def sixClasses(numImgs):
# Classes of objects which are to be used
classlist = [
"005.volvic",
"006.barillabox",
"004.fantabottle",
"007.kinderschokoladetafel",
"003.pringles",
"002.cokecan",
]
numCluster = 5000
et = 7.5
pt = 5.0
etClassify = 7.5
ptClassify = 5.0
fDist = 0.0015
nu = 0.5
gamma = 1.0
confThr = 0.00
rec.logger.info("Training gleissenthalls six classes")
rec.logger.info("SIFT parameters: edge threshold=%f, peak threshold=%f", et, pt)
rec.logger.info("Number of clusters: %d", numCluster)
rec.logger.info("SVM parameter: nu=%f, sigma(RBF-Kernel)=%f", nu, gamma)
# Load images from folder structure
trainImgs = im.loadImages("img/train/6classes", classlist, numImgs)
testImgs = im.loadImages("img/test_big_images", classlist)
trainLabel = im.loadLabels("img/train/6classes", classlist, numImgs)
testLabels = im.loadLabels("img/test_big_images", classlist)
# Train classifier
learner = cl.Learner()
learner.trainPerClass(trainImgs, trainLabel, numCluster, fDist, pt, et)
c = cl.Classifier(learner)
testDesc, _ = im.extractFeaturesPerClass(testImgs, testLabels, ptClassify, etClassify)
tmpHistograms = cl._buildHistograms(learner.codebook, testDesc)
orngHistograms = cl._convertToOrangeDataSet(tmpHistograms, learner.domain, testLabels)
c.classificationAccuracy(orngHistograms, None, confThr, ptClassify, etClassify, nu, gamma, False)
c.saveToDB()
rec.logger.info("Classes: %s", learner.strClasses)
rec.logger.info("\n" + str(c.confusion))
rec.logger.info("\nAccuracy: %f CV: %f", c.clAccuracy, c.cvAccuracy)
def calltech(numTrain, numTest, masterCBs, pNorm, numCluster):
# Classes of objects which are to be used
classlist = None
# numCluster = 10000
et = 5.0
pt = 0.0
etClassify = 10.0
ptClassify = 2.5
fDist = 0.0001
nu = 0.5
gamma = 2.0
confThr = 0.00
rec.logger.info("Training calltech")
rec.logger.info("SIFT parameters: edge threshold=%f, peak threshold=%f", et, pt)
rec.logger.info("Number of clusters: %d", numCluster)
rec.logger.info("SVM parameter: nu=%f, sigma(RBF-Kernel)=%f", nu, gamma)
# Load images from folder structure
trainImgs = im.loadImages("256_ObjectCategories", classlist, numTrain)
testImgs = im.loadImages("256_ObjectCategories", classlist, numTest, rev=True)
trainLabel = im.loadLabels("256_ObjectCategories", classlist, numTrain)
testLabels = im.loadLabels("256_ObjectCategories", classlist, numTest)
# Train classifier
learner = cl.Learner()
learner.trainPerClass(trainImgs, trainLabel, numCluster, fDist, pt, et, masterCBs, pNorm)
c = cl.Classifier(learner)
testDesc, _ = im.extractFeaturesPerClass(testImgs, testLabels, ptClassify, etClassify)
tmpHistograms = cl._buildHistograms(learner.codebook, testDesc)
orngHistograms = cl._convertToOrangeDataSet(tmpHistograms, learner.domain, testLabels)
c.classificationAccuracy(orngHistograms, None, confThr, ptClassify, etClassify, nu, gamma, False)
c.saveToDB()
rec.logger.info("Classes: %s", learner.strClasses)
rec.logger.info("\n" + str(c.confusion))
rec.logger.info("\nAccuracy: %f CV: %f", c.clAccuracy, c.cvAccuracy)
def googleImages(numTrainImgs):
# Classes of objects which are to be used
classlist = None
numCluster = 5000
et = 5.0
pt = 7.5
etClassify = 7.5
ptClassify = 5.0
fDist = 0.0009
nu = 0.5
gamma = 2.0
confThr = 0.00
rec.logger.info("Training %i googleSimilarImages", numTrainImgs)
rec.logger.info("SIFT parameters: edge threshold=%f, peak threshold=%f", et, pt)
rec.logger.info("Number of clusters: %d", numCluster)
rec.logger.info("SVM parameter: nu=%f, sigma(RBF-Kernel)=%f", nu, gamma)
# Load images from folder structure
trainImgs = im.loadImages("img/train/googleSimilarImages", classlist, numTrainImgs)
testImgs = im.loadImages("img/test_big_images", classlist, 30)
trainLabel = im.loadLabels("img/train/googleSimilarImages", classlist, numTrainImgs)
testLabels = im.loadLabels("img/test_big_images", classlist, 30)
# Train classifier
learner = cl.Learner()
learner.trainPerClass(trainImgs, trainLabel, numCluster, fDist, pt, et)
c = cl.Classifier(learner)
testDesc, _ = im.extractFeaturesPerClass(testImgs, testLabels, ptClassify, etClassify)
tmpHistograms = cl._buildHistograms(learner.codebook, testDesc)
orngHistograms = cl._convertToOrangeDataSet(tmpHistograms, learner.domain, testLabels)
c.classificationAccuracy(orngHistograms, None, confThr, ptClassify, etClassify, nu, gamma, False)
c.saveToDB()
rec.logger.info("Classes: %s", learner.strClasses)
rec.logger.info("\n" + str(c.confusion))
rec.logger.info("\nAccuracy: %f CV: %f", c.clAccuracy, c.cvAccuracy)
def clusteringParamSearch(trainPath, trainClasses, trainCount, clusterRange, ptRange, etRange, fisherRange):
trainImgs = im.loadImages(trainPath, trainClasses, trainCount)
trainLabels = im.loadLabels(trainPath, trainClasses, trainCount)
for peakVal in ptRange:
for edgeVal in etRange:
# Extract SIFT features
rec.logger.info("SIFT Parameter. Peak: %f Edge: %f", peakVal, edgeVal)
trainDesc, numTrainingDesc = im.extractFeatures(trainImgs, peakVal, edgeVal)
for clusterParam in clusterRange:
for fDist in fisherRange:
learner = cl.Learner()
learner.peakThreshold = peakVal
learner.edgeThreshold = edgeVal
learner.numTrainingDesc = numTrainingDesc
rec.logger.info("Cluster parameter. Cluster: %i MinDist %f", clusterParam, fDist)
learner.averageSilhouetteCoefficient(trainLabels, trainDesc, clusterParam, fDist)
learner.saveToDB()
def parameterGridSearch(
trainPath,
trainClasses,
trainCount,
testPath,
testCount,
clusterRange,
ptRange,
etRange,
fisherRange,
nuRange,
gammaRange,
ctRange,
ptTestRg=None,
etTestRg=None,
numMastCB=1,
):
trainLabels = im.loadLabels(trainPath, trainClasses, trainCount)
trClasses = cl._getAllClasses(trainLabels)
testLabels = im.loadLabels(testPath, trClasses, testCount)
if ptTestRg is None and etTestRg is None:
ptTestRg = [-1]
etTestRg = [-1]
for peakVal in ptRange:
for edgeVal in etRange:
# Extract SIFT features
rec.logger.info("SIFT Training Parameter. Peak: %f Edge: %f", peakVal, edgeVal)
trainImgs = im.loadImages(trainPath, trainClasses, trainCount)
trainDescPerClass, numTrainDesc = im.extractFeaturesPerClass(trainImgs, trainLabels, peakVal, edgeVal)
for clusterParam in clusterRange:
for fDist in fisherRange:
learner = cl.Learner()
learner.peakThreshold = peakVal
learner.edgeThreshold = edgeVal
learner.numTrainingDesc = numTrainDesc
rec.logger.info("Cluster parameter. Cluster: %i MinDist %f", clusterParam, fDist)
try:
learner.trainPerClass(trainDescPerClass, trainLabels, clusterParam, fDist, masterCBs=numMastCB)
except ValueError:
rec.logger.warning("Skipped this paramter set because there are not enough features.")
break
for p in ptTestRg:
for e in etTestRg:
if p == -1 and e == -1:
p = peakVal
e = edgeVal
rec.logger.info("SIFT Test Parameter. Peak: %f Edge: %f", p, e)
testImgs = im.loadImages(testPath, trClasses, testCount, False)
testDesc, numTestDesc = im.extractFeaturesPerClass(testImgs, testLabels, p, e)
tmpHistograms = cl._buildHistograms(learner.codebook, testDesc)
orngHistograms = cl._convertToOrangeDataSet(tmpHistograms, learner.domain, testLabels)
for n in nuRange:
for g in gammaRange:
for ct in ctRange:
c = cl.Classifier(learner)
c.numTestDesc = numTestDesc
c.peakThreshold = p
c.edgeThreshold = e
rec.logger.info(
"SVM parameter. Nu: %f gamma %f," "Confidence Threshold: %f", n, g, ct
)
_, _ = c.classificationAccuracy(orngHistograms, None, ct, p, e, n, g)
c.saveToDB()
rec.logger.info(
"Ref count of classifier: %i, learner: %i",
sys.getrefcount(c),
sys.getrefcount(learner),
)
