Versioned name: HardSwish-1

Category: Activation

Short description: HardSwish element-wise activation function.

OpenVINO description: This OP is as same as OpenVINO OP

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

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

The HardSwish operation was introduced in the article available here.

Attributes: HardSwish operation has no attributes.


  • 1: input - multidimensional input tensor. Required.

    • Type: T


  • 1: output - result of HardSwish function applied to the input tensor. Required.

    • Type: T


  • T: f32, f16, bf16.

  • Note: Inputs and outputs have the same data type denoted by T. For example, if input is f32 tensor, then all other tensors have f32 data type.