Package io.github.kirstenali.deepj.nn

Class Pool2D

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Pool2D

All Implemented Interfaces:

Layer, Trainable

public final class Pool2D
extends Module

Floor-mode max/average pooling of channel-first images. Average pooling includes padded zeros.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	Pool2D.Reduction

Constructor Summary

Constructors

Constructor	Description
Pool2D(Window2D window, Pool2D.Reduction reduction)

Method Summary

Modifier and Type	Method	Description
static Pool2D	average(int kernel)
Tensor	forward(Tensor input)
static Pool2D	max(int kernel)

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

buffers, children, 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

Pool2D

public Pool2D(Window2D window,
 Pool2D.Reduction reduction)

Method Details

max

public static Pool2D max(int kernel)

average

public static Pool2D average(int kernel)

forward

public Tensor forward(Tensor input)