mindspore.Tensor.mm

Tensor.mm(mat2) → Tensor[source]

Returns the matrix product of two arrays. If self is a \((n \times m)\) Tensor, mat2 is a \((m \times p)\) Tensor, out will be a \((n \times p)\) Tensor.

Note

This function cannot support broadcasting. Refer to mindspore.ops.matmul() instead if you need a broadcastable function.

Warning

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

Parameters:

mat2 (Tensor) – The second matrix of matrix multiplication. The last dimension of self must be the same size as the first dimension of mat2.

Returns:

Tensor, the matrix product of the inputs.

Raises:

  • TypeError – If self or mat2 is not a Tensor.

  • RuntimeError – If the last dimension of self is not the same size as the second-to-last dimension of mat2.

  • RuntimeError – If dtype of self or mat2 is not float16, float32 or bfloat16.

Supported Platforms:

Ascend

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> x1 = ms.Tensor(np.random.rand(2, 3), ms.float32)
>>> x2 = ms.Tensor(np.random.rand(3, 4), ms.float32)
>>> out = x1.mm(x2)
>>> print(out.shape)
(2, 4)