Package io.github.kirstenali.deepj.nn

Class Recurrent

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Recurrent

All Implemented Interfaces:

Layer, Trainable

Direct Known Subclasses:

GRU, LSTM, RNN

public class Recurrent
extends Module

Batch-first recurrent sequence execution, with optional lengths and caller-owned initial/final state.

Constructor Summary

Constructors

Constructor	Description
Recurrent(RecurrentCell cell)

Method Summary

Modifier and Type	Method	Description
final RecurrentCell	cell()
protected List<Layer>	children()
final Tensor	forward(Tensor input)
final RecurrentResult	run(Tensor input, RecurrentState initial, int[] lengths)

Methods inherited from class io.github.kirstenali.deepj.nn.Module

buffers, eval, isTraining, parameters, setTraining, train

Methods inherited from class java.lang.Object

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

Methods inherited from interface io.github.kirstenali.deepj.layers.Layer

forward, supportsIncrementalInference

Methods inherited from interface io.github.kirstenali.deepj.training.Trainable

zeroGrad

Constructor Details

Recurrent

public Recurrent(RecurrentCell cell)

Method Details

cell

public final RecurrentCell cell()

children

protected List<Layer> children()

Overrides:

children in class Module

forward

public final Tensor forward(Tensor input)

run

public final RecurrentResult run(Tensor input,
 RecurrentState initial,
 int[] lengths)