openvino.runtime.opset10.hard_sigmoid#

openvino.runtime.opset10.hard_sigmoid(data: Node, alpha: Node | int | float | ndarray, beta: Node | int | float | ndarray, name: str | None = None) → Node#

Perform Hard Sigmoid operation element-wise on data from input node.

Parameters:

  • data – The node with data tensor.

  • alpha – A node producing the alpha parameter.

  • beta – A node producing the beta parameter

  • name – Optional output node name.

Returns:

The new node performing a Hard Sigmoid element-wise on input tensor.

Hard Sigmoid uses the following logic:

y = max(0, min(1, alpha * data + beta))