Package ai.djl.nn

Class ParallelBlock

java.lang.Object

ai.djl.nn.AbstractBaseBlock

ai.djl.nn.AbstractBlock

ai.djl.nn.ParallelBlock

All Implemented Interfaces:

Block

public class ParallelBlock
extends AbstractBlock

ParallelBlock is a Block whose children form a parallel branch in the network and are combined to produce a single output.

ParallelBlock has no direct parameters.

Field Summary

Fields inherited from class ai.djl.nn.AbstractBlock

children, parameters

Fields inherited from class ai.djl.nn.AbstractBaseBlock

inputNames, inputShapes, outputDataTypes, version

Constructor Summary

Constructors

Constructor	Description
ParallelBlock(Function<List<NDList>,NDList> function)	Creates a parallel block whose branches are combined to form a single output by the given function.
ParallelBlock(Function<List<NDList>,NDList> function, List<Block> blocks)	Creates a parallel block whose branches are formed by each block in the list of blocks, and are combined to form a single output by the given function.

Method Summary

Modifier and Type	Method	Description
final ParallelBlock	add(Block block)	Adds the given Block to the block, which is one parallel branch.
final ParallelBlock	add(Function<NDList,NDList> f)	Adds a LambdaBlock, that applies the given function, to the list of parallel branches.
ParallelBlock	add(Function<NDList,NDList> f, String name)	Adds a LambdaBlock, that applies the given function, to the list of parallel branches.
final ParallelBlock	addAll(Block... blocks)	Adds an array of blocks, each of which is a parallel branch.
final ParallelBlock	addAll(Collection<Block> blocks)	Adds a Collection of blocks, each of which is a parallel branch.
ParallelBlock	addSingleton(Function<NDArray,NDArray> f)	Adds a LambdaBlock.singleton(Function), that applies the given function, to the list of parallel branches.
ParallelBlock	addSingleton(Function<NDArray,NDArray> f, String name)	Adds a LambdaBlock.singleton(Function), that applies the given function, to the list of parallel branches.
protected NDList	forwardInternal(ParameterStore parameterStore, NDList inputs, boolean training, ai.djl.util.PairList<String,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<String,Object> params)	A helper for Block.forward(ParameterStore, NDList, NDList, PairList) after initialization.
Shape[]	getOutputShapes(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.
void	loadMetadata(byte loadVersion, DataInputStream is)	Overwrite this to load additional metadata with the parameter values.

Methods inherited from class ai.djl.nn.AbstractBlock

addChildBlock, addChildBlock, addChildBlockSingleton, addParameter, getChildren, getDirectParameters

Methods inherited from class ai.djl.nn.AbstractBaseBlock

beforeInitialize, cast, clear, describeInput, forward, forward, getInputShapes, getOutputDataTypes, getParameters, initialize, isInitialized, loadParameters, prepare, readInputShapes, saveInputShapes, saveMetadata, saveParameters, setInitializer, 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, freezeParameters, freezeParameters, getOutputShapes

Constructor Details

ParallelBlock

public ParallelBlock(Function<List<NDList>,NDList> function)

Creates a parallel block whose branches are combined to form a single output by the given function.

Parameters:

function - the function to define how the parallel branches are combined to form a single output

ParallelBlock

public ParallelBlock(Function<List<NDList>,NDList> function,
 List<Block> blocks)

Creates a parallel block whose branches are formed by each block in the list of blocks, and are combined to form a single output by the given function.

Parameters:

function - the function to define how the parallel branches are combined

blocks - the blocks that form each of the parallel branches

Method Details

addAll

public final ParallelBlock addAll(Block... blocks)

Adds an array of blocks, each of which is a parallel branch.

Parameters:

blocks - the array of blocks to add

Returns:

this block

addAll

public final ParallelBlock addAll(Collection<Block> blocks)

Adds a Collection of blocks, each of which is a parallel branch.

Parameters:

blocks - the Collection of blocks to add

Returns:

this block

add

public final ParallelBlock add(Block block)

Adds the given Block to the block, which is one parallel branch.

Parameters:

block - the block to be added as a parallel branch

Returns:

this block

add

public final ParallelBlock add(Function<NDList,NDList> f)

Adds a LambdaBlock, that applies the given function, to the list of parallel branches.

Parameters:

f - the function that forms the LambdaBlock

Returns:

this block

add

public ParallelBlock add(Function<NDList,NDList> f,
 String name)

Adds a LambdaBlock, that applies the given function, to the list of parallel branches.

Parameters:

f - the function forms the LambdaBlock

name - the function name

Returns:

this block

addSingleton

public ParallelBlock addSingleton(Function<NDArray,NDArray> f)

Adds a LambdaBlock.singleton(Function), that applies the given function, to the list of parallel branches.

Parameters:

f - the function forms the LambdaBlock

Returns:

this block

See Also:

• LambdaBlock.singleton(Function)

addSingleton

public ParallelBlock addSingleton(Function<NDArray,NDArray> f,
 String name)

Adds a LambdaBlock.singleton(Function), that applies the given function, to the list of parallel branches.

Parameters:

f - the function forms the LambdaBlock

name - the function name

Returns:

this block

See Also:

• LambdaBlock.singleton(Function)

forwardInternal

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

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

Specified by:

forwardInternal in class AbstractBaseBlock

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<String,Object> params)

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

Overrides:

forwardInternal in class AbstractBaseBlock

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:

• AbstractBaseBlock.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 AbstractBaseBlock

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[] inputShapes)

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

Parameters:

inputShapes - the shapes of the inputs

Returns:

the expected output shapes of the block

loadMetadata

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

Overwrite this to load additional metadata with the parameter values.

If you overwrite AbstractBaseBlock.saveMetadata(DataOutputStream) or need to provide backward compatibility to older binary formats, you probably 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 AbstractBaseBlock

Parameters:

loadVersion - the version used for loading this metadata.

is - the input stream we are loading from

Throws:

IOException - loading failed

MalformedModelException - data can be loaded but has wrong format