Rate this Page
★★★★★
torch.broadcast_shapes#
- torch.broadcast_shapes(*shapes)→Size[source]#
Similar to
broadcast_tensors()but for shapes.This is equivalent to
torch.broadcast_tensors(*map(torch.empty,shapes))[0].shapebut avoids the need create to intermediate tensors. This is useful forbroadcasting tensors of common batch shape but different rightmost shape,e.g. to broadcast mean vectors with covariance matrices.Example:
>>>torch.broadcast_shapes((2,),(3,1),(1,1,1))torch.Size([1, 3, 2])
- Parameters
*shapes (torch.Size) – Shapes of tensors.
- Returns
A shape compatible with all input shapes.
- Return type
shape (torch.Size)
- Raises
RuntimeError – If shapes are incompatible.
On this page
