kernel = 'rbf'
gamma = 0.0012
C = 250
experience = '2018'
positiveCsvFileName = 'hard-video.csv'
negativeCsvFileName = 'easy-video.csv'
path = './result/{0}/{1}/g{2}/c{3}'.format(experience, dir_name, gamma, C)
dicimate = 4
mil = MIL(method=method,
experience=experience,
dirName=dir_name,
estimatorName='misvm')
mil.setData(positiveCsvFileName=positiveCsvFileName,
negativeCsvFileName=negativeCsvFileName,
saveMotionTmplate=False,
dicimate=dicimate,
videoExtension='mp4',
csvExtension='csv')
#mil.importCsv2Feature(positiveCsvFileName, negativeCsvFileName, dicimate, data='all')
def main(): # read hard and easy
estimator = misvm.miSVM(kernel=kernel,
gamma=gamma,
C=C,
verbose=True,
max_iters=100)
#estimator = misvm.miPSVM(feature=kernel, gamma=gamma, C=C, verbose=True, max_iters=100, n_components=36*3, sparse=['P'])
mil.train(estimator=estimator, resultSuperDirPath=path)
kernel = 'rbf'
gamma = 0.0012
C = 1000
sample_num_per_label = 0
experience = '2018'
path = './result/{0}/{1}/g{2}/c{3}'.format(experience, dir_name, gamma, C)
dicimate = 4
person = []
mil = MIL(method=method,
experience=experience,
dirName=dir_name,
estimatorName='MISVM')
mil.setData(positiveCsvFileName='easy-video.csv',
negativeCsvFileName='hard-video.csv',
saveMotionTmplate=False,
dicimate=4,
videoExtension='mp4',
csvExtension='csv')
def main(): # read hard and easy
estimator = misvm.MISVM(kernel=kernel,
gamma=gamma,
C=C,
verbose=True,
max_iters=100)
mil.train(estimator=estimator, resultSuperDirPath=path)
def check_identification_func_max():
bags, labels, csvnamelist = mil.bags, mil.labels, mil.csvFilePaths