Miscellaneous Classes

Kernel Generator

class MinkowskiEngine.KernelGenerator(kernel_size=-1, stride=1, dilation=1, is_transpose: bool = False, region_type: MinkowskiEngineBackend._C.RegionType = <RegionType.HYPER_CUBE: 0>, region_offsets: Optional[torch.Tensor] = None, expand_coordinates: bool = False, axis_types=None, dimension=-1)

__init__(kernel_size=-1, stride=1, dilation=1, is_transpose: bool = False, region_type: MinkowskiEngineBackend._C.RegionType = <RegionType.HYPER_CUBE: 0>, region_offsets: Optional[torch.Tensor] = None, expand_coordinates: bool = False, axis_types=None, dimension=-1)

region_type (RegionType, optional): defines the kernel shape. Please refer to MinkowskiEngine.Comon for details.

region_offset (torch.IntTensor, optional): when the region_type is RegionType.CUSTOM, the convolution kernel uses the provided region_offset to define offsets. It should be a matrix of size \(N \times D\) where \(N\) is the number of offsets and \(D\) is the dimension of the space.

axis_types (list of RegionType, optional): If given, it uses different methods to create a kernel for each axis. e.g., when it is [RegionType.HYPER_CUBE, RegionType.HYPER_CUBE, RegionType.HYPER_CROSS], the kernel would be rectangular for the first two dimensions and cross shaped for the thrid dimension.

axis_types

cache

dimension

expand_coordinates

get_kernel(tensor_stride, is_transpose)

kernel_dilation

kernel_size

kernel_stride

kernel_volume

region_offsets

region_type

requires_strided_coordinates

RegionType

class MinkowskiEngine.RegionType

Members:

HYPER_CUBE

HYPER_CROSS

CUSTOM

CUSTOM = <RegionType.CUSTOM: 2>

HYPER_CROSS = <RegionType.HYPER_CROSS: 1>

HYPER_CUBE = <RegionType.HYPER_CUBE: 0>

property name