ai.djl.modality.nlp

Class EncoderDecoder

java.lang.Object

ai.djl.nn.AbstractBlock

ai.djl.modality.nlp.EncoderDecoder

All Implemented Interfaces:

Block

public class EncoderDecoder
extends AbstractBlock

EncoderDecoder is a general implementation of the very popular encoder-decoder architecture. This class depends on implementations of Encoder and Decoder to provide encoder-decoder architecture for different tasks and inputs such as machine translation(text-text), image captioning(image-text) etc.

Field Summary

Fields

Modifier and Type	Field and Description
protected Decoder	decoder
protected Encoder	encoder

Fields inherited from class ai.djl.nn.AbstractBlock

inputNames, inputShapes

Constructor Summary

Constructors

Constructor and Description
EncoderDecoder(Encoder encoder, Decoder decoder) Constructs a new instance of EncoderDecoder class with the given Encoder and Decoder.

Method Summary

Modifier and Type	Method and Description
ai.djl.util.PairList<java.lang.String,Shape>	describeInput() Returns a PairList of input names, and shapes.
NDList	forward(ParameterStore parameterStore, NDList inputs, boolean training) Applies the forward function of the encoder and the decoder.
NDList	forward(ParameterStore parameterStore, NDList inputs, boolean training, ai.djl.util.PairList<java.lang.String,java.lang.Object> params) Applies the forward function of the encoder and the decoder.
NDList	forward(ParameterStore parameterStore, NDList encoderInputs, NDList decoderInputs, boolean training, ai.djl.util.PairList<java.lang.String,java.lang.Object> params) Applies the forward function of the encoder and the decoder.
BlockList	getChildren() Returns a list of all the children of the block.
java.util.List<Parameter>	getDirectParameters() Returns a list of all the direct parameters of the block.
Shape[]	getOutputShapes(NDManager manager, Shape[] inputShapes) Returns the expected output shapes of the block for the specified input shapes.
Shape	getParameterShape(java.lang.String name, Shape[] inputShapes) Returns the shape of the specified direct parameter of this block given the shapes of the input to the block.
Shape[]	initialize(NDManager manager, DataType dataType, Shape... inputShapes) Initializes the parameters of the block.
void	loadParameters(NDManager manager, java.io.DataInputStream is) Loads the parameters from the given input stream.
void	saveParameters(java.io.DataOutputStream os) Writes the parameters of the block to the given outputStream.

Methods inherited from class ai.djl.nn.AbstractBlock

beforeInitialize, cast, clear, getParameters, isInitialized, readInputShapes, saveInputShapes, setInitializer, setInitializer

Methods inherited from class java.lang.Object

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

Methods inherited from interface ai.djl.nn.Block

validateLayout

Field Detail

encoder

protected Encoder encoder

decoder

protected Decoder decoder

Constructor Detail

EncoderDecoder

public EncoderDecoder(Encoder encoder,
                      Decoder decoder)

Constructs a new instance of EncoderDecoder class with the given Encoder and Decoder.

Parameters:

encoder - the Encoder

decoder - the Decoder

Method Detail

describeInput

public ai.djl.util.PairList<java.lang.String,Shape> describeInput()

Returns a PairList of input names, and shapes.

Specified by:

describeInput in interface Block

Overrides:

describeInput in class AbstractBlock

Returns:

the PairList of input names, and shapes

forward

public NDList forward(ParameterStore parameterStore,
                      NDList encoderInputs,
                      NDList decoderInputs,
                      boolean training,
                      ai.djl.util.PairList<java.lang.String,java.lang.Object> params)

Applies the forward function of the encoder and the decoder. This method should be called only on blocks that are initialized.

Parameters:

parameterStore - the parameter store

encoderInputs - the input for the encoder

decoderInputs - the input for the decoder

training - true to run a training forward pass

params - optional parameters

Returns:

the output of the forward pass

forward

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

Applies the forward function of the encoder and the decoder. This method should be called only on blocks that are initialized.

This forward function in the EncoderDecoder class assumes the input NDList contains both the encoder and decoder inputs. Further, it assumes that the first index in the input NDList contains the encoder input and the second index contains the decoder input.

Parameters:

parameterStore - the parameter store

inputs - the input NDList

training - true if running a forward pass for training

params - optional parameters

Returns:

the output of the forward pass

forward

public NDList forward(ParameterStore parameterStore,
                      NDList inputs,
                      boolean training)

Applies the forward function of the encoder and the decoder. This method should be called only on blocks that are initialized.

This forward function in the EncoderDecoder class assumes the input NDList contains both the encoder and decoder inputs. Further, it assumes that the first index in the input NDList contains the encoder input and the second index contains the decoder input.

Parameters:

parameterStore - the parameter store

inputs - the input NDList

training - true if running a forward pass for training

Returns:

the output of the forward pass

initialize

public Shape[] initialize(NDManager manager,
                          DataType dataType,
                          Shape... inputShapes)

Initializes the parameters of the block. This method must be called before calling `forward`.

This method assumes that inputShapes contains encoder and decoder inputs in index 0 and 1 respectively.

Parameters:

manager - the NDManager to initialize the parameters

dataType - the datatype of the parameters

inputShapes - the shapes of the inputs to the block

Returns:

the shapes of the outputs of the block

getChildren

public BlockList getChildren()

Returns a list of all the children of the block.

Returns:

the list of child blocks

getDirectParameters

public java.util.List<Parameter> getDirectParameters()

Returns a list of all the direct parameters of the block.

Returns:

the list of Parameter

getParameterShape

public Shape getParameterShape(java.lang.String name,
                               Shape[] inputShapes)

Returns the shape of the specified direct parameter of this block given the shapes of the input to the block.

Parameters:

name - the name of the parameter

inputShapes - the shapes of the input to the block

Returns:

the shape of the parameter specified

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

saveParameters

public void saveParameters(java.io.DataOutputStream os)
                    throws java.io.IOException

Writes the parameters of the block to the given outputStream.

Parameters:

os - the outputstream to save the parameters to

Throws:

java.io.IOException - if an I/O error occurs

loadParameters

public void loadParameters(NDManager manager,
                           java.io.DataInputStream is)
                    throws java.io.IOException,
                           MalformedModelException

Loads the parameters from the given input stream.

Parameters:

manager - an NDManager to create the parameter arrays

is - the inputstream that stream the parameter values

Throws:

java.io.IOException - if an I/O error occurs

MalformedModelException - if the model file is corrupted or unsupported