mindspore.mint.addbmm

mindspore.mint.addbmm(input, batch1, batch2, *, beta=1, alpha=1)

Applies batch matrix multiplication to batch1 and batch2, with a reduced add step and add input to the result.

The optional value alpha is the matrix-matrix product between batch1 and batch2, and beta is the scale factor for the added tensor input. If beta is 0, then input will be ignored.

$$output=\beta input+\alpha (\sum _{i=0}^{b-1}batch{1}_i@batch{2}_i)$$

Warning

This is an experimental API that is subject to change or deletion.

Parameters

• input (Tensor) – Tensor to be added.

• batch1 (Tensor) – The first batch of tensor to be multiplied.

• batch2 (Tensor) – The second batch of tensor to be multiplied.

Keyword Arguments

• beta (Union[int, float], optional) – Multiplier for input. Default: 1 .

• alpha (Union[int, float], optional) – Multiplier for batch1 @ batch2. Default: 1 .

Returns

Tensor, has the same dtype as input.

Raises

• TypeError – If alpha or beta is not an int or float.

• ValueError – If batch1, batch2 cannot apply batch matrix multiplication.

• ValueError – If batch1 and batch2 are not 3-D tensors.

Supported Platforms:

Ascend

Examples

>>> import numpy as np
>>> from mindspore import Tensor, mint
>>> m = np.ones((3, 3)).astype(np.float32)
>>> arr1 = np.arange(24).astype(np.float32).reshape((2, 3, 4))
>>> arr2 = np.arange(24).astype(np.float32).reshape((2, 4, 3))
>>> a = Tensor(arr1)
>>> b = Tensor(arr2)
>>> c = Tensor(m)
>>> output = mint.addbmm(c, a, b)
>>> print(output)
[[ 949. 1009. 1069.]
 [1285. 1377. 1469.]
 [1621. 1745. 1869.]]