mindspore.ops.HSigmoid

class mindspore.ops.HSigmoid(*args, **kwargs)[source]

Hard sigmoid activation function.

Applies hard sigmoid activation element-wise. The input is a Tensor with any valid shape.

Hard sigmoid is defined as:

\[\text{hsigmoid}(x_{i}) = max(0, min(1, \frac{x_{i} + 3}{6})),\]

where \(x_i\) is an element of the input Tensor.

Inputs:

input_x (Tensor) - Tensor of shape \((N, *)\), where \(*\) means, any number of additional dimensions, with float16 or float32 data type.

Outputs:

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

Raises

TypeError – If input_x is not a Tensor.
TypeError – If dtype of input_x is neither float16 nor float32.

Supported Platforms:: GPU CPU

Examples

>>> hsigmoid = ops.HSigmoid()
>>> input_x = Tensor(np.array([-1, -2, 0, 2, 1]), mindspore.float16)
>>> result = hsigmoid(input_x)
>>> print(result)
[0.3333  0.1666  0.5  0.833  0.6665]