本文整理汇总了Python中nolearn.lasagne.BatchIterator方法的典型用法代码示例。如果您正苦于以下问题：Python lasagne.BatchIterator方法的具体用法？Python lasagne.BatchIterator怎么用？Python lasagne.BatchIterator使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nolearn.lasagne的用法示例。
在下文中一共展示了lasagne.BatchIterator方法的6个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: model_initial
# 需要导入模块: from nolearn import lasagne [as 别名]
# 或者: from nolearn.lasagne import BatchIterator [as 别名]
def model_initial(X_train,y_train,max_iter = 5):
global params, val_acc
params = []
val_acc = np.zeros(max_iter)
lr = theano.shared(np.float32(1e-4))
for iteration in range(max_iter):
print 'Initializing weights (%d/5) ...'%(iteration+1)
network_init = create_network()
net_init = NeuralNet(
network_init,
max_epochs=3,
update=adam,
update_learning_rate=lr,
train_split=TrainSplit(eval_size=0.1),
batch_iterator_train=BatchIterator(batch_size=32),
batch_iterator_test=BatchIterator(batch_size=64),
on_training_finished=[SaveTrainHistory(iteration = iteration)],
verbose=0)
net_init.initialize()
net_init.fit(X_train, y_train)
#model training 示例2: model_train
# 需要导入模块: from nolearn import lasagne [as 别名]
# 或者: from nolearn.lasagne import BatchIterator [as 别名]
def model_train(X_train, y_train,learning_rate = 1e-4,epochs = 50):
network = create_network()
lr = theano.shared(np.float32(learning_rate))
net = NeuralNet(
network,
max_epochs=epochs,
update=adam,
update_learning_rate=lr,
train_split=TrainSplit(eval_size=0.1),
batch_iterator_train=BatchIterator(batch_size=32),
batch_iterator_test=BatchIterator(batch_size=64),
#on_training_started=[LoadBestParam(iteration=val_acc.argmax())],
on_epoch_finished=[EarlyStopping(patience=5)],
verbose=1)
print 'Loading pre-training weights...'
net.load_params_from(params[val_acc.argmax()])
print 'Continue to train...'
net.fit(X_train, y_train)
print 'Model training finished.'
return net
#model testing 示例3: model_train
# 需要导入模块: from nolearn import lasagne [as 别名]
# 或者: from nolearn.lasagne import BatchIterator [as 别名]
def model_train(X_train, y_train,learning_rate = 1e-4,epochs = 50):
network = create_network()
lr = theano.shared(np.float32(learning_rate))
net = NeuralNet(
network,
max_epochs=epochs,
update=adam,
update_learning_rate=lr,
train_split=TrainSplit(eval_size=0.1),
batch_iterator_train=BatchIterator(batch_size=32),
batch_iterator_test=BatchIterator(batch_size=64),
regression = True,
objective_loss_function = squared_error,
#on_training_started=[LoadBestParam(iteration=val_loss.argmin())],
on_epoch_finished=[EarlyStopping(patience=5)],
verbose=1)
print 'loading pre-training weights...'
net.load_params_from(params[val_loss.argmin()])
print 'continue to train...'
net.fit(X_train, y_train)
print 'training finished'
return net
#model testing 示例4: model_initial
# 需要导入模块: from nolearn import lasagne [as 别名]
# 或者: from nolearn.lasagne import BatchIterator [as 别名]
def model_initial(X_train,y_train,max_iter = 5):
global params, val_loss
params = []
val_loss = np.zeros(max_iter)
lr = theano.shared(np.float32(1e-4))
for iteration in range(max_iter):
print 'initializing weights (%d/5) ...'%(iteration+1)
print iteration
network_init = create_network()
net_init = NeuralNet(
network_init,
max_epochs=3,
update=adam,
update_learning_rate=lr,
train_split=TrainSplit(eval_size=0.1),
batch_iterator_train=BatchIterator(batch_size=32),
batch_iterator_test=BatchIterator(batch_size=64),
regression = True,
objective_loss_function = squared_error,
on_training_finished=[SaveTrainHistory(iteration = iteration)],
verbose=0)
net_init.initialize()
net_init.fit(X_train, y_train)
#model training 示例5: get_nn_model
# 需要导入模块: from nolearn import lasagne [as 别名]
# 或者: from nolearn.lasagne import BatchIterator [as 别名]
def get_nn_model(shape):
np.random.seed(9)
model = NeuralNet(
layers=[
('input', layers.InputLayer),
('hidden1', layers.DenseLayer),
('hidden2', layers.DenseLayer),
('output', layers.DenseLayer),
],
input_shape=(None, shape[1]),
hidden1_num_units=16, # number of units in hidden layer
hidden1_nonlinearity=sigmoid,
hidden2_num_units=8, # number of units in hidden layer
hidden2_nonlinearity=sigmoid,
output_nonlinearity=softmax,
output_num_units=2, # target values
# optimization method:
update=adagrad,
update_learning_rate=theano.shared(np.float32(0.1)),
on_epoch_finished=[
],
use_label_encoder=False,
batch_iterator_train=BatchIterator(batch_size=500),
regression=False, # flag to indicate we're dealing with regression problem
max_epochs=900, # we want to train this many epochs
verbose=1,
eval_size=0.0,
)
return model 示例6: get_estimator
# 需要导入模块: from nolearn import lasagne [as 别名]
# 或者: from nolearn.lasagne import BatchIterator [as 别名]
def get_estimator(n_features, files, labels, eval_size=0.1):
layers = [
(InputLayer, {'shape': (None, n_features)}),
(DenseLayer, {'num_units': N_HIDDEN_1, 'nonlinearity': rectify,
'W': init.Orthogonal('relu'),
'b': init.Constant(0.01)}),
(FeaturePoolLayer, {'pool_size': 2}),
(DenseLayer, {'num_units': N_HIDDEN_2, 'nonlinearity': rectify,
'W': init.Orthogonal('relu'),
'b': init.Constant(0.01)}),
(FeaturePoolLayer, {'pool_size': 2}),
(DenseLayer, {'num_units': 1, 'nonlinearity': None}),
]
args = dict(
update=adam,
update_learning_rate=theano.shared(util.float32(START_LR)),
batch_iterator_train=ResampleIterator(BATCH_SIZE),
batch_iterator_test=BatchIterator(BATCH_SIZE),
objective=nn.get_objective(l1=L1, l2=L2),
eval_size=eval_size,
custom_score=('kappa', util.kappa) if eval_size > 0.0 else None,
on_epoch_finished=[
nn.Schedule('update_learning_rate', SCHEDULE),
],
regression=True,
max_epochs=N_ITER,
verbose=1,
)
net = BlendNet(layers, **args)
net.set_split(files, labels)
return net