mindspore.ops.vecdot

mindspore.ops.vecdot(x, y, *, axis=- 1)[source]

Calculates the dot product of two batches of vectors along the specified dimension.

Warning

After version 2.9.0, the keyword axis will be renamed to dim.

Support broadcasting.

The formula of calculation is as follows. \(\bar{x_{i}}\) represents the conjugate for complex vectors, and \(\bar{x_{i}}\) is the raw value for real vectors.

\[\sum_{i=1}^{n} \bar{x_{i}}{y_{i}}\]

Parameters

x (Tensor) – The first batch of tensors.
y (Tensor) – The second batch of tensors.

Keyword Arguments

axis (int) – Specify the axis for computation. Default -1 .

Returns

Tensor

Supported Platforms:: Ascend GPU CPU

Note

Currently, complex numbers are not supported on GPU.

Examples

>>> import mindspore
>>> x = mindspore.tensor([[1, 3], [5, 7], [9, 8]])
>>> y = mindspore.tensor([[4, 5], [6, 7], [3, 2]])
>>> mindspore.ops.vecdot(x, y)
Tensor(shape=[3], dtype=Int64, value= [19, 79, 43])
>>> mindspore.ops.vecdot(x, y, axis=0)
Tensor(shape=[2], dtype=Int64, value= [61, 80])