I want to copy a 2D sparse matrix along a new third axis. With a dense matrix, I’d use unsqueeze followed by repeat, but with a sparse matrix, I get the following error:
RuntimeError: sparse tensors do not have strides
How do I fix this?
Any help would be greatly appreciated. Thank you!
Would you mind sharing the code?
As you said unsqueeze and then repeat don’t work,
matrix=torch.sparse_coo_tensor(size=(3,3))
matrix.unsqueeze(2).repeat(1,1,4)
#RuntimeError: sparse tensors do not have strides
However, you can get around this via using list comprehension and torch.stack, by,
matrix=torch.sparse_coo_tensor(size=(3,3))
new_matrix = torch.stack([matrix for _ in range(4)], dim=2)
#returns
#tensor(indices=tensor([], size=(3, 0)),
# values=tensor([], size=(0,)),
# size=(3, 3, 4), nnz=0, layout=torch.sparse_coo)
I hope this helps! 