tensorflow:: ops:: Dequantize:: Attrs


   #include <array_ops.h>

Optional attribute setters for Dequantize .

Summary

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.

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

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

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

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

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

Defaults to -1.

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

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

Defaults to "MIN_COMBINED".

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

Defaults to false.