Versioned name : HSigmoid-5

Category : Activation function

Short description : HSigmoid takes one input tensor and produces output tensor where the hard version of sigmoid function is applied to the tensor elementwise.

Detailed description : For each element from the input tensor calculates corresponding element in the output tensor with the following formula:

\[HSigmoid(x) = \frac{min(max(x + 3,\ 0),\ 6)}{6}\]

The HSigmoid operation is introduced in the following article.

Attributes : operations has no attributes.

Inputs :

  • 1 : A tensor of type T. Required.

Outputs :

  • 1 : The resulting tensor of the same shape and type as input tensor.


  • T : any floating-point type.


<layer ... type="HSigmoid">
        <port id="0">
        <port id="1">