torch.narrow¶
- torch.narrow(input, dim, start, length) Tensor ¶
Returns a new tensor that is a narrowed version of
input
tensor. The dimensiondim
is input fromstart
tostart + length
. The returned tensor andinput
tensor share the same underlying storage.- Parameters:
input (Tensor) – the tensor to narrow
dim (int) – the dimension along which to narrow
start (int or Tensor) – index of the element to start the narrowed dimension from. Can be negative, which means indexing from the end of dim. If Tensor, it must be an 0-dim integral Tensor (bools not allowed)
length (int) – length of the narrowed dimension, must be weakly positive
Example:
>>> x = torch.tensor([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) >>> torch.narrow(x, 0, 0, 2) tensor([[ 1, 2, 3], [ 4, 5, 6]]) >>> torch.narrow(x, 1, 1, 2) tensor([[ 2, 3], [ 5, 6], [ 8, 9]]) >>> torch.narrow(x, -1, torch.tensor(-1), 1) tensor([[3], [6], [9]])