public static class
MetadataExtractor.QuantizationParams
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)
Public Constructors
|
QuantizationParams(float scale, int zeroPoint)
|
Public Methods
| float |
getScale()
Returns the scale value.
|
| int |
getZeroPoint()
Returns the zero point value.
|
Inherited Methods
Public Constructors
public QuantizationParams (float scale, int zeroPoint)
Creates a MetadataExtractor.QuantizationParams with scale and zero_point.
Parameters
| scale | The scale value used in quantization. |
|---|---|
| zeroPoint | The zero point value used in quantization. |
Public Methods
public float getScale ()
Returns the scale value.
public int getZeroPoint ()
Returns the zero point value.