ai.djl.training.hyperparameter.param

Class Hyperparameter<T>

java.lang.Object

ai.djl.training.hyperparameter.param.Hyperparameter<T>

Type Parameters:

T - the type of the hyperparameter

Direct Known Subclasses:

HpCategorical, HpFloat, HpInt, HpSet, HpVal

public abstract class Hyperparameter<T>
extends java.lang.Object

A class representing an input to the network that can't be differentiated.

Some hyperparameters include learning rates, network sizes and shapes, activation choices, and model selection. In order to evaluate a set of hyperparameters, the only way is to fully train your model using those choices of hyperparameters. So, the full training loop involves training the model a number of times using different choices of hyperparameters. This can be mostly automated by using a HpOptimizer.

Field Summary

Fields

Modifier and Type	Field and Description
protected java.lang.String	name

Constructor Summary

Constructors

Constructor and Description
Hyperparameter(java.lang.String name) Constructs a hyperparameter with the given name.

Method Summary

Modifier and Type	Method and Description
java.lang.String	getName() Returns the name of the hyperparameter.
abstract T	random() Returns a random value for the hyperparameter for a range of a fixed value if it is a HpVal.

Methods inherited from class java.lang.Object

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

Field Detail

name

protected java.lang.String name

Constructor Detail

Hyperparameter

public Hyperparameter(java.lang.String name)

Constructs a hyperparameter with the given name.

Parameters:

name - the name of the hyperparameter

Method Detail

getName

public java.lang.String getName()

Returns the name of the hyperparameter.

Returns:

the name of the hyperparameter

random

public abstract T random()

Returns a random value for the hyperparameter for a range of a fixed value if it is a HpVal.

Returns:

a random value for the hyperparameter for a range of a fixed value if it is a HpVal