Class SingleHeadAttention

Represents the fused multihead attention layer based on the PyTorch implementation. This layer computes attention outputs given input tensors.

Inheritance

object

Layer

SingleHeadAttention

Inherited Members

Layer.inputs

Layer.name

Layer.outputs

Layer.flags

Layer.ToString()

object.Equals(object)

object.Equals(object, object)

object.ReferenceEquals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

Namespace: Unity.Sentis.Layers

Assembly: solution.dll

Syntax

[Serializable]
public class SingleHeadAttention : Layer

Constructors

Name	Description
SingleHeadAttention(string, string, string, string, string, string, string, string, string, string, float)	Creates a fused Multihead Attention layer based on the PyTorch implementation.

Fields

Name	Description
scaling_factor	The scaling factor for scaling the query.

Methods

Name	Description
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.