tensorflow :: operaciones :: FakeQuantWithMinMaxArgsGradient
#include <array_ops.h>
Calcule gradientes para una operación FakeQuantWithMinMaxArgs .
Resumen
Argumentos:
- alcance: un objeto de alcance
- gradients: gradientes retropropagados por encima de la operación FakeQuantWithMinMaxArgs .
- entradas: valores pasados como entradas a la operación FakeQuantWithMinMaxArgs .
Devoluciones:
-
Output
: gradientes retropropagados debajo de la operación FakeQuantWithMinMaxArgs :gradients * (inputs >= min && inputs <= max)
.
Constructores y Destructores | |
---|---|
FakeQuantWithMinMaxArgsGradient (const :: tensorflow::Scope & scope, :: tensorflow::Input gradients, :: tensorflow::Input inputs) | |
FakeQuantWithMinMaxArgsGradient (const :: tensorflow::Scope & scope, :: tensorflow::Input gradients, :: tensorflow::Input inputs, const FakeQuantWithMinMaxArgsGradient::Attrs & attrs) |
Atributos públicos | |
---|---|
backprops | |
operation |
Funciones publicas | |
---|---|
node () const | ::tensorflow::Node * |
operator::tensorflow::Input () const | |
operator::tensorflow::Output () const |
Funciones estáticas públicas | |
---|---|
Max (float x) | |
Min (float x) | |
NarrowRange (bool x) | |
NumBits (int64 x) |
Estructuras | |
---|---|
tensorflow :: ops :: FakeQuantWithMinMaxArgsGradient :: Attrs | Establecedores de atributos opcionales para FakeQuantWithMinMaxArgsGradient . |
Atributos públicos
apoyos
::tensorflow::Output backprops
operación
Operation operation
Funciones publicas
FakeQuantWithMinMaxArgsGradient
FakeQuantWithMinMaxArgsGradient( const ::tensorflow::Scope & scope, ::tensorflow::Input gradients, ::tensorflow::Input inputs )
FakeQuantWithMinMaxArgsGradient
FakeQuantWithMinMaxArgsGradient( const ::tensorflow::Scope & scope, ::tensorflow::Input gradients, ::tensorflow::Input inputs, const FakeQuantWithMinMaxArgsGradient::Attrs & attrs )
nodo
::tensorflow::Node * node() const
operador :: tensorflow :: Entrada
operator::tensorflow::Input() const
operador :: tensorflow :: Salida
operator::tensorflow::Output() const
Funciones estáticas públicas
Max
Attrs Max( float x )
Min
Attrs Min( float x )
Rango estrecho
Attrs NarrowRange( bool x )
NumBits
Attrs NumBits( int64 x )