Package ai.djl.nn

Class SequentialBlock

java.lang.Object

ai.djl.nn.AbstractBlock

ai.djl.nn.SequentialBlock

All Implemented Interfaces:

Block

Direct Known Subclasses:

PointwiseFeedForwardBlock

public class SequentialBlock
extends AbstractBlock

SequentialBlock is a Block whose children form a chain of blocks with each child block feeding its output to the next. The output of the last child is returned as the output of the SequentialBlock.

SequentialBlock has no direct parameters.

Field Summary

Fields inherited from class ai.djl.nn.AbstractBlock

children, inputNames, inputShapes, parameters, version

Constructor Summary

Constructors

Constructor	Description
SequentialBlock()	Creates an empty sequential block.

Method Summary

Modifier and Type	Method	Description
SequentialBlock	add(Block block)	Adds the given Block to the block to be executed in order.
SequentialBlock	add(java.util.function.Function<NDList,NDList> f)	Adds a LambdaBlock that applies the given function to the sequence of blocks.
SequentialBlock	addAll(Block... blocks)	Adds an array of blocks to be executed in sequence, in order.
SequentialBlock	addAll(java.util.Collection<Block> blocks)	Adds a Collection of blocks to be executed in sequence, in order.
SequentialBlock	addSingleton(java.util.function.Function<NDArray,NDArray> f)	Adds a LambdaBlock.singleton(Function) that applies the given function to the sequence of blocks.
protected NDList	forwardInternal(ParameterStore parameterStore, NDList inputs, boolean training, ai.djl.util.PairList<java.lang.String,java.lang.Object> params)	A helper for Block.forward(ParameterStore, NDList, boolean, PairList) after initialization.
protected NDList	forwardInternal(ParameterStore parameterStore, NDList data, NDList labels, ai.djl.util.PairList<java.lang.String,java.lang.Object> params)	A helper for Block.forward(ParameterStore, NDList, NDList, PairList) after initialization.
Shape[]	getOutputShapes(Shape[] inputs)	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.
void	loadMetadata(byte loadVersion, java.io.DataInputStream is)	Overwrite this to load additional metadata with the parameter values.
void	removeLastBlock()	Removes the Block added last from the sequence of blocks.
void	replaceLastBlock(Block block)	Replaces the Block last added from the sequence of blocks, and adds the given block.
java.lang.String	toString()

Methods inherited from class ai.djl.nn.AbstractBlock

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

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

Constructor Detail

SequentialBlock

public SequentialBlock()

Creates an empty sequential block. Use add and addAll to add blocks to be executed in sequence.

Method Detail

addAll

public SequentialBlock addAll(Block... blocks)

Adds an array of blocks to be executed in sequence, in order.

Parameters:

blocks - the array of blocks

Returns:

this block

addAll

public SequentialBlock addAll(java.util.Collection<Block> blocks)

Adds a Collection of blocks to be executed in sequence, in order.

Parameters:

blocks - the Collection of blocks

Returns:

this block

add

public SequentialBlock add(Block block)

Adds the given Block to the block to be executed in order.

Parameters:

block - the block to be added to the sequence of blocks

Returns:

this block

add

public SequentialBlock add(java.util.function.Function<NDList,NDList> f)

Adds a LambdaBlock that applies the given function to the sequence of blocks.

Parameters:

f - the function forms the LambdaBlock

Returns:

this block

addSingleton

public SequentialBlock addSingleton(java.util.function.Function<NDArray,NDArray> f)

Adds a LambdaBlock.singleton(Function) that applies the given function to the sequence of blocks.

Parameters:

f - the function forms the LambdaBlock

Returns:

this block

See Also:

LambdaBlock.singleton(Function)

removeLastBlock

public void removeLastBlock()

Removes the Block added last from the sequence of blocks.

replaceLastBlock

public void replaceLastBlock(Block block)

Replaces the Block last added from the sequence of blocks, and adds the given block.

Parameters:

block - the block to replace the last block with

forwardInternal

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

A helper for Block.forward(ParameterStore, NDList, boolean, PairList) after initialization.

Specified by:

forwardInternal in class AbstractBlock

Parameters:

parameterStore - the parameter store

inputs - the input NDList

training - true for a training forward pass

params - optional parameters

Returns:

the output of the forward pass

forwardInternal

protected NDList forwardInternal(ParameterStore parameterStore,
                                 NDList data,
                                 NDList labels,
                                 ai.djl.util.PairList<java.lang.String,java.lang.Object> params)

A helper for Block.forward(ParameterStore, NDList, NDList, PairList) after initialization.

Overrides:

forwardInternal in class AbstractBlock

Parameters:

parameterStore - the parameter store

data - the input data NDList

labels - the input labels NDList

params - optional parameters

Returns:

the output of the forward pass

See Also:

AbstractBlock.forward(ParameterStore, NDList, boolean, PairList)

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

getOutputShapes

public Shape[] getOutputShapes(Shape[] inputs)

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

Parameters:

inputs - the shapes of the inputs

Returns:

the expected output shapes of the block

loadMetadata

public void loadMetadata(byte loadVersion,
                         java.io.DataInputStream is)
                  throws java.io.IOException,
                         MalformedModelException

Overwrite this to load additional metadata with the parameter values.

If you overwrite AbstractBlock.saveMetadata(DataOutputStream) or need to provide backward compatibility to older binary formats, you prabably need to overwrite this. This default implementation checks if the version number fits, if not it throws an MalformedModelException. After that it restores the input shapes.

Overrides:

loadMetadata in class AbstractBlock

Parameters:

loadVersion - the version used for loading this metadata.

is - the input stream we are loading from

Throws:

java.io.IOException - loading failed

MalformedModelException - data can be loaded but has wrong format

toString

public java.lang.String toString()

Overrides:

toString in class AbstractBlock