def execute(self, slot, subindex, roi, result):
t1 = time.time()
key = roi.toSlice()
nlabels=self.inputs["LabelsCount"].value
traceLogger.debug("OpPredictRandomForest: Requesting classifier. roi={}".format(roi))
forests=self.inputs["Classifier"][:].wait()
if forests is None:
# Training operator may return 'None' if there was no data to train with
return numpy.zeros(numpy.subtract(roi.stop, roi.start), dtype=numpy.float32)[...]
traceLogger.debug("OpPredictRandomForest: Got classifier")
#assert RF.labelCount() == nlabels, "ERROR: OpPredictRandomForest, labelCount differs from true labelCount! %r vs. %r" % (RF.labelCount(), nlabels)
newKey = key[:-1]
newKey += (slice(0,self.inputs["Image"].meta.shape[-1],None),)
res = self.inputs["Image"][newKey].wait()
shape=res.shape
prod = numpy.prod(shape[:-1])
res.shape = (prod, shape[-1])
features=res
predictions = [0]*len(forests)
def predict_forest(number):
predictions[number] = forests[number].predictProbabilities(numpy.asarray(features, dtype=numpy.float32))
t2 = time.time()
# predict the data with all the forests in parallel
pool = Pool()
for i,f in enumerate(forests):
req = pool.request(partial(predict_forest, i))
pool.wait()
pool.clean()
prediction=numpy.dstack(predictions)
prediction = numpy.average(prediction, axis=2)
prediction.shape = shape[:-1] + (forests[0].labelCount(),)
#prediction = prediction.reshape(*(shape[:-1] + (forests[0].labelCount(),)))
# If our LabelsCount is higher than the number of labels in the training set,
# then our results aren't really valid. FIXME !!!
# Duplicate the last label's predictions
for c in range(result.shape[-1]):
result[...,c] = prediction[...,min(c+key[-1].start, prediction.shape[-1]-1)]
t3 = time.time()
# logger.info("Predict took %fseconds, actual RF time was %fs, feature time was %fs" % (t3-t1, t3-t2, t2-t1))
return result
def execute(self, slot, subindex, roi, result):
progress = 0
self.progressSignal(progress)
numImages = len(self.Images)
key = roi.toSlice()
featMatrix=[]
labelsMatrix=[]
for i,labels in enumerate(self.inputs["Labels"]):
if labels.meta.shape is not None:
#labels=labels[:].allocate().wait()
blocks = self.inputs["nonzeroLabelBlocks"][i][0].allocate().wait()
progress += 10/numImages
self.progressSignal(progress)
reqlistlabels = []
reqlistfeat = []
traceLogger.debug("Sending requests for {} non-zero blocks (labels and data)".format( len(blocks[0])) )
for b in blocks[0]:
request = labels[b].allocate()
featurekey = list(b)
featurekey[-1] = slice(None, None, None)
request2 = self.inputs["Images"][i][featurekey].allocate()
reqlistlabels.append(request)
reqlistfeat.append(request2)
traceLogger.debug("Requests prepared")
numLabelBlocks = len(reqlistlabels)
progress_outer = [progress] # Store in list for closure access
if numLabelBlocks > 0:
progressInc = (80-10)/numLabelBlocks/numImages
def progressNotify(req):
# Note: If we wanted perfect progress reporting, we could use lock here
# to protect the progress from being incremented simultaneously.
# But that would slow things down and imperfect reporting is okay for our purposes.
progress_outer[0] += progressInc/2
self.progressSignal(progress_outer[0])
for ir, req in enumerate(reqlistfeat):
image = req.notify(progressNotify)
for ir, req in enumerate(reqlistlabels):
labblock = req.notify(progressNotify)
traceLogger.debug("Requests fired")
for ir, req in enumerate(reqlistlabels):
traceLogger.debug("Waiting for a label block...")
labblock = req.wait()
traceLogger.debug("Waiting for an image block...")
image = reqlistfeat[ir].wait()
indexes=numpy.nonzero(labblock[...,0].view(numpy.ndarray))
features=image[indexes]
labbla=labblock[indexes]
featMatrix.append(features)
labelsMatrix.append(labbla)
progress = progress_outer[0]
traceLogger.debug("Requests processed")
self.progressSignal(80/numImages)
if len(featMatrix) == 0 or len(labelsMatrix) == 0:
# If there was no actual data for the random forest to train with, we return None
result[:] = None
else:
featMatrix=numpy.concatenate(featMatrix,axis=0)
labelsMatrix=numpy.concatenate(labelsMatrix,axis=0)
maxLabel = self.inputs["MaxLabel"].value
labelList = range(1, maxLabel+1) if maxLabel > 0 else list()
try:
logger.debug("Learning with Vigra...")
# train and store self._forest_count forests in parallel
pool = Pool()
for i in range(self._forest_count):
def train_and_store(number):
result[number] = vigra.learning.RandomForest(self._tree_count, labels=labelList)
result[number].learnRF( numpy.asarray(featMatrix, dtype=numpy.float32),
numpy.asarray(labelsMatrix, dtype=numpy.uint32))
req = pool.request(partial(train_and_store, i))
pool.wait()
pool.clean()
logger.debug("Vigra finished")
except:
logger.error( "ERROR: could not learn classifier" )
logger.error( "featMatrix shape={}, max={}, dtype={}".format(featMatrix.shape, featMatrix.max(), featMatrix.dtype) )
logger.error( "labelsMatrix shape={}, max={}, dtype={}".format(labelsMatrix.shape, labelsMatrix.max(), labelsMatrix.dtype ) )
raise
finally:
self.progressSignal(100)
return result
def execute(self, slot, subindex, rroi, result):
assert slot == self.Features or slot == self.Output
if slot == self.Features:
key = roiToSlice(rroi.start, rroi.stop)
index = subindex[0]
subslot = self.Features[index]
key = list(key)
channelIndex = self.Input.meta.axistags.index('c')
# Translate channel slice to the correct location for the output slot.
key[channelIndex] = slice(self.featureOutputChannels[index][0] + key[channelIndex].start,
self.featureOutputChannels[index][0] + key[channelIndex].stop)
rroi = SubRegion(subslot, pslice=key)
# Get output slot region for this channel
return self.execute(self.Output, (), rroi, result)
elif slot == self.outputs["Output"]:
key = rroi.toSlice()
cnt = 0
written = 0
assert (rroi.stop<=self.outputs["Output"].meta.shape).all()
flag = 'c'
channelAxis=self.inputs["Input"].meta.axistags.index('c')
axisindex = channelAxis
oldkey = list(key)
oldkey.pop(axisindex)
inShape = self.inputs["Input"].meta.shape
shape = self.outputs["Output"].meta.shape
axistags = self.inputs["Input"].meta.axistags
result = result.view(vigra.VigraArray)
result.axistags = copy.copy(axistags)
hasTimeAxis = self.inputs["Input"].meta.axistags.axisTypeCount(vigra.AxisType.Time)
timeAxis=self.inputs["Input"].meta.axistags.index('t')
subkey = popFlagsFromTheKey(key,axistags,'c')
subshape=popFlagsFromTheKey(shape,axistags,'c')
at2 = copy.copy(axistags)
at2.dropChannelAxis()
subshape=popFlagsFromTheKey(subshape,at2,'t')
subkey = popFlagsFromTheKey(subkey,at2,'t')
oldstart, oldstop = roi.sliceToRoi(key, shape)
start, stop = roi.sliceToRoi(subkey,subkey)
maxSigma = max(0.7,self.maxSigma)
# The region of the smoothed image we need to give to the feature filter (in terms of INPUT coordinates)
vigOpSourceStart, vigOpSourceStop = roi.extendSlice(start, stop, subshape, 0.7, window = 2)
# The region of the input that we need to give to the smoothing operator (in terms of INPUT coordinates)
newStart, newStop = roi.extendSlice(vigOpSourceStart, vigOpSourceStop, subshape, maxSigma, window = 3.5)
# Translate coordinates (now in terms of smoothed image coordinates)
vigOpSourceStart = roi.TinyVector(vigOpSourceStart - newStart)
vigOpSourceStop = roi.TinyVector(vigOpSourceStop - newStart)
readKey = roi.roiToSlice(newStart, newStop)
writeNewStart = start - newStart
writeNewStop = writeNewStart + stop - start
treadKey=list(readKey)
if hasTimeAxis:
if timeAxis < channelAxis:
treadKey.insert(timeAxis, key[timeAxis])
else:
treadKey.insert(timeAxis-1, key[timeAxis])
if self.inputs["Input"].meta.axistags.axisTypeCount(vigra.AxisType.Channels) == 0:
treadKey = popFlagsFromTheKey(treadKey,axistags,'c')
else:
treadKey.insert(channelAxis, slice(None,None,None))
treadKey=tuple(treadKey)
req = self.inputs["Input"][treadKey].allocate()
sourceArray = req.wait()
req.result = None
req.destination = None
if sourceArray.dtype != numpy.float32:
sourceArrayF = sourceArray.astype(numpy.float32)
sourceArray.resize((1,), refcheck = False)
del sourceArray
sourceArray = sourceArrayF
sourceArrayV = sourceArray.view(vigra.VigraArray)
sourceArrayV.axistags = copy.copy(axistags)
dimCol = len(self.scales)
dimRow = self.matrix.shape[0]
sourceArraysForSigmas = [None]*dimCol
#connect individual operators
for j in range(dimCol):
hasScale = False
for i in range(dimRow):
if self.matrix[i,j]:
hasScale = True
if not hasScale:
continue
destSigma = 1.0
if self.scales[j] > destSigma:
tempSigma = math.sqrt(self.scales[j]**2 - destSigma**2)
else:
destSigma = 0.0
tempSigma = self.scales[j]
vigOpSourceShape = list(vigOpSourceStop - vigOpSourceStart)
if hasTimeAxis:
if timeAxis < channelAxis:
vigOpSourceShape.insert(timeAxis, ( oldstop - oldstart)[timeAxis])
else:
vigOpSourceShape.insert(timeAxis-1, ( oldstop - oldstart)[timeAxis])
vigOpSourceShape.insert(channelAxis, inShape[channelAxis])
sourceArraysForSigmas[j] = numpy.ndarray(tuple(vigOpSourceShape),numpy.float32)
for i,vsa in enumerate(sourceArrayV.timeIter()):
droi = (tuple(vigOpSourceStart._asint()), tuple(vigOpSourceStop._asint()))
tmp_key = getAllExceptAxis(len(sourceArraysForSigmas[j].shape),timeAxis, i)
sourceArraysForSigmas[j][tmp_key] = vigra.filters.gaussianSmoothing(vsa,tempSigma, roi = droi, window_size = 3.5 )
else:
droi = (tuple(vigOpSourceStart._asint()), tuple(vigOpSourceStop._asint()))
#print droi, sourceArray.shape, tempSigma,self.scales[j]
sourceArraysForSigmas[j] = vigra.filters.gaussianSmoothing(sourceArrayV, sigma = tempSigma, roi = droi, window_size = 3.5)
#sourceArrayForSigma = sourceArrayForSigma.view(numpy.ndarray)
del sourceArrayV
try:
sourceArray.resize((1,), refcheck = False)
except ValueError:
# Sometimes this fails, but that's okay.
logger.debug("Failed to free array memory.")
del sourceArray
closures = []
#connect individual operators
for i in range(dimRow):
for j in range(dimCol):
val=self.matrix[i,j]
if val:
vop= self.featureOps[i][j]
oslot = vop.outputs["Output"]
req = None
inTagKeys = [ax.key for ax in oslot.meta.axistags]
if flag in inTagKeys:
slices = oslot.meta.shape[axisindex]
if cnt + slices >= rroi.start[axisindex] and rroi.start[axisindex]-cnt<slices and rroi.start[axisindex]+written<rroi.stop[axisindex]:
begin = 0
if cnt < rroi.start[axisindex]:
begin = rroi.start[axisindex] - cnt
end = slices
if cnt + end > rroi.stop[axisindex]:
end -= cnt + end - rroi.stop[axisindex]
key_ = copy.copy(oldkey)
key_.insert(axisindex, slice(begin, end, None))
reskey = [slice(None, None, None) for x in range(len(result.shape))]
reskey[axisindex] = slice(written, written+end-begin, None)
destArea = result[tuple(reskey)]
roi_ = SubRegion(self.Input, pslice=key_)
closure = partial(oslot.operator.execute, oslot, (), roi_, destArea, sourceArray = sourceArraysForSigmas[j])
closures.append(closure)
written += end - begin
cnt += slices
else:
if cnt>=rroi.start[axisindex] and rroi.start[axisindex] + written < rroi.stop[axisindex]:
reskey = copy.copy(oldkey)
reskey.insert(axisindex, written)
#print "key: ", key, "reskey: ", reskey, "oldkey: ", oldkey
#print "result: ", result.shape, "inslot:", inSlot.shape
destArea = result[tuple(reskey)]
logger.debug(oldkey, destArea.shape, sourceArraysForSigmas[j].shape)
oldroi = SubRegion(self.Input, pslice=oldkey)
closure = partial(oslot.operator.execute, oslot, (), oldroi, destArea, sourceArray = sourceArraysForSigmas[j])
closures.append(closure)
written += 1
cnt += 1
pool = Pool()
for c in closures:
r = pool.request(c)
pool.wait()
pool.clean()
for i in range(len(sourceArraysForSigmas)):
if sourceArraysForSigmas[i] is not None:
try:
sourceArraysForSigmas[i].resize((1,))
except:
sourceArraysForSigmas[i] = None