tensorflow:: ops:: Dequantize
#include <array_ops.h>
Dequantize the 'input' tensor into a float or bfloat16 Tensor.
Summary
[min_range, max_range] are scalar floats that specify the range for the output. 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))
range(T) = numeric_limits::max() - numeric_limits::min()
MIN_COMBINED Mode Example
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)
If the mode is SCALED
, dequantization is performed by multiplying each input value by a scaling_factor. (Thus an input of 0 always maps to 0.0).
The scaling_factor is determined from min_range
, max_range
, and narrow_range
in a way that is compatible with QuantizeAndDequantize{V2|V3}
and QuantizeV2
, using the following algorithm:
const int min_expected_T = std::numeric_limits::min() + (narrow_range ? 1 : 0); const int max_expected_T = std::numeric_limits ::max(); const float max_expected_T = std::numeric_limits ::max();
const float scale_factor = (std::numeric_limits::min() == 0) ? (max_range / max_expected_T) : std::max(min_range / min_expected_T, max_range / max_expected_T);
Args:
- 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.
Optional attributes (see Attrs
):
- dtype: Type of the output tensor. Currently Dequantize supports float and bfloat16. If 'dtype' is 'bfloat16', it only supports 'MIN_COMBINED' mode.
Returns:
Output
: The output tensor.
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 |
|
---|---|
operation
|
|
output
|
Public functions |
|
---|---|
node() const
|
::tensorflow::Node *
|
operator::tensorflow::Input() const
|
|
operator::tensorflow::Output() const
|
|
Public static functions |
|
---|---|
Axis(int64 x)
|
|
Dtype(DataType x)
|
|
Mode(StringPiece x)
|
|
NarrowRange(bool x)
|
Structs |
|
---|---|
tensorflow:: |
Optional attribute setters for Dequantize. |
Public attributes
operation
Operation operation
output
::tensorflow::Output output
Public functions
Dequantize
Dequantize( const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input min_range, ::tensorflow::Input max_range )
Dequantize
Dequantize( const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input min_range, ::tensorflow::Input max_range, const Dequantize::Attrs & attrs )
node
::tensorflow::Node * node() const
operator::tensorflow::Input
operator::tensorflow::Input() const
operator::tensorflow::Output
operator::tensorflow::Output() const
Public static functions
Axis
Attrs Axis( int64 x )
Dtype
Attrs Dtype( DataType x )
Mode
Attrs Mode( StringPiece x )
NarrowRange
Attrs NarrowRange( bool x )