liegroups.torch¶
The PyTorch implementation uses torch.Tensor as the backend linear algebra library, which allows the user to on the GPU or CPU and integrate with other aspects of PyTorch.
This version provides sensible options for batching the transformations themselves, as well as anything they might operate on, and is generally agnostic to the specific Tensor type (e.g., given a torch.cuda.FloatTensor as input, the output will also be a torch.cuda.FloatTensor).
-
liegroups.torch.
SO2
¶ alias of
liegroups.torch.so2.SO2Matrix
-
class
liegroups.torch.so2.
SO2Matrix
(mat)¶ See
liegroups.SO2
-
cpu
()¶ Return a copy with the underlying tensor on the CPU.
-
cuda
(device=None, non_blocking=False)¶ Return a copy with the underlying tensor on the GPU.
-
classmethod
from_numpy
(other, pin_memory=False)¶ Create a torch-based copy of a numpy-based rotation.
-
is_cuda
()¶ Returns true if the underlying tensor is a CUDA tensor
-
is_pinned
()¶ Returns true if the underlying tensor resides in pinned memory
-
pin_memory
()¶ Return a copy with the underlying tensor in pinned (page-locked) memory. Makes host-to-GPU copies faster.
See: http://pytorch.org/docs/master/notes/cuda.html?highlight=pinned
-
-
liegroups.torch.
SE2
¶ alias of
liegroups.torch.se2.SE2Matrix
-
class
liegroups.torch.se2.
SE2Matrix
(rot, trans)¶ See
liegroups.SE2
-
cpu
()¶ Return a copy with the underlying tensors on the CPU.
-
cuda
(device=None, non_blocking=False)¶ Return a copy with the underlying tensors on the GPU.
-
classmethod
from_numpy
(other, pin_memory=False)¶ Create a torch-based copy of a numpy-based transformation.
-
is_cuda
()¶ Returns true if the underlying tensors are CUDA tensors
-
is_pinned
()¶ Returns true if the underlying tensors reside in pinned memory
-
pin_memory
()¶ Return a copy with the underlying tensor in pinned (page-locked) memory. Makes host-to-GPU copies faster.
See: http://pytorch.org/docs/master/notes/cuda.html?highlight=pinned
-
-
liegroups.torch.
SO3
¶ alias of
liegroups.torch.so3.SO3Matrix
-
class
liegroups.torch.so3.
SO3Matrix
(mat)¶ See
liegroups.SO3
-
cpu
()¶ Return a copy with the underlying tensor on the CPU.
-
cuda
(device=None, non_blocking=False)¶ Return a copy with the underlying tensor on the GPU.
-
classmethod
from_numpy
(other, pin_memory=False)¶ Create a torch-based copy of a numpy-based rotation.
-
is_cuda
()¶ Returns true if the underlying tensor is a CUDA tensor
-
is_pinned
()¶ Returns true if the underlying tensor resides in pinned memory
-
pin_memory
()¶ Return a copy with the underlying tensor in pinned (page-locked) memory. Makes host-to-GPU copies faster.
See: http://pytorch.org/docs/master/notes/cuda.html?highlight=pinned
-
-
liegroups.torch.
SE3
¶ alias of
liegroups.torch.se3.SE3Matrix
-
class
liegroups.torch.se3.
SE3Matrix
(rot, trans)¶ See
liegroups.SE3
-
cpu
()¶ Return a copy with the underlying tensors on the CPU.
-
cuda
(device=None, non_blocking=False)¶ Return a copy with the underlying tensors on the GPU.
-
classmethod
from_numpy
(other, pin_memory=False)¶ Create a torch-based copy of a numpy-based transformation.
-
is_cuda
()¶ Returns true if the underlying tensors are CUDA tensors
-
is_pinned
()¶ Returns true if the underlying tensors reside in pinned memory
-
pin_memory
()¶ Return a copy with the underlying tensor in pinned (page-locked) memory. Makes host-to-GPU copies faster.
See: http://pytorch.org/docs/master/notes/cuda.html?highlight=pinned
-