Rate this Page
★★★★★

torch.dstack#

torch.dstack(tensors,*,out=None)→Tensor#

Stack tensors in sequence depthwise (along third axis).

This is equivalent to concatenation along the third axis after 1-D and 2-D tensors have been reshaped bytorch.atleast_3d().

Parameters

tensors (sequence ofTensors) – sequence of tensors to concatenate

Keyword Arguments

out (Tensor,optional) – the output tensor.

Example:

>>>a=torch.tensor([1,2,3])>>>b=torch.tensor([4,5,6])>>>torch.dstack((a,b))tensor([[[1, 4],         [2, 5],         [3, 6]]])>>>a=torch.tensor([[1],[2],[3]])>>>b=torch.tensor([[4],[5],[6]])>>>torch.dstack((a,b))tensor([[[1, 4]],        [[2, 5]],        [[3, 6]]])