tensorflow::
#include <math_ops.h>
Optional attribute setters for QuantizedMatMul.
Summary
Public attributes |
|
|---|---|
Tactivation_ = DT_QUINT8
|
DataType
|
Toutput_ = DT_QINT32
|
DataType
|
transpose_a_ = false
|
bool
|
transpose_b_ = false
|
bool
|
Public functions |
|
|---|---|
Tactivation(DataType x)
|
TF_MUST_USE_RESULT Attrs
The type of output produced by activation function following this operation.
|
Toutput(DataType x)
|
TF_MUST_USE_RESULT Attrs
Defaults to DT_QINT32.
|
TransposeA(bool x)
|
TF_MUST_USE_RESULT Attrs
If true,
a is transposed before multiplication. |
TransposeB(bool x)
|
TF_MUST_USE_RESULT Attrs
If true,
b is transposed before multiplication. |
Public attributes
Tactivation_
DataType tensorflow::ops::QuantizedMatMul::Attrs::Tactivation_ = DT_QUINT8
Toutput_
DataType tensorflow::ops::QuantizedMatMul::Attrs::Toutput_ = DT_QINT32
transpose_a_
bool tensorflow::ops::QuantizedMatMul::Attrs::transpose_a_ = false
transpose_b_
bool tensorflow::ops::QuantizedMatMul::Attrs::transpose_b_ = false
Public functions
Tactivation
TF_MUST_USE_RESULT Attrs tensorflow::ops::QuantizedMatMul::Attrs::Tactivation( DataType x )
The type of output produced by activation function following this operation.
Defaults to DT_QUINT8
Toutput
TF_MUST_USE_RESULT Attrs tensorflow::ops::QuantizedMatMul::Attrs::Toutput( DataType x )
Defaults to DT_QINT32.
TransposeA
TF_MUST_USE_RESULT Attrs tensorflow::ops::QuantizedMatMul::Attrs::TransposeA( bool x )
If true, a is transposed before multiplication.
Defaults to false
TransposeB
TF_MUST_USE_RESULT Attrs tensorflow::ops::QuantizedMatMul::Attrs::TransposeB( bool x )
If true, b is transposed before multiplication.
Defaults to false