def killCellRegion(self, centerColumn, radius):
"""
Kill cells around a centerColumn, within radius
"""
self.deadCols = topology.wrappingNeighborhood(centerColumn, radius,
self._columnDimensions)
self.deadColumnInputSpan = self.getConnectedSpan(self.deadCols)
self.removeDeadColumns()
def killCellRegion(self, centerColumn, radius):
"""
Kill cells around a centerColumn, within radius
"""
self.deadCols = topology.wrappingNeighborhood(centerColumn,
radius,
self._columnDimensions)
self.deadColumnInputSpan = self.getConnectedSpan(self.deadCols)
self.removeDeadColumns()
def expectWrappingNeighborhoodCoords(self, centerCoords, radius, dimensions, expected):
centerIndex = indexFromCoordinates(centerCoords, dimensions)
numIndices = 0
for index, expectedIndex in zip(wrappingNeighborhood(centerIndex, radius, dimensions), expected):
numIndices += 1
self.assertEquals(index, indexFromCoordinates(expectedIndex, dimensions))
self.assertEquals(numIndices, len(expected))
def plotMovie(expName, numEpochs, killAt):
# plot RFcenters and inputCoverage over training
centerColumn = indexFromCoordinates((15, 15), (32, 32))
deadCols = topology.wrappingNeighborhood(centerColumn, 5, (32, 32))
for epoch in range(killAt, numEpochs):
fig, axs = plt.subplots(2, 2)
RFcenterInfo = np.load('results/RFcenters/{}/epoch_{}.npz'.format(expName, epoch))
RFcenters = RFcenterInfo['arr_0']
avgDistToCenter = RFcenterInfo['arr_1']
axs[0, 1].scatter(RFcenters[:, 0], RFcenters[:, 1], s=4, c=[1,1,1])
axs[0, 1].set_title('RF centers')
axs[0, 1].set_xlim([-1, 33])
axs[0, 1].set_ylim([-1, 33])
axs[0, 1].set_aspect('equal')
plt.axis('equal')
# # plot input space coverage
inputSpaceCoverage = np.load('results/InputCoverage/{}/epoch_{}.npz'.format(expName, epoch))
inputSpaceCoverage = inputSpaceCoverage['arr_0']
im1 = axs[0, 0].pcolor(inputSpaceCoverage, vmin=10, vmax=80)
axs[0, 0].set_title('Input Space Coverage')
axs[0, 0].set_xlim([-1, 33])
axs[0, 0].set_ylim([-1, 33])
axs[0, 0].set_aspect('equal')
plt.axis('equal')
boostFactors = np.load('results/boostFactors/{}/epoch_{}.npz'.format(expName, epoch))
boostFactors = boostFactors['arr_0']
# boostFactors[deadCols] = np.nan
boostFactors = np.reshape(boostFactors, (32, 32))
im2 = axs[1, 0].pcolor(boostFactors, vmin=0.5, vmax=1.5)
axs[1, 0].set_title('Boost Factors')
axs[1, 0].set_xlim([-1, 33])
axs[1, 0].set_ylim([-1, 33])
axs[1, 0].set_aspect('equal')
plt.axis('equal')
# fig.delaxes(axs[1, 0])
cax = fig.add_axes([0.55, 0.4, 0.3, 0.05])
fig.colorbar(im1, cax=cax, orientation='horizontal',
ticks=[0, 20, 40, 60, 80])
cax.set_xlabel('input space coverage')
cax = fig.add_axes([0.55, 0.2, 0.3, 0.05])
fig.colorbar(im2, cax=cax, orientation='horizontal',
ticks=[0, .5, 1, 1.5, 2])
cax.set_xlabel('boost factors')
fig.delaxes(axs[1, 1])
plt.savefig('figures/traumaMovie/{}_frame_{}.pdf'.format(expName, epoch))
plt.close(fig)
def expectWrappingNeighborhoodCoords(self, centerCoords, radius, dimensions,
expected):
centerIndex = indexFromCoordinates(centerCoords, dimensions)
numIndices = 0
for index, expectedIndex in zip(wrappingNeighborhood(centerIndex, radius,
dimensions),
expected):
numIndices += 1
self.assertEqual(index, indexFromCoordinates(expectedIndex, dimensions))
self.assertEqual(numIndices, len(expected))
def runSPexperiments(expConfig):
inputVectorType = expConfig.dataSet
params = getSDRDataSetParams(expConfig.dataSet, int(expConfig.seed))
expName = getExperimentName(expConfig)
createDirectories(expName)
sdrData = SDRDataSet(params)
inputVectors = sdrData.getInputVectors()
numInputVector, inputSize = inputVectors.shape
plt.figure()
plt.imshow(np.reshape(inputVectors[2], (params['nX'], params['nY'])),
interpolation='nearest',
cmap='gray')
plt.savefig('figures/exampleInputs/{}'.format(expName))
print
print "Runnning experiment: {}".format(expName)
print "Training Data Size {} Dimensions {}".format(numInputVector,
inputSize)
spParams = getSpatialPoolerParams(params, expConfig)
sp = createSpatialPooler(expConfig.spatialImp, spParams)
if expConfig.topology == 1 and expConfig.spatialImp in ['faulty_sp', 'py']:
initializeSPConnections(sp, potentialRaidus=10, initConnectionRadius=5)
numColumns = np.prod(sp.getColumnDimensions())
numTestInputs = int(numInputVector * 0.5)
testInputs = inputVectors[:numTestInputs, :]
connectedCounts = np.zeros((numColumns, ), dtype=uintType)
boostFactors = np.zeros((numColumns, ), dtype=realDType)
activeDutyCycle = np.zeros((numColumns, ), dtype=realDType)
metrics = {
'numConnectedSyn': [],
'numNewSyn': [],
'numRemoveSyn': [],
'stability': [],
'entropy': [],
'maxEntropy': [],
'sparsity': [],
'noiseRobustness': [],
'classification': [],
'meanBoostFactor': [],
'reconstructionError': [],
'witnessError': []
}
connectedSyns = getConnectedSyns(sp)
activeColumnsCurrentEpoch, dum = runSPOnBatch(sp, testInputs, learn=False)
inspectSpatialPoolerStats(sp, inputVectors, expName + "beforeTraining")
checkPoints = [
0, expConfig.changeDataSetAt - 1, expConfig.changeDataSetAt,
expConfig.numEpochs - 1
]
epoch = 0
while epoch < expConfig.numEpochs:
print "training SP epoch {} ".format(epoch)
if (expConfig.changeDataSetContinuously
or epoch == expConfig.changeDataSetAt):
params['seed'] = epoch
sdrData.generateInputVectors(params)
inputVectors = sdrData.getInputVectors()
numInputVector, inputSize = inputVectors.shape
testInputs = inputVectors[:numTestInputs, :]
if expConfig.killInputsAfter > 0 and epoch > expConfig.killInputsAfter:
if expConfig.topology == 1:
inputSpaceDim = (params['nX'], params['nY'])
centerColumn = indexFromCoordinates((15, 15), inputSpaceDim)
deadInputs = topology.wrappingNeighborhood(
centerColumn, 5, inputSpaceDim)
else:
zombiePermutation = np.random.permutation(inputSize)
deadInputs = zombiePermutation[:100]
inputVectors[:, deadInputs] = 0
if epoch == expConfig.killCellsAt:
if expConfig.spatialImp in ['faulty_sp', 'monitored_faulty_sp']:
if expConfig.topology == 1:
centerColumn = indexFromCoordinates((15, 15),
sp._columnDimensions)
sp.killCellRegion(centerColumn, 5)
else:
sp.killCells(expConfig.killCellPrct)
if expConfig.trackOverlapCurve:
noiseLevelList, inputOverlapScore, outputOverlapScore = \
calculateOverlapCurve(sp, testInputs)
metrics['noiseRobustness'].append(
np.trapz(np.flipud(np.mean(outputOverlapScore, 0)),
noiseLevelList))
np.savez(
'./results/input_output_overlap/{}/epoch_{}'.format(
expName, epoch), noiseLevelList, inputOverlapScore,
outputOverlapScore)
if expConfig.classification:
# classify SDRs with noise
noiseLevelList = np.linspace(0, 1.0, 21)
classification_accuracy = classificationAccuracyVsNoise(
sp, testInputs, noiseLevelList)
metrics['classification'].append(
np.trapz(classification_accuracy, noiseLevelList))
np.savez(
'./results/classification/{}/epoch_{}'.format(expName, epoch),
noiseLevelList, classification_accuracy)
# train SP here,
# Learn is turned off at the first epoch to gather stats of untrained SP
learn = False if epoch == 0 else True
# randomize the presentation order of input vectors
sdrOrders = np.random.permutation(np.arange(numInputVector))
activeColumnsTrain, meanBoostFactors = runSPOnBatch(
sp, inputVectors, learn, sdrOrders)
# run SP on test dataset and compute metrics
activeColumnsPreviousEpoch = copy.copy(activeColumnsCurrentEpoch)
activeColumnsCurrentEpoch, dum = runSPOnBatch(sp,
testInputs,
learn=False)
stability = calculateStability(activeColumnsCurrentEpoch,
activeColumnsPreviousEpoch)
if (expConfig.changeDataSetContinuously
or epoch == expConfig.changeDataSetAt):
stability = float('nan')
metrics['stability'].append(stability)
metrics['sparsity'].append(
np.mean(np.mean(activeColumnsCurrentEpoch, 1)))
metrics['entropy'].append(calculateEntropy(activeColumnsCurrentEpoch))
# generate ideal SP outputs where all columns have the same activation prob.
activeColumnsIdeal = np.random.rand(
numInputVector, numColumns) > metrics['sparsity'][-1]
metrics['maxEntropy'].append(calculateEntropy(activeColumnsIdeal))
connectedSynsPreviousEpoch = copy.copy(connectedSyns)
sp.getConnectedCounts(connectedCounts)
connectedSyns = getConnectedSyns(sp)
metrics['meanBoostFactor'].append(np.mean(meanBoostFactors))
sp.getActiveDutyCycles(activeDutyCycle)
metrics['numConnectedSyn'].append(np.sum(connectedCounts))
numNewSynapses = connectedSyns - connectedSynsPreviousEpoch
numNewSynapses[numNewSynapses < 0] = 0
metrics['numNewSyn'].append(np.sum(numNewSynapses))
numEliminatedSynapses = connectedSynsPreviousEpoch - connectedSyns
numEliminatedSynapses[numEliminatedSynapses < 0] = 0
metrics['numRemoveSyn'].append(np.sum(numEliminatedSynapses))
metrics['reconstructionError'].append(
reconstructionError(sp, testInputs, activeColumnsCurrentEpoch))
metrics['witnessError'].append(
witnessError(sp, testInputs, activeColumnsCurrentEpoch))
print tabulate(metrics, headers="keys")
if expConfig.checkRFCenters:
# check distribution of RF centers, useful to monitor recovery from trauma
RFcenters, avgDistToCenter = getRFCenters(sp,
params,
type='connected')
if expConfig.spatialImp == 'faulty_sp':
aliveColumns = sp.getAliveColumns()
else:
aliveColumns = np.arange(numColumns)
fig = plotReceptiveFieldCenter(RFcenters[aliveColumns, :],
connectedCounts[aliveColumns],
(params['nX'], params['nY']))
plt.savefig('figures/RFcenters/{}/epoch_{}.png'.format(
expName, epoch))
plt.close(fig)
np.savez('results/RFcenters/{}/epoch_{}'.format(expName, epoch),
RFcenters, avgDistToCenter)
if expConfig.checkInputSpaceCoverage:
# check coverage of input space, useful to monitor recovery from trauma
inputSpaceCoverage = calculateInputSpaceCoverage(sp)
np.savez(
'results/InputCoverage/{}/epoch_{}'.format(expName, epoch),
inputSpaceCoverage, connectedCounts)
plt.figure(2)
plt.clf()
plt.imshow(inputSpaceCoverage, interpolation='nearest', cmap="jet")
plt.colorbar()
plt.savefig('figures/InputCoverage/{}/epoch_{}.png'.format(
expName, epoch))
if expConfig.checkTestInput:
RFcenters, avgDistToCenter = getRFCenters(sp,
params,
type='connected')
inputIdx = 0
outputColumns = np.zeros((numColumns, 1), dtype=uintType)
sp.compute(testInputs[inputIdx, :], False, outputColumns)
activeColumns = np.where(outputColumns > 0)[0]
fig = plotReceptiveFieldCenter(RFcenters[aliveColumns, :],
connectedCounts[aliveColumns],
(params['nX'], params['nY']))
plt.scatter(RFcenters[activeColumns, 0],
RFcenters[activeColumns, 1],
color='r')
plt.savefig('figures/ResponseToTestInputs/{}/epoch_{}.png'.format(
expName, epoch))
if expConfig.saveBoostFactors:
np.savez('results/boostFactors/{}/epoch_{}'.format(expName, epoch),
meanBoostFactors)
if expConfig.showExampleRFs:
fig = plotReceptiveFields2D(sp, params['nX'], params['nY'])
plt.savefig('figures/exampleRFs/{}/epoch_{}'.format(
expName, epoch))
plt.close(fig)
if epoch in checkPoints:
# inspect SP again
inspectSpatialPoolerStats(sp, inputVectors,
expName + "epoch{}".format(epoch))
epoch += 1
# plot stats over training
fileName = 'figures/network_stats_over_training_{}.pdf'.format(expName)
plotSPstatsOverTime(metrics, fileName)
metrics['expName'] = expName
pickle.dump(metrics, open('results/traces/{}/trace'.format(expName), 'wb'))
plotReceptiveFields2D(sp, params['nX'], params['nY'])
inspectSpatialPoolerStats(sp, inputVectors,
inputVectorType + "afterTraining")
plotExampleInputOutput(sp, inputVectors, expName + "final")
return metrics, expName
def runSPexperiments(expConfig):
inputVectorType = expConfig.dataSet
params = getSDRDataSetParams(expConfig.dataSet, int(expConfig.seed))
expName = getExperimentName(expConfig)
createDirectories(expName)
sdrData = SDRDataSet(params)
inputVectors = sdrData.getInputVectors()
numInputVector, inputSize = inputVectors.shape
plt.figure()
plt.imshow(np.reshape(inputVectors[2], (params['nX'], params['nY'])),
interpolation='nearest', cmap='gray')
plt.savefig('figures/exampleInputs/{}'.format(expName))
print
print "Runnning experiment: {}".format(expName)
print "Training Data Size {} Dimensions {}".format(numInputVector, inputSize)
spParams = getSpatialPoolerParams(params, expConfig)
sp = createSpatialPooler(expConfig.spatialImp, spParams)
if expConfig.topology == 1 and expConfig.spatialImp in ['faulty_sp', 'py']:
initializeSPConnections(sp, potentialRaidus=10, initConnectionRadius=5)
numColumns = np.prod(sp.getColumnDimensions())
numTestInputs = int(numInputVector * 0.5)
testInputs = inputVectors[:numTestInputs, :]
connectedCounts = np.zeros((numColumns,), dtype=uintType)
boostFactors = np.zeros((numColumns,), dtype=realDType)
activeDutyCycle = np.zeros((numColumns,), dtype=realDType)
metrics = {'numConnectedSyn': [],
'numNewSyn': [],
'numRemoveSyn': [],
'stability': [],
'entropy': [],
'maxEntropy': [],
'sparsity': [],
'noiseRobustness': [],
'classification': [],
'meanBoostFactor': [],
'reconstructionError': [],
'witnessError': []}
connectedSyns = getConnectedSyns(sp)
activeColumnsCurrentEpoch, dum = runSPOnBatch(sp, testInputs, learn=False)
inspectSpatialPoolerStats(sp, inputVectors, expName + "beforeTraining")
checkPoints = [0, expConfig.changeDataSetAt - 1,
expConfig.changeDataSetAt, expConfig.numEpochs - 1]
epoch = 0
while epoch < expConfig.numEpochs:
print "training SP epoch {} ".format(epoch)
if (expConfig.changeDataSetContinuously or
epoch == expConfig.changeDataSetAt):
params['seed'] = epoch
sdrData.generateInputVectors(params)
inputVectors = sdrData.getInputVectors()
numInputVector, inputSize = inputVectors.shape
testInputs = inputVectors[:numTestInputs, :]
if expConfig.killInputsAfter > 0 and epoch > expConfig.killInputsAfter:
if expConfig.topology == 1:
inputSpaceDim = (params['nX'], params['nY'])
centerColumn = indexFromCoordinates((15, 15), inputSpaceDim)
deadInputs = topology.wrappingNeighborhood(centerColumn, 5, inputSpaceDim)
else:
zombiePermutation = np.random.permutation(inputSize)
deadInputs = zombiePermutation[:100]
inputVectors[:, deadInputs] = 0
if epoch == expConfig.killCellsAt:
if expConfig.spatialImp in ['faulty_sp', 'monitored_faulty_sp']:
if expConfig.topology == 1:
centerColumn = indexFromCoordinates((15, 15), sp._columnDimensions)
sp.killCellRegion(centerColumn, 5)
else:
sp.killCells(expConfig.killCellPrct)
if expConfig.trackOverlapCurve:
noiseLevelList, inputOverlapScore, outputOverlapScore = \
calculateOverlapCurve(sp, testInputs)
metrics['noiseRobustness'].append(
np.trapz(np.flipud(np.mean(outputOverlapScore, 0)),
noiseLevelList))
np.savez(
'./results/input_output_overlap/{}/epoch_{}'.format(expName, epoch),
noiseLevelList, inputOverlapScore, outputOverlapScore)
if expConfig.classification:
# classify SDRs with noise
noiseLevelList = np.linspace(0, 1.0, 21)
classification_accuracy = classificationAccuracyVsNoise(
sp, testInputs, noiseLevelList)
metrics['classification'].append(
np.trapz(classification_accuracy, noiseLevelList))
np.savez('./results/classification/{}/epoch_{}'.format(expName, epoch),
noiseLevelList, classification_accuracy)
# train SP here,
# Learn is turned off at the first epoch to gather stats of untrained SP
learn = False if epoch == 0 else True
# randomize the presentation order of input vectors
sdrOrders = np.random.permutation(np.arange(numInputVector))
activeColumnsTrain, meanBoostFactors = runSPOnBatch(sp, inputVectors, learn, sdrOrders)
# run SP on test dataset and compute metrics
activeColumnsPreviousEpoch = copy.copy(activeColumnsCurrentEpoch)
activeColumnsCurrentEpoch, dum = runSPOnBatch(sp, testInputs, learn=False)
stability = calculateStability(activeColumnsCurrentEpoch,
activeColumnsPreviousEpoch)
if (expConfig.changeDataSetContinuously or
epoch == expConfig.changeDataSetAt):
stability = float('nan')
metrics['stability'].append(stability)
metrics['sparsity'].append(np.mean(np.mean(activeColumnsCurrentEpoch, 1)))
metrics['entropy'].append(calculateEntropy(activeColumnsCurrentEpoch))
# generate ideal SP outputs where all columns have the same activation prob.
activeColumnsIdeal = np.random.rand(numInputVector, numColumns) > metrics['sparsity'][-1]
metrics['maxEntropy'].append(calculateEntropy(activeColumnsIdeal))
connectedSynsPreviousEpoch = copy.copy(connectedSyns)
sp.getConnectedCounts(connectedCounts)
connectedSyns = getConnectedSyns(sp)
metrics['meanBoostFactor'].append(np.mean(meanBoostFactors))
sp.getActiveDutyCycles(activeDutyCycle)
metrics['numConnectedSyn'].append(np.sum(connectedCounts))
numNewSynapses = connectedSyns - connectedSynsPreviousEpoch
numNewSynapses[numNewSynapses < 0] = 0
metrics['numNewSyn'].append(np.sum(numNewSynapses))
numEliminatedSynapses = connectedSynsPreviousEpoch - connectedSyns
numEliminatedSynapses[numEliminatedSynapses < 0] = 0
metrics['numRemoveSyn'].append(np.sum(numEliminatedSynapses))
metrics['reconstructionError'].append(
reconstructionError(sp, testInputs, activeColumnsCurrentEpoch))
metrics['witnessError'].append(
witnessError(sp, testInputs, activeColumnsCurrentEpoch))
print tabulate(metrics, headers="keys")
if expConfig.checkRFCenters:
# check distribution of RF centers, useful to monitor recovery from trauma
RFcenters, avgDistToCenter = getRFCenters(sp, params, type='connected')
if expConfig.spatialImp == 'faulty_sp':
aliveColumns = sp.getAliveColumns()
else:
aliveColumns = np.arange(numColumns)
fig = plotReceptiveFieldCenter(RFcenters[aliveColumns, :],
connectedCounts[aliveColumns],
(params['nX'], params['nY']))
plt.savefig('figures/RFcenters/{}/epoch_{}.png'.format(expName, epoch))
plt.close(fig)
np.savez('results/RFcenters/{}/epoch_{}'.format(expName, epoch),
RFcenters, avgDistToCenter)
if expConfig.checkInputSpaceCoverage:
# check coverage of input space, useful to monitor recovery from trauma
inputSpaceCoverage = calculateInputSpaceCoverage(sp)
np.savez('results/InputCoverage/{}/epoch_{}'.format(expName, epoch),
inputSpaceCoverage, connectedCounts)
plt.figure(2)
plt.clf()
plt.imshow(inputSpaceCoverage, interpolation='nearest', cmap="jet")
plt.colorbar()
plt.savefig(
'figures/InputCoverage/{}/epoch_{}.png'.format(expName, epoch))
if expConfig.checkTestInput:
RFcenters, avgDistToCenter = getRFCenters(sp, params, type='connected')
inputIdx = 0
outputColumns = np.zeros((numColumns, 1), dtype=uintType)
sp.compute(testInputs[inputIdx, :], False, outputColumns)
activeColumns = np.where(outputColumns > 0)[0]
fig = plotReceptiveFieldCenter(RFcenters[aliveColumns, :],
connectedCounts[aliveColumns],
(params['nX'], params['nY']))
plt.scatter(RFcenters[activeColumns, 0], RFcenters[activeColumns, 1],
color='r')
plt.savefig(
'figures/ResponseToTestInputs/{}/epoch_{}.png'.format(expName, epoch))
if expConfig.saveBoostFactors:
np.savez('results/boostFactors/{}/epoch_{}'.format(expName, epoch),
meanBoostFactors)
if expConfig.showExampleRFs:
fig = plotReceptiveFields2D(sp, params['nX'], params['nY'])
plt.savefig('figures/exampleRFs/{}/epoch_{}'.format(expName, epoch))
plt.close(fig)
if epoch in checkPoints:
# inspect SP again
inspectSpatialPoolerStats(sp, inputVectors, expName+"epoch{}".format(epoch))
epoch += 1
# plot stats over training
fileName = 'figures/network_stats_over_training_{}.pdf'.format(expName)
plotSPstatsOverTime(metrics, fileName)
metrics['expName'] = expName
pickle.dump(metrics, open('results/traces/{}/trace'.format(expName), 'wb'))
plotReceptiveFields2D(sp, params['nX'], params['nY'])
inspectSpatialPoolerStats(sp, inputVectors, inputVectorType + "afterTraining")
plotExampleInputOutput(sp, inputVectors, expName + "final")
return metrics, expName
def plotMovie(expName, numEpochs, killAt):
# plot RFcenters and inputCoverage over training
centerColumn = indexFromCoordinates((15, 15), (32, 32))
deadCols = topology.wrappingNeighborhood(centerColumn, 5, (32, 32))
for epoch in range(killAt, numEpochs):
fig, axs = plt.subplots(2, 2)
RFcenterInfo = np.load('results/RFcenters/{}/epoch_{}.npz'.format(
expName, epoch))
RFcenters = RFcenterInfo['arr_0']
avgDistToCenter = RFcenterInfo['arr_1']
axs[0, 1].scatter(RFcenters[:, 0], RFcenters[:, 1], s=4, c=[1, 1, 1])
axs[0, 1].set_title('RF centers')
axs[0, 1].set_xlim([-1, 33])
axs[0, 1].set_ylim([-1, 33])
axs[0, 1].set_aspect('equal')
plt.axis('equal')
# # plot input space coverage
inputSpaceCoverage = np.load(
'results/InputCoverage/{}/epoch_{}.npz'.format(expName, epoch))
inputSpaceCoverage = inputSpaceCoverage['arr_0']
im1 = axs[0, 0].pcolor(inputSpaceCoverage, vmin=10, vmax=80)
axs[0, 0].set_title('Input Space Coverage')
axs[0, 0].set_xlim([-1, 33])
axs[0, 0].set_ylim([-1, 33])
axs[0, 0].set_aspect('equal')
plt.axis('equal')
boostFactors = np.load('results/boostFactors/{}/epoch_{}.npz'.format(
expName, epoch))
boostFactors = boostFactors['arr_0']
# boostFactors[deadCols] = np.nan
boostFactors = np.reshape(boostFactors, (32, 32))
im2 = axs[1, 0].pcolor(boostFactors, vmin=0.5, vmax=1.5)
axs[1, 0].set_title('Boost Factors')
axs[1, 0].set_xlim([-1, 33])
axs[1, 0].set_ylim([-1, 33])
axs[1, 0].set_aspect('equal')
plt.axis('equal')
# fig.delaxes(axs[1, 0])
cax = fig.add_axes([0.55, 0.4, 0.3, 0.05])
fig.colorbar(im1,
cax=cax,
orientation='horizontal',
ticks=[0, 20, 40, 60, 80])
cax.set_xlabel('input space coverage')
cax = fig.add_axes([0.55, 0.2, 0.3, 0.05])
fig.colorbar(im2,
cax=cax,
orientation='horizontal',
ticks=[0, .5, 1, 1.5, 2])
cax.set_xlabel('boost factors')
fig.delaxes(axs[1, 1])
plt.savefig('figures/traumaMovie/{}_frame_{}.pdf'.format(
expName, epoch))
plt.close(fig)
sdrData.generateInputVectors(params)
inputVectors = sdrData.getInputVectors()
numInputVector, inputSize = inputVectors.shape
plt.figure(10)
plt.clf()
plt.imshow(np.reshape(np.sum(inputVectors, 0),
(params['nX'], params['nY'])),
interpolation='nearest',
cmap='jet')
plt.colorbar()
plt.savefig('figures/avgInputs/{}/epoch_{}'.format(expName, epoch))
if killInputsAfter > 0 and epoch > killInputsAfter:
inputSpaceDim = (params['nX'], params['nY'])
centerColumn = indexFromCoordinates((15, 15), inputSpaceDim)
deadInputs = topology.wrappingNeighborhood(centerColumn, 5,
inputSpaceDim)
inputVectors[:, deadInputs] = 0
if epoch == killCellsAt:
if spatialImp == "faulty_sp" or spatialImp == "monitored_faulty_sp":
# sp.killCells(killCellPrct)
centerColumn = indexFromCoordinates((15, 15),
sp._columnDimensions)
sp.killCellRegion(centerColumn, 5)
if trackOverlapCurveOverTraining:
noiseLevelList, inputOverlapScore, outputOverlapScore = \
calculateOverlapCurve(sp, inputVectors[:20, :])
noiseRobustnessTrace.append(
np.trapz(np.flipud(np.mean(outputOverlapScore, 0)),
noiseLevelList))