Class TopK

Represents a TopK layer. This calculates the top-K largest or smallest elements of an input tensor along a given axis.

This layer calculates both the values tensor of the top-K elements and the indices tensor of the top-K elements as outputs.

Inheritance
Object
Layer
TopK
Inherited Members
Layer.inputs
Layer.name
Layer.outputs
Layer.flags
Layer.ToString()
Namespace: Unity.Sentis.Layers
Syntax
[Serializable]
public class TopK : Layer

Constructors

TopK(String, String, String, Int32, Boolean, Boolean, String[])

Initializes and returns an instance of TopK layer.

Declaration
public TopK(string name, string input, string k, int axis, bool largest, bool sorted, string[] outputNames)
Parameters
Type Name Description
String name

The name to use for the values tensor of the layer.
String input

The name to use for the input tensor of the layer.
String k

The name to use for the single value 1D tensor containing the number of elements to calculate.
Int32 axis

The axis along which to perform the top-K operation.
Boolean largest

Whether to calculate the top-K largest elements. If this is false the layer calculates the top-K smallest elements.
Boolean sorted

Whether to return the elements in sorted order in the output tensor.
String[] outputNames

A two-element array containing the names to use for the values and indices output tensors of the layer respectively.

Fields

axis

The axis along which to perform the top-K operation.

Declaration
public int axis
Field Value
Type Description
Int32

largest

Whether to calculate the top-K largest elements. If this is false the layer calculates the top-K smallest elements.

Declaration
public bool largest
Field Value
Type Description
Boolean

sorted

Whether to return the elements in sorted order in the output tensor.

Declaration
public bool sorted
Field Value
Type Description
Boolean

Methods

Execute(Tensor[], ExecutionContext)

Executes the layer using the operations and variables from the ExecutionContext and returns the output tensor.

If the layer has more than one output, output tensors are saved to variables.

Declaration
public override Tensor Execute(Tensor[] inputTensors, ExecutionContext ctx)
Parameters
Type Name Description
Tensor[] inputTensors
ExecutionContext ctx
Returns
Type Description
Tensor
Overrides