def verifyProxies(self, proxies):
''' Take as input dictionary of {name:proxystring} and verify that
we can communicate with the server (by getting the detector or trainer).
Return a dictionary with 'detector running' or 'trainer running' if running
and 'configured' if not. Also print now so with long config files user
sees output.
'''
res = {}
for key, value in proxies.iteritems():
# add short timeout
value = value + ' -t 100'
try:
detector = easy.getDetector(value)
res[key] = 'detector running'
print("{0} {1}".format(key, res[key]))
continue
except:
pass
try:
trainer = easy.getTrainer(value)
res[key] = 'trainer running'
print("{0} {1}".format(key, res[key]))
continue
except:
pass
try:
trainer = easy.getFileServer(value)
res[key] = 'FileServer running'
print("{0} {1}".format(key, res[key]))
continue
except:
pass
try:
trainer = easy.getCorpusServer(value)
res[key] = 'Corpus running'
print("{0} {1}".format(key, res[key]))
continue
except:
pass
res[key] = 'not running'
print("{0} {1}".format(key, res[key]))
return res
doWithNegativeSample = True
if doWithNegativeSample:
###############################################################
# With background data
'''
Execute jousting for generating ROC points
'''
contenders = []
for nWord in list_nWord:
c1 = evaluate.Contender("bowROC_binary_"+str(nWord))
c1.trainerString = strTrainer
c1.detectorString = strDetector
trainer = easy.getTrainer(c1.trainerString)
trainerProps = easy.getTrainerProperties(trainer)
trainerProps.props["NumWords"] = str(nWord)
c1.trainerProps = trainerProps
c1.foundMap = {'1':easy.getPurpose('pos'), '0':easy.getPurpose('neg')}
contenders.append(c1)
sortedperfdata, perfdata = evaluate.joust( contenders, runset, folds=3 )
easy.showROCPlot(perfdata)
'''
Extract only optimal ROC points
'''
rocData_full,optimalIndices = easy.discardSuboptimal(perfdata)
#rocData_full,optimalIndices = easy.discardSuboptimal(perfdata,"sboxes/BOW_Trainer_127_0_0_1")
Easy! mini tutorial
Compare the performance of several trainers and/or detectors
matz 11/26/2013
'''
import easy
import easy.evaluate as ev
# perform a comparative detector evaluation including
# training of a model
# easy.CVAC_ClientVerbosity = 4
posPurpose = easy.getPurpose('pos')
negPurpose = easy.getPurpose('neg')
contenders = []
# Bag of Words
if (easy.getTrainer("BOW_Trainer")==None):
print("BOW service(s) are insufficiently configured, skipping.")
else:
c = ev.Contender("BOW")
c.trainerString = "BOW_Trainer"
c.detectorString = "BOW_Detector"
c.foundMap = {'1':posPurpose, '0':negPurpose}
contenders.append( c );
# Histogram of Oriented Gradients
if (easy.getTrainer("HOG_Trainer")==None):
print("HOG service(s) are insufficiently configured, skipping.")
else:
c = ev.Contender("HOG")
c.trainerString = "HOG_Trainer"
c.detectorString = "HOGTest"
# it is the client's responsibility to upload them if not.
# The putResult contains information about which files were actually transferred.
#
fileserver = easy.getFileServer( "FileService:default -p 10110 " + host )
putResult = easy.putAllFiles( fileserver, rs1 )
modelfile = "detectors/haarcascade_frontalface_alt.xml"
if not fileserver.exists( easy.getCvacPath(modelfile) ):
easy.putFile( fileserver, easy.getCvacPath(modelfile) )
#
# detect remotely: note the host specification
#
print("------- Remote detection, local result display: -------")
detector = easy.getDetector( "OpenCVCascadeDetector:default -p 10102 "+host )
results = easy.detect( detector, modelfile, rs1 )
easy.printResults( results )
#
# Example 2:
# Train on a remote machine, obtain the model file, and test locally.
# Assume the files are on the remote machine, or transfer with putAllFiles.
#
trainer = easy.getTrainer( "bowTrain:default -p 10103 "+ host) # remote
trainset = easy.createRunSet( "trainImg" );
trainedModel = easy.train( trainer, trainset )
easy.getFile( fileserver, trainedModel.file ) # downloads the model from remote
print("{0}".format(trainedModel))
detector = easy.getDetector( "bowTest:default -p 10104" ) # local service
testset = easy.createRunSet("testImg","UNPURPOSED" )
results = easy.detect( detector, trainedModel, testset )
def getTrainer( self ):
if not self.trainer:
self.trainer = easy.getTrainer( self.trainerString )
return self.trainer
#trainset = easy.createRunSet( "trainImg" )
trainset = cvac.RunSet()
caset = easy.createRunSet("trainImg/ca")
krset = easy.createRunSet("trainImg/kr")
usset = easy.createRunSet("trainImg/us")
easy.addToRunSet(trainset, caset, cvac.Purpose(cvac.PurposeType.MULTICLASS, 0))
easy.addToRunSet(trainset, krset, cvac.Purpose(cvac.PurposeType.MULTICLASS, 1))
easy.addToRunSet(trainset, usset, cvac.Purpose(cvac.PurposeType.MULTICLASS, 2))
easy.printRunSetInfo(trainset, printLabels=True)
#
# Connect to the trainer for a Bag of Words algorithm, then
# train with the given runset
#
print("starting training, this might take a few minutes...")
trainer = easy.getTrainer("BOW_Trainer")
trainedModel = easy.train(trainer, trainset)
#
# Display information about the file in which the model is stored;
# this is generally no concern to algorithm users and only of
# interest to algorithm developers since it is algorithm-specific
#
zipfname = easy.getFSPath(trainedModel)
print("{0}".format(zipfname))
zipf = zipfile.ZipFile(zipfname)
print("Training model stored in file {0}".format(zipfname))
# print("file contents:\n{0}".format(zipf.namelist()))
#
# test the trained model on a separate set of images
Easy! mini tutorial
Compare the performance of several trainers and/or detectors
matz 11/26/2013
'''
import easy
import easy.evaluate as ev
# perform a comparative detector evaluation including
# training of a model
# easy.CVAC_ClientVerbosity = 4
posPurpose = easy.getPurpose('pos')
negPurpose = easy.getPurpose('neg')
contenders = []
# Bag of Words
if (easy.getTrainer("BOW_Trainer") == None):
print("BOW service(s) are insufficiently configured, skipping.")
else:
c = ev.Contender("BOW")
c.trainerString = "BOW_Trainer"
c.detectorString = "BOW_Detector"
c.foundMap = {'1': posPurpose, '0': negPurpose}
contenders.append(c)
# Histogram of Oriented Gradients
if (easy.getTrainer("HOG_Trainer") == None):
print("HOG service(s) are insufficiently configured, skipping.")
else:
c = ev.Contender("HOG")
c.trainerString = "HOG_Trainer"
c.detectorString = "HOGTest"
# pick a subset: all license plates
license_plates = categories['license plate']
print("There are {0} license plate labels.".format( len(license_plates) ))
# another subset: all labels starting with "car"
cars = []
for key in categories.keys():
if key.startswith("car"):
cars.append( categories[key] )
print("There are {0} car-related labels.".format( len(cars) ))
# Note that Labels are cached in the CorpusServer, but the corpus currently
# needs to re-mirror if the CorpusServer is restarted because Labels are
# not stored to disk. Images are stored to disk.
quit() # done for now
# Train a detector on license plates
trainer = easy.getTrainer( "BOW_Trainer:default -p 10103 ")
trainset = easy.createRunSet( license_plates, "pos" )
easy.printRunSetInfo( trainset )
licenseplateModel = easy.train( trainer, trainset )
# test the license plate detector on the known locations of cars;
# this will only try to detect within the boundaries of cars.
testset = easy.createRunSet( cars, "unpurposed" )
detector = easy.getDetector( "BOW_Detector:default -p 10104" )
results = easy.detect( detector, licenseplateModel, testset )
printResults( results )
#
# detect remotely: note the host specification
#
detector = easy.getDetector("OpenCVCascadeDetector:default -p 10102 " + host)
results = easy.detect(detector, modelfile, rs1)
easy.printResults(results)
#
# Example 2:
# Train on a remote machine, obtain the model file, and test locally.
# Assume the files are on the remote machine, or transfer with putAllFiles.
# If no local services are installed, this will be skipped.
#
print("------- Remote training, local detection: -------")
try:
detector = easy.getDetector(
"BOW_Detector:default -p 10104") # local service
trainer = easy.getTrainer("BOW_Trainer:default -p 10103 " + host) # remote
trainset = easy.createRunSet("trainImg")
trainedModel = easy.train(trainer, trainset)
easy.getFile(fileserver, trainedModel) # downloads the model from remote
print("obtained trained detector, stored in file {0}".format(
easy.getFSPath(trainedModel)))
testset = easy.createRunSet("testImg", "UNPURPOSED")
results = easy.detect(detector, trainedModel, testset)
easy.printResults(results)
except:
print("Cannot connect to local detector. Have you started the services?\n"\
"This part of the demo does not work with the client-only distribution.")
# it is the client's responsibility to upload them if not.
# The putResult contains information about which files were actually transferred.
#
fileserver = easy.getFileServer( "FileService:default -p 10110 " + host )
putResult = easy.putAllFiles( fileserver, rs1 )
modelfile = "detectors/haarcascade_frontalface_alt.xml"
if not fileserver.exists( easy.getCvacPath(modelfile) ):
easy.putFile( fileserver, easy.getCvacPath(modelfile) )
#
# detect remotely: note the host specification
#
print("------- Remote detection, local result display: -------")
detector = easy.getDetector( "OpenCVCascadeDetector:default -p 10102 "+host )
results = easy.detect( detector, modelfile, rs1 )
easy.printResults( results )
#
# Example 2:
# Train on a remote machine, obtain the model file, and test locally.
# Assume the files are on the remote machine, or transfer with putAllFiles.
#
trainer = easy.getTrainer( "BOW_Trainer:default -p 10103 "+ host) # remote
trainset = easy.createRunSet( "trainImg" );
trainedModel = easy.train( trainer, trainset )
easy.getFile( fileserver, trainedModel ) # downloads the model from remote
print("{0}".format(trainedModel))
detector = easy.getDetector( "BOW_Detector:default -p 10104" ) # local service
testset = easy.createRunSet("testImg","UNPURPOSED" )
results = easy.detect( detector, trainedModel, testset )
''' Easy! mini tutorial Repeatedly train and evaluate for efficient label use; bootstrap. matz 6/21/2013 ''' import os import easy # # Create a training set from one sample each of 9 corporate logos # trainset1 = easy.createRunSet( "corporate_logos" ) # train, round 1 trainer = easy.getTrainer( "BOW_Trainer") model1 = easy.train( trainer, trainset1 ) # evaluate the model on a separate test set, images and videos # in DataDir/testdata1 testset1 = easy.createRunSet( "testImg", "UNPURPOSED" ) easy.printRunSetInfo( testset1 ) detector = easy.getDetector( "BOW_Detector" ) result1 = easy.detect( detector, model1, testset1 ) easy.printResults(result1) # sort the images from the testdata1 folder into subfolders of # "testresults1" corresponding to the found labels; # if multiple labels were found per original, consider only # the label with the highest confidence easy.sortIntoFolders( result1, outfolder="testresults1", multi="highest")
# pick a subset: all license plates
license_plates = categories['license plate']
print("There are {0} license plate labels.".format( len(license_plates) ))
# another subset: all labels starting with "car"
cars = []
for key in categories.keys():
if key.startswith("car"):
cars.append( categories[key] )
print("There are {0} car-related labels.".format( len(cars) ))
# Note that Labels are cached in the CorpusServer, but the corpus currently
# needs to re-mirror if the CorpusServer is restarted because Labels are
# not stored to disk. Images are stored to disk.
quit() # done for now
# Train a detector on license plates
trainer = easy.getTrainer( "bowTrain:default -p 10103 ")
trainset = easy.createRunSet( license_plates, "pos" )
easy.printRunSetInfo( trainset )
licenseplateModel = easy.train( trainer, trainset )
# test the license plate detector on the known locations of cars;
# this will only try to detect within the boundaries of cars.
testset = easy.createRunSet( cars, "unpurposed" )
detector = easy.getDetector( "bowTest:default -p 10104" )
results = easy.detect( detector, licenseplateModel, testset )
printResults( results )
# pick a subset: all license plates
license_plates = categories['license plate']
print("There are {0} license plate labels.".format(len(license_plates)))
# another subset: all labels starting with "car"
cars = []
for key in categories.keys():
if key.startswith("car"):
cars.append(categories[key])
print("There are {0} car-related labels.".format(len(cars)))
# Note that Labels are cached in the CorpusServer, but the corpus currently
# needs to re-mirror if the CorpusServer is restarted because Labels are
# not stored to disk. Images are stored to disk.
quit() # done for now
# Train a detector on license plates
trainer = easy.getTrainer("BOW_Trainer:default -p 10103 ")
trainset = easy.createRunSet(license_plates, "pos")
easy.printRunSetInfo(trainset)
licenseplateModel = easy.train(trainer, trainset)
# test the license plate detector on the known locations of cars;
# this will only try to detect within the boundaries of cars.
testset = easy.createRunSet(cars, "unpurposed")
detector = easy.getDetector("BOW_Detector:default -p 10104")
results = easy.detect(detector, licenseplateModel, testset)
printResults(results)
list_nWord = [5, 10, 15, 20]
doWithNegativeSample = True
if doWithNegativeSample:
###############################################################
# With background data
'''
Execute jousting for generating ROC points
'''
contenders = []
for nWord in list_nWord:
c1 = evaluate.Contender("bowROC_binary_" + str(nWord))
c1.trainerString = strTrainer
c1.detectorString = strDetector
trainer = easy.getTrainer(c1.trainerString)
trainerProps = easy.getTrainerProperties(trainer)
trainerProps.props["NumWords"] = str(nWord)
c1.trainerProps = trainerProps
c1.foundMap = {
'1': easy.getPurpose('pos'),
'0': easy.getPurpose('neg')
}
contenders.append(c1)
sortedperfdata, perfdata = evaluate.joust(contenders, runset, folds=3)
easy.showROCPlot(perfdata)
'''
Extract only optimal ROC points
'''
rocData_full, optimalIndices = easy.discardSuboptimal(perfdata)
