).Log().tensor()
...
... device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
... inputs = pp.randn_SE3(2, 2).to(device)
... invnet = PoseInv(2, 2).to(device)
... strategy = pp.optim.strategy.Constant(damping=1e-6)
... optimizer = pp.optim.LM(invnet, strategy=strategy)
...
... for idx in range(10):
...     loss = optimizer.step(inputs)
...     print('Pose loss %.7f @ %dit'%(loss, idx))
...     if loss < 1e-5:
...         print('Early Stoping!')
...         print('Optimization Early Done with loss:', loss.item())
...         break
Pose loss 0.0000000 @ 0it
Early Stoping!
Optimization Early Done with loss: 9.236661990819073e-10

Note

More details about optimization go to pypose.optim.LevenbergMarquardt().