Rate this Page
★★★★★

torch.Tensor.to_dense#

Tensor.to_dense(dtype=None,*,masked_grad=True)→Tensor#

Creates a strided copy ofself ifself is not a strided tensor, otherwise returnsself.

Keyword Arguments

  • {dtype} –

  • masked_grad (bool,optional) – If set toTrue (default) andself has a sparse layout then the backward ofto_dense() returnsgrad.sparse_mask(self).

Example:

>>>s=torch.sparse_coo_tensor(...torch.tensor([[1,1],...[0,2]]),...torch.tensor([9,10]),...size=(3,3))>>>s.to_dense()tensor([[ 0,  0,  0],        [ 9,  0, 10],        [ 0,  0,  0]])