Functional convolution

torch_lattice.nn.functional.conv.conv.conv3d(input, weight, kernel_size, bias=None, stride=1, padding=0, dilation=1, config=None, subm=False, transposed=False, generative=False, training=False)

Return type:

SparseTensor

Parameters:

• input (SparseTensor)

• weight (Tensor)

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

• bias (Tensor | None)

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

• padding (int | Tuple[int, ...])

• dilation (int | Tuple[int, ...])

• config (Dict)

• subm (bool)

• transposed (bool)

• generative (bool)

• training (bool)

torch_lattice.nn.functional.conv.conv.target_conv3d(input, target, weight, kernel_size, bias=None, stride=1, padding=0, dilation=1, config=None, training=False)

Sparse convolution evaluated only at target coordinates.

Return type:

SparseTensor

Parameters:

• input (SparseTensor)

• target (SparseTensor)

• weight (Tensor)

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

• bias (Tensor | None)

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

• padding (int | Tuple[int, ...])

• dilation (int | Tuple[int, ...])

• config (Dict)

• training (bool)