Package io.github.kirstenali.deepj.nn

Class Pool1D

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Pool1D

All Implemented Interfaces:

Layer, Trainable

public final class Pool1D
extends Module

Max/average pooling of [batch, channels, length] inputs.

Constructor Summary

Constructors

Constructor	Description
Pool1D(int kernel, int stride, int padding, Pool2D.Reduction reduction)

Method Summary

Modifier and Type	Method	Description
static Pool1D	average(int kernel)
protected List<Layer>	children()
Tensor	forward(Tensor input)
static Pool1D	max(int kernel)

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

Pool1D

public Pool1D(int kernel,
 int stride,
 int padding,
 Pool2D.Reduction reduction)

Method Details

max

public static Pool1D max(int kernel)

average

public static Pool1D average(int kernel)

children

protected List<Layer> children()

Overrides:

children in class Module

forward

public Tensor forward(Tensor input)