def _allocateSpatialFDR(self, rfInput):
"""Allocate the spatial pooler instance."""
if self._sfdr:
return
# Retrieve the necessary extra arguments that were handled automatically
autoArgs = dict((name, getattr(self, name))
for name in self._spatialArgNames)
autoArgs.pop('coincidencesShape')
autoArgs.pop('inputShape')
autoArgs.pop('inputBorder')
autoArgs.pop('coincInputRadius')
autoArgs.pop('cloneMap')
autoArgs.pop('numCloneMasters')
coincidencesShape = (self.columnCount, 1)
inputShape = (1, self.inputWidth)
inputBorder = inputShape[1]/2
if inputBorder*2 >= inputShape[1]:
inputBorder -= 1
coincInputRadius = inputShape[1]/2
cloneMap, numCloneMasters = fdru.makeCloneMap(
columnsShape=coincidencesShape,
outputCloningWidth=coincidencesShape[1],
outputCloningHeight=coincidencesShape[0]
)
self._sfdr = FDRCSpatial2.FDRCSpatial2(
# These parameters are standard defaults for SPRegion
# They can be overridden by explicit calls to
# getParameter
cloneMap=cloneMap,
numCloneMasters=numCloneMasters,
coincidencesShape=coincidencesShape,
inputShape=inputShape,
inputBorder=inputBorder,
coincInputRadius = coincInputRadius,
**autoArgs)
self._sfdr.setStoreDenseOutput(self.storeDenseOutput)
def testSPFile():
""" Run test on the data file - the file has records previously encoded.
"""
spSize = 2048
spSet = 40
poolPct = 0.5
pattern = [50, 1000]
doLearn = True
PLOT_PRECISION = 100.0
distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1))
inputs = []
#file = open('~/Desktop/ExperimentResults/sampleArtificial.csv', 'rb')
#elemSize = 400
#numSet = 42
#file = open('~/Desktop/ExperimentResults/sampleDataBasilOneField.csv', 'rb')
#elemSize = 499
#numSet = 7
outdir = '~/Desktop/ExperimentResults/Basil100x21'
inputFile = outdir + '.csv'
file = open(inputFile, 'rb')
elemSize = 100
numSet = 21
reader = csv.reader(file)
for row in reader:
input = np.array(map(float, row), dtype=realDType)
if len(input.nonzero()[0]) != numSet:
continue
inputs.append(input.copy())
file.close()
# Setup a SP
sp = FDRCSpatial2.FDRCSpatial2(coincidencesShape=(spSize, 1),
inputShape=(1, elemSize),
inputBorder=(elemSize - 1) / 2,
coincInputRadius=elemSize / 2,
numActivePerInhArea=spSet,
spVerbosity=0,
stimulusThreshold=0,
synPermConnected=0.10,
seed=1,
coincInputPoolPct=poolPct,
globalInhibition=True)
cleanPlot = False
doLearn = False
print 'Finished reading file, inputs/outputs to process =', len(inputs)
size = len(inputs)
for iter in xrange(100):
print 'Iteration', iter
# Learn
if iter != 0:
for learnRecs in xrange(pattern[0]):
ind = np.random.random_integers(0, size - 1, 1)[0]
sp.compute(inputs[ind], learn=True, infer=False)
# Test
for _ in xrange(pattern[1]):
rand1 = np.random.random_integers(0, size - 1, 1)[0]
rand2 = np.random.random_integers(0, size - 1, 1)[0]
output1 = sp.compute(inputs[rand1], learn=False, infer=True).copy()
output2 = sp.compute(inputs[rand2], learn=False, infer=True).copy()
outDist = (abs(output1 - output2) > 0.1)
intOutDist = int(outDist.sum() / 2 + 0.1)
inDist = (abs(inputs[rand1] - inputs[rand2]) > 0.1)
intInDist = int(inDist.sum() / 2 + 0.1)
if intInDist != numSet or intOutDist != spSet:
print rand1, rand2, '-', intInDist, intOutDist
x = int(PLOT_PRECISION * intOutDist / spSet)
y = int(PLOT_PRECISION * intInDist / numSet)
if distribMatrix[x, y] < 0.1:
distribMatrix[x, y] = 3
else:
if distribMatrix[x, y] < 10:
distribMatrix[x, y] += 1
if True:
plt.imshow(distribMatrix, origin='lower', interpolation="nearest")
plt.ylabel('SP (%d/%d) distance in pct' % (spSize, spSet))
plt.xlabel('Input (%d/%d) distance in pct' % (elemSize, numSet))
title = 'SP distribution'
title += ', iter = %d' % iter
title += ', Pct =%f' % poolPct
plt.suptitle(title, fontsize=12)
#plt.savefig(os.path.join('~/Desktop/ExperimentResults/videosArtData', '%s' % iter))
plt.savefig(os.path.join(outdir, '%s' % iter))
plt.clf()
distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1))
def testSPNew():
""" New version of the test"""
elemSize = 400
numSet = 42
addNear = True
numRecords = 1000
wantPlot = False
poolPct = 0.5
itr = 5
pattern = [60, 1000]
doLearn = True
start = 1
learnIter = 0
noLearnIter = 0
numLearns = 0
numTests = 0
numIter = 1
numGroups = 1000
PLOT_PRECISION = 100.0
distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1))
inputs = generateRandomInput(numGroups, elemSize, numSet)
# Setup a SP
sp = FDRCSpatial2.FDRCSpatial2(coincidencesShape=(2048, 1),
inputShape=(1, elemSize),
inputBorder=elemSize / 2 - 1,
coincInputRadius=elemSize / 2,
numActivePerInhArea=40,
spVerbosity=0,
stimulusThreshold=0,
synPermConnected=0.12,
seed=1,
coincInputPoolPct=poolPct,
globalInhibition=True)
cleanPlot = False
for i in xrange(numRecords):
input1 = getRandomWithMods(inputs, 4)
if i % 2 == 0:
input2 = getRandomWithMods(inputs, 4)
else:
input2 = input1.copy()
input2 = modifyBits(input2, 21)
inDist = (abs(input1 - input2) > 0.1)
intInDist = int(inDist.sum() / 2 + 0.1)
#print intInDist
if start == 0:
doLearn = True
learnIter += 1
if learnIter == pattern[start]:
numLearns += 1
start = 1
noLearnIter = 0
elif start == 1:
doLearn = False
noLearnIter += 1
if noLearnIter == pattern[start]:
numTests += 1
start = 0
learnIter = 0
cleanPlot = True
output1 = sp.compute(input1, learn=doLearn, infer=False).copy()
output2 = sp.compute(input2, learn=doLearn, infer=False).copy()
time.sleep(0.001)
outDist = (abs(output1 - output2) > 0.1)
intOutDist = int(outDist.sum() / 2 + 0.1)
if not doLearn and intOutDist < 2 and intInDist > 10:
"""
sp.spVerbosity = 10
sp.compute(input1, learn=doLearn, infer=False)
sp.compute(input2, learn=doLearn, infer=False)
sp.spVerbosity = 0
print 'Elements has very small SP distance: %d' % intOutDist
print output1.nonzero()
print output2.nonzero()
print sp._firingBoostFactors[output1.nonzero()[0]]
print sp._synPermBoostFactors[output1.nonzero()[0]]
print 'Input elements distance is %d' % intInDist
print input1.nonzero()
print input2.nonzero()
sys.stdin.readline()
"""
if not doLearn:
x = int(PLOT_PRECISION * intOutDist / 40.0)
y = int(PLOT_PRECISION * intInDist / 42.0)
if distribMatrix[x, y] < 0.1:
distribMatrix[x, y] = 3
else:
if distribMatrix[x, y] < 10:
distribMatrix[x, y] += 1
#print i
# If we don't want a plot, just continue
if wantPlot and cleanPlot:
plt.imshow(distribMatrix, origin='lower', interpolation="nearest")
plt.ylabel('SP (2048/40) distance in %')
plt.xlabel('Input (400/42) distance in %')
title = 'SP distribution'
#if doLearn:
# title += ', leaning ON'
#else:
# title += ', learning OFF'
title += ', learn sets = %d' % numLearns
title += ', test sets = %d' % numTests
title += ', iter = %d' % numIter
title += ', groups = %d' % numGroups
title += ', Pct =%f' % poolPct
plt.suptitle(title, fontsize=12)
#plt.show()
plt.savefig(
os.path.join('~/Desktop/ExperimentResults/videosNew',
'%s' % i))
plt.clf()
distribMatrix = np.zeros((PLOT_PRECISION + 1, PLOT_PRECISION + 1))
cleanPlot = False
def testSP():
""" Run a SP test
"""
elemSize = 400
numSet = 42
addNear = True
numRecords = 2
wantPlot = True
poolPct = 0.5
itr = 1
doLearn = True
while numRecords < 3:
# Setup a SP
sp = FDRCSpatial2.FDRCSpatial2(coincidencesShape=(2048, 1),
inputShape=(1, elemSize),
inputBorder=elemSize / 2 - 1,
coincInputRadius=elemSize / 2,
numActivePerInhArea=40,
spVerbosity=0,
stimulusThreshold=0,
seed=1,
coincInputPoolPct=poolPct,
globalInhibition=True)
# Generate inputs using rand()
inputs = generateRandomInput(numRecords, elemSize, numSet)
if addNear:
# Append similar entries (distance of 1)
appendInputWithNSimilarValues(inputs, 42)
inputSize = len(inputs)
print 'Num random records = %d, inputs to process %d' % (numRecords,
inputSize)
# Run a number of iterations, with learning on or off,
# retrieve results from the last iteration only
outputs = np.zeros((inputSize, 2048))
numIter = 1
if doLearn:
numIter = itr
for iter in xrange(numIter):
for i in xrange(inputSize):
time.sleep(0.001)
if iter == numIter - 1:
outputs[i] = sp.compute(inputs[i],
learn=doLearn,
infer=False)
#print outputs[i].sum(), outputs[i]
else:
sp.compute(inputs[i], learn=doLearn, infer=False)
# Build a plot from the generated input and output and display it
distribMatrix = generatePlot(outputs, inputs)
# If we don't want a plot, just continue
if wantPlot:
plt.imshow(distribMatrix, origin='lower', interpolation="nearest")
plt.ylabel('SP (2048/40) distance in %')
plt.xlabel('Input (400/42) distance in %')
title = 'SP distribution'
if doLearn:
title += ', leaning ON'
else:
title += ', learning OFF'
title += ', inputs = %d' % len(inputs)
title += ', iterations = %d' % numIter
title += ', poolPct =%f' % poolPct
plt.suptitle(title, fontsize=12)
plt.show()
#plt.savefig(os.path.join('~/Desktop/ExperimentResults/videos5', '%s' % numRecords))
#plt.clf()
numRecords += 1
return
def testInhibition(self):
"""
Test if the firing number of coincidences after inhibition
equals spatial poolernumActivePerInhArea.
"""
# Miscellaneous variables:
# n, w: n, w of encoders
# inputLen: Length of binary input
# synPermConnected: Spatial pooler synPermConnected
# synPermActiveInc: Spatial pooler synPermActiveInc
# connectPct: Initial connect percentage of permanences
# coincidencesShape: Number of spatial pooler coincidences
# numActivePerInhArea: Spatial pooler numActivePerInhArea
# stimulusThreshold: Spatial pooler stimulusThreshold
# spSeed: Spatial pooler for initial permanences
# stimulusThresholdInh: Parameter for inhibition, default value 0.00001
# kDutyCycleFactor: kDutyCycleFactor for dutyCycleTieBreaker in
# Inhibition
# spVerbosity: Verbosity to print other sp initial parameters
# testIter: Testing iterations
n = 100
w = 15
inputLen = 300
coincidencesShape = 2048
numActivePerInhArea = 40
stimulusThreshold = 0
spSeed = 1956
stimulusThresholdInh = 0.00001
kDutyCycleFactor = 0.01
spVerbosity = 0
testIter = 100
spTest = FDRCSpatial2.FDRCSpatial2(
coincidencesShape=(coincidencesShape, 1),
inputShape=(1, inputLen),
inputBorder=inputLen / 2 - 1,
coincInputRadius=inputLen / 2,
numActivePerInhArea=numActivePerInhArea,
spVerbosity=spVerbosity,
stimulusThreshold=stimulusThreshold,
seed=spSeed)
initialPermanence = spTest._initialPermanence()
spTest._masterPotentialM, spTest._masterPermanenceM = (
spTest._makeMasterCoincidences(spTest.numCloneMasters,
spTest._coincRFShape,
spTest.coincInputPoolPct,
initialPermanence, spTest.random))
spTest._updateInhibitionObj()
boostFactors = numpy.ones(coincidencesShape)
for i in range(testIter):
spTest._iterNum = i
# random binary input
input_ = numpy.zeros((1, inputLen))
nonzero = numpy.random.random(inputLen)
input_[0][numpy.where(nonzero < float(w) / float(n))] = 1
# overlap step
spTest._computeOverlapsFP(
input_, stimulusThreshold=spTest.stimulusThreshold)
spTest._overlaps *= boostFactors
onCellIndices = numpy.where(spTest._overlaps > 0)
spTest._onCells.fill(0)
spTest._onCells[onCellIndices] = 1
denseOn = spTest._onCells
# update _dutyCycleBeforeInh
spTest.dutyCyclePeriod = min(i + 1, 1000)
spTest._dutyCycleBeforeInh = (
(spTest.dutyCyclePeriod - 1) * spTest._dutyCycleBeforeInh +
denseOn) / spTest.dutyCyclePeriod
dutyCycleTieBreaker = spTest._dutyCycleAfterInh.copy()
dutyCycleTieBreaker *= kDutyCycleFactor
# inhibition step
numOn = spTest._inhibitionObj.compute(
spTest._overlaps + dutyCycleTieBreaker,
spTest._onCellIndices,
stimulusThresholdInh, # stimulusThresholdInh
max(spTest._overlaps) / 1000, # addToWinners
)
# update _dutyCycleAfterInh
spTest._onCells.fill(0)
onCellIndices = spTest._onCellIndices[0:numOn]
spTest._onCells[onCellIndices] = 1
denseOn = spTest._onCells
spTest._dutyCycleAfterInh = (
((spTest.dutyCyclePeriod - 1) * spTest._dutyCycleAfterInh +
denseOn) / spTest.dutyCyclePeriod)
# learning step
spTest._adaptSynapses(onCellIndices, [], input_)
# update boostFactor
spTest._updateBoostFactors()
boostFactors = spTest._firingBoostFactors
# update dutyCycle and boost
if ((spTest._iterNum + 1) % 50) == 0:
spTest._updateInhibitionObj()
spTest._updateMinDutyCycles(spTest._dutyCycleBeforeInh,
spTest.minPctDutyCycleBeforeInh,
spTest._minDutyCycleBeforeInh)
spTest._updateMinDutyCycles(spTest._dutyCycleAfterInh,
spTest.minPctDutyCycleAfterInh,
spTest._minDutyCycleAfterInh)
# test numOn and spTest.numActivePerInhArea
self.assertEqual(
numOn, spTest.numActivePerInhArea,
"Error at input %s, actual numOn are: %i, "
"numActivePerInhAre is: %s" % (i, numOn, numActivePerInhArea))
def frequency(self,
n=15,
w=7,
coincidencesShape=2048,
numActivePerInhArea=40,
stimulusThreshold=0,
spSeed=1,
spVerbosity=0,
numColors=2,
seed=42,
minVal=0,
maxVal=10,
encoder='category',
forced=True):
""" Helper function that tests whether the SP predicts the most
frequent record """
print "\nRunning SP overlap test..."
print encoder, 'encoder,', 'Random seed:', seed, 'and', numColors, 'colors'
#Setting up SP and creating training patterns
# Instantiate Spatial Pooler
spImpl = FDRCSpatial2.FDRCSpatial2(
coincidencesShape=(coincidencesShape, 1),
inputShape=(1, n),
inputBorder=(n - 2) / 2,
coincInputRadius=n / 2,
numActivePerInhArea=numActivePerInhArea,
spVerbosity=spVerbosity,
stimulusThreshold=stimulusThreshold,
coincInputPoolPct=0.5,
seed=spSeed,
spReconstructionParam='dutycycle',
)
rnd.seed(seed)
numpy.random.seed(seed)
colors = []
coincs = []
reUsedCoincs = []
spOutput = []
patterns = set([])
# Setting up the encodings
if encoder == 'scalar':
enc = scalar.ScalarEncoder(
name='car',
w=w,
n=n,
minval=minVal,
maxval=maxVal,
periodic=False,
forced=True
) # forced: it's strongly recommended to use w>=21, in the example we force skip the check for readibility
for y in xrange(numColors):
temp = enc.encode(rnd.random() * maxVal)
colors.append(numpy.array(temp, dtype=realDType))
else:
for y in xrange(numColors):
sdr = numpy.zeros(n, dtype=realDType)
# Randomly setting w out of n bits to 1
sdr[rnd.sample(xrange(n), w)] = 1
colors.append(sdr)
# Training the sp
print 'Starting to train the sp on', numColors, 'patterns'
startTime = time.time()
for i in xrange(numColors):
spInput = colors[i]
onCells = spImpl.compute(spInput, learn=True, infer=False)
spOutput.append(onCells.tolist())
activeCoincIndices = set(onCells.nonzero()[0])
# Checking if any of the active cells have been previously active
reUsed = activeCoincIndices.intersection(patterns)
if len(reUsed) == 0:
# The set of all coincidences that have won at least once
coincs.append((i, activeCoincIndices, colors[i]))
else:
reUsedCoincs.append((i, activeCoincIndices, colors[i]))
# Adding the active cells to the set of coincs that have been active at
# least once
patterns.update(activeCoincIndices)
if (i + 1) % 100 == 0:
print 'Record number:', i + 1
print "Elapsed time: %.2f seconds" % (time.time() - startTime)
print len(reUsedCoincs), "re-used coinc(s),"
# Check if results match expectations
summ = []
for z in coincs:
summ.append(
sum([len(z[1].intersection(y[1])) for y in reUsedCoincs]))
zeros = len([x for x in summ if x == 0])
factor = max(summ) * len(summ) / sum(summ)
if len(reUsed) < 10:
self.assertLess(
factor, 30,
"\nComputed factor: %d\nExpected Less than %d" % (factor, 30))
self.assertLess(
zeros, 0.99 * len(summ),
"\nComputed zeros: %d\nExpected Less than %d" %
(zeros, 0.99 * len(summ)))
else:
self.assertLess(
factor, 8,
"\nComputed factor: %d\nExpected Less than %d" % (factor, 8))
self.assertLess(
zeros, 12,
"\nComputed zeros: %d\nExpected Less than %d" % (zeros, 12))
def _runLearnInference(self,
n=30,
w=15,
coincidencesShape=2048,
numActivePerInhArea=40,
spSeed=1951,
spVerbosity=0,
numTrainingRecords=100,
seed=42):
# Instantiate two identical spatial pooler. One will be used only for
# learning. The other will be trained with identical records, but with
# random inference calls thrown in
spLearnOnly = FDRCSpatial2.FDRCSpatial2(
coincidencesShape=(coincidencesShape, 1),
inputShape=(1, n),
inputBorder=n / 2 - 1,
coincInputRadius=n / 2,
numActivePerInhArea=numActivePerInhArea,
spVerbosity=spVerbosity,
seed=spSeed,
synPermInactiveDec=0.01,
synPermActiveInc=0.2,
)
spLearnInfer = FDRCSpatial2.FDRCSpatial2(
coincidencesShape=(coincidencesShape, 1),
inputShape=(1, n),
inputBorder=n / 2 - 1,
coincInputRadius=n / 2,
numActivePerInhArea=numActivePerInhArea,
spVerbosity=spVerbosity,
seed=spSeed,
synPermInactiveDec=0.01,
synPermActiveInc=0.2,
)
random.seed(seed)
np.random.seed(seed)
# Build up training set with numTrainingRecords patterns
inputs = [] # holds post-encoded input patterns
for i in xrange(numTrainingRecords):
inputVector = np.zeros(n, dtype=realDType)
inputVector[random.sample(xrange(n), w)] = 1
inputs.append(inputVector)
# Train each SP with identical inputs
startTime = time.time()
random.seed(seed)
np.random.seed(seed)
for i in xrange(numTrainingRecords):
if spVerbosity > 0:
print "Input #%d" % i
encodedInput = inputs[i]
spLearnOnly.compute(encodedInput, learn=True, infer=False)
random.seed(seed)
np.random.seed(seed)
for i in xrange(numTrainingRecords):
if spVerbosity > 0:
print "Input #%d" % i
encodedInput = inputs[i]
spLearnInfer.compute(encodedInput, learn=True, infer=False)
print "\nElapsed time: %.2f seconds\n" % (time.time() - startTime)
# Test that both SP"s are identical by checking learning stats
# A more in depth test would check all the coincidences, duty cycles, etc.
# ala tpDiff
# Edit: spDiff has been written as an in depth tester of the spatial pooler
learnOnlyStats = spLearnOnly.getLearningStats()
learnInferStats = spLearnInfer.getLearningStats()
success = True
# Check that the two spatial poolers are equivalent after the same training.
success = success and spDiff(spLearnInfer, spLearnOnly)
self.assertTrue(success)
# Make sure that the pickled and loaded SPs are equivalent.
spPickle = pickle.dumps(spLearnOnly, protocol=0)
spLearnOnlyLoaded = pickle.loads(spPickle)
success = success and spDiff(spLearnOnly, spLearnOnlyLoaded)
self.assertTrue(success)
for k in learnOnlyStats.keys():
if learnOnlyStats[k] != learnInferStats[k]:
success = False
print "Stat", k, "is different:", learnOnlyStats[
k], learnInferStats[k]
self.assertTrue(success)
if success:
print "Test succeeded"