Class TensorFloat

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
- call CompleteOperationsAndDownloadAsync/ReadbackRequest for a non blocking call to finish computing the tensor's data Data can be in a non readable type (GPU/NPU)
- Call CompleteOperationsAndDownload to make the tensor readable (this will fetch the data on the backend and convert it to a readable format)
- CompleteOperationsAndDownload is a blocking call if called on its own. for a non blocking call, make sure that CompleteOperationsAndDownloadAsync/ReadbackRequest have been called previously you can check that with IsReadbackRequestDone

Data manipulation

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

Inheritance

object

Tensor

TensorFloat

Implements

IDisposable

Inherited Members

Tensor.shape

Tensor.dataOnBackend

Tensor.backendType

Tensor.Reshape(TensorShape)

Tensor.AttachToDevice(ITensorData)

Tensor.DetachFromDevice(bool)

Tensor.CompleteOperationsAndDownload()

Tensor.CompleteOperationsAndDownloadAsync()

Tensor.IsReadbackRequestDone()

Tensor.ReadbackRequest(Action<bool>)

Tensor.ReadbackRequestAsync()

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 TensorFloat : Tensor, IDisposable

Constructors

TensorFloat(float)

Initializes and returns a scalar tensor with the value of srcData.

Declaration

public TensorFloat(float srcData)

Parameters

Type	Name	Description
float	srcData	The data element of the tensor.

TensorFloat(TensorShape, float[], int)

Initializes and returns a tensor with specified shape and a float[] array of srcData data. Sentis reads srcData from dataStartIndex.

srcData.Length - dataStartIndex must be bigger than or equal to shape.length.

Declaration

public TensorFloat(TensorShape shape, float[] srcData, int dataStartIndex = 0)

Parameters

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

TensorFloat(TensorShape, NativeArray<float>, int)

Initializes and returns a tensor with specified shape and a native float array of srcData data. Sentis reads srcData from dataStartIndex.

srcData.Length - dataStartIndex must be bigger than or equal to shape.length.

Declaration

public TensorFloat(TensorShape shape, NativeArray<float> srcData, int dataStartIndex)

Parameters

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

TensorFloat(TensorShape, ITensorData)

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

Declaration

public TensorFloat(TensorShape shape, ITensorData data)

Parameters

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

Properties

this[int]

Returns the tensor element at offset d0.

Declaration

public float this[int d0] { get; set; }

Parameters

Type	Name	Description
int	d0	Axis 0.

Property Value

Type	Description
float

this[int, int]

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

Declaration

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

Parameters

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

Property Value

Type	Description
float

this[int, int, int]

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

Declaration

public float 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
float

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 float 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
float

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 float 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
float

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 float 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
float

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 float 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
float

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 float 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
float

count

The length of the tensor.

Declaration

public override int count { get; }

Property Value

Type	Description
int

Overrides

Tensor.count

dataType

The data type of the elements of the tensor.

Declaration

public override DataType dataType { get; }

Property Value

Type	Description
DataType

Overrides

Tensor.dataType

Methods

AllocNoData(TensorShape)

Initializes and returns a tensor with the specified shape and with no data.

Declaration

public static TensorFloat AllocNoData(TensorShape shape)

Parameters

Type	Name	Description
TensorShape	shape	The shape of the tensor.

Returns

Type	Description
TensorFloat	The instantiated empty tensor.

AllocZeros(TensorShape)

Initializes and returns a tensor with the specified shape and filled with 0.

Declaration

public static TensorFloat AllocZeros(TensorShape shape)

Parameters

Type	Name	Description
TensorShape	shape	The shape of the tensor.

Returns

Type	Description
TensorFloat	The instantiated zero tensor.

ToReadOnlyArray()

Returns 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 float[] ToReadOnlyArray()

Returns

Type	Description
float[]	Float array copy of tensor data.

ToReadOnlyNativeArray()

Returns a NativeArray on the linear memory representation of the data in this tensor.

Declaration

public NativeArray<float>.ReadOnly ToReadOnlyNativeArray()

Returns

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

ToReadOnlySpan()

Returns a ReadOnlySpan on the linear memory representation of the data in this tensor.

Declaration

public ReadOnlySpan<float> ToReadOnlySpan()

Returns

Type	Description
ReadOnlySpan<float>	Span of tensor data.

UploadToDevice(ITensorData)

Uploads the tensor data to the destination data location on device.

Declaration

public override void UploadToDevice(ITensorData destination)

Parameters

Type	Name	Description
ITensorData	destination	The data on device to upload the tensor data to.