org.tensorflow.lite

Class Tensor.QuantizationParams

java.lang.Object

org.tensorflow.lite.Tensor.QuantizationParams

Enclosing class:

Tensor

public static class Tensor.QuantizationParams
extends java.lang.Object

Quantization parameters that corresponds to the table, QuantizationParameters, in the TFLite Model schema file.

Since per-channel quantization does not apply to input and output tensors, scale and zero_point are both single values instead of arrays.

For tensor that are not quantized, the values of scale and zero_point are both 0.

Given a quantized value q, the corresponding float value f should be:
f = scale * (q - zero_point)

Constructor Summary

Constructors

Constructor and Description
QuantizationParams(float scale, int zeroPoint) Creates a Tensor.QuantizationParams with scale and zero_point.

Method Summary

Modifier and Type	Method and Description
float	getScale() Returns the scale value.
int	getZeroPoint() Returns the zero point value.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

QuantizationParams

public QuantizationParams(float scale,
                          int zeroPoint)

Creates a Tensor.QuantizationParams with scale and zero_point.

Parameters:

scale - The scale value used in quantization.

zeroPoint - The zero point value used in quantization.

Method Detail

getScale

public float getScale()

Returns the scale value.

getZeroPoint

public int getZeroPoint()

Returns the zero point value.