copapy.nn.conv1d

copapy.nn.conv1d(x, weight, bias=None, stride=1, padding=0, dilation=1)

1D convolution (cross-correlation as in most deep learning frameworks) computed by a single array stencil.

Parameters:

• x (TArr) – Input of shape (channels, length) or (batch, channels, length).

• weight (array[Any] | ArrayType[Any] | Sequence[Any]) – Kernels of shape (out_channels, channels, kernel_length).

• bias (array[Any] | ArrayType[Any] | Sequence[Any] | None) – Optional bias of shape (out_channels,).

• stride (int) – Step of the kernel.

• padding (int) – Zero padding on both sides of the input.

• dilation (int) – Spacing between the kernel elements.

Return type:

TArr

Returns:

Float array or tensor (same type as x) of shape (out_channels, out_length) with a leading batch dimension if x has one.