#include <array_ops.h>

Dequantize the 'input' tensor into a float Tensor.


[min_range, max_range] are scalar floats that specify the range for the 'input' data. The 'mode' attribute controls exactly which calculations are used to convert the float values to their quantized equivalents.

In 'MIN_COMBINED' mode, each value of the tensor will undergo the following:

if T == qint8, in[i] += (range(T) + 1)/ 2.0
out[i] = min_range + (in[i]* (max_range - min_range) / range(T))
here range(T) = numeric_limits::max() - numeric_limits::min()


If the input comes from a QuantizedRelu6, the output type is quint8 (range of 0-255) but the possible range of QuantizedRelu6 is 0-6. The min_range and max_range values are therefore 0.0 and 6.0. Dequantize on quint8 will take each value, cast to float, and multiply by 6 / 255. Note that if quantizedtype is qint8, the operation will additionally add each value by 128 prior to casting.

If the mode is 'MIN_FIRST', then this approach is used:

num_discrete_values = 1 << (# of bits in T)
range_adjust = num_discrete_values / (num_discrete_values - 1)
range = (range_max - range_min) * range_adjust
range_scale = range / num_discrete_values
const double offset_input = static_cast(input) - lowest_quantized;
result = range_min + ((input - numeric_limits::min()) * range_scale)

SCALED mode Example

SCALED mode matches the quantization approach used in QuantizeAndDequantize{V2|V3}.

If the mode is SCALED, we do not use the full range of the output type, choosing to elide the lowest possible value for symmetry (e.g., output range is -127 to 127, not -128 to 127 for signed 8 bit quantization), so that 0.0 maps to 0.

We first find the range of values in our tensor. The range we use is always centered on 0, so we find m such that

  m = max(abs(input_min), abs(input_max))

Our input tensor range is then [-m, m].

Next, we choose our fixed-point quantization buckets, [min_fixed, max_fixed]. If T is signed, this is

  num_bits = sizeof(T) * 8
  [min_fixed, max_fixed] =
      [-(1 << (num_bits - 1) - 1), (1 << (num_bits - 1)) - 1]

Otherwise, if T is unsigned, the fixed-point range is

  [min_fixed, max_fixed] = [0, (1 << num_bits) - 1]

From this we compute our scaling factor, s:

  s = (2 * m) / (max_fixed - min_fixed)

Now we can dequantize the elements of our tensor:

result = input * s


  • scope: A Scope object
  • min_range: The minimum scalar value possibly produced for the input.
  • max_range: The maximum scalar value possibly produced for the input.


Constructors and Destructors

Dequantize(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input min_range, ::tensorflow::Input max_range)
Dequantize(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input min_range, ::tensorflow::Input max_range, const Dequantize::Attrs & attrs)

Public attributes


Public functions

node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions

Mode(StringPiece x)



Optional attribute setters for Dequantize.

Public attributes


::tensorflow::Output output

Public functions


  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input min_range,
  ::tensorflow::Input max_range


  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input min_range,
  ::tensorflow::Input max_range,
  const Dequantize::Attrs & attrs


::tensorflow::Node * node() const 


 operator::tensorflow::Input() const 


 operator::tensorflow::Output() const 

Public static functions


Attrs Mode(
  StringPiece x