def __init__(self):
"""Initialise base fitness function class and its variables.
"""
super().__init__()
self.num_obj = 2
dummyfit = base_ff()
dummyfit.maximise = True
self.fitness_functions = [dummyfit, dummyfit]
self.default_fitness = [-1, -1]
t = time.localtime()
current_time = time.strftime("%H-%M-%S", t)
self.filename = current_time + ".txt"
in_file = "../data/haralick02_50K.csv"
df = pd.read_csv(in_file)
df.sort_values(by=['Label'], inplace=True)
haralick_features = []
for i in range(104):
feature = "x" + str(i)
haralick_features.append(feature)
self.data = df[haralick_features]
self.labels = df['Label']
self.training = self.data
self.test = self.data
self.n_vars = len(self.data)
self.test1 = 0
self.test2 = 0
def __init__(self):
super().__init__()
self.num_obj = 2
fit = base_ff()
fit.maximise = True
self.fitness_functions = [fit, fit]
self.default_fitness = [float('nan'), float('nan')]
def __init__(self):
super().__init__()
self.filename = '/pesquisa/phenotypes.csv'
self.num_obj = 2
fit = base_ff()
fit.maximise = True
self.fitness_functions = [fit, fit]
self.default_fitness = [float('nan'), float('nan')]
def __init__(self):
super().__init__()
self.num_obj = 2
fit = base_ff()
fit.maximise = True
self.fitness_functions = [fit, fit]
self.default_fitness = [float('nan'), float('nan')]
tpu = tf.distribute.cluster_resolver.TPUClusterResolver.connect()
tpu_strategy = tf.distribute.experimental.TPUStrategy(tpu)
self.tpu_strategy = tpu_strategy
def __init__(self):
# Initialise base fitness function class.
super().__init__()
# Set list of individual fitness functions.
self.num_obj = 2
dummyfit = base_ff()
dummyfit.maximise = True
self.fitness_functions = [dummyfit, dummyfit]
self.default_fitness = [float('nan'), float('nan')]
def __init__(self):
# Initialise base fitness function class.
super().__init__()
# Set list of individual fitness functions.
self.num_obj = 2
dummyfit = base_ff()
dummyfit.maximise = True
self.fitness_functions = [dummyfit, dummyfit]
self.default_fitness = [float('nan'), float('nan')]
def __init__(self):
# Initialise base fitness function class.
super().__init__()
test_set = face(['./deeplearn/test.hdf5'])
train_set = face(['./deeplearn/train.hdf5'])
self.test_loader = DataLoader(test_set,
shuffle=False,
batch_size=32,
num_workers=1)
self.train_loader = DataLoader(train_set,
batch_size=32,
shuffle=False,
num_workers=1,
pin_memory=True)
# Set list of individual fitness functions.
self.num_obj = 2
dummyfit = base_ff()
dummyfit.maximise = True
self.fitness_functions = [dummyfit, dummyfit]
self.default_fitness = [float('nan'), float('nan')]