def __init__(self, columnCount, inputWidth, historyLength,
minHistory, poolerType, **kwargs):
if columnCount <= 0 or inputWidth <=0:
raise TypeError("Parameters columnCount and inputWidth must be > 0")
# Pull out the pooler arguments automatically
# These calls whittle down kwargs and create instance variables of TemporalPoolerRegion
self._poolerType = poolerType
self._poolerClass = _getPoolerClass(poolerType)
pArgTuples = _buildArgs(self._poolerClass, self, kwargs)
# include parent spatial pooler parameters
if poolerType == "union" or poolerType == "unionMonitored":
pArgTuplesSP = _buildArgs(_getParentSpatialPoolerClass(poolerType), self, kwargs)
# Make a list of automatic pooler arg names for later use
self._poolerArgNames = [t[0] for t in pArgTuples] + [t[0] for t in pArgTuplesSP]
else:
self._poolerArgNames = [t[0] for t in pArgTuples]
PyRegion.__init__(self, **kwargs)
# Defaults for all other parameters
self.learningMode = True
self.inferenceMode = True
self._inputWidth = inputWidth
self._columnCount = columnCount
self._historyLength = historyLength
self._minHistory = minHistory
# pooler instance
self._pooler = None
def __init__(self,
columnCount, # Number of columns in the SP, a required parameter
inputWidth, # Size of inputs to the SP, a required parameter
spatialImp=getDefaultSPImp(), #'py', 'cpp'
**kwargs):
if columnCount <= 0 or inputWidth <=0:
raise TypeError("Parameters columnCount and inputWidth must be > 0")
# Pull out the spatial arguments automatically
# These calls whittle down kwargs and create instance variables of SPRegion
self.SpatialClass = getSPClass(spatialImp)
sArgTuples = _buildArgs(self.SpatialClass.__init__, self, kwargs)
# Make a list of automatic spatial arg names for later use
self._spatialArgNames = [t[0] for t in sArgTuples]
# Learning and SP parameters.
# By default we start out in stage learn with inference disabled
self.learningMode = True
self.inferenceMode = False
self.anomalyMode = False
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initializeEphemeralMembers()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# Defaults for all other parameters
self.logPathInput = ''
self.logPathOutput = ''
self.logPathOutputDense = ''
self._fpLogSPInput = None
self._fpLogSP = None
self._fpLogSPDense = None
#
# Variables set up in initInNetwork()
#
# Spatial instance
self._sfdr = None
# Spatial pooler's bottom-up output value: hang on to this output for
# top-down inference and for debugging
self._spatialPoolerOutput = None
# Spatial pooler's bottom-up input: hang on to this for supporting the
# spInputNonZeros parameter
self._spatialPoolerInput = None
def __init__(self,
moduleCount,
cellsPerAxis,
scale,
orientation,
anchorInputSize,
activeFiringRate,
bumpSigma,
activationThreshold=10,
initialPermanence=0.21,
connectedPermanence=0.50,
learningThreshold=10,
sampleSize=20,
permanenceIncrement=0.1,
permanenceDecrement=0.0,
maxSynapsesPerSegment=-1,
bumpOverlapMethod="probabilistic",
learningMode=False,
seed=42,
dualPhase=True,
dimensions=2,
**kwargs):
if moduleCount <= 0 or cellsPerAxis <= 0:
raise TypeError("Parameters moduleCount and cellsPerAxis must be > 0")
if moduleCount != len(scale) or moduleCount != len(orientation):
raise TypeError("scale and orientation arrays len must match moduleCount")
if dimensions < 2:
raise TypeError("dimensions must be >= 2")
self.moduleCount = moduleCount
self.cellsPerAxis = cellsPerAxis
self.cellCount = cellsPerAxis * cellsPerAxis
self.scale = list(scale)
self.orientation = list(orientation)
self.anchorInputSize = anchorInputSize
self.activeFiringRate = activeFiringRate
self.bumpSigma = bumpSigma
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.learningThreshold = learningThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.bumpOverlapMethod = bumpOverlapMethod
self.learningMode = learningMode
self.dualPhase = dualPhase
self.dimensions = dimensions
self.seed = seed
# This flag controls whether the region is processing sensation or movement
# on dual phase configuration
self._sensing = False
self._modules = None
self._projection = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount, # Number of columns in the SP, a required parameter
inputWidth, # Size of inputs to the SP, a required parameter
cellsPerColumn, # Number of cells per column, required
# Constructor arguments are picked up automatically. There is no
# need to add them anywhere in TMRegion, unless you need to do
# something special with them. See docstring above.
orColumnOutputs=False,
cellsSavePath='',
temporalImp=gDefaultTemporalImp,
anomalyMode=False,
computePredictedActiveCellIndices=False,
**kwargs):
# Which Temporal implementation?
TemporalClass = _getTPClass(temporalImp)
# Make a list of automatic temporal arg names for later use
# Pull out the temporal arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
tArgTuples = _buildArgs(TemporalClass.__init__, self, kwargs)
self._temporalArgNames = [t[0] for t in tArgTuples]
self.learningMode = True # Start out with learning enabled
self.inferenceMode = False
self.anomalyMode = anomalyMode
self.computePredictedActiveCellIndices = computePredictedActiveCellIndices
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
self.outputWidth = columnCount * cellsPerColumn
self.cellsPerColumn = cellsPerColumn
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initialize()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# TMRegion only, or special handling
self.orColumnOutputs = orColumnOutputs
self.temporalImp = temporalImp
# Various file names
self.storeDenseOutput = False
self.logPathOutput = ''
self.cellsSavePath = cellsSavePath
self._fpLogTPOutput = None
# Variables set up in initInNetwork()
self._tfdr = None # FDRTemporal instance
def __init__(self,
columnCount=2048,
cellsPerColumn=16,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
defaultOutputType = "active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.inputWidth = self.columnCount*self.cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
PyRegion.__init__(self, **kwargs)
def __init__(self,
# Input sizes
columnCount,
basalInputWidth,
apicalInputWidth=0,
# TM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
reducedBasalThreshold=13, # ApicalTiebreak and ApicalDependent only
sampleSize=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
basalPredictedSegmentDecrement=0.0,
apicalPredictedSegmentDecrement=0.0,
learnOnOneCell=False, # ApicalTiebreakCPP only
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255, # ApicalTiebreakCPP only
seed=42,
# Region params
implementation="ApicalTiebreak",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.reducedBasalThreshold = reducedBasalThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.basalPredictedSegmentDecrement = basalPredictedSegmentDecrement
self.apicalPredictedSegmentDecrement = apicalPredictedSegmentDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.maxSegmentsPerCell = maxSegmentsPerCell
self.learnOnOneCell = learnOnOneCell
self.seed = seed
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def setParameter(self, name, index, value):
"""Set the value of a parameter."""
if name == "SVDSampleCount":
self._SVDSampleCount = value
elif name == "logPath":
self._logPath = value
else:
PyRegion.setParameter(self, name, index, value)
def __init__(self,
cellCount=4096,
inputWidth=16384,
numOtherCorticalColumns=0,
sdrSize=40,
# Proximal
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence=0.6,
sampleSizeProximal=20,
minThresholdProximal=1,
connectedPermanenceProximal=0.50,
# Distal
synPermDistalInc=0.10,
synPermDistalDec=0.10,
initialDistalPermanence=0.21,
sampleSizeDistal=20,
activationThresholdDistal=13,
connectedPermanenceDistal=0.50,
distalSegmentInhibitionFactor=1.5,
seed=42,
defaultOutputType = "active",
**kwargs):
# Used to derive Column Pooler params
self.numOtherCorticalColumns = numOtherCorticalColumns
# Column Pooler params
self.inputWidth = inputWidth
self.cellCount = cellCount
self.sdrSize = sdrSize
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.sampleSizeProximal = sampleSizeProximal
self.minThresholdProximal = minThresholdProximal
self.connectedPermanenceProximal = connectedPermanenceProximal
self.synPermDistalInc = synPermDistalInc
self.synPermDistalDec = synPermDistalDec
self.initialDistalPermanence = initialDistalPermanence
self.sampleSizeDistal = sampleSizeDistal
self.activationThresholdDistal = activationThresholdDistal
self.connectedPermanenceDistal = connectedPermanenceDistal
self.distalSegmentInhibitionFactor = distalSegmentInhibitionFactor
self.seed = seed
# Region params
self.learningMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount=2048,
inputWidth=16384,
lateralInputWidth=0,
activationThresholdDistal=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThresholdProximal=1,
minThresholdDistal=10,
maxNewProximalSynapseCount=20,
maxNewDistalSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence = 0.6,
seed=42,
numActiveColumnsPerInhArea=40,
defaultOutputType = "active",
**kwargs):
# Modified Column Pooler params
self.columnCount = columnCount
# Column Pooler params
self.inputWidth = inputWidth
self.lateralInputWidth = lateralInputWidth
self.activationThresholdDistal = activationThresholdDistal
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThresholdProximal = minThresholdProximal
self.minThresholdDistal = minThresholdDistal
self.maxNewProximalSynapseCount = maxNewProximalSynapseCount
self.maxNewDistalSynapseCount = maxNewDistalSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.seed = seed
self.numActiveColumnsPerInhArea = numActiveColumnsPerInhArea
self.maxSynapsesPerSegment = inputWidth
# Region params
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def getParameter(self, parameterName, index=-1):
"""
Get the value of a NodeSpec parameter. Most parameters are handled
automatically by PyRegion's parameter get mechanism. The ones that need
special treatment are explicitly handled here.
"""
return PyRegion.getParameter(self, parameterName, index)
def getParameter(self, parameterName, index=-1):
"""
Overrides :meth:`~nupic.bindings.regions.PyRegion.PyRegion.getParameter`.
Most parameters are handled automatically by PyRegion's parameter get
mechanism. The ones that need special treatment are explicitly handled here.
"""
if parameterName == 'activeOutputCount':
return self.columnCount
elif parameterName == 'spatialPoolerInput':
return list(self._spatialPoolerInput.reshape(-1))
elif parameterName == 'spatialPoolerOutput':
return list(self._spatialPoolerOutput)
elif parameterName == 'spNumActiveOutputs':
return len(self._spatialPoolerOutput.nonzero()[0])
elif parameterName == 'spOutputNonZeros':
return [len(self._spatialPoolerOutput)] + \
list(self._spatialPoolerOutput.nonzero()[0])
elif parameterName == 'spInputNonZeros':
import pdb
pdb.set_trace()
return [len(self._spatialPoolerInput)] + \
list(self._spatialPoolerInput.nonzero()[0])
elif parameterName == 'spLearningStatsStr':
try:
return str(self._sfdr.getLearningStats())
except:
return str(dict())
else:
return PyRegion.getParameter(self, parameterName, index)
def getParameter(self, parameterName, index=-1):
"""
Get the value of a NodeSpec parameter. Most parameters are handled
automatically by PyRegion's parameter get mechanism. The ones that need
special treatment are explicitly handled here.
"""
return PyRegion.getParameter(self, parameterName, index)
def setParameter(self, name, index, value):
"""
Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.setParameter`.
"""
if name == "learningMode":
self.learningMode = bool(int(value))
self._epoch = 0
elif name == "inferenceMode":
self._epoch = 0
if int(value) and not self.inferenceMode:
self._finishLearning()
self.inferenceMode = bool(int(value))
elif name == "distanceNorm":
self._knn.distanceNorm = value
elif name == "distanceMethod":
self._knn.distanceMethod = value
elif name == "keepAllDistances":
self.keepAllDistances = bool(value)
if not self.keepAllDistances:
# Discard all distances except the latest
if self._protoScores is not None and self._protoScores.shape[0] > 1:
self._protoScores = self._protoScores[-1,:]
if self._protoScores is not None:
self._protoScoreCount = 1
else:
self._protoScoreCount = 0
elif name == "verbosity":
self.verbosity = value
self._knn.verbosity = value
else:
return PyRegion.setParameter(self, name, index, value)
def setParameter(self, name, index, value):
"""
Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.setParameter`.
"""
if name == "learningMode":
self.learningMode = bool(int(value))
self._epoch = 0
elif name == "inferenceMode":
self._epoch = 0
if int(value) and not self.inferenceMode:
self._finishLearning()
self.inferenceMode = bool(int(value))
elif name == "distanceNorm":
self._knn.distanceNorm = value
elif name == "distanceMethod":
self._knn.distanceMethod = value
elif name == "keepAllDistances":
self.keepAllDistances = bool(value)
if not self.keepAllDistances:
# Discard all distances except the latest
if self._protoScores is not None and self._protoScores.shape[0] > 1:
self._protoScores = self._protoScores[-1,:]
if self._protoScores is not None:
self._protoScoreCount = 1
else:
self._protoScoreCount = 0
elif name == "verbosity":
self.verbosity = value
self._knn.verbosity = value
else:
return PyRegion.setParameter(self, name, index, value)
def getParameter(self, name, index=-1): """ Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.getParameter`. """ # If any spec parameter name is the same as an attribute, this call # will get it automatically, e.g. self.learningMode return PyRegion.getParameter(self, name, index)
def setParameter(self, name, index, value):
"""
Set the value of the parameter.
@param name -- the name of the parameter to update, as defined
by the Node Spec.
@param value -- the value to which the parameter is to be set.
"""
if name == "learningMode":
self.learningMode = bool(int(value))
self._epoch = 0
elif name == "inferenceMode":
self._epoch = 0
if int(value) and not self.inferenceMode:
self._finishLearning()
self.inferenceMode = bool(int(value))
elif name == "distanceNorm":
self._knn.distanceNorm = value
elif name == "distanceMethod":
self._knn.distanceMethod = value
elif name == "keepAllDistances":
self.keepAllDistances = bool(value)
if not self.keepAllDistances:
# Discard all distances except the latest
if self._protoScores is not None and self._protoScores.shape[0] > 1:
self._protoScores = self._protoScores[-1,:]
if self._protoScores is not None:
self._protoScoreCount = 1
else:
self._protoScoreCount = 0
elif name == "clVerbosity":
self.verbosity = value
self._knn.verbosity = value
else:
return PyRegion.setParameter(self, name, index, value)
def getParameter(self, name, index=-1): """ Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.getParameter`. """ # If any spec parameter name is the same as an attribute, this call # will get it automatically, e.g. self.learningMode return PyRegion.getParameter(self, name, index)
def getParameter(self, parameterName, index=-1):
"""
Get the value of a NodeSpec parameter. Most parameters are handled
automatically by PyRegion's parameter get mechanism. The ones that need
special treatment are explicitly handled here.
"""
if parameterName == 'activeOutputCount':
return self.columnCount
elif parameterName == 'spatialPoolerInput':
return list(self._spatialPoolerInput.reshape(-1))
elif parameterName == 'spatialPoolerOutput':
return list(self._spatialPoolerOutput)
elif parameterName == 'spNumActiveOutputs':
return len(self._spatialPoolerOutput.nonzero()[0])
elif parameterName == 'spOutputNonZeros':
return [len(self._spatialPoolerOutput)] + \
list(self._spatialPoolerOutput.nonzero()[0])
elif parameterName == 'spInputNonZeros':
import pdb; pdb.set_trace()
return [len(self._spatialPoolerInput)] + \
list(self._spatialPoolerInput.nonzero()[0])
elif parameterName == 'spLearningStatsStr':
try:
return str(self._sfdr.getLearningStats())
except:
return str(dict())
else:
return PyRegion.getParameter(self, parameterName, index)
def __init__(self,
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=1,
formInternalConnections=1,
formInternalBasalConnections=1,
defaultOutputType = "active",
monitor=False,
implementation="cpp",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = bool(learnOnOneCell)
self.learningMode = True
self.inferenceMode = True
self.formInternalConnections = bool(formInternalConnections)
self.formInternalBasalConnections = bool(formInternalBasalConnections)
self.defaultOutputType = defaultOutputType
self.monitor = monitor
self.implementation = implementation
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
verbosity=0,
colorOption=False,
colorDiscreteIntensity=5,
**kwargs):
self._colorOption = colorOption
self._colorDiscreteIntensity = colorDiscreteIntensity
self.dataSource = None
self.verbosity = verbosity
self._inputWidth = 768 * 1024 * 3
# fixed universe input
self._dataWidth = 160 * 160 * 3 * 5 if colorOption else 160 * 160
# output size dependent on color option
# lastRecord is the last record returned. Used for debugging only
self.lastRecord = None
PyRegion.__init__(self, **kwargs)
def getParameter(self, name, index=-1):
"""
Get the value of the parameter.
@param name -- the name of the parameter to retrieve, as defined
by the Node Spec.
"""
if name == "patternCount":
return self._knn._numPatterns
elif name == "patternMatrix":
return self._getPatternMatrix()
elif name == "k":
return self._knn.k
elif name == "distanceNorm":
return self._knn.distanceNorm
elif name == "distanceMethod":
return self._knn.distanceMethod
elif name == "distThreshold":
return self._knn.distThreshold
elif name == "inputThresh":
return self._knn.binarizationThreshold
elif name == "doBinarization":
return self._knn.doBinarization
elif name == "useSparseMemory":
return self._knn.useSparseMemory
elif name == "sparseThreshold":
return self._knn.sparseThreshold
elif name == "winnerCount":
return self._knn.numWinners
elif name == "relativeThreshold":
return self._knn.relativeThreshold
elif name == "SVDSampleCount":
v = self._knn.numSVDSamples
return v if v is not None else 0
elif name == "SVDDimCount":
v = self._knn.numSVDDims
return v if v is not None else 0
elif name == "fractionOfMax":
v = self._knn.fractionOfMax
return v if v is not None else 0
elif name == "useAuxiliary":
return self._useAuxiliary
elif name == "justUseAuxiliary":
return self._justUseAuxiliary
elif name == "doSphering":
return self._doSphering
elif name == "cellsPerCol":
return self._knn.cellsPerCol
elif name == "maxStoredPatterns":
return self.maxStoredPatterns
elif name == 'categoryRecencyList':
return self._knn._categoryRecencyList
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def getParameter(self, name, index=-1):
"""
Get the value of the parameter.
@param name -- the name of the parameter to retrieve, as defined
by the Node Spec.
"""
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def setParameter(self, name, index, value):
"""
Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.setParameter`.
"""
if name == "learningMode":
self.learningMode = bool(int(value))
elif name == "inferenceMode":
self.inferenceMode = bool(int(value))
else:
return PyRegion.setParameter(self, name, index, value)
def setParameter(self, name, index, value):
"""
Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.setParameter`.
"""
if name == "learningMode":
self.learningMode = bool(int(value))
elif name == "inferenceMode":
self.inferenceMode = bool(int(value))
else:
return PyRegion.setParameter(self, name, index, value)
def __init__(self,
columnDimensions=(2048, ),
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=False,
tmImp=getDefaultTMImp(),
**kwargs):
# Pull out the tm arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
self._tmClass = getTMClass(tmImp)
tmArgTuples = _buildArgs(self._tmClass, self, kwargs)
# Make a list of automatic tm arg names for later use
self._tmArgNames = [t[0] for t in tmArgTuples]
# Defaults for all other parameters
self.columnDimensions = copy.deepcopy(columnDimensions)
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = learnOnOneCell
self.learningMode = True
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnDimensions=(2048,),
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=False,
tmImp=getDefaultTMImp(),
**kwargs):
# Pull out the tm arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
self._tmClass = getTMClass(tmImp)
tmArgTuples = _buildArgs(self._tmClass, self, kwargs)
# Make a list of automatic tm arg names for later use
self._tmArgNames = [t[0] for t in tmArgTuples]
# Defaults for all other parameters
self.columnDimensions = copy.deepcopy(columnDimensions)
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = learnOnOneCell
self.learningMode = True
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def getParameter(self, parameterName, index=-1):
"""
Get the value of a parameter. Most parameters are handled automatically by
PyRegion's parameter get mechanism. The ones that need special treatment
are explicitly handled here.
"""
if parameterName in self._temporalArgNames:
return getattr(self._tfdr, parameterName)
else:
return PyRegion.getParameter(self, parameterName, index)
def getParameter(self, parameterName, index=-1):
"""
Get the value of a parameter. Most parameters are handled automatically by
PyRegion's parameter get mechanism. The ones that need special treatment
are explicitly handled here.
"""
if parameterName in self._temporalArgNames:
return getattr(self._tfdr, parameterName)
else:
return PyRegion.getParameter(self, parameterName, index)
def __init__(self,
columnCount=2048,
inputWidth=16384,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence = 0.6,
seed=42,
numActiveColumnsPerInhArea=40,
defaultOutputType = "active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.inputWidth = inputWidth
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.seed = seed
self.learningMode = True
self.inferenceMode = True
self.defaultOutputType = defaultOutputType
self.numActiveColumnsPerInhArea = numActiveColumnsPerInhArea
self._pooler = None
PyRegion.__init__(self, **kwargs)
def getParameter(self, parameterName, index=-1):
"""
Overrides :meth:`~nupic.bindings.regions.PyRegion.PyRegion.getParameter`.
Get the value of a parameter. Most parameters are handled automatically by
:class:`~nupic.bindings.regions.PyRegion.PyRegion`'s parameter get mechanism. The
ones that need special treatment are explicitly handled here.
"""
if parameterName in self._temporalArgNames:
return getattr(self._tfdr, parameterName)
else:
return PyRegion.getParameter(self, parameterName, index)
def __init__(self,
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=1,
temporalImp="tm",
formInternalConnections=1,
defaultOutputType="active",
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = bool(learnOnOneCell)
self.learningMode = True
self.inferenceMode = True
self.temporalImp = temporalImp
self.formInternalConnections = bool(formInternalConnections)
self.defaultOutputType = defaultOutputType
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
seed=42,
learnOnOneCell=1,
temporalImp="tm",
formInternalConnections = 1,
**kwargs):
# Defaults for all other parameters
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.seed = seed
self.learnOnOneCell = bool(learnOnOneCell)
self.learningMode = True
self.inferenceMode = True
self.temporalImp = temporalImp
self.formInternalConnections = bool(formInternalConnections)
self.previouslyPredictedCells = set()
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def setParameter(self, name, index, value):
"""
Set the value of the parameter.
@param name -- the name of the parameter to update, as defined
by the Node Spec.
@param value -- the value to which the parameter is to be set.
"""
if name == "learningMode":
self.learningMode = bool(int(value))
elif name == "inferenceMode":
self.inferenceMode = bool(int(value))
else:
return PyRegion.setParameter(self, name, index, value)
def getParameter(self, name, index=-1):
"""
Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.getParameter`.
"""
if name == "trainRecords":
return self.trainRecords
elif name == "anomalyThreshold":
return self.anomalyThreshold
elif name == "activeColumnCount":
return self._activeColumnCount
elif name == "classificationMaxDist":
return self._classificationMaxDist
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def getParameter(self, name, index=-1):
"""
Overrides :meth:`nupic.bindings.regions.PyRegion.PyRegion.getParameter`.
"""
if name == "trainRecords":
return self.trainRecords
elif name == "anomalyThreshold":
return self.anomalyThreshold
elif name == "activeColumnCount":
return self._activeColumnCount
elif name == "classificationMaxDist":
return self._classificationMaxDist
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def setParameter(self, name, index, value):
"""
Set the value of the parameter.
@param name -- the name of the parameter to update, as defined
by the Node Spec.
@param value -- the value to which the parameter is to be set.
"""
if name == "trainRecords":
# Ensure that the trainRecords can only be set to minimum of the ROWID in
# the saved states
if not (isinstance(value, float) or isinstance(value, int)):
raise CLAModelInvalidArgument(
"Invalid argument type \'%s\'. threshold "
"must be a number." % (type(value)))
if len(self._recordsCache
) > 0 and value < self._recordsCache[0].ROWID:
raise CLAModelInvalidArgument(
"Invalid value. autoDetectWaitRecord "
"value must be valid record within output stream. Current minimum "
" ROWID in output stream is %d." %
(self._recordsCache[0].ROWID))
self.trainRecords = value
# Remove any labels before the first cached record (wont be used anymore)
self._deleteRangeFromKNN(0, self._recordsCache[0].ROWID)
# Reclassify all states
self.classifyStates()
elif name == "anomalyThreshold":
if not (isinstance(value, float) or isinstance(value, int)):
raise CLAModelInvalidArgument(
"Invalid argument type \'%s\'. threshold "
"must be a number." % (type(value)))
self.anomalyThreshold = value
self.classifyStates()
elif name == "classificationMaxDist":
if not (isinstance(value, float) or isinstance(value, int)):
raise CLAModelInvalidArgument(
"Invalid argument type \'%s\'. "
"classificationMaxDist must be a number." % (type(value)))
self._classificationMaxDist = value
self.classifyStates()
elif name == "activeColumnCount":
self._activeColumnCount = value
else:
return PyRegion.setParameter(self, name, index, value)
def getParameter(self, name, index=-1):
"""
Get the value of the parameter.
@param name -- the name of the parameter to retrieve, as defined
by the Node Spec.
"""
if name == "trainRecords":
return self.trainRecords
elif name == "anomalyThreshold":
return self.anomalyThreshold
elif name == "activeColumnCount":
return self._activeColumnCount
elif name == "classificationMaxDist":
return self._classificationMaxDist
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def getParameter(self, name, index=-1):
"""
Get the value of the parameter.
@param name -- the name of the parameter to retrieve, as defined
by the Node Spec.
"""
if name == "trainRecords":
return self.trainRecords
elif name == "anomalyThreshold":
return self.anomalyThreshold
elif name == "activeColumnCount":
return self._activeColumnCount
elif name == "classificationMaxDist":
return self._classificationMaxDist
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def setParameter(self, name, index, value):
"""
Set the value of the parameter.
@param name -- the name of the parameter to update, as defined
by the Node Spec.
@param value -- the value to which the parameter is to be set.
"""
if name == "trainRecords":
# Ensure that the trainRecords can only be set to minimum of the ROWID in
# the saved states
if not (isinstance(value, float) or isinstance(value, int)):
raise CLAModelInvalidArgument("Invalid argument type \'%s\'. threshold "
"must be a number." % (type(value)))
if len(self._recordsCache) > 0 and value < self._recordsCache[0].ROWID:
raise CLAModelInvalidArgument("Invalid value. autoDetectWaitRecord "
"value must be valid record within output stream. Current minimum "
" ROWID in output stream is %d." % (self._recordsCache[0].ROWID))
self.trainRecords = value
# Remove any labels before the first cached record (wont be used anymore)
self._deleteRangeFromKNN(0, self._recordsCache[0].ROWID)
# Reclassify all states
self.classifyStates()
elif name == "anomalyThreshold":
if not (isinstance(value, float) or isinstance(value, int)):
raise CLAModelInvalidArgument("Invalid argument type \'%s\'. threshold "
"must be a number." % (type(value)))
self.anomalyThreshold = value
self.classifyStates()
elif name == "classificationMaxDist":
if not (isinstance(value, float) or isinstance(value, int)):
raise CLAModelInvalidArgument("Invalid argument type \'%s\'. "
"classificationMaxDist must be a number." % (type(value)))
self._classificationMaxDist = value
self.classifyStates()
elif name == "activeColumnCount":
self._activeColumnCount = value
else:
return PyRegion.setParameter(self, name, index, value)
def setParameter(self, name, index, value):
"""
Set the value of the parameter.
@param name -- the name of the parameter to update, as defined
by the Node Spec.
@param value -- the value to which the parameter is to be set.
"""
if name == "learningMode":
if int(value) and not self.learningMode:
self._restartLearning()
self.learningMode = bool(int(value))
self._epoch = 0
elif name == "inferenceMode":
self._epoch = 0
if int(value) and not self.inferenceMode:
self._finishLearning()
self.inferenceMode = bool(int(value))
elif name == "distanceNorm":
self._knn.distanceNorm = value
elif name == "distanceMethod":
self._knn.distanceMethod = value
elif name == "keepAllDistances":
self.keepAllDistances = bool(value)
if not self.keepAllDistances:
# Discard all distances except the latest
if self._protoScores is not None and self._protoScores.shape[
0] > 1:
self._protoScores = self._protoScores[-1, :]
if self._protoScores is not None:
self._protoScoreCount = 1
else:
self._protoScoreCount = 0
elif name == "clVerbosity":
self.verbosity = value
self._knn.verbosity = value
elif name == "doSelfValidation":
self.doSelfValidation = value
else:
return PyRegion.setParameter(self, name, index, value)
def getParameter(self, name, index=-1):
"""
Get the value of a parameter.
Note: this method may be overridden by derived classes, but if so, then
the derived class should invoke this base method if 'name'
is unknown to the derived class.
@param name -- the name of the parameter to retrieve, as defined
by the Node Spec.
"""
if name == "SVDSampleCount":
return self._SVDSampleCount
elif name == "SVDDimCount":
return self._SVDDimCount
elif name == "fractionOfMax":
return self._fractionOfMax
elif name == "trainingSampleCount":
return self.gettrainingSampleCount()
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def getParameter(self, name, index=-1):
"""
Get the value of a parameter.
Note: this method may be overridden by derived classes, but if so, then
the derived class should invoke this base method if 'name'
is unknown to the derived class.
@param name -- the name of the parameter to retrieve, as defined
by the Node Spec.
"""
if name == "SVDSampleCount":
return self._SVDSampleCount
elif name == "SVDDimCount":
return self._SVDDimCount
elif name == "fractionOfMax":
return self._fractionOfMax
elif name == "trainingSampleCount":
return self.gettrainingSampleCount()
else:
# If any spec parameter name is the same as an attribute, this call
# will get it automatically, e.g. self.learningMode
return PyRegion.getParameter(self, name, index)
def __init__(
self,
# Modified ETM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
TDTraceDecay=0.0,
TDDiscount=0.0,
TDLearningRate=0.1,
globalValueDecay=0.0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
implementation="etm",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
# Reinforcement Learning variables (Eligability traces and values for each neuron)
self.TDDiscount = TDDiscount
self.TDLearningRate = TDLearningRate
self.TDTraceDecay = TDTraceDecay
self.globalValueDecay = globalValueDecay
self.traces = np.zeros(columnCount * cellsPerColumn)
self.values = np.zeros(columnCount * cellsPerColumn)
self.stateValue = 0
self.prevActiveCells = []
# Save prev. distal input for calculation with L5(t-1) distal input
self.prevActiveCellsExternalBasal = []
# For Debug save errors
self.TDError = 0
def __init__(
self,
# Modified ETM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
implementation="etm",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
# Custom use L2(t-1) and L4(t-1) input for basal
self.prevBasalInput = ()
def __init__(self, maxActive, outputWidth, **kwargs):
PyRegion.__init__(self, **kwargs)
self.maxActive = maxActive
self.outputWidth = outputWidth
def compute(self, inputs, outputs):
if "dataIn" in inputs:
PyRegion.setSparseOutput(outputs, "dataOut", inputs["dataIn"])
else:
PyRegion.setSparseOutput(outputs, "dataOut", self.data)
def compute(self, inputs, outputs):
if "dataIn" in inputs:
PyRegion.setSparseOutput(outputs, "dataOut", inputs["dataIn"])
else:
PyRegion.setSparseOutput(outputs, "dataOut", self.data)
def __init__(self,
cellCount=4096,
inputWidth=16384,
numOtherCorticalColumns=0,
sdrSize=40,
onlineLearning = False,
maxSdrSize = None,
minSdrSize = None,
# Proximal
synPermProximalInc=0.1,
synPermProximalDec=0.001,
initialProximalPermanence=0.6,
sampleSizeProximal=20,
minThresholdProximal=1,
connectedPermanenceProximal=0.50,
predictedInhibitionThreshold=20,
# Distal
synPermDistalInc=0.10,
synPermDistalDec=0.10,
initialDistalPermanence=0.21,
sampleSizeDistal=20,
activationThresholdDistal=13,
connectedPermanenceDistal=0.50,
inertiaFactor=1.,
seed=42,
defaultOutputType = "active",
**kwargs):
# Used to derive Column Pooler params
self.numOtherCorticalColumns = numOtherCorticalColumns
# Column Pooler params
self.inputWidth = inputWidth
self.cellCount = cellCount
self.sdrSize = sdrSize
self.onlineLearning = onlineLearning
self.maxSdrSize = maxSdrSize
self.minSdrSize = minSdrSize
self.synPermProximalInc = synPermProximalInc
self.synPermProximalDec = synPermProximalDec
self.initialProximalPermanence = initialProximalPermanence
self.sampleSizeProximal = sampleSizeProximal
self.minThresholdProximal = minThresholdProximal
self.connectedPermanenceProximal = connectedPermanenceProximal
self.predictedInhibitionThreshold = predictedInhibitionThreshold
self.synPermDistalInc = synPermDistalInc
self.synPermDistalDec = synPermDistalDec
self.initialDistalPermanence = initialDistalPermanence
self.sampleSizeDistal = sampleSizeDistal
self.activationThresholdDistal = activationThresholdDistal
self.connectedPermanenceDistal = connectedPermanenceDistal
self.inertiaFactor = inertiaFactor
self.seed = seed
# Region params
self.learningMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(self,
columnCount, # Number of columns in the SP, a required parameter
inputWidth, # Size of inputs to the SP, a required parameter
cellsPerColumn, # Number of cells per column, required
# Constructor arguments are picked up automatically. There is no
# need to add them anywhere in TMRegion, unless you need to do
# something special with them. See docstring above.
orColumnOutputs=False,
cellsSavePath='',
temporalImp=gDefaultTemporalImp,
anomalyMode=False,
computePredictedActiveCellIndices=False,
**kwargs):
# Which Temporal implementation?
TemporalClass = _getTPClass(temporalImp)
# Make a list of automatic temporal arg names for later use
# Pull out the temporal arguments automatically
# These calls whittle down kwargs and create instance variables of TMRegion
tArgTuples = _buildArgs(TemporalClass.__init__, self, kwargs)
self._temporalArgNames = [t[0] for t in tArgTuples]
self.learningMode = True # Start out with learning enabled
self.inferenceMode = False
self.anomalyMode = anomalyMode
self.computePredictedActiveCellIndices = computePredictedActiveCellIndices
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
self.outputWidth = columnCount * cellsPerColumn
self.cellsPerColumn = cellsPerColumn
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initialize()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# TMRegion only, or special handling
self.orColumnOutputs = orColumnOutputs
self.temporalImp = temporalImp
# Various file names
self.storeDenseOutput = False
self.logPathOutput = ''
self.cellsSavePath = cellsSavePath
self._fpLogTPOutput = None
# Variables set up in initInNetwork()
self._tfdr = None # FDRTemporal instance
def __init__(self,
moduleCount,
cellsPerAxis,
scale,
orientation,
anchorInputSize,
activeFiringRate,
bumpSigma,
activationThreshold=10,
initialPermanence=0.21,
connectedPermanence=0.50,
learningThreshold=10,
sampleSize=20,
permanenceIncrement=0.1,
permanenceDecrement=0.0,
maxSynapsesPerSegment=-1,
bumpOverlapMethod="probabilistic",
learningMode=False,
seed=42,
dualPhase=True,
dimensions=2,
**kwargs):
if moduleCount <= 0 or cellsPerAxis <= 0:
raise TypeError(
"Parameters moduleCount and cellsPerAxis must be > 0")
if moduleCount != len(scale) or moduleCount != len(orientation):
raise TypeError(
"scale and orientation arrays len must match moduleCount")
if dimensions < 2:
raise TypeError("dimensions must be >= 2")
self.moduleCount = moduleCount
self.cellsPerAxis = cellsPerAxis
self.cellCount = cellsPerAxis * cellsPerAxis
self.scale = list(scale)
self.orientation = list(orientation)
self.anchorInputSize = anchorInputSize
self.activeFiringRate = activeFiringRate
self.bumpSigma = bumpSigma
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.learningThreshold = learningThreshold
self.sampleSize = sampleSize
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.bumpOverlapMethod = bumpOverlapMethod
self.learningMode = learningMode
self.dualPhase = dualPhase
self.dimensions = dimensions
self.seed = seed
# This flag controls whether the region is processing sensation or movement
# on dual phase configuration
self._sensing = False
self._modules = None
self._projection = None
PyRegion.__init__(self, **kwargs)
def __init__(self, maxActive, outputWidth, **kwargs):
PyRegion.__init__(self, **kwargs)
self.maxActive = maxActive
self.outputWidth = outputWidth
def __init__(self,
cellCount=4096,
inputWidth=16384,
numOtherCorticalColumns=0,
sdrSize=40,
maxSdrSize = None,
minSdrSize = None,
# Proximal
sampleSizeProximal=20,
# Distal
sampleSizeDistal=20,
inertiaFactor=1.,
# Bayesian
noise=0.01, # lambda
learningRate=0.1, # alpha
activationThreshold=0.5, # probability such that a cell becomes active
forgetting=0.1,
initMovingAverages=0.0,
useSupport=False,
avoidWeightExplosion=True,
resetProximalCounter=False,
useProximalProbabilities=True,
implementation="Bayesian",
seed=42,
defaultOutputType = "active",
**kwargs):
# Used to derive Column Pooler params
self.numOtherCorticalColumns = numOtherCorticalColumns
# Column Pooler params
self.inputWidth = inputWidth
self.cellCount = cellCount
self.sdrSize = sdrSize
self.maxSdrSize = maxSdrSize
self.minSdrSize = minSdrSize
self.sampleSizeProximal = sampleSizeProximal
self.sampleSizeDistal = sampleSizeDistal
self.inertiaFactor = inertiaFactor
self.seed = seed
self.activationThreshold = activationThreshold
self.learningRate = learningRate
self.noise = noise
self.implementation = implementation
self.forgetting = forgetting
self.initMovingAverages = initMovingAverages
self.useSupport = useSupport
self.avoidWeightExplosion = avoidWeightExplosion
self.resetProximalCounter = resetProximalCounter
self.useProximalProbabilities = useProximalProbabilities
# Region params
self.learningMode = True
self.defaultOutputType = defaultOutputType
self._pooler = None
PyRegion.__init__(self, **kwargs)
def __init__(
self,
# Modified TM params
basalInputWidth=0,
apicalInputWidth=0,
apicalGlobalDecay=0.000001,
TDLearningRate=0.5,
winnerSize=4,
motorCount=32,
synPermActiveIncMotor=0.04,
synPermInactiveDecMotor=0.008,
# TM params
columnCount=2048,
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
punishPredDec=0.0,
maxSynapsesPerSegment=255,
seed=42,
# Region params
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.columnCount = columnCount
self.cellsPerColumn = cellsPerColumn
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
# Motor specific
self.TDLearningRate = TDLearningRate
self.apicalGlobalDecay = apicalGlobalDecay
self.winnerSize = winnerSize
self.punishPredDec = punishPredDec
self.motorCount = motorCount
self.synPermActiveIncMotor = synPermActiveIncMotor
self.synPermInactiveDecMotor = synPermInactiveDecMotor
# Region params
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(self,
columnCount, # Number of columns in the SP, a required parameter
inputWidth, # Size of inputs to the SP, a required parameter
spatialImp=getDefaultSPImp(), #'py', 'cpp'
**kwargs):
if columnCount <= 0 or inputWidth <=0:
raise TypeError("Parameters columnCount and inputWidth must be > 0")
# Pull out the spatial arguments automatically
# These calls whittle down kwargs and create instance variables of SPRegion
self.spatialImp = spatialImp
self.SpatialClass = getSPClass(spatialImp)
sArgTuples = _buildArgs(self.SpatialClass.__init__, self, kwargs)
# Make a list of automatic spatial arg names for later use
self._spatialArgNames = [t[0] for t in sArgTuples]
# Learning and SP parameters.
# By default we start out in stage learn with inference disabled
self.learningMode = True
self.inferenceMode = False
self.anomalyMode = False
self.topDownMode = False
self.columnCount = columnCount
self.inputWidth = inputWidth
PyRegion.__init__(self, **kwargs)
# Initialize all non-persistent base members, as well as give
# derived class an opportunity to do the same.
self._loaded = False
self._initializeEphemeralMembers()
# Debugging support, used in _conditionalBreak
self.breakPdb = False
self.breakKomodo = False
# Defaults for all other parameters
self.logPathInput = ''
self.logPathOutput = ''
self.logPathOutputDense = ''
self._fpLogSPInput = None
self._fpLogSP = None
self._fpLogSPDense = None
#
# Variables set up in initInNetwork()
#
# Spatial instance
self._sfdr = None
# Spatial pooler's bottom-up output value: hang on to this output for
# top-down inference and for debugging
self._spatialPoolerOutput = None
# Spatial pooler's bottom-up input: hang on to this for supporting the
# spInputNonZeros parameter
self._spatialPoolerInput = None
def __init__(
self,
# Modified TM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
activationThreshold=13,
initialPermanence=0.21,
connectedPermanence=0.50,
minThreshold=10,
maxNewSynapseCount=20,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
formInternalBasalConnections=True,
learnOnOneCell=False,
maxSegmentsPerCell=255,
maxSynapsesPerSegment=255,
seed=42,
checkInputs=True,
# Region params
defaultOutputType="active",
implementation="etm",
learningMode=True,
inferenceMode=True,
**kwargs):
# Modified TM params
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.activationThreshold = activationThreshold
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.minThreshold = minThreshold
self.maxNewSynapseCount = maxNewSynapseCount
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.formInternalBasalConnections = formInternalBasalConnections
self.learnOnOneCell = learnOnOneCell
self.maxSegmentsPerCell = maxSegmentsPerCell
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.checkInputs = checkInputs
# Region params
self.defaultOutputType = defaultOutputType
self.implementation = implementation
self.learningMode = learningMode
self.inferenceMode = inferenceMode
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
def __init__(
self,
# Modified ETM params
columnCount=2048,
basalInputWidth=0,
apicalInputWidth=0,
# ETM params
cellsPerColumn=32,
initialPermanence=0.21,
connectedPermanence=0.50,
permanenceIncrement=0.10,
permanenceDecrement=0.10,
predictedSegmentDecrement=0.0,
maxSynapsesPerSegment=255,
seed=42,
sampleSize=20,
# apical, basal weighting
activationThresholdBasal=13,
activationThresholdApical=2,
minThresholdBasal=10,
minThresholdApical=1,
basalPredictedSegmentDecrement=0.001,
apicalPredictedSegmentDecrement=0.001,
# Region params
implementation="etm",
learn=True,
**kwargs):
# Input sizes (the network API doesn't provide these during initialize)
self.columnCount = columnCount
self.basalInputWidth = basalInputWidth
self.apicalInputWidth = apicalInputWidth
# TM params
self.cellsPerColumn = cellsPerColumn
self.initialPermanence = initialPermanence
self.connectedPermanence = connectedPermanence
self.permanenceIncrement = permanenceIncrement
self.permanenceDecrement = permanenceDecrement
self.predictedSegmentDecrement = predictedSegmentDecrement
self.maxSynapsesPerSegment = maxSynapsesPerSegment
self.seed = seed
self.sampleSize = sampleSize
# TM weight distal and apical differently
self.minThresholdBasal = minThresholdBasal
self.minThresholdApical = minThresholdApical
self.activationThresholdBasal = activationThresholdBasal
self.activationThresholdApical = activationThresholdApical
self.basalPredictedSegmentDecrement = basalPredictedSegmentDecrement
self.apicalPredictedSegmentDecrement = apicalPredictedSegmentDecrement
# Region params
self.implementation = implementation
self.learn = learn
PyRegion.__init__(self, **kwargs)
# TM instance
self._tm = None
# Custom use internal activation t-1 as basal input
self.prevActivation = np.array([])