Package ai.djl.nn.core

Class Linear

java.lang.Object

ai.djl.nn.AbstractBlock

ai.djl.nn.core.Linear

All Implemented Interfaces:

Block

public class Linear
extends AbstractBlock

A Linear block applies a linear transformation \(Y = XW^T + b\).

It has the following shapes:

• input X: [x1, x2, …, xn, input_dim]
• weight W: [units, input_dim]
• Bias b: [units]
• output Y: [x1, x2, …, xn, units]

The Linear block should be constructed using Linear.Builder.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	Linear.Builder	The Builder to construct a Linear type of Block.

Field Summary

Fields inherited from class ai.djl.nn.AbstractBlock

children, inputNames, inputShapes, parameters, version

Method Summary

Modifier and Type	Method	Description
protected void	beforeInitialize(Shape... inputShapes)	Performs any action necessary before initialization.
static Linear.Builder	builder()	Creates a builder to build a Linear.
ai.djl.util.PairList<java.lang.String,Shape>	describeInput()	Returns a PairList of input names, and shapes.
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.
Shape[]	getOutputShapes(Shape[] inputs)	Returns the expected output shapes of the block for the specified input shapes.
static NDList	linear(NDArray input, NDArray weight)	Applies a linear transformation to the incoming data.
static NDList	linear(NDArray input, NDArray weight, NDArray bias)	Applies a linear transformation to the incoming data.
void	loadMetadata(byte loadVersion, java.io.DataInputStream is)	Overwrite this to load additional metadata with the parameter values.
void	prepare(Shape[] inputShapes)	Sets the shape of Parameters.
protected void	saveMetadata(java.io.DataOutputStream os)	Override this method to save additional data apart from parameter values.

Methods inherited from class ai.djl.nn.AbstractBlock

addChildBlock, addParameter, cast, clear, forward, forward, forwardInternal, getChildren, getDirectParameters, getParameters, initialize, initializeChildBlocks, isInitialized, loadParameters, readInputShapes, saveInputShapes, 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

Method Detail

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

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

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

beforeInitialize

protected void beforeInitialize(Shape... inputShapes)

Performs any action necessary before initialization. For example, keep the input information or verify the layout.

Overrides:

beforeInitialize in class AbstractBlock

Parameters:

inputShapes - the expected shapes of the input

prepare

public void prepare(Shape[] inputShapes)

Sets the shape of Parameters.

Overrides:

prepare in class AbstractBlock

Parameters:

inputShapes - the shapes of inputs

saveMetadata

protected void saveMetadata(java.io.DataOutputStream os)
                     throws java.io.IOException

Override this method to save additional data apart from parameter values.

This default implementation saves the currently set input shapes.

Overrides:

saveMetadata in class AbstractBlock

Parameters:

os - the non-null output stream the parameter values and metadata are written to

Throws:

java.io.IOException - saving failed

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

linear

public static NDList linear(NDArray input,
                            NDArray weight)

Applies a linear transformation to the incoming data.

Parameters:

input - input X: [x1, x2, …, xn, input_dim]

weight - weight W: [units, input_dim]

Returns:

output Y: [x1, x2, …, xn, units]

linear

public static NDList linear(NDArray input,
                            NDArray weight,
                            NDArray bias)

Applies a linear transformation to the incoming data.

Parameters:

input - input X: [x1, x2, …, xn, input_dim]

weight - weight W: [units, input_dim]

bias - bias b: [units]

Returns:

output Y: [x1, x2, …, xn, units]

builder

public static Linear.Builder builder()

Creates a builder to build a Linear.

Returns:

a new builder