tensorflow::ops::QuantizedMatMul::Attrs
#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_QUINT8Toutput_
DataType tensorflow::ops::QuantizedMatMul::Attrs::Toutput_ = DT_QINT32transpose_a_
bool tensorflow::ops::QuantizedMatMul::Attrs::transpose_a_ = falsetranspose_b_
bool tensorflow::ops::QuantizedMatMul::Attrs::transpose_b_ = falsePublic 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
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 4.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/cc/struct/tensorflow/ops/quantized-mat-mul/attrs