mindspore.ops.kron

mindspore.ops.kron(input, other)[source]

Computes the Kronecker product \(input ⊗ other\), denoted by ⊗, of input and other.

If input is a \((a_{0}\) input \(a_{1}\) input … input \(a_{n})\) Tensor and other is a \((b_{0}\) input \(b_{1}\) input … input \(b_{n})\) Tensor, the result will be a \((a_{0}*b_{0}\) input \(a_{1}*b_{1}\) input … input \(a_{n}*b_{n})\) Tensor with the following entries:

\[(input ⊗ other)_{k_{0},k_{1},...k_{n}} = input_{i_{0},i_{1},...i_{n}} * other_{j_{0},j_{1},...j_{n}},\]

where \(k_{t} = i_{t} * b_{t} + j_{t}\) for 0 ≤ t ≤ n. If one Tensor has fewer dimensions than the other it is unsqueezed until it has the same number of dimensions.

Note

Supports real-valued and complex-valued inputs.

Parameters

  • input (Tensor) – Input Tensor, has the shape \((r0, r1, ... , rN)\).

  • other (Tensor) – Input Tensor, has the shape \((s0, s1, ... , sN)\).

Returns

Tensor, has the shape \((r0 * s0, r1 * s1, ... , rN * sN)\).

Raises
Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, nn
>>> from mindspore import ops
>>> input = Tensor(np.array([[0, 1, 2], [3, 4, 5]])).astype(np.float32)
>>> other = Tensor(np.array([[-1, -2, -3], [-4, -6, -8]])).astype(np.float32)
>>> output = ops.kron(input, other)
>>> print(output)
[[  0.   0.   0.  -1.  -2.  -3.  -2.  -4.  -6.]
 [  0.   0.   0.  -4.  -6.  -8.  -8. -12. -16.]
 [ -3.  -6.  -9.  -4.  -8. -12.  -5. -10. -15.]
 [-12. -18. -24. -16. -24. -32. -20. -30. -40.]]