UniformDequantize

public final class UniformDequantize

Perform dequantization on the quantized Tensor `input`.

Given quantized `input` which was quantized using `scales` and `zero_points`, performs dequantization using the formula: dequantized_data = (quantized_data - zero_point) * scale.

Nested Classes

class UniformDequantize.Options Optional attributes for UniformDequantize  

Public Methods

Output<U>
asOutput()
Returns the symbolic handle of a tensor.
static <U extends Number, T> UniformDequantize<U>
create(Scope scope, Operand<T> input, Operand<Float> scales, Operand<Integer> zeroPoints, Class<U> Tout, Long quantizationMinVal, Long quantizationMaxVal, Options... options)
Factory method to create a class wrapping a new UniformDequantize operation.
Output<U>
output()
The output dequantized Tensor of Tout, whose shape is same as input.
static UniformDequantize.Options
quantizationAxis(Long quantizationAxis)

Inherited Methods

Public Methods

public Output<U> asOutput ()

Returns the symbolic handle of a 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 UniformDequantize<U> create (Scope scope, Operand<T> input, Operand<Float> scales, Operand<Integer> zeroPoints, Class<U> Tout, Long quantizationMinVal, Long quantizationMaxVal, Options... options)

Factory method to create a class wrapping a new UniformDequantize operation.

Parameters
scope current scope
input Must be a Tensor of Tin.
scales The float value(s) used as scale(s) when quantizing original data that input represents. Must be a scalar Tensor if quantization_axis is -1 (per-tensor quantization), otherwise 1D Tensor of size (input.dim_size(quantization_axis),) (per-axis quantization).
zeroPoints The int32 value(s) used as zero_point(s) when quantizing original data that input represents. Same shape condition as scales.
Tout The type of output Tensor. A tf.DType from: tf.qint8, tf.qint32
quantizationMinVal The quantization min value that was used when input was quantized. The purpose of this attribute is typically (but not limited to) to indicate narrow range, where this is set to: `(Tin lowest) + 1` if narrow range, and `(Tin lowest)` otherwise. For example, if Tin is qint8, this is set to -127 if narrow range quantized or -128 if not.
quantizationMaxVal The quantization max value that was used when input was quantized. The purpose of this attribute is typically (but not limited to) indicate narrow range, where this is set to: `(Tout max)` for both narrow range and not narrow range. For example, if Tin is qint8, this is set to 127.
options carries optional attributes values
Returns
  • a new instance of UniformDequantize

public Output<U> output ()

The output dequantized Tensor of Tout, whose shape is same as input.

public static UniformDequantize.Options quantizationAxis (Long quantizationAxis)

Parameters
quantizationAxis Indicates the dimension index of the tensor where per-axis quantization is applied for the slices along that dimension. If set to -1 (default), this indicates per-tensor quantization. Otherwise, it must be set within range [0, input.dims()).