HardSigmoid¶

HardSigmoid - 6¶

Version¶

name: HardSigmoid (GitHub)
domain: main
since_version: 6
function: True
support_level: SupportType.COMMON
shape inference: True

This version of the operator has been available since version 6.

Summary¶

HardSigmoid takes one input data (Tensor) and produces one output data (Tensor) where the HardSigmoid function, y = max(0, min(1, alpha * x + beta)), is applied to the tensor elementwise.

Function Body¶

The function definition for this operator.

<
  domain: "",
  opset_import: ["" : 18]
>
HardSigmoid <alpha,beta>(X) => (Y)
{
   Alpha = Constant <value_float: float = @alpha> ()
   AlphaCast = CastLike (Alpha, X)
   Beta = Constant <value_float: float = @beta> ()
   BetaCast = CastLike (Beta, X)
   Zero = Constant <value: tensor = float {0}> ()
   ZeroCast = CastLike (Zero, X)
   One = Constant <value: tensor = float {1}> ()
   OneCast = CastLike (One, X)
   AlphaMulX = Mul (X, AlphaCast)
   AlphaMulXAddBeta = Add (AlphaMulX, BetaCast)
   MinOneOrAlphaMulXAddBeta = Min (AlphaMulXAddBeta, OneCast)
   Y = Max (MinOneOrAlphaMulXAddBeta, ZeroCast)
}

Attributes¶

alpha - FLOAT (default is '0.2'):

Value of alpha.
beta - FLOAT (default is '0.5'):

Value of beta.

Inputs¶

X (heterogeneous) - T:

Input tensor

Outputs¶

Y (heterogeneous) - T:

Output tensor

Type Constraints¶

T in ( tensor(double), tensor(float), tensor(float16) ):

Constrain input and output types to float tensors.

HardSigmoid - 1 vs 6

HardSigmoid - 1¶