mindspore.nn.HSigmoid

class mindspore.nn.HSigmoid[source]

Applies Hard Sigmoid activation function element-wise.

Hard Sigmoid is defined as:

\[\begin{split}\text{Hardsigmoid}(input) = \begin{cases} 0, & \text{ if } input \leq -3, \\ 1, & \text{ if } input \geq +3, \\ input/6 + 1/2, & \text{ otherwise } \end{cases}\end{split}\]

HSigmoid Activation Function Graph:

Inputs:

input (Tensor) - The input of HSigmoid.

Outputs:

Tensor, with the same type and shape as the input.

Raises

TypeError – If input is not a Tensor.
TypeError – If input is neither int nor float.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> input = Tensor(np.array([-1, -2, 0, 2, 1]), mindspore.float16)
>>> hsigmoid = nn.HSigmoid()
>>> result = hsigmoid(input)
>>> print(result)
[0.3333 0.1666 0.5    0.8335 0.6665]