org.bytedeco.onnxruntime

Class Float16_t

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.onnxruntime.Float16_t

All Implemented Interfaces:

AutoCloseable

@Namespace(value="Ort")
 @Properties(inherit=onnxruntime.class)
public class Float16_t
extends Pointer

\brief IEEE 754 half-precision floating point data type \details This struct is used for converting float to float16 and back so the user could feed inputs and fetch outputs using these type. The size of the structure should align with uint16_t and one can freely cast uint16_t buffers to/from Ort::Float16_t to feed and retrieve data.

 {.unparsed}
 // This example demonstrates conversion from float to float16
 constexpr float values[] = {1.f, 2.f, 3.f, 4.f, 5.f};
 std::vector<Ort::Float16_t> fp16_values;
 fp16_values.reserve(std::size(values));
 std::transform(std::begin(values), std::end(values), std::back_inserter(fp16_values),
     [](float value) { return Ort::Float16_t(value); });

 

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
Float16_t() Default constructor
Float16_t(float v) __ctor from float.
Float16_t(Pointer p) Pointer cast constructor.

Method Summary

Modifier and Type	Method and Description
float	asFloat() User defined conversion operator.
static Float16_t	FromBits(short v) Explicit conversion to uint16_t representation of float16.
float	ToFloat() Converts float16 to float float representation of float16 value

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, trimMemory, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

Float16_t

public Float16_t(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

Float16_t

public Float16_t()

Default constructor

Float16_t

public Float16_t(float v)

__ctor from float. Float is converted into float16 16-bit representation.

float value

Method Detail

FromBits

@Const
 @ByVal
 @NoException(value=true)
public static Float16_t FromBits(@Cast(value="uint16_t")
                                                                          short v)

Explicit conversion to uint16_t representation of float16.

uint16_t bit representation of float16 new instance of Float16_t

ToFloat

@NoException(value=true)
public float ToFloat()

Converts float16 to float

float representation of float16 value

asFloat

@Name(value="operator float")
 @NoException(value=true)
public float asFloat()

User defined conversion operator. Converts Float16_t to float.