tensorflow::ops::Dequantize::Attrs

#include <array_ops.h>

Optional attribute setters for Dequantize.

Summary

Public attributes

axis_ = -1
int64
dtype_ = DT_FLOAT
DataType
mode_ = "MIN_COMBINED"
StringPiece
narrow_range_ = false
bool

Public functions

Axis(int64 x)
TF_MUST_USE_RESULT Attrs
Defaults to -1.
Dtype(DataType x)
TF_MUST_USE_RESULT Attrs
Type of the output tensor.
Mode(StringPiece x)
TF_MUST_USE_RESULT Attrs
Defaults to "MIN_COMBINED".
NarrowRange(bool x)
TF_MUST_USE_RESULT Attrs
Defaults to false.

Public attributes

axis_

int64 tensorflow::ops::Dequantize::Attrs::axis_ = -1

dtype_

DataType tensorflow::ops::Dequantize::Attrs::dtype_ = DT_FLOAT

mode_

StringPiece tensorflow::ops::Dequantize::Attrs::mode_ = "MIN_COMBINED"

narrow_range_

bool tensorflow::ops::Dequantize::Attrs::narrow_range_ = false

Public functions

Axis

TF_MUST_USE_RESULT Attrs tensorflow::ops::Dequantize::Attrs::Axis(
  int64 x
)

Defaults to -1.

Dtype

TF_MUST_USE_RESULT Attrs tensorflow::ops::Dequantize::Attrs::Dtype(
  DataType x
)

Type of the output tensor.

Currently Dequantize supports float and bfloat16. If 'dtype' is 'bfloat16', it only supports 'MIN_COMBINED' mode.

Defaults to DT_FLOAT

Mode

TF_MUST_USE_RESULT Attrs tensorflow::ops::Dequantize::Attrs::Mode(
  StringPiece x
)

Defaults to "MIN_COMBINED".

NarrowRange

TF_MUST_USE_RESULT Attrs tensorflow::ops::Dequantize::Attrs::NarrowRange(
  bool x
)

Defaults to false.