Convolution modules

class torch_lattice.nn.modules.conv.Conv3d(in_channels, out_channels, kernel_size=3, stride=1, padding=0, dilation=1, bias=False, config=None)[source]

Bases: _BaseConv3d

Support-generating sparse 3D convolution.

Parameters:

  • in_channels (int)

  • out_channels (int)

  • kernel_size (Union[int, List[int], Tuple[int, ...]])

  • stride (Union[int, List[int], Tuple[int, ...]])

  • padding (Union[int, Tuple[int, ...]])

  • dilation (int)

  • bias (bool)

  • config (Dict | None)

class torch_lattice.nn.modules.conv.SubmConv3d(in_channels, out_channels, kernel_size=3, dilation=1, bias=False, config=None)[source]

Bases: _BaseConv3d

Support-preserving submanifold sparse 3D convolution.

Parameters:

  • in_channels (int)

  • out_channels (int)

  • kernel_size (Union[int, List[int], Tuple[int, ...]])

  • dilation (int)

  • bias (bool)

  • config (Dict | None)

class torch_lattice.nn.modules.conv.ConvTranspose3d(in_channels, out_channels, kernel_size=3, stride=1, padding=0, dilation=1, bias=False, config=None)[source]

Bases: _BaseConv3d

Sparse transposed 3D convolution using an existing inverse support map.

Parameters:

  • in_channels (int)

  • out_channels (int)

  • kernel_size (Union[int, List[int], Tuple[int, ...]])

  • stride (Union[int, List[int], Tuple[int, ...]])

  • padding (Union[int, Tuple[int, ...]])

  • dilation (int)

  • bias (bool)

  • config (Dict | None)

class torch_lattice.nn.modules.conv.GenerativeConvTranspose3d(in_channels, out_channels, kernel_size=3, stride=1, padding=0, dilation=1, bias=False, config=None)[source]

Bases: _BaseConv3d

Sparse transposed 3D convolution that generates its output support.

Parameters:

  • in_channels (int)

  • out_channels (int)

  • kernel_size (Union[int, List[int], Tuple[int, ...]])

  • stride (Union[int, List[int], Tuple[int, ...]])

  • padding (Union[int, Tuple[int, ...]])

  • dilation (int)

  • bias (bool)

  • config (Dict | None)

class torch_lattice.nn.modules.conv.TargetConv3d(in_channels, out_channels, kernel_size=3, stride=1, padding=0, dilation=1, bias=False, config=None)[source]

Bases: _BaseConv3d

Sparse 3D convolution evaluated on explicit target coordinates.

Parameters:

  • in_channels (int)

  • out_channels (int)

  • kernel_size (Union[int, List[int], Tuple[int, ...]])

  • stride (Union[int, List[int], Tuple[int, ...]])

  • padding (Union[int, Tuple[int, ...]])

  • dilation (int)

  • bias (bool)

  • config (Dict | None)

forward(input, target)[source]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Return type:

SparseTensor

Parameters: