def test_relu(self):
model = NeuralNet(n_in=self.D, n_out=self.n_out,
layers=[1000], activation_function='relu',
dropout=True)
optimizer = SGD(model, SimpleSGDUpdate, self.train_data,
self.test_data,
learning_rate_schedule=exponential_scheduler(1., .99),
progress_monitor=SimpleProgressMonitor())
optimizer.run(20)
self.assertLess(optimizer.progress_monitor.train_error[-1][1],
optimizer.progress_monitor.train_error[0][1])
del model, optimizer
from hebel.parameter_updaters import MomentumUpdate
from hebel.data_providers import MNISTDataProvider
from hebel.monitors import ProgressMonitor
from hebel.schedulers import exponential_scheduler, linear_scheduler_up
# Initialize data providers
train_data = MNISTDataProvider('train', batch_size=100)
validation_data = MNISTDataProvider('val')
test_data = MNISTDataProvider('test')
D = train_data.D # Dimensionality of inputs
K = 10 # Number of classes
# Create model object
model = NeuralNet(n_in=train_data.D, n_out=K,
layers=[1000, 500, 500],
activation_function='relu',
dropout=True)
# Create optimizer object
progress_monitor = ProgressMonitor(
experiment_name='mnist',
save_model_path='examples/mnist',
save_interval=5,
output_to_log=True)
optimizer = SGD(model, MomentumUpdate, train_data, validation_data,
learning_rate_schedule=exponential_scheduler(1., .995),
momentum_schedule=linear_scheduler_up(.5, .9, 10))
# Run model
optimizer.run(100)
from hebel.parameter_updaters import MomentumUpdate
from hebel.data_providers import MNISTDataProvider
from hebel.monitors import ProgressMonitor
from hebel.schedulers import exponential_scheduler, linear_scheduler_up
# Initialize data providers
train_data = MNISTDataProvider('train', batch_size=100)
validation_data = MNISTDataProvider('val')
test_data = MNISTDataProvider('test')
D = train_data.D # Dimensionality of inputs
K = 10 # Number of classes
# Create model object
model = NeuralNet(n_in=train_data.D, n_out=K,
layers=[1000, 500, 500],
activation_function='relu',
dropout=True)
# Create optimizer object
optimizer = SGD(model, MomentumUpdate, train_data, validation_data,
learning_rate_schedule=exponential_scheduler(1., .995),
momentum_schedule=linear_scheduler_up(.5, .9, 10))
# Run model
optimizer.run(100)
# Evaulate error on test set
test_error = 0
for batch_data, batch_targets in test_data:
test_error += model.test_error(batch_data, batch_targets, average=False)
test_error /= float(test_data.N)
from hebel.schedulers import exponential_scheduler, linear_scheduler_up
hebel.init(random_seed=0)
# Initialize data providers
train_data = MNISTDataProvider('train', batch_size=100)
validation_data = MNISTDataProvider('val')
test_data = MNISTDataProvider('test')
D = train_data.D # Dimensionality of inputs
K = 10 # Number of classes
# Create model object
model = NeuralNet(n_in=train_data.D,
n_out=K,
layers=[2000, 2000, 2000, 500],
activation_function='relu',
dropout=True,
input_dropout=0.2)
# Create optimizer object
progress_monitor = ProgressMonitor(experiment_name='mnist',
save_model_path='examples/mnist',
save_interval=5,
output_to_log=True)
optimizer = SGD(model,
MomentumUpdate,
train_data,
validation_data,
progress_monitor,
learning_rate_schedule=exponential_scheduler(5., .995),
