mindspore.ops.ger

mindspore.ops.ger(input, vec2)[source]

Ger product of input and vec2. Calculate the outer product of two arrays. If input is a 1D Tensor of shape $(m,)$ and vec2 is a 1D Tensor of shape $(n,)$ , then output must be a 2D Tensor of shape $(m, n)$ .

Note

Currently Ascend does not support float64 data input.

Parameters

input (Tensor) – input Tensor, with dtype of float16, float32 or float64.
vec2 (Tensor) – input Tensor, with dtype of float16, float32 or float64, must have the same dtype as input.

Returns

Tensor, output matrix with the same dtype as inputs. With input shape $(m,)$ and vec2 shape of $(n,)$ , the output has shape $(m, n)$ .

Raises

TypeError – If input or vec2 is not a 1-D Tensor.
TypeError – If the dtype of input and vec2 is not float16, float32 or float64.
TypeError – If the dtype of input and vec2 are not the same.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, ops
>>> input = Tensor([1., 2., 3., 4.], mindspore.float32)
>>> vec2 = Tensor([1., 2., 3.], mindspore.float32)
>>> output = ops.ger(input, vec2)
>>> print(output)
[[ 1.  2.  3.]
 [ 2.  4.  6.]
 [ 3.  6.  9.]
 [ 4.  8. 12.]]