def __init__(self,
gamma=1,
teta_onl=1,
teta_agglo=1,
bthres=0.5,
simil='mid',
sing='max',
isDraw=False,
oper='min',
isNorm=True,
norm_range=[0, 1],
V_pre=np.array([], dtype=np.float64),
W_pre=np.array([], dtype=np.float64),
classId_pre=np.array([], dtype=np.int16)):
BaseBatchLearningGFMM.__init__(self, gamma, teta_onl, isDraw, oper,
isNorm, norm_range)
self.teta_onl = teta_onl
self.teta_agglo = teta_agglo
self.V = V_pre
self.W = W_pre
self.classId = classId_pre
self.bthres = bthres
self.simil = simil
self.sing = sing
def __init__(self, gamma = 1, teta = 1, bthres = 0.5, simil = 'mid', sing = 'max', isDraw = False, oper = 'min', isNorm = True, norm_range = [0, 1], cardin = np.array([], dtype=np.int64), clusters = np.array([], dtype=object)):
BaseBatchLearningGFMM.__init__(self, gamma, teta, isDraw, oper, isNorm, norm_range)
self.bthres = bthres
self.simil = simil
if simil == 'mid':
self.sing = sing
else:
self.sing = 'max'
self.cardin = cardin
self.clusters = clusters
def __init__(self,
numClassifier=10,
numFold=10,
gamma=1,
teta=1,
bthres=0.5,
simil='mid',
sing='max',
oper='min',
isNorm=True,
norm_range=[0, 1]):
BaseBatchLearningGFMM.__init__(self, gamma, teta, False, oper, isNorm,
norm_range)
self.numFold = numFold
self.numClassifier = numClassifier
self.bthres = bthres
self.simil = simil
self.sing = sing
self.numHyperboxes = 0
def __init__(self,
gamma=1,
teta_onl=1,
teta_agglo=1,
bthres=0.5,
simil='mid',
sing='max',
isDraw=False,
oper='min',
isNorm=True,
norm_range=[0, 1]):
BaseBatchLearningGFMM.__init__(self, gamma, teta_onl, isDraw, oper,
isNorm, norm_range)
self.teta_onl = teta_onl
self.teta_agglo = teta_agglo
self.bthres = bthres
self.simil = simil
self.sing = sing
def __init__(self,
numClassifier=5,
gamma=1,
teta=1,
bthres=0.95,
bthres_min=0.05,
simil='mid',
sing='max',
oper='min',
isNorm=True,
norm_range=[0, 1]):
BaseBatchLearningGFMM.__init__(self, gamma, teta, False, oper, isNorm,
norm_range)
self.bthres_min = bthres_min
self.numClassifier = numClassifier
self.bthres = bthres
self.simil = simil
self.sing = sing
self.baseClassifiers = np.empty(numClassifier,
dtype=BaseBatchLearningGFMM)
self.numHyperboxes = 0