narrow

→Tensor

narrow(input: Tensor, dim: int, start: int, length: int)

Return a contiguous slice of input along dim.

Equivalent to input[..., start:start+length, ...] with the slice applied at position dim. Returns a view — no data copy.

inputTensor

Source tensor.

dimint

Dimension to slice.

startint

First index (inclusive).

lengthint

Number of elements to take. Must satisfy start + length <= input.size(dim).

Tensor

View into input of size length along dim.

Unlike NumPy slicing, narrow accepts only step 1; for general strided slicing use indexing syntax.

>>> import lucid
>>> x = lucid.arange(10)
>>> lucid.narrow(x, dim=0, start=3, length=4)
Tensor([3, 4, 5, 6])