cc.mallet.grmm.learning
Class ACRF.FixedFactorTemplate
java.lang.Object
cc.mallet.grmm.learning.ACRF.Template
cc.mallet.grmm.learning.ACRF.FixedFactorTemplate
- All Implemented Interfaces:
- java.io.Serializable
- Enclosing class:
- ACRF
public abstract static class ACRF.FixedFactorTemplate
- extends ACRF.Template
- See Also:
- Serialized Form
Methods inherited from class cc.mallet.grmm.learning.ACRF.Template |
addInstantiatedCliques, addSomeUnsupportedWeights, computeAssignment, createFactorMatrix, getAssignmentsPresent, getDefaultWeight, isSupportedOnly, isUnsupportedWeightsAdded, modifyPotential, setDefaultWeight, setDefaultWeights, setWeights |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
ACRF.FixedFactorTemplate
public ACRF.FixedFactorTemplate()
initWeights
public int initWeights(InstanceList training)
- Description copied from class:
ACRF.Template
- Initializes the weight vectors to the appropriate size for a
set of training data.
- Overrides:
initWeights
in class ACRF.Template
- Returns:
- Number of weights created.
getWeights
public SparseVector[] getWeights()
- Description copied from class:
ACRF.Template
- Returns the weights for this clique template. Each possible
assignment to the clique can in general have a different set of
weights ,so this method returns an array of SparseVectors w,
where w[i] are the weights for assignment i.
- Overrides:
getWeights
in class ACRF.Template
getDefaultWeights
public SparseVector getDefaultWeights()
- Overrides:
getDefaultWeights
in class ACRF.Template
isTrainable
public boolean isTrainable()
- Overrides:
isTrainable
in class ACRF.Template
setTrainable
public void setTrainable(boolean tr)
- Overrides:
setTrainable
in class ACRF.Template
computeFactor
public abstract AbstractTableFactor computeFactor(ACRF.UnrolledVarSet clique)
- Overrides:
computeFactor
in class ACRF.Template