TransposeIrrepsLayout

class cuequivariance_torch.TransposeIrrepsLayout

Transpose the irreps layout of a tensor.

Parameters:

• irreps (Irreps) – The irreps of the tensor.

• source (IrrepsLayout) – The source layout.

• target (IrrepsLayout) – The target layout.

Forward Pass

forward(x)

Perform the transposition.

Parameters:

• x (torch.Tensor) – The input tensor.

• use_fallback (bool, optional) – If None (default), a CUDA kernel will be used if available. If False, a CUDA kernel will be used, and an exception is raised if it’s not available. If True, a PyTorch fallback method is used regardless of CUDA kernel availability.

Returns:

The transposed tensor.

Return type:

torch.Tensor

__init__(

irreps,

*,

source,

target,

device=None,

use_fallback=None,

)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• irreps (Irreps)

• source (IrrepsLayout)

• target (IrrepsLayout)

• device (device | None)

• use_fallback (bool | None)

classmethod __new__(*args, **kwargs)