Dequantize the 'input' tensor into a float or bfloat16 Tensor.
[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))
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<double>(input) - lowest_quantized;
result = range_min + ((input - numeric_limits<T>::min()) * range_scale)
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<T>::min() +
(narrow_range ? 1 : 0);
const int max_expected_T = std::numeric_limits<T>::max();
const float max_expected_T = std::numeric_limits<float>::max();
const float scale_factor =
(std::numeric_limits<T>::min() == 0) ? (max_range / max_expected_T)
: std::max(min_range / min_expected_T,
max_range / max_expected_T);
Nested Classes
class | Dequantize.Options | Optional attributes for Dequantize
|
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
Output<U> |
asOutput()
Returns the symbolic handle of the tensor.
|
static Dequantize.Options |
axis(Long axis)
|
static <U extends TNumber> Dequantize<U> | |
static Dequantize<TFloat32> | |
static Dequantize.Options |
mode(String mode)
|
static Dequantize.Options |
narrowRange(Boolean narrowRange)
|
Output<U> |
output()
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public Output<U> asOutput ()
Returns the symbolic handle of the tensor.
Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
public static Dequantize<U> create (Scope scope, Operand<? extends TType> input, Operand<TFloat32> minRange, Operand<TFloat32> maxRange, Class<U> dtype, Options... options)
Factory method to create a class wrapping a new Dequantize operation.
Parameters
scope | current scope |
---|---|
minRange | The minimum scalar value possibly produced for the input. |
maxRange | The maximum scalar value possibly produced for the input. |
dtype | Type of the output tensor. Currently Dequantize supports float and bfloat16. If 'dtype' is 'bfloat16', it only supports 'MIN_COMBINED' mode. |
options | carries optional attributes values |
Returns
- a new instance of Dequantize
public static Dequantize<TFloat32> create (Scope scope, Operand<? extends TType> input, Operand<TFloat32> minRange, Operand<TFloat32> maxRange, Options... options)
Factory method to create a class wrapping a new Dequantize operation using default output types.
Parameters
scope | current scope |
---|---|
minRange | The minimum scalar value possibly produced for the input. |
maxRange | The maximum scalar value possibly produced for the input. |
options | carries optional attributes values |
Returns
- a new instance of Dequantize