def main(SEED):
# input 生成
numOnBitsPerPattern = 3
(numCols, trainingSequences) = buildOverlappedSequences(
numSequences = 2, # 生成するsequenceの数
seqLen = 5, # sequenceの長さ
sharedElements = [2,3], # 異なるsequence間で同じものが含まれている番号
numOnBitsPerPattern = 3, # activeになるカラム数
patternOverlap = 0 # activeになるカラムが重なっている数
)
print numCols
for sequence in trainingSequences:
print sequence
# TP生成
tp = TP(
numberOfCols = numCols,
cellsPerColumn = 2,
initialPerm = 0.6,
connectedPerm = 0.5,
minThreshold = 3,
newSynapseCount = 3,
permanenceInc = 0.1,
permanenceDec = 0.0,
activationThreshold = 3,
globalDecay = 0.0,
burnIn = 1,
seed = SEED,
verbosity = 0,
checkSynapseConsistency = True,
pamLength = 1
)
# TP学習
for _ in range(10):
for seq_num, sequence in enumerate(trainingSequences):
for x in sequence:
x = numpy.array(x).astype('float32')
tp.compute(x, enableLearn = True, computeInfOutput=True)
#tp.printStates(False, False)
tp.reset()
# TP 予測
for seq_num, sequence in enumerate(trainingSequences):
for x in sequence:
x = numpy.array(x).astype('float32')
tp.compute(x, enableLearn = False, computeInfOutput = True)
tp.printStates(False, False)
print "\n\n--------","ABCDE"[j],"-----------" print "Raw input vector\n",formatRow(x[j]) # Send each vector to the TP, with learning turned off tp.compute(x[j], enableLearn = False, computeInfOutput = True) # This method prints out the active state of each cell followed by the # predicted state of each cell. For convenience the cells are grouped # 10 at a time. When there are multiple cells per column the printout # is arranged so the cells in a column are stacked together # # What you should notice is that the columns where active state is 1 # represent the SDR for the current input pattern and the columns where # predicted state is 1 represent the SDR for the next expected pattern print "\nAll the active and predicted cells:" tp.printStates(printPrevious = False, printLearnState = False) # tp.getPredictedState() gets the predicted cells. # predictedCells[c][i] represents the state of the i'th cell in the c'th # column. To see if a column is predicted, we can simply take the OR # across all the cells in that column. In numpy we can do this by taking # the max along axis 1. print "\n\nThe following columns are predicted by the temporal pooler. This" print "should correspond to columns in the *next* item in the sequence." predictedCells = tp.getPredictedState() print formatRow(predictedCells.max(axis=1).nonzero()) ####################################################################### # # This command prints the segments associated with every single cell. This is
# zeros out all the states. It is not strictly necessary but it's a bit
# messier without resets, and the TP learns quicker with resets.
tp.reset()
#######################################################################
#
# Step 3: send the same sequence of vectors and look at predictions made by
# temporal pooler
for j in range(5):
print "\n\n--------", "ABCDE"[j], "-----------"
print "Raw input vector\n", formatRow(x[j])
# Send each vector to the TP, with learning turned off
tp.compute(x[j], enableLearn=False, computeInfOutput=True)
# This method prints out the active state of each cell followed by the
# predicted state of each cell. For convenience the cells are grouped
# 10 at a time. When there are multiple cells per column the printout
# is arranged so the cells in a column are stacked together
#
# What you should notice is that the columns where active state is 1
# represent the SDR for the current input pattern and the columns where
# predicted state is 1 represent the SDR for the next expected pattern
tp.printStates(printPrevious=False, printLearnState=False)
#######################################################################
#
# This command prints the segments associated with every single cell
# This is commented out because it prints a ton of stuff.
#tp.printCells()
def main():
# create Temporal Pooler instance
tp = TP(numberOfCols=50, # カラム数
cellsPerColumn=2, # 1カラム中のセル数
initialPerm=0.5, # initial permanence
connectedPerm=0.5, # permanence の閾値
minThreshold=10, # 末梢樹状セグメントの閾値の下限?
newSynapseCount=10, # ?
permanenceInc=0.1, # permanenceの増加
permanenceDec=0.0, # permanenceの減少
activationThreshold=8, # synapseの発火がこれ以上かを確認している.
globalDecay=0, # decrease permanence?
burnIn=1, # Used for evaluating the prediction score
checkSynapseConsistency=False,
pamLength=10 # Number of time steps
)
# create input vectors to feed to the temporal pooler.
# Each input vector must be numberOfCols wide.
# Here we create a simple sequence of 5 vectors
# representing the sequence A -> B -> C -> D -> E
x = numpy.zeros((5,tp.numberOfCols), dtype="uint32")
x[0, 0:10] = 1 # A
x[1,10:20] = 1 # B
x[2,20:30] = 1 # C
x[3,30:40] = 1 # D
x[4,40:50] = 1 # E
print x
# repeat the sequence 10 times
for i in range(10):
# Send each letter in the sequence in order
# A -> B -> C -> D -> E
print
print
print '#### :', i
for j in range(5):
tp.compute(x[j], enableLearn = True, computeInfOutput=True)
#tp.printCells(predictedOnly=False)
tp.printStates(printPrevious = False, printLearnState = False)
# sequenceの最後を教える. 絶対必要なわけではないが, あった方が学習速い.
tp.reset()
for j in range(5):
print "\n\n--------","ABCDE"[j],"-----------"
print "Raw input vector\n",formatRow(x[j])
# Send each vector to the TP, with learning turned off
tp.compute(x[j], enableLearn = False, computeInfOutput = True)
# print predict state
print "\nAll the active and predicted cells:"
tp.printStates(printPrevious = False, printLearnState = False)
# get predict state
print "\n\nThe following columns are predicted by the temporal pooler. This"
print "should correspond to columns in the *next* item in the sequence."
predictedCells = tp.getPredictedState()
print formatRow(predictedCells.max(axis=1).nonzero())
