def compareDefaultPlots(wildcard="lambda_SE"):
wu2013GroundTruth = "/Users/Ivan/Files/Data/wu2013"
datasetType = 'wu2013'
dataset = Dataset(wu2013GroundTruth, datasetType)
runsNames = glob.glob("./Runs/" + wildcard + "*.p")
formatSave='pdf'
regexp= re.compile("(.*\/)(.+)(.p)")
#s0_e0.2
#s0_e0.5
#s0.1_e0.3
#s0.2_e0.2
#s0.3_e0.4
d=dict()
runs=list()
for runName in runsNames:
m=re.match(regexp,runName)
name=m.group(2)
print name
run = loadPickle(runName)
run.trackerLabel=runName
run.data['TRE'].data=[]
run.data['SRE'].data=[]
d[runName] = run
runs.append(run)
evaluator = Evaluator(dataset, runs)
evaluator.evaluateSingleTracker(runs[0])
def evaluate(self,
n=1000,
successAndPrecisionPlotName='',
histogramPlot=''):
'''
Evaluate the dataset
:return: accuracy and precision
'''
listGT = self.dataset.data
pr_x_list = list()
pr_y_list = list()
sc_x_list = list()
sc_y_list = list()
experimentNames = list()
defaultExpList = list()
sreExpList = list()
treExpList = list()
for listRun, name in zip(self.listOfExperiments, self.experimentNames):
runs = listRun.data
experimentNames.append(name)
defaultExpList.append(runs['default'])
sreExpList.append(runs['SRE'])
treExpList.append(runs['TRE'])
allExpList = list()
allExpList.append(defaultExpList)
allExpList.append(sreExpList)
allExpList.append(treExpList)
pr_x_all_list = list()
pr_y_all_list = list()
sc_x_all_list = list()
sc_y_all_list = list()
for exp in allExpList: # experiment type
# exp
e = Evaluator(self.dataset, exp)
pr_x_list = list()
pr_y_list = list()
sc_x_list = list()
sc_y_list = list()
measures_specific_list = list()
for listRun in exp: # different tracker runs
(precision_x, precision_y, success_x,
success_y) = e.evaluateSingleTracker(listRun, n)
pr_x_list.append(precision_x)
pr_y_list.append(precision_y)
sc_x_list.append(success_x)
sc_y_list.append(success_y)
pr_x_all_list.append(pr_x_list)
pr_y_all_list.append(pr_y_list)
sc_x_all_list.append(sc_x_list)
sc_y_all_list.append(sc_y_list)
def evaluate(self, n=1000, successAndPrecisionPlotName='', histogramPlot=''):
'''
Evaluate the dataset
:return: accuracy and precision
'''
listGT = self.dataset.data
pr_x_list = list()
pr_y_list = list()
sc_x_list = list()
sc_y_list = list();
experimentNames = list()
defaultExpList=list()
sreExpList=list()
treExpList=list()
for listRun,name in zip(self.listOfExperiments,self.experimentNames):
runs = listRun.data
experimentNames.append(name)
defaultExpList.append(runs['default'])
sreExpList.append(runs['SRE'])
treExpList.append(runs['TRE'])
allExpList=list()
allExpList.append(defaultExpList)
allExpList.append(sreExpList)
allExpList.append(treExpList)
pr_x_all_list=list()
pr_y_all_list=list()
sc_x_all_list = list()
sc_y_all_list = list()
for exp in allExpList: # experiment type
# exp
e=Evaluator(self.dataset,exp)
pr_x_list = list()
pr_y_list = list()
sc_x_list = list()
sc_y_list = list()
measures_specific_list=list()
for listRun in exp: # different tracker runs
(precision_x, precision_y, success_x, success_y) = e.evaluateSingleTracker(listRun, n)
pr_x_list.append(precision_x)
pr_y_list.append(precision_y)
sc_x_list.append(success_x)
sc_y_list.append(success_y)
pr_x_all_list.append(pr_x_list)
pr_y_all_list.append(pr_y_list)
sc_x_all_list.append(sc_x_list)
sc_y_all_list.append(sc_y_list)
