jsat.classifiers.svm

Enum SupportVectorLearner.CacheMode

java.lang.Object

java.lang.Enum<SupportVectorLearner.CacheMode>

jsat.classifiers.svm.SupportVectorLearner.CacheMode

All Implemented Interfaces:

Serializable, Comparable<SupportVectorLearner.CacheMode>

Enclosing class:

SupportVectorLearner

public static enum SupportVectorLearner.CacheMode
extends Enum<SupportVectorLearner.CacheMode>

Determines how the final kernel values are cached. The total number of raw kernel evaluations can be tracked using SupportVectorLearner.evalCount
SupportVectorLearner.setCacheMode(jsat.classifiers.svm.SupportVectorLearner.CacheMode) should be called before training begins by the training algorithm as described in the method documentation.

Enum Constant Summary

Enum Constants

Enum Constant and Description
FULL The entire kernel matrix will be created and cached ahead of time.
NONE No kernel value caching will be performed.
ROWS Only the most recently used rows of the kernel matrix will be cached (LRU).

Method Summary

Modifier and Type	Method and Description
static SupportVectorLearner.CacheMode	valueOf(String name) Returns the enum constant of this type with the specified name.
static SupportVectorLearner.CacheMode[]	values() Returns an array containing the constants of this enum type, in the order they are declared.

Methods inherited from class java.lang.Enum

clone, compareTo, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Detail

NONE

public static final SupportVectorLearner.CacheMode NONE

No kernel value caching will be performed.

FULL

public static final SupportVectorLearner.CacheMode FULL

The entire kernel matrix will be created and cached ahead of time. This is the best option if your data set is small and the kernel cache can fit into memory.

ROWS

public static final SupportVectorLearner.CacheMode ROWS

Only the most recently used rows of the kernel matrix will be cached (LRU). When a call to SupportVectorLearner.k(int, int) occurs, the first value will be taken to be the row of the matrix.
Because the kernel matrix is symmetric, if a cache miss occurs - the column value will be checked for its existence. If the row is present, it will be used instead. If both rows are not present, then a new row is inserted for the first index, and another row evicted if necessary.
The SupportVectorLearner.cacheEvictions indicates how many times a row has been evicted from the cache.
Row values are computed lazily.

Method Detail

values

public static SupportVectorLearner.CacheMode[] values()

Returns an array containing the constants of this enum type, in the order they are declared. This method may be used to iterate over the constants as follows:

for (SupportVectorLearner.CacheMode c : SupportVectorLearner.CacheMode.values())
    System.out.println(c);

Returns:

an array containing the constants of this enum type, in the order they are declared

valueOf

public static SupportVectorLearner.CacheMode valueOf(String name)

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

IllegalArgumentException - if this enum type has no constant with the specified name

NullPointerException - if the argument is null