ReplicationPad1d

class dragon.vm.torch.nn.ReplicationPad1d(padding)[source]

Pad input according to the last dimension by replicating boundary.

The padded dimension is computed as:

\[\text{Dim}_{out} = \text{Dim}_{in} + pad_l + pad_r \]

Examples:

m = torch.nn.ReplicationPad1d(1)
x = torch.randn(1, 4)
y = m(x)  # (1, 4) -> (1, 6)

__init__

ReplicationPad1d.__init__(padding)[source]

Create a ReplicationPad1d module.

Parameters:
  • padding (Union[int, Sequence[int]]) – The 1d padding sizes.