def create_member(self, data_files):
#Gets the training indexes
if self.member_number > 0:
train_indexes = \
self.resampler.make_new_train(self.params.resample_size)
else:
train_indexes = [None, None]
#Packs the needed data
dataset = [train_indexes, data_files]
#Trains the model
m = mlp.sequential_model(dataset,
self.params,
member_number=self.member_number)
#Gets the errors for the train set and updates the weights
print('Getting the train errors and updating the weights')
errors = common.errors(m, data_files[0], self.params.batch_size)
e = np.sum((errors * self.D))
if e > 0:
n_classes = data_files[0]['y'].shape[1]
alpha = .5 * (math.log((1 - e) / e) + math.log(n_classes - 1))
if alpha <= 0.0:
#By setting to 0 (instead of crashing), we should avoid
# cicleci problems
print("\nWARNING - NEGATIVE ALPHA (setting to 0.0)\n")
alpha = 0.0
w = np.where(errors == 1, self.D * math.exp(alpha),
self.D * math.exp(-alpha))
self.D = w / w.sum()
else:
alpha = 1.0 / (self.member_number + 1)
self.resampler.update_weights(self.D)
self.alphas.append(alpha)
self.member_number += 1
return (m.to_yaml(), m.get_weights())
def create_member(self):
train_set, sample_weights = self.resampler.make_new_train(
self.params.resample_size)
if self.member_number > 0:
resampled = [
train_set,
self.resampler.get_valid(),
self.resampler.get_test()
]
else:
sample_weights = None
resampled = [
self.resampler.get_train(),
self.resampler.get_valid(),
self.resampler.get_test()
]
m = mlp.sequential_model(resampled,
self.params,
member_number=self.member_number,
sample_weight=sample_weights)
orig_train = self.resampler.get_train()
errors = common.errors(m, orig_train[0], orig_train[1])
e = np.sum((errors * self.D))
if e > 0:
alpha = .5 * math.log((1 - e) / e)
w = np.where(errors == 1, self.D * math.exp(alpha),
self.D * math.exp(-alpha))
self.D = w / w.sum()
else:
alpha = 1.0 / (self.member_number + 1)
self.resampler.update_weights(self.D)
self.alphas.append(alpha)
self.member_number += 1
return (m.to_yaml(), m.get_weights())
def create_member(self):
self.set_defaults()
if self.member_number > 0:
if self.resample:
train_set, sample_weights = self.resampler.make_new_train(
self.params.resample_size)
resampled = [
train_set,
self.resampler.get_valid(),
self.resampler.get_test()
]
else:
sample_weights = self.D
resampled = [
self.resampler.get_train(),
self.resampler.get_valid(),
self.resampler.get_test()
]
else:
sample_weights = None
resampled = [
self.resampler.get_train(),
self.resampler.get_valid(),
self.resampler.get_test()
]
if self.member_number > 0:
self.params.n_epochs = self.n_epochs_after_first
if not self.use_sample_weights:
sample_weights = None
m = mlp.sequential_model(
resampled,
self.params,
member_number=self.member_number,
model_weights=self.weights,
#the copy is because there is a bug in Keras that deletes names
model_config=copy.deepcopy(self.model_config),
frozen_layers=self.frozen_layers,
sample_weight=sample_weights)
self.weights = [l.get_weights() for l in m.layers]
injection_index = self.incremental_index + self.member_number
if self.incremental_layers is not None:
if injection_index == -1:
injection_index = len(self.model_config)
new_layers = []
for i, l in enumerate(self.incremental_layers):
new_layers.append(copy.deepcopy(l))
#make residual block
new_block = self._residual_block(injection_index, new_layers, m,
self.member_number)
new_model_config = self.model_config[:injection_index] + [
new_block
] + self.model_config[injection_index:]
if self.freeze_old_layers:
self.frozen_layers = list(range(0, injection_index))
self.model_config = copy.deepcopy(new_model_config)
self.weights = self.weights[:injection_index]
orig_train = self.resampler.get_train()
K = orig_train[1].shape[1]
self.n_classes = K
errors = common.errors(m, orig_train[0], orig_train[1])
error_rate = np.mean(errors)
if error_rate >= 1. - (1. / K):
return (None, None, False)
if self.real:
#Real BRN
print(("-" * 40))
print(("error rate: {}".format(error_rate)))
if error_rate > 0:
continue_boosting = True
y_coding = np.where(orig_train[1] == 0., -1. / (K - 1), 1.)
proba = m.predict(orig_train[0])
proba[proba < np.finfo(proba.dtype).eps] = np.finfo(
proba.dtype).eps
print((proba[:10]))
print((self.D[:10]))
factor = np.exp(
-1. * (((K - 1.) / K) * inner1d(y_coding, np.log(proba))))
print((factor[:10]))
w = self.D * factor
print((w[:10]))
self.D = w / w.sum()
self.resampler.update_weights(self.D)
else:
continue_boosting = not self.early_stopping
self.member_number += 1
return (m.to_yaml(), m.get_weights(), continue_boosting)
else:
if error_rate > 0:
continue_boosting = True
#e = sum((errors * self.D)) / sum(self.D)
e = np.average(errors, weights=self.D)
alpha = math.log((1 - e) / e) + math.log(K - 1)
factor = np.clip(
np.where(errors == 1, math.exp(alpha), math.exp(-alpha)),
1e-3, 1e3)
w = self.D * factor
self.D = w / w.sum()
self.resampler.update_weights(self.D)
else:
continue_boosting = not self.early_stopping
alpha = 1. / (self.member_number + 1)
self.alphas.append(alpha)
self.member_number += 1
return (m.to_yaml(), m.get_weights(), continue_boosting)
def create_member(self):
self.set_defaults()
train_set, sample_weights = self.resampler.make_new_train(
self.params.resample_size)
if self.member_number > 0:
if self.resample:
resampled = [
train_set,
self.resampler.get_valid(),
self.resampler.get_test()
]
else:
resampled = [
self.resampler.get_train(),
self.resampler.get_valid(),
self.resampler.get_test()
]
else:
sample_weights = None
resampled = [
self.resampler.get_train(),
self.resampler.get_valid(),
self.resampler.get_test()
]
if self.member_number > 0:
self.params.n_epochs = self.n_epochs_after_first
if 'lr_after_first' in self.params.__dict__:
self.params.optimizer['config'][
'lr'] = self.params.lr_after_first
if not self.use_sample_weights:
sample_weights = None
m = mlp.sequential_model(
resampled,
self.params,
member_number=self.member_number,
model_weights=self.weights,
#the copy is because there is a bug in Keras that deletes names
model_config=copy.deepcopy(self.model_config),
sample_weight=sample_weights)
self.weights = [l.get_weights() for l in m.layers]
injection_index = self.incremental_index + self.member_number * len(
self.incremental_layers)
if self.incremental_layers is not None:
if injection_index == -1:
injection_index = len(self.model_config)
new_layers = []
for i, l in enumerate(self.incremental_layers):
l['config']['name'] = "DIB-incremental-{0}-{1}".format(
self.member_number, i)
new_layers.append(l)
new_model_config = self.model_config[:
injection_index] + new_layers + self.model_config[
injection_index:]
self.model_config = copy.deepcopy(new_model_config)
self.weights = self.weights[:injection_index]
orig_train = self.resampler.get_train()
K = orig_train[1].shape[1]
errors = common.errors(m, orig_train[0], orig_train[1])
e = sum((errors * self.D)) / sum(errors + np.finfo(np.float32).eps)
alpha = math.log((1 - e) / e + np.finfo(np.float32).eps) + math.log(K -
1)
w = np.where(errors == 1, self.D * math.exp(alpha),
self.D * math.exp(-alpha))
self.D = w / w.sum()
self.resampler.update_weights(self.D)
self.alphas.append(alpha)
self.member_number += 1
m_yaml = m.to_yaml()
m_weights = m.get_weights()
del m
return (m_yaml, m_weights)