mindspore.ops.Addcmul

View Source On Gitee
class mindspore.ops.Addcmul[source]

Adds the element-wise product of x1 by x2, multiplied by value to input_data. It computes the following operation:

\[output[i] = input\_data[i] + value[i] * (x1[i] * x2[i])\]
Inputs:

  • input_data (Tensor) - The tensor to be added.

  • x1 (Tensor) - The tensor to be multiplied.

  • x2 (Tensor) - The tensor to be multiplied.

  • value (Tensor) - The multiplier for tensor x1*x2.

Outputs:

Tensor, has the same shape and dtype as x1*x2.

Raises

  • TypeError – If dtype of x1, x2, value, input_data is not tensor.

  • TypeError – If dtype of x1, x2, value, input_data are not the same.

  • ValueError – If x1 could not be broadcast to x2.

  • ValueError – If value could not be broadcast to x1 * x2.

  • ValueError – If input_data could not be broadcast to value*(x1*x2).

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input_data = Tensor(np.array([1, 1, 1]), mindspore.float32)
>>> x1 = Tensor(np.array([[1], [2], [3]]), mindspore.float32)
>>> x2 = Tensor(np.array([[1, 2, 3]]), mindspore.float32)
>>> value = Tensor([1], mindspore.float32)
>>> addcmul = ops.Addcmul()
>>> y = addcmul(input_data, x1, x2, value)
>>> print(y)
[[ 2.  3.  4.]
[ 3.  5.  7.]
[ 4.  7. 10.]]