Package io.github.kirstenali.deepj.nn

Class Activation

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Activation

All Implemented Interfaces:

Layer, Trainable

public final class Activation
extends Module

Adapts DeepJ activations to the existing Layer contract.

Constructor Summary

Constructors

Constructor	Description
Activation(ActivationFunction function)

Method Summary

Modifier and Type	Method	Description
Tensor	forward(Tensor input)
static Activation	gelu()
static Activation	relu()
static Activation	sigmoid()
static Activation	softmax(int axis)
static Activation	tanh()

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

Activation

public Activation(ActivationFunction function)

Method Details

relu

public static Activation relu()

gelu

public static Activation gelu()

sigmoid

public static Activation sigmoid()

tanh

public static Activation tanh()

softmax

public static Activation softmax(int axis)

forward

public Tensor forward(Tensor input)