mindspore.ops.bmm

mindspore.ops.bmm(input_x, mat2)

Perform a batch matrix-matrix product of matrices in input tensors.

$$\text{output}[...,:,:]=\text{matrix}(inpu{t}_x[...,:,:])\ast \text{matrix}(mat2[...,:,:])$$

The dim of input_x can not be less than 3 and the dim of mat2 can not be less than 2.

Parameters

• input_x (Tensor) – The first tensor to be multiplied.

• mat2 (Tensor) – The second tensor to be multiplied.

Returns

Tensor

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> input_x = mindspore.ops.arange(24, dtype=mindspore.float32).reshape(2, 4, 1, 3)
>>> mat2 = mindspore.ops.arange(72, dtype=mindspore.float32).reshape(2, 4, 3, 3)
>>> out = mindspore.ops.bmm(input_x, mat2)
>>> print(out)
[[[[  15,   18,   21]],
 [[ 150,  162,  174]],
 [[ 447,  468,  489]],
 [[ 906,  936,  966]]],
 [[[1527, 1566, 1605]],
 [[2310, 2358, 2406]],
 [[3255, 3312, 3369]],
 [[4362, 4428, 4494]]]]