Block

java.lang.Object

me.damoebe.architectures.transformer.Block<H,N>

Typparameter:: H - The Head type that should be used to construct the MultiHeadAttention attribute.; N - The MLP type that will be used in this block.

public class Block<H extends Head,N extends FFNetwork> extends Object

The Transformer Bock class containing a mha and multiple mlps.

Konstruktorübersicht

Konstruktoren

Konstruktor

Beschreibung

Block(@NotNull MultiHeadAttention<H> multiHeadAttention, N multiLayerPerceptron)

The main constructor of the Block class
Methodenübersicht

Modifizierer und Typ

Methode

Beschreibung

Block<H,N>

clone()

Sequence

getOutputFor(Sequence... inputEmbeddings)

Gets the output for the inserted input(s) by passing them through the mha module and mlp.

Von Klasse geerbte Methoden java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Konstruktordetails
- Block
  
  public Block(@NotNull @NotNull MultiHeadAttention<H> multiHeadAttention, @NotNull N multiLayerPerceptron)
  
  The main constructor of the Block class
  
  Parameter:
  
  multiHeadAttention - A MultiHeadAttention object that will be cloned and used for this block.
  
  multiLayerPerceptron - A FFNetwork object that will be cloned and used as an MLP architecture.
Methodendetails
- getOutputFor
  
  public Sequence getOutputFor(Sequence... inputEmbeddings)
  
  Gets the output for the inserted input(s) by passing them through the mha module and mlp.
  
  Parameter:
  
  inputEmbeddings - A list of inputs: if the head type is EDHead: [0] is the decoder input and [1] is the encoder input. Else: [0] is the head input.
  
  Gibt zurück:
  
  The output embeddings for this block.
- clone
  
  public Block<H,N> clone()
  
  Setzt außer Kraft:
  
  clone in Klasse Object