torch.broadcast_shapes

torch.broadcast_shapes(*shapes) → Size

Similar to broadcast_tensors() but for shapes.

This is equivalent to torch.broadcast_tensors(*map(torch.empty, shapes))[0].shape but avoids the need create to intermediate tensors. This is useful for broadcasting 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.