Package ai.onnxruntime

Class TensorInfo

java.lang.Object

ai.onnxruntime.TensorInfo

All Implemented Interfaces:

ValueInfo

public class TensorInfo
extends java.lang.Object
implements ValueInfo

Describes an OnnxTensor, including it's size, shape and element type.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	TensorInfo.OnnxTensorType	The native element types supported by the ONNX runtime.

Field Summary

Fields

Modifier and Type	Field	Description
static int	MAX_DIMENSIONS	Maximum number of dimensions supported by the Java interface methods.
TensorInfo.OnnxTensorType	onnxType	The native type of this tensor.
OnnxJavaType	type	The Java type of this tensor.

Method Summary

Modifier and Type	Method	Description
static TensorInfo	constructFromBuffer(java.nio.Buffer buffer, long[] shape, OnnxJavaType type)	Constructs a TensorInfo from the supplied byte buffer.
static TensorInfo	constructFromJavaArray(java.lang.Object obj)	Constructs a TensorInfo from the supplied multidimensional Java array, used to allocate the appropriate amount of native memory.
static <T extends java.nio.Buffer> TensorInfo	constructFromSparseTensor(OnnxSparseTensor.SparseTensor<T> tensor)	Constructs a TensorInfo from the supplied OnnxSparseTensor.SparseTensor.
java.lang.String[]	getDimensionNames()	Get a copy of the tensor's named dimensions.
long	getNumElements()	Returns the number of elements in this tensor.
long[]	getShape()	Get a copy of the tensor's shape.
boolean	isScalar()	Returns true if the shape represents a scalar value (i.e.
java.lang.Object	makeCarrier()	Constructs an array the right shape and type to hold this tensor.
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Field Detail

MAX_DIMENSIONS

public static final int MAX_DIMENSIONS

Maximum number of dimensions supported by the Java interface methods.

See Also:

Constant Field Values

type

public final OnnxJavaType type

The Java type of this tensor.

onnxType

public final TensorInfo.OnnxTensorType onnxType

The native type of this tensor.

Method Detail

getShape

public long[] getShape()

Get a copy of the tensor's shape.

Returns:

A copy of the tensor's shape.

getDimensionNames

public java.lang.String[] getDimensionNames()

Get a copy of the tensor's named dimensions.

Returns:

A copof the tensor's named dimensions.

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

isScalar

public boolean isScalar()

Returns true if the shape represents a scalar value (i.e. it has zero dimensions).

Returns:

True if the shape is a scalar.

getNumElements

public long getNumElements()

Returns the number of elements in this tensor.

If the returned value is negative, then this tensor info refers to an input or output placeholder which has symbolic dimensions, and the element count cannot be computed without specifying the symbolic dimensions.

Returns:

The number of elements.

makeCarrier

public java.lang.Object makeCarrier()
                             throws OrtException

Constructs an array the right shape and type to hold this tensor.

Note for String tensors, this carrier is a single dimensional array with enough space for all elements as that's the expected format of the native code. It can be reshaped to the correct shape using OrtUtil.reshape(String[],long[]).

For fp16 and bf16 tensors the output carrier type is float, and so this method produces multidimensional float arrays.

Returns:

A multidimensional array of the appropriate primitive type (or String).

Throws:

OrtException - If the shape isn't representable in Java (i.e. if one of its indices is greater than an int).

constructFromJavaArray

public static TensorInfo constructFromJavaArray(java.lang.Object obj)
                                         throws OrtException

Constructs a TensorInfo from the supplied multidimensional Java array, used to allocate the appropriate amount of native memory.

Parameters:

obj - The object to inspect.

Returns:

A TensorInfo which can be used to make the right size Tensor.

Throws:

OrtException - If the supplied Object isn't an array, or is an invalid type.

constructFromBuffer

public static TensorInfo constructFromBuffer(java.nio.Buffer buffer,
                                             long[] shape,
                                             OnnxJavaType type)
                                      throws OrtException

Constructs a TensorInfo from the supplied byte buffer.

Parameters:

buffer - The buffer to inspect.

shape - The shape of the tensor.

type - The Java type.

Returns:

A TensorInfo for a tensor.

Throws:

OrtException - If the supplied buffer doesn't match the shape.

constructFromSparseTensor

public static <T extends java.nio.Buffer> TensorInfo constructFromSparseTensor(OnnxSparseTensor.SparseTensor<T> tensor)
                                                                        throws OrtException

Constructs a TensorInfo from the supplied OnnxSparseTensor.SparseTensor.

Type Parameters:

T - The buffer type.

Parameters:

tensor - The sparse tensor.

Returns:

A TensorInfo for a sparse tensor.

Throws:

OrtException - If the supplied tensor has too many elements for it's shape.