randomState = None
if not randomClassif:
randomState = 100
tsSize = testingUse
if testingUse > maxTestingSize:
tsSize = maxTestingSize
#--SVM--
baseClassif = LinearSVC(verbose=verbose, random_state=randomState)
#--Classifier
classifier = uClassifier(coordinator=None,
base_classifier=baseClassif,
n_jobs=nbJobsEstimator,
random_state=randomState,
verbose=verbose)
#--Data--
loader = CifarFromNumpies(learningSetDir, learningIndexFile)
learningSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
learningSet = learningSet[0:histSize]
loader = CifarFromNumpies(testingSetDir, testingIndexFile)
testingSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
testingSet = testingSet[0:tsSize]
#--Learning--#
print "Starting learning"
fitStart = time()
randomState = None
if not randomClassif:
randomState = 100
tsSize = testingUse
if testingUse > maxTestingSize:
tsSize = maxTestingSize
#--SVM--
baseClassif = LinearSVC(verbose=verbose, random_state=randomState)
#--Classifier
classifier = uClassifier(coordinator=None,
base_classifier=baseClassif,
n_jobs=nbJobsEstimator,
random_state=randomState,
verbose=verbose)
#--Data--
loader = CifarFromNumpies(learningSetDir, learningIndexFile)
learningSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
learningSet = learningSet[0:histSize]
loader = CifarFromNumpies(testingSetDir, testingIndexFile)
testingSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
testingSet = testingSet[0:tsSize]
#--Learning--#
print "Starting learning"
fitStart = time()
def run(nb_filters=nb_filters,
filterPolicy=filterPolicy,
poolings=poolings,
nbSubwindows=nbSubwindows,
subwindowMinSizeRatio=subwindowMinSizeRatio,
subwindowMaxSizeRatio=subwindowMaxSizeRatio,
subwindowTargetWidth=subwindowTargetWidth,
subwindowTargetHeight=subwindowTargetHeight,
fixedSize=fixedSize,
subwindowInterpolation=subwindowInterpolation,
includeOriginalImage=includeOriginalImage,
random=random,
nbJobs=nbJobs,
verbosity=verbosity,
tempFolder=tempFolder,
nbTrees=nbTrees,
maxDepth=maxDepth,
minSamplesSplit=minSamplesSplit,
minSamplesLeaf=minSamplesLeaf,
randomClassif=randomClassif,
nbJobsEstimator=nbJobsEstimator,
verbose=verbose,
learningUse=learningUse,
testingUse=testingUse,
saveFile=saveFile,
shouldSave=shouldSave):
randomState = None
if not randomClassif:
randomState = 100
lsSize = learningUse
if learningUse > maxLearningSize:
lsSize = maxLearningSize
tsSize = testingUse
if testingUse > maxTestingSize:
tsSize = maxTestingSize
#======INSTANTIATING========#
#--randconv--
randConvCoord = coordinatorRandConvFactory(
nbFilters=nb_filters,
filterPolicy=filterPolicy,
nbSubwindows=nbSubwindows,
subwindowMinSizeRatio=subwindowMinSizeRatio,
subwindowMaxSizeRatio=subwindowMaxSizeRatio,
subwindowTargetWidth=subwindowTargetWidth,
subwindowTargetHeight=subwindowTargetHeight,
poolings=poolings,
subwindowInterpolation=subwindowInterpolation,
includeOriginalImage=includeOriginalImage,
nbJobs=nbJobs,
verbosity=verbosity,
tempFolder=tempFolder,
random=random)
nb_filters = len(randConvCoord.getFilters())
#--SVM--
baseClassif = LinearSVC(verbose=verbose, random_state=randomState)
#--Classifier
classifier = uClassifier(coordinator=randConvCoord,
base_classifier=baseClassif,
n_estimators=nbTrees,
max_depth=maxDepth,
min_samples_split=minSamplesSplit,
min_samples_leaf=minSamplesLeaf,
n_jobs=nbJobsEstimator,
random_state=randomState,
verbose=verbose)
#--Data--
loader = CifarFromNumpies(learningSetDir, learningIndexFile)
learningSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
learningSet = learningSet[0:lsSize]
loader = CifarFromNumpies(testingSetDir, testingIndexFile)
testingSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
testingSet = testingSet[0:tsSize]
#=====COMPUTATION=====#
#--Learning--#
print "Starting learning"
fitStart = time()
hist = classifier._preprocess(learningSet, learningPhase=True)
y = learningSet.getLabels()
if shouldSave:
np.savez(saveFile,
data=hist.data,
indices=hist.indices,
indptr=hist.indptr,
shape=hist.shape)
classifier.fit_histogram(hist, y)
fitEnd = time()
print "Learning done", formatDuration(fitEnd - fitStart)
sys.stdout.flush()
#--Testing--#
y_truth = testingSet.getLabels()
predStart = time()
y_pred = classifier.predict(testingSet)
predEnd = time()
accuracy = classifier.accuracy(y_pred, y_truth)
confMat = classifier.confusionMatrix(y_pred, y_truth)
#====ANALYSIS=====#
importance, order = randConvCoord.importancePerFeatureGrp(
classifier._visualBagger)
print "==================Bag of Visual Words======================="
print "-----------Filtering--------------"
print "nb_filters", nb_filters
print "filterPolicy", filterPolicy
print "----------Pooling--------------"
print "poolings", poolings
print "--------SW extractor----------"
print "#Subwindows", nbSubwindows
print "subwindowMinSizeRatio", subwindowMinSizeRatio
print "subwindowMaxSizeRatio", subwindowMaxSizeRatio
print "subwindowTargetWidth", subwindowTargetWidth
print "subwindowTargetHeight", subwindowTargetHeight
print "fixedSize", fixedSize
print "------------Misc-----------------"
print "includeOriginalImage", includeOriginalImage
print "random", random
print "tempFolder", tempFolder
print "verbosity", verbosity
print "nbJobs", nbJobs
print "--------Bag of words params + SVC----------"
print "nbTrees", nbTrees
print "maxDepth", maxDepth
print "minSamplesSplit", minSamplesSplit
print "minSamplesLeaf", minSamplesLeaf
print "nbJobsEstimator", nbJobsEstimator
print "verbose", verbose
print "randomState", randomState
print "------------Data---------------"
print "LearningSet size", len(learningSet)
print "TestingSet size", len(testingSet)
print "-------------------------------"
if shouldSave:
print "saveFile", saveFile
print "Fit time", formatDuration(fitEnd - fitStart)
print "Classifcation time", formatDuration(predEnd - predStart)
print "Accuracy", accuracy
print "Leafs", formatBigNumber(classifier.histoSize)
return accuracy, confMat, importance, order
def run(nb_filters=nb_filters,
filterPolicy=filterPolicy,
poolings=poolings,
nbSubwindows=nbSubwindows,
subwindowMinSizeRatio=subwindowMinSizeRatio,
subwindowMaxSizeRatio=subwindowMaxSizeRatio,
subwindowTargetWidth=subwindowTargetWidth,
subwindowTargetHeight=subwindowTargetHeight,
fixedSize=fixedSize,
subwindowInterpolation=subwindowInterpolation,
includeOriginalImage=includeOriginalImage,
random=random,
nbJobs=nbJobs,
verbosity=verbosity,
tempFolder=tempFolder,
nbTrees=nbTrees,
maxDepth=maxDepth,
minSamplesSplit=minSamplesSplit,
minSamplesLeaf=minSamplesLeaf,
randomClassif=randomClassif,
nbJobsEstimator=nbJobsEstimator,
verbose=verbose,
learningUse=learningUse,
testingUse=testingUse,
saveFile=saveFile,
shouldSave=shouldSave):
randomState = None
if not randomClassif:
randomState = 100
lsSize = learningUse
if learningUse > maxLearningSize:
lsSize = maxLearningSize
tsSize = testingUse
if testingUse > maxTestingSize:
tsSize = maxTestingSize
#======INSTANTIATING========#
#--randconv--
randConvCoord = coordinatorRandConvFactory(
nbFilters=nb_filters,
filterPolicy=filterPolicy,
nbSubwindows=nbSubwindows,
subwindowMinSizeRatio=subwindowMinSizeRatio,
subwindowMaxSizeRatio=subwindowMaxSizeRatio,
subwindowTargetWidth=subwindowTargetWidth,
subwindowTargetHeight=subwindowTargetHeight,
poolings=poolings,
subwindowInterpolation=subwindowInterpolation,
includeOriginalImage=includeOriginalImage,
nbJobs=nbJobs,
verbosity=verbosity,
tempFolder=tempFolder,
random=random)
nb_filters = len(randConvCoord.getFilters())
#--SVM--
baseClassif = LinearSVC(verbose=verbose, random_state=randomState)
#--Classifier
classifier = uClassifier(coordinator=randConvCoord,
base_classifier=baseClassif,
n_estimators=nbTrees,
max_depth=maxDepth,
min_samples_split=minSamplesSplit,
min_samples_leaf=minSamplesLeaf,
n_jobs=nbJobsEstimator,
random_state=randomState,
verbose=verbose)
#--Data--
loader = CifarFromNumpies(learningSetDir, learningIndexFile)
learningSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
learningSet = learningSet[0:lsSize]
loader = CifarFromNumpies(testingSetDir, testingIndexFile)
testingSet = FileImageBuffer(loader.getFiles(), NumpyImageLoader())
testingSet = testingSet[0:tsSize]
#=====COMPUTATION=====#
#--Learning--#
print "Starting learning"
fitStart = time()
hist = classifier._preprocess(learningSet, learningPhase=True)
y = learningSet.getLabels()
if shouldSave:
np.savez(saveFile, data=hist.data, indices=hist.indices,
indptr=hist.indptr, shape=hist.shape)
classifier.fit_histogram(hist, y)
fitEnd = time()
print "Learning done", formatDuration(fitEnd-fitStart)
sys.stdout.flush()
#--Testing--#
y_truth = testingSet.getLabels()
predStart = time()
y_pred = classifier.predict(testingSet)
predEnd = time()
accuracy = classifier.accuracy(y_pred, y_truth)
confMat = classifier.confusionMatrix(y_pred, y_truth)
#====ANALYSIS=====#
importance, order = randConvCoord.importancePerFeatureGrp(classifier._visualBagger)
print "==================Bag of Visual Words======================="
print "-----------Filtering--------------"
print "nb_filters", nb_filters
print "filterPolicy", filterPolicy
print "----------Pooling--------------"
print "poolings", poolings
print "--------SW extractor----------"
print "#Subwindows", nbSubwindows
print "subwindowMinSizeRatio", subwindowMinSizeRatio
print "subwindowMaxSizeRatio", subwindowMaxSizeRatio
print "subwindowTargetWidth", subwindowTargetWidth
print "subwindowTargetHeight", subwindowTargetHeight
print "fixedSize", fixedSize
print "------------Misc-----------------"
print "includeOriginalImage", includeOriginalImage
print "random", random
print "tempFolder", tempFolder
print "verbosity", verbosity
print "nbJobs", nbJobs
print "--------Bag of words params + SVC----------"
print "nbTrees", nbTrees
print "maxDepth", maxDepth
print "minSamplesSplit", minSamplesSplit
print "minSamplesLeaf", minSamplesLeaf
print "nbJobsEstimator", nbJobsEstimator
print "verbose", verbose
print "randomState", randomState
print "------------Data---------------"
print "LearningSet size", len(learningSet)
print "TestingSet size", len(testingSet)
print "-------------------------------"
if shouldSave:
print "saveFile", saveFile
print "Fit time", formatDuration(fitEnd-fitStart)
print "Classifcation time", formatDuration(predEnd-predStart)
print "Accuracy", accuracy
print "Leafs", formatBigNumber(classifier.histoSize)
return accuracy, confMat, importance, order