Shrink¶
Shrink - 9¶
Version¶
name: Shrink (GitHub)
domain:
main
since_version:
9
function:
True
support_level:
SupportType.COMMON
shape inference:
True
This version of the operator has been available since version 9.
Summary¶
Shrink takes one input data (Tensor
Function Body¶
The function definition for this operator.
<
domain: "",
opset_import: ["" : 18]
>
Shrink <bias,lambd>(input) => (output)
{
Lambd = Constant <value_float: float = @lambd> ()
LambdCast = CastLike (Lambd, input)
Bias = Constant <value_float: float = @bias> ()
BiasCast = CastLike (Bias, input)
Zero = Constant <value: tensor = float {0}> ()
ZeroCast = CastLike (Zero, input)
NegLmbda = Neg (LambdCast)
InputLessThanNegLambda = Less (input, NegLmbda)
InputAddBias = Add (input, BiasCast)
InputSubBias = Sub (input, BiasCast)
LambdaLessThanInput = Less (LambdCast, input)
InputSubBiasOrZero = Where (LambdaLessThanInput, InputSubBias, ZeroCast)
output = Where (InputLessThanNegLambda, InputAddBias, InputSubBiasOrZero)
}
Attributes¶
bias - FLOAT (default is
'0.0'
):The bias value added to output. Default is 0.
lambd - FLOAT (default is
'0.5'
):The lambd value for the Shrink formulation. Default is 0.5.
Inputs¶
input (heterogeneous) - T:
The input data as Tensor.
Outputs¶
output (heterogeneous) - T:
The output.
Type Constraints¶
T in (
tensor(double)
,tensor(float)
,tensor(float16)
,tensor(int16)
,tensor(int32)
,tensor(int64)
,tensor(int8)
,tensor(uint16)
,tensor(uint32)
,tensor(uint64)
,tensor(uint8)
):Constrain input to only numeric types.