On 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 by
torch.atleast_3d()
.- Parameters
-
tensors (sequence of Tensors) – 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]]])
© 2024, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://pytorch.org/docs/2.1/generated/torch.dstack.html