mindspore.ops.heaviside

mindspore.ops.heaviside(input, values)

Perform Heaviside step function element-wise.

Support broadcasting.

\[\begin{split}\text { heaviside }(\text { input, values })=\left\{\begin{array}{ll} 0, & \text { if input }<0 \\ \text { values, } & \text { if input }=0 \\ 1, & \text { if input }>0 \end{array}\right.\end{split}\]

Parameters

• input (Tensor) – The input tensor.

• values (Tensor) – The value to fill when the element in input is 0.

Returns

Tensor

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> input = mindspore.tensor([[-2., 0, 3],
...                           [5, -1, 0],
...                           [0, 7, -3]])
>>> values = mindspore.tensor([2, 0.5, 1])
>>> output = mindspore.ops.heaviside(input, values)
>>> print(output)
[[0.  0.5 1. ]
 [1.  0.  1. ]
 [2.  1.  0. ]]
>>> output = mindspore.ops.heaviside(input, mindspore.tensor(0.5))
>>> print(output)
[[0.  0.5 1. ]
 [1.  0.  0.5]
 [0.5 1.  0. ]]
>>> output = mindspore.ops.heaviside(mindspore.tensor(-3.), values)
>>> print(output)
[0. 0. 0.]