Package ai.onnxruntime

Class OnnxSparseTensor

java.lang.Object

ai.onnxruntime.OnnxTensorLike

ai.onnxruntime.OnnxSparseTensor

All Implemented Interfaces:

OnnxValue, java.lang.AutoCloseable

public final class OnnxSparseTensor
extends OnnxTensorLike

A Java object wrapping an OnnxSparseTensor.

Sparse tensors support a variety of formats, and the getValue() method returns a different static inner class representing each type.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	OnnxSparseTensor.BlockSparseTensor	The Java side representation of a block sparse tensor.
static class	OnnxSparseTensor.COOTensor	The Java side representation of a COO sparse tensor.
static class	OnnxSparseTensor.CSRCTensor	The Java side representation of a CSRC sparse tensor.
static class	OnnxSparseTensor.SparseTensor<T extends java.nio.Buffer>	Abstract base class for Java sparse tensors
static class	OnnxSparseTensor.SparseTensorType	The type of the sparse tensor.

Nested classes/interfaces inherited from interface ai.onnxruntime.OnnxValue

OnnxValue.OnnxValueType

Field Summary

Fields inherited from class ai.onnxruntime.OnnxTensorLike

allocatorHandle, closed, info, nativeHandle

Method Summary

Modifier and Type	Method	Description
void	close()	Closes the OnnxValue, freeing its native memory.
static <T extends java.nio.Buffer> OnnxSparseTensor	createSparseTensor(OrtEnvironment env, OnnxSparseTensor.SparseTensor<T> tensor)	Creates a Sparse Tensor in ORT from the Java side representation.
java.nio.Buffer	getIndicesBuffer()	Gets a copy of the indices.
long[]	getIndicesShape()	Gets the shape of the (outer) indices.
java.nio.LongBuffer	getInnerIndicesBuffer()	Gets a copy of the inner indices in a CSRC sparse tensor.
long[]	getInnerIndicesShape()	Gets the shape of the inner indices in a CSRC sparse tensor.
OnnxSparseTensor.SparseTensorType	getSparseTensorType()	Returns the type of this OnnxSparseTensor.
OnnxValue.OnnxValueType	getType()	Gets the type of this OnnxValue.
OnnxSparseTensor.SparseTensor<? extends java.nio.Buffer>	getValue()	Returns the value as a Java object copying it out of the native heap.
java.nio.Buffer	getValuesBuffer()	Gets a copy of the data buffer.
long[]	getValuesShape()	Gets the shape of the values.

Methods inherited from class ai.onnxruntime.OnnxTensorLike

checkClosed, getInfo, isClosed

Methods inherited from class java.lang.Object

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

Method Detail

createSparseTensor

public static <T extends java.nio.Buffer> OnnxSparseTensor createSparseTensor(OrtEnvironment env,
                                                                              OnnxSparseTensor.SparseTensor<T> tensor)
                                                                       throws OrtException

Creates a Sparse Tensor in ORT from the Java side representation.

Type Parameters:

T - The buffer type.

Parameters:

env - The OrtEnvironment.

tensor - The Java side representation.

Returns:

The sparse tensor in ORT.

Throws:

OrtException - If the tensor could not be created or was invalid.

getType

public OnnxValue.OnnxValueType getType()

Description copied from interface: OnnxValue

Gets the type of this OnnxValue.

Returns:

The value type.

getValue

public OnnxSparseTensor.SparseTensor<? extends java.nio.Buffer> getValue()
                                                                  throws OrtException

Description copied from interface: OnnxValue

Returns the value as a Java object copying it out of the native heap. This operation can be quite slow for high dimensional tensors, where you should prefer OnnxTensor.getByteBuffer() etc.

Overridden by the subclasses with a more specific type if available.

Returns:

The value.

Throws:

OrtException - If an error occurred reading the value.

close

public void close()

Description copied from interface: OnnxValue

Closes the OnnxValue, freeing its native memory.

getSparseTensorType

public OnnxSparseTensor.SparseTensorType getSparseTensorType()

Returns the type of this OnnxSparseTensor.

Returns:

The sparsity type.

getIndicesBuffer

public java.nio.Buffer getIndicesBuffer()

Gets a copy of the indices.

These are the outer indices if it's a CSRC sparse tensor.

It's a LongBuffer if COO or CSRC, and IntBuffer if Block Sparse.

Returns:

The indices.

getInnerIndicesBuffer

public java.nio.LongBuffer getInnerIndicesBuffer()

Gets a copy of the inner indices in a CSRC sparse tensor.

Throws IllegalStateException if called on a different sparse tensor type.

Returns:

The inner indices.

getValuesBuffer

public java.nio.Buffer getValuesBuffer()

Gets a copy of the data buffer.

As with OnnxTensor fp16 values are upcast into fp32 and returned as a FloatBuffer.

Returns:

The data buffer.

getIndicesShape

public long[] getIndicesShape()

Gets the shape of the (outer) indices.

Returns:

The indices shape.

getInnerIndicesShape

public long[] getInnerIndicesShape()

Gets the shape of the inner indices in a CSRC sparse tensor.

Returns:

The indices shape.

getValuesShape

public long[] getValuesShape()

Gets the shape of the values.

Returns:

The values shape.