QuantizedInstanceNorm.Options

public static class QuantizedInstanceNorm.Options

Optional attributes for QuantizedInstanceNorm

Public Methods

QuantizedInstanceNorm.Options	givenYMax(Float givenYMax)
QuantizedInstanceNorm.Options	givenYMin(Float givenYMin)
QuantizedInstanceNorm.Options	minSeparation(Float minSeparation)
QuantizedInstanceNorm.Options	outputRangeGiven(Boolean outputRangeGiven)
QuantizedInstanceNorm.Options	varianceEpsilon(Float varianceEpsilon)

Inherited Methods

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

Public Methods

public QuantizedInstanceNorm.Options givenYMax (Float givenYMax)

Parameters

givenYMax	Output in `y_max` if `output_range_given` is True.

public QuantizedInstanceNorm.Options givenYMin (Float givenYMin)

Parameters

givenYMin	Output in `y_min` if `output_range_given` is True.

public QuantizedInstanceNorm.Options minSeparation (Float minSeparation)

Parameters

minSeparation	Minimum value of `y_max - y_min`

public QuantizedInstanceNorm.Options outputRangeGiven (Boolean outputRangeGiven)

Parameters

outputRangeGiven	If True, `given_y_min` and `given_y_min` and `given_y_max` are used as the output range. Otherwise, the implementation computes the output range.

public QuantizedInstanceNorm.Options varianceEpsilon (Float varianceEpsilon)

Parameters

varianceEpsilon	A small float number to avoid dividing by 0.