SG++-Doxygen-Documentation
|
The class implements heuristics for testing if the learn process should be finished before learner is overfitted. More...
Public Member Functions | |
def | __init__ (self) |
Contructor. More... | |
def | fromJson (cls, jsonObject) |
def | getAccuracyLimit (self) |
Returns the accuracy on validation data, that have to be achieved. More... | |
def | getAdaptiveIterationLimit (self) |
Returns the maximal number of refinement iterations. More... | |
def | getGridSizeLimit (self) |
Returns the maximal grid size. More... | |
def | hasGridSizeChanged (self, sampler) |
def | hasLimitReached (self, sampler) |
def | isTrainingComplete (self, sampler) |
Checks if learning process have to be stopped. More... | |
def | setAccuracyLimit (self, limit) |
Setter for accuracy limit. More... | |
def | setAdaptiveIterationLimit (self, limit) |
def | setGridSizeLimit (self, limit) |
Setter for maximal grid size. More... | |
def | toString (self) |
Returns a string that represents the object. More... | |
The class implements heuristics for testing if the learn process should be finished before learner is overfitted.
The test is made by calling method isTrainingComplete(learner)
of the class, which returns True if training process should be finished.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__init__ | ( | self | ) |
Contructor.
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__accuracyLimit, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__accuracyLimit, python.learner.TrainingStopPolicy.TrainingStopPolicy.__adaptiveIterationLimit, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__adaptiveIterationLimit, python.learner.TrainingStopPolicy.TrainingStopPolicy.__gridSizeLimit, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__gridSizeLimit, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__oldGridSize, and python.learner.TrainingStopPolicy.TrainingStopPolicy.__oldGridSize.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.fromJson | ( | cls, | |
jsonObject | |||
) |
Referenced by python.uq.uq_setting.UQSetting.UQSetting.setMemento().
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.getAccuracyLimit | ( | self | ) |
Returns the accuracy on validation data, that have to be achieved.
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__accuracyLimit, and python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__accuracyLimit.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.getAdaptiveIterationLimit | ( | self | ) |
Returns the maximal number of refinement iterations.
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__adaptiveIterationLimit, and python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__adaptiveIterationLimit.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.getGridSizeLimit | ( | self | ) |
Returns the maximal grid size.
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__gridSizeLimit, and python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__gridSizeLimit.
Referenced by python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.hasLimitReached().
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.hasGridSizeChanged | ( | self, | |
sampler | |||
) |
References python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__oldGridSize, and python.learner.TrainingStopPolicy.TrainingStopPolicy.__oldGridSize.
Referenced by python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.isTrainingComplete().
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.hasLimitReached | ( | self, | |
sampler | |||
) |
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__adaptiveIterationLimit, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__adaptiveIterationLimit, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.getGridSizeLimit(), and python.learner.TrainingStopPolicy.TrainingStopPolicy.getGridSizeLimit().
Referenced by python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.isTrainingComplete().
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.isTrainingComplete | ( | self, | |
sampler | |||
) |
Checks if learning process have to be stopped.
sampler | Learner object |
References python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__oldGridSize, python.learner.TrainingStopPolicy.TrainingStopPolicy.__oldGridSize, python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.hasGridSizeChanged(), python.learner.TrainingStopPolicy.TrainingStopPolicy.hasGridSizeChanged(), python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.hasLimitReached(), and python.learner.TrainingStopPolicy.TrainingStopPolicy.hasLimitReached().
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.setAccuracyLimit | ( | self, | |
limit | |||
) |
Setter for accuracy limit.
limit | double accuracy on validation data, that have to be achieved |
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__accuracyLimit, and python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__accuracyLimit.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.setAdaptiveIterationLimit | ( | self, | |
limit | |||
) |
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__adaptiveIterationLimit, and python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__adaptiveIterationLimit.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.setGridSizeLimit | ( | self, | |
limit | |||
) |
Setter for maximal grid size.
limit | integer maximal grid size |
References python.learner.TrainingStopPolicy.TrainingStopPolicy.__gridSizeLimit, and python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.__gridSizeLimit.
def python.uq.sampler.asgc.ASGCSamplerStopPolicy.ASGCSamplerStopPolicy.toString | ( | self | ) |
Returns a string that represents the object.
References create_dataset.type.