torch.vdot

torch.vdot(input, other, *, out=None) → Tensor

Computes the dot product of two 1D tensors. The vdot(a, b) function handles complex numbers differently than dot(a, b). If the first argument is complex, the complex conjugate of the first argument is used for the calculation of the dot product.

Note

Unlike NumPy’s vdot, torch.vdot intentionally only supports computing the dot product of two 1D tensors with the same number of elements.

Parameters

• input (Tensor) – first tensor in the dot product, must be 1D. Its conjugate is used if it’s complex.
• other (Tensor) – second tensor in the dot product, must be 1D.

Keyword Arguments

out (Tensor, optional) – the output tensor.

Example:

>>> torch.vdot(torch.tensor([2, 3]), torch.tensor([2, 1]))
tensor(7)
>>> a = torch.tensor((1 +2j, 3 - 1j))
>>> b = torch.tensor((2 +1j, 4 - 0j))
>>> torch.vdot(a, b)
tensor([16.+1.j])
>>> torch.vdot(b, a)
tensor([16.-1.j])