Copying Tensors to a an allocated torch storage

[lakehanne]

I have a bunch of Tensors, say of size torch.Size([3, 224, 224]) each, totaling 99 tensors. If I put all these tensors in a python list say t_list, I want to put this list in a Tensor object, such as t_storage = torch.LongTensor(99, 3, 224, 224),

what is the most efficient way to accomplish this?

[vvanirudh]

torch.stack should do the job for this.

torch.stack(sequence, dim=0)

Concatenates sequence of tensors along a new dimension.

All tensors need to be of the same size.

Parameters:
sequence (Sequence) – sequence of tensors to concatenate.
dim (int) – dimension to insert. Has to be between 0 and the number of dimensions of concatenated tensors (inclusive).

[lakehanne]

Thank you, @vvanirudh!