Package io.github.kirstenali.deepj.nn

Class Conv1D

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Conv1D

All Implemented Interfaces:

Layer, Trainable

public final class Conv1D
extends Module

Temporal cross-correlation for [batch, channels, length], sharing the 2D implementation.

Constructor Summary

Constructors

Constructor	Description
Conv1D(int inputs, int outputs, int kernel, int stride, int padding, int dilation, boolean bias, Random random, ParameterFactory parameters)
Conv1D(int inputs, int outputs, int kernel, Random random)

Method Summary

Modifier and Type	Method	Description
Parameter	bias()
protected List<Layer>	children()
Tensor	forward(Tensor input)
Parameter	weight()

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

Conv1D

public Conv1D(int inputs,
 int outputs,
 int kernel,
 Random random)

Conv1D

public Conv1D(int inputs,
 int outputs,
 int kernel,
 int stride,
 int padding,
 int dilation,
 boolean bias,
 Random random,
 ParameterFactory parameters)

Method Details

weight

public Parameter weight()

bias

public Parameter bias()

children

protected List<Layer> children()

Overrides:

children in class Module

forward

public Tensor forward(Tensor input)