bitstream::half_precision Class Reference

Class for quantizing single-precision floats into half-precision. More...

#include <half_precision.h>

Static Public Member Functions
static uint16_t	quantize (float value) noexcept
static float	dequantize (uint16_t value) noexcept

Detailed Description

Class for quantizing single-precision floats into half-precision.

Member Function Documentation

dequantize()

static float bitstream::half_precision::dequantize ( uint16_t  value )

inlinestaticnoexcept

quantize()

static uint16_t bitstream::half_precision::quantize ( float  value )

inlinestaticnoexcept

---

The documentation for this class was generated from the following file:

• include/bitstream/quantization/half_precision.h