def POST(self):
global spFacades
params = json.loads(web.data())
requestInput = web.input()
# We will always return the initial state of columns and overlaps because
# they are cheap.
returnSnapshots = [SNAPS.ACT_COL, SNAPS.OVERLAPS]
saveSnapshots = []
if __name__ == '__main__':
if "save" in requestInput and len(requestInput["save"]) > 0:
saveSnapshots += [
str(s) for s in requestInput["save"].split(",")
]
# Be sure to also return any snapshots that were specified to be saved.
returnSnapshots += saveSnapshots
# Remove potential duplicates from both
returnSnapshots = list(set(returnSnapshots))
saveSnapshots = list(set(saveSnapshots))
sp = SP(**params)
spFacade = spHistory.create(sp, save=saveSnapshots)
spId = spFacade.getId()
spFacades[spId] = spFacade
print "Created SP {} | Saving: {}".format(spId, saveSnapshots)
payload = {"meta": {"id": spId, "saving": returnSnapshots}}
spState = spFacade.getState(*returnSnapshots)
for key in spState:
payload[key] = spState[key]
web.header("Content-Type", "application/json")
return json.dumps(payload)
def _initSpatialPooler(self):
print "Creating spatial pooler .."
spatialPooler = SP(
self.inputSize,
self.columnDimensions,
numActiveColumnsPerInhArea=int(0.02 * self.columnNumber),
globalInhibition=True,
synPermActiveInc=0.01,
potentialPct=
1, # Essential parameter: Neurons can connect to 100% of input
potentialRadius=self.inputSize
# stimulusThreshold = 0,
# synPermInactiveDec = 0.01,
# synPermActiveInc = 0.1,
# synPermConnected = 0.1, # Connected threshold
# maxBoost = 3
)
return spatialPooler
def __init__(self, inputDimensions, columnDimensions):
"""
Parameters:
----------
_inputDimensions: The size of the input. (m,n) will give a size m x n
_columnDimensions: The size of the 2 dimensional array of columns
"""
self.inputDimensions = inputDimensions
self.columnDimensions = columnDimensions
self.inputSize = np.array(inputDimensions).prod()
self.columnNumber = np.array(columnDimensions).prod()
self.inputArray = np.zeros(self.inputSize)
self.activeArray = np.zeros(self.columnNumber)
self.sp = SP(self.inputDimensions,
self.columnDimensions,
potentialRadius = self.inputSize,
numActiveColumnsPerInhArea = int(0.02*self.columnNumber),
globalInhibition = True,
synPermActiveInc = 0.01)
def __init__(self, inputShape, columnDimensions):
"""
Parameters:
----------
_inputShape : The size of the input. The product of the first and second elements of this parameter determines the size of the input vectors
_columnDimensions: The size of the 2 dimensional array of columns
"""
self.inputShape = inputShape
self.columnDimensions = columnDimensions
self.inputSize = np.array(inputShape).prod()
self.columnNumber = np.array(columnDimensions).prod()
self.inputArray = np.zeros(self.inputSize)
self.activeArray = np.zeros(self.columnNumber)
self.sp = SP(self.inputShape,
self.columnDimensions,
potentialRadius=self.inputSize,
numActiveColumnsPerInhArea=int(0.02 * self.columnNumber),
globalInhibition=True,
synPermActiveInc=0.01)
def createSpatialPooler(inputSize):
return SP(
inputDimensions=(inputSize,),
columnDimensions=(200,),
potentialRadius=16,
potentialPct=0.85,
globalInhibition=True,
localAreaDensity=-1.0,
numActiveColumnsPerInhArea=40.0,
stimulusThreshold=1,
synPermInactiveDec=0.008,
synPermActiveInc=0.05,
synPermConnected=0.10,
minPctOverlapDutyCycle=0.001,
minPctActiveDutyCycle=0.001,
dutyCyclePeriod=1000,
maxBoost=2.0,
seed=-1,
spVerbosity=0,
wrapAround=True
)
def runSaveTest():
inputSize = 600
outputSize = 2048
sp = SP(inputDimensions=(inputSize, ),
columnDimensions=(outputSize, ),
potentialRadius=16,
potentialPct=0.85,
globalInhibition=True,
localAreaDensity=-1.0,
numActiveColumnsPerInhArea=40.0,
stimulusThreshold=1,
synPermInactiveDec=0.008,
synPermActiveInc=0.05,
synPermConnected=0.10,
minPctOverlapDutyCycle=0.001,
minPctActiveDutyCycle=0.001,
dutyCyclePeriod=1000,
maxBoost=2.0,
seed=-1,
spVerbosity=0,
wrapAround=True)
# Totally nukes any SP History data that exists in Redis.
spHistory.nuke()
# Create a facade around the SP that saves history as it runs.
sp = spHistory.create(sp)
# If the SP Facade is "active" that means it has a life spatial pooler. If it
# is not active, it cannot compute, only playback the history.
assert sp.isActive()
for _ in range(0, 10):
encoding = np.zeros(shape=(inputSize, ))
for j, _ in enumerate(encoding):
if random() < 0.1:
encoding[j] = 1
# For each compute cycle, save the SP state to Redis for playback later.
sp.compute(encoding, learn=True, save=True)
# This SP's history can be retrieved with an id.
return sp.getId()
minThreshold=8,
maxNewSynapseCount=20,
permanenceIncrement=0.1,
permanenceDecrement=0.0,
activationThreshold=8,
)
sp = SP(inputDimensions=(2325, ),
columnDimensions=(2048, ),
potentialRadius=16,
potentialPct=0.5,
globalInhibition=True,
localAreaDensity=-1.0,
numActiveColumnsPerInhArea=10.0,
stimulusThreshold=0,
synPermInactiveDec=0.008,
synPermActiveInc=0.05,
synPermConnected=0.10,
minPctOverlapDutyCycle=0.001,
dutyCyclePeriod=1000,
maxBoost=20.0,
seed=-1,
spVerbosity=0,
wrapAround=True)
sdr = SDR(steps=(3, ), alpha=0.001, actValueAlpha=0.3, verbosity=0)
def createEncoder():
volume_encoder = ScalarEncoder(21,
0.0,
uintType = "uint32" inputDimensions = (1000,1) columnDimensions = (2048,1) inputSize = np.array(inputDimensions).prod() columnNumber = np.array(columnDimensions).prod() inputArray = np.zeros(inputSize, dtype=uintType) for i in range(inputSize): inputArray[i] = random.randrange(2) activeCols = np.zeros(columnNumber, dtype=uintType) sp = SP(inputDimensions, columnDimensions, potentialRadius = int(0.5*inputSize), numActiveColumnsPerInhArea = int(0.02*columnNumber), globalInhibition = True, seed = 1, synPermActiveInc = 0.01, synPermInactiveDec = 0.008 ) # Part 1: # ------- # A column connects to a subset of the input vector (specified # by both the potentialRadius and potentialPct). The overlap score # for a column is the number of connections to the input that become # active when presented with a vector. When learning is 'on' in the SP, # the active connections are reinforced, whereas those inactive are # depressed (according to parameters synPermActiveInc and synPermInactiveDec. # In order for the SP to create a sparse representation of the input, it # will select a small percentage (usually 2%) of its most active columns,