Class Tensor<T>

Represents data in a multidimensional array-like structure.

Ownership and lifetime:

• Disposed needs to be called on the main thread.
• Ownership is always to the owner of the object.

Data Representation:

• TensorShape represents the data layout of the tensor
• Data is held by a tensorData (ITensorData) which can be on a given backend
• Data is stored in a flattened row major format
• Data can be pending (ie computation is being done in parallel)
  • call CompleteAllPendingOperations for a blocking call to finish computing the tensor's data Data can be in a non readable type (GPU/NPU)
  • Call CompleteAllPendingOperations to finish computing the tensor's data
  • Call ReadbackAndClone or ReadBackAndCloneAsync to allow reading the tensor's data

Data manipulation

• ToReadOnlyArray returns a copy of the tensor's data
• dataOnBackend can be manipulated directly to avoid a unnecessary copy see ComputeTensorData/CPUTensorData for info

Inheritance

object

Tensor

Tensor<T>

Implements

IDisposable

Inherited Members

Tensor.dataType

Tensor.count

Tensor.shape

Tensor.dataOnBackend

Tensor.backendType

Tensor.AdoptTensorData(ITensorData, bool)

Tensor.ReleaseTensorData()

Tensor.IsReadbackRequestDone()

Tensor.ReadbackRequest()

Tensor.CompleteAllPendingOperations()

Tensor.Dispose()

Tensor.ToString()

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

Namespace: Unity.Sentis

Assembly: Unity.Sentis.dll

Syntax

public class Tensor<T> : Tensor, IDisposable where T : unmanaged

Type Parameters

Name	Description
T

Constructors

Tensor(TensorShape, bool)

Initializes and returns a tensor with the specified shape.

Declaration

public Tensor(TensorShape shape, bool clearOnInit = true)

Parameters

Type	Name	Description
TensorShape	shape	The shape of the tensor.
bool	clearOnInit	Whether to clear the tensor data to zeros.

Tensor(TensorShape, NativeArray<T>, int)

Initializes and returns a tensor with specified shape and a native T array of srcData data.

Declaration

public Tensor(TensorShape shape, NativeArray<T> srcData, int dataStartIndex = 0)

Parameters

Type	Name	Description
TensorShape	shape	The shape of the tensor.
NativeArray<T>	srcData	The data elements of the tensor.
int	dataStartIndex	The index of the first tensor element in the srcData array.

Tensor(TensorShape, ITensorData)

Initializes and returns a Tensor with the specified shape, an ITensorData data.

Declaration

public Tensor(TensorShape shape, ITensorData data)

Parameters

Type	Name	Description
TensorShape	shape	The shape of the tensor.
ITensorData	data	The optional tensor data.

Tensor(TensorShape, T[], int)

Initializes and returns a tensor with specified shape and a T[] array of srcData data.

Declaration

public Tensor(TensorShape shape, T[] srcData, int dataStartIndex = 0)

Parameters

Type	Name	Description
TensorShape	shape	The shape of the tensor.
T[]	srcData	The data elements of the tensor.
int	dataStartIndex	The index of the first tensor element in the srcData array.

Properties

this[int]

Returns the tensor element at offset d0.

Declaration

public T this[int d0] { get; set; }

Parameters

Type	Name	Description
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int]

Returns the tensor element at offset (d1, d0), which is position d1 * stride0 + d0.

Declaration

public T this[int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int, int]

Returns the tensor element at offset (d2, d1, d0), which is position d2 * stride1 + d1 * stride0 + d0.

Declaration

public T this[int d2, int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d2	Axis 2.
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int, int, int]

Returns the tensor element at offset (d3, d2, d1, d0), which is position d3 * stride2 + d2 * stride1 + d1 * stride0 + d0 in this tensor.

Declaration

public T this[int d3, int d2, int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d3	Axis 3.
int	d2	Axis 2.
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int, int, int, int]

Returns the tensor element at offset (d4, d3, d2, d1, d0), which is position d4 * stride3 + d3 * stride2 + d2 * stride1 + d1 * stride0 + d0.

Declaration

public T this[int d4, int d3, int d2, int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d4	Axis 4.
int	d3	Axis 3.
int	d2	Axis 2.
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int, int, int, int, int]

Returns the tensor element at offset (d5, d4, d3, d2, d1, d0), which is position d5 * stride4 + d4 * stride3 + d3 * stride2 + d2 * stride1 + d1 * stride0 + d0.

Declaration

public T this[int d5, int d4, int d3, int d2, int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d5	Axis 5.
int	d4	Axis 4.
int	d3	Axis 3.
int	d2	Axis 2.
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int, int, int, int, int, int]

Returns the tensor element at offset (d6, d5, d4, d3, d2, d1, d0), which is position d6 * stride5 + d5 * stride4 + d4 * stride3 + d3 * stride2 + d2 * stride1 + d1 * stride0 + d0.

Declaration

public T this[int d6, int d5, int d4, int d3, int d2, int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d6	Axis 6.
int	d5	Axis 5.
int	d4	Axis 4.
int	d3	Axis 3.
int	d2	Axis 2.
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

this[int, int, int, int, int, int, int, int]

Returns the tensor element at offset (d7, d6, d5, d4, d3, d2, d1, d0), which is position d7 * stride6 + d6 * stride5 + d5 * stride4 + d4 * stride3 + d3 * stride2 + d2 * stride1 + d1 * stride0 + d0.

Declaration

public T this[int d7, int d6, int d5, int d4, int d3, int d2, int d1, int d0] { get; set; }

Parameters

Type	Name	Description
int	d7	Axis 7.
int	d6	Axis 6.
int	d5	Axis 5.
int	d4	Axis 4.
int	d3	Axis 3.
int	d2	Axis 2.
int	d1	Axis 1.
int	d0	Axis 0.

Property Value

Type	Description
T

Methods

AsReadOnlyNativeArray()

Exposes the linear memory data representation of this tensor as a readonly NativeArray.

Declaration

public NativeArray<T>.ReadOnly AsReadOnlyNativeArray()

Returns

Type	Description
NativeArray<T>.ReadOnly	NativeArray of tensor data.

AsReadOnlySpan()

Exposes the linear memory data representation of this tensor as a ReadOnlySpan.

Declaration

public ReadOnlySpan<T> AsReadOnlySpan()

Returns

Type	Description
ReadOnlySpan<T>	Span of tensor data.

DownloadToArray()

Blocking Call to return a copy of linear memory representation of the data in this tensor.

the returned array is a deepcopy of the tensor, the caller of this methods is now responsible for it. If you modify the contents of the returned array, it will not modify the underlying tensor

Declaration

public T[] DownloadToArray()

Returns

Type	Description
T[]	T array copy of tensor data.

DownloadToNativeArray()

Blocking Call to return a copy of linear memory representation of the data in this tensor.

the returned native array is a deepcopy of the tensor, the caller of this methods is now responsible for it. If you modify the contents of the returned native array, it will not modify the underlying tensor

Declaration

public NativeArray<T> DownloadToNativeArray()

Returns

Type	Description
NativeArray<T>	T native array copy of tensor data.

ReadbackAndClone()

Blocking download task of the internal data.

Declaration

public Tensor<T> ReadbackAndClone()

Returns

Type	Description
Tensor<T>	returns cpu copy of the tensor.

Reshape(TensorShape)

Changes the shape of a tensor without changing the backing data.

The new shape must fit in the allocated backend tensor data, and the data cannot be on the GPUPixel backend.

Declaration

public override void Reshape(TensorShape shape)

Parameters

Type	Name	Description
TensorShape	shape	The new shape for the tensor.

Overrides

Tensor.Reshape(TensorShape)

Upload(NativeArray<T>)

Uploads a contiguous block of tensor data to internal storage.

Declaration

public void Upload(NativeArray<T> srcData)

Parameters

Type	Name	Description
NativeArray<T>	srcData	The data to upload.

Upload(T[])

Uploads a contiguous block of tensor data to internal storage.

Declaration

public void Upload(T[] srcData)

Parameters

Type	Name	Description
T[]	srcData	The data to upload.

Implements

IDisposable