ai.djl.nn.transformer

Class PointwiseFeedForwardBlock

java.lang.Object

ai.djl.nn.AbstractBlock

ai.djl.nn.transformer.PointwiseFeedForwardBlock

All Implemented Interfaces:

Block

public class PointwiseFeedForwardBlock
extends AbstractBlock

Fully connected Feed-Forward network, only applied to the last dimension of the input.

Field Summary

Fields inherited from class ai.djl.nn.AbstractBlock

children, inputNames, inputShapes, parameters, parameterShapeCallbacks, version

Constructor Summary

Constructors

Constructor and Description
PointwiseFeedForwardBlock(java.util.List<java.lang.Integer> hiddenSizes, int outputSize, java.util.function.Function<NDList,NDList> activationFunction) Creates a pointwise feed-forward block.

Method Summary

Modifier and Type	Method and Description
protected NDList	forwardInternal(ParameterStore ps, NDList inputs, boolean training, ai.djl.util.PairList<java.lang.String,java.lang.Object> params)
Shape[]	getOutputShapes(NDManager manager, Shape[] inputShapes) Returns the expected output shapes of the block for the specified input shapes.
void	initializeChildBlocks(NDManager manager, DataType dataType, Shape... inputShapes) Initializes the Child blocks of this block.

Methods inherited from class ai.djl.nn.AbstractBlock

addChildBlock, addParameter, addParameter, addParameter, beforeInitialize, cast, clear, describeInput, forward, getChildren, getDirectParameters, getParameters, getParameterShape, initialize, isInitialized, loadMetadata, loadParameters, readInputShapes, saveInputShapes, saveMetadata, saveParameters, setInitializer, setInitializer, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface ai.djl.nn.Block

forward, forward, validateLayout

Constructor Detail

PointwiseFeedForwardBlock

public PointwiseFeedForwardBlock(java.util.List<java.lang.Integer> hiddenSizes,
                                 int outputSize,
                                 java.util.function.Function<NDList,NDList> activationFunction)

Creates a pointwise feed-forward block.

Parameters:

hiddenSizes - the sizes of the hidden layers

outputSize - the output size

activationFunction - the activation function to use for the hidden layers (not applied to output)

Method Detail

getOutputShapes

public Shape[] getOutputShapes(NDManager manager,
                               Shape[] inputShapes)

Returns the expected output shapes of the block for the specified input shapes.

Parameters:

manager - an NDManager

inputShapes - the shapes of the inputs

Returns:

the expected output shapes of the block

initializeChildBlocks

public void initializeChildBlocks(NDManager manager,
                                  DataType dataType,
                                  Shape... inputShapes)

Initializes the Child blocks of this block. You need to override this method if your subclass has child blocks. Used to determine the correct input shapes for child blocks based on the requested input shape for this block.

Overrides:

initializeChildBlocks in class AbstractBlock

Parameters:

manager - the manager to use for initialization

dataType - the requested data type

inputShapes - the expected input shapes for this block

forwardInternal

protected NDList forwardInternal(ParameterStore ps,
                                 NDList inputs,
                                 boolean training,
                                 ai.djl.util.PairList<java.lang.String,java.lang.Object> params)

Specified by:

forwardInternal in class AbstractBlock