torch_harmonics.distributed.DistributedDiscreteContinuousConvTransposeS2#

class torch_harmonics.distributed.DistributedDiscreteContinuousConvTransposeS2(
in_channels,
out_channels,
in_shape,
out_shape,
kernel_shape,
basis_type='piecewise linear',
basis_norm_mode='nodal',
groups=1,
grid_in='equiangular',
grid_out='equiangular',
bias=True,
theta_cutoff=None,
optimized_kernel=True,
)[source]#

Bases: DiscreteContinuousConv

Distributed version of discrete-continuous transpose convolutions (DISCO) on the 2-Sphere as described in [1].

See also

torch_harmonics.DiscreteContinuousConvTransposeS2

Serial counterpart with full mathematical description and parameter documentation.

Parameters:

  • in_channels (int) – Number of input channels

  • out_channels (int) – Number of output channels

  • in_shape (Tuple[int]) – Shape of the input tensor

  • out_shape (Tuple[int]) – Shape of the output tensor

  • kernel_shape (Union[int, Tuple[int], Tuple[int, int]]) – Shape of the kernel

  • basis_type (Optional[str]) – Type of basis to use

  • basis_norm_mode (Optional[str]) – Normalization mode for the filter basis

  • groups (Optional[int]) – Number of groups

  • grid_in (Optional[str]) – Grid type for the input tensor

  • grid_out (Optional[str]) – Grid type for the output tensor

  • bias (Optional[bool]) – Whether to use bias

  • theta_cutoff (Optional[float]) – Theta cutoff for the filter basis

  • optimized_kernel (bool | None)

Returns:

Output tensor

Return type:

torch.Tensor

References

[1]