dot

paddle. dot ( x, y, name=None ) [source]

This operator calculates inner product for vectors.

Note

Support 1-d and 2-d Tensor. When it is 2d, the first dimension of this matrix is the batch dimension, which means that the vectors of multiple batches are dotted.

Parameters
  • x (Tensor) – 1-D or 2-D Tensor. Its dtype should be float32, float64, int32, int64, complex64, complex128

  • y (Tensor) – 1-D or 2-D Tensor. Its dtype should be float32, float64, int32, int64, complex64, complex128

  • name (str, optional) – Name of the output. Default is None. It’s used to print debug info for developers. Details: Name

Returns

the calculated result Tensor.

Return type

Tensor

Examples

>>> import paddle

>>> # 1-D Tensor * 1-D Tensor
>>> x = paddle.to_tensor([1, 2, 3])
>>> y = paddle.to_tensor([4, 5, 6])
>>> z = paddle.dot(x, y)
>>> print(z)
Tensor(shape=[], dtype=int64, place=Place(cpu), stop_gradient=True,
32)

>>> # 2-D Tensor * 2-D Tensor
>>> x = paddle.to_tensor([[1, 2, 3], [2, 4, 6]])
>>> y = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
>>> z = paddle.dot(x, y)
>>> print(z)
Tensor(shape=[2], dtype=int64, place=Place(cpu), stop_gradient=True,
[32, 64])