def net_dict_ae(seq_length):
NUM_FILTERS = 4
return dict(
epochs=100000,
save_plot_interval=25000,
loss_function=lambda x, t: squared_error(x, t).mean(),
updates_func=nesterov_momentum,
learning_rate=1e-1,
learning_rate_changes_by_iteration={
50000: 1e-2,
75000: 1e-3
},
do_save_activations=True,
auto_reshape=False,
plotter=Plotter(n_seq_to_plot=32, n_training_examples_to_plot=16),
layers_config=[
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{
'label': 'conv0',
'type': Conv1DLayer, # convolve over the time axis
'num_filters': NUM_FILTERS,
'filter_size': 4,
'stride': 1,
'nonlinearity': None,
'border_mode': 'valid'
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # back to (batch, time, features)
},
{
'type': DenseLayer,
'num_units': (seq_length - 3) * NUM_FILTERS,
'nonlinearity': rectify
},
{
'type': ReshapeLayer,
'shape': (-1, (seq_length - 3), NUM_FILTERS)
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{ # DeConv
'type': Conv1DLayer,
'num_filters': 1,
'filter_size': 4,
'stride': 1,
'nonlinearity': None,
'border_mode': 'full'
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # back to (batch, time, features)
}
])
# loss_function=lambda x, t: binary_crossentropy(x, t).mean(),
# loss_function=partial(scaled_cost, loss_func=mse),
# loss_function=ignore_inactive,
# loss_function=partial(scaled_cost3, ignore_inactive=False),
# updates_func=momentum,
updates_func=clipped_nesterov_momentum,
updates_kwargs={'clip_range': (0, 10)},
learning_rate=1e-2,
learning_rate_changes_by_iteration={
1000: 1e-3,
5000: 1e-4
},
do_save_activations=True,
auto_reshape=False,
# plotter=CentralOutputPlotter
plotter=Plotter(n_seq_to_plot=32))
def exp_a(name, target_appliance, seq_length):
global source
source_dict_copy = deepcopy(source_dict)
source_dict_copy.update(
dict(target_appliance=target_appliance,
logger=logging.getLogger(name),
seq_length=seq_length))
source = SameLocation(**source_dict_copy)
net_dict_copy = deepcopy(net_dict)
net_dict_copy.update(dict(experiment_name=name, source=source))
NUM_FILTERS = 4
net_dict_copy['layers_config'] = [
{
# 800: 1e-4
# 500: 1e-3
# 4000: 1e-03,
# 6000: 5e-06,
# 7000: 1e-06
# 2000: 5e-06
# 3000: 1e-05
# 7000: 5e-06,
# 10000: 1e-06,
# 15000: 5e-07,
# 50000: 1e-07
},
do_save_activations=True,
# auto_reshape=False,
# plotter=CentralOutputPlotter
plotter=Plotter(n_seq_to_plot=10))
def exp_a(name):
# tanh hidden layers
# linear output
# output one appliance
# 0% skip prob for first appliance
# 100% skip prob for other appliances
# input is diff
global source
source_dict_copy = deepcopy(source_dict)
source = RealApplianceSource(**source_dict_copy)
net_dict_copy = deepcopy(net_dict)
net_dict_copy.update(dict(experiment_name=name, source=source))
net_dict_copy['layers_config'] = [{
# loss_function=lambda x, t: binary_crossentropy(x, t).mean(),
# loss_function=partial(scaled_cost, loss_func=mse),
# loss_function=ignore_inactive,
# loss_function=partial(scaled_cost3, ignore_inactive=False),
# updates_func=momentum,
updates_func=clipped_nesterov_momentum,
updates_kwargs={'clip_range': (0, 10)},
learning_rate=1e-1,
learning_rate_changes_by_iteration={
2000: 1e-2,
4000: 1e-3
},
do_save_activations=True,
auto_reshape=False,
# plotter=CentralOutputPlotter
plotter=Plotter(n_seq_to_plot=20))
def exp_a(name):
global source
source_dict_copy = deepcopy(source_dict)
source = RealApplianceSource(**source_dict_copy)
net_dict_copy = deepcopy(net_dict)
net_dict_copy.update(dict(experiment_name=name, source=source))
net_dict_copy['layers_config'] = [
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{
'type': Conv1DLayer, # convolve over the time axis
def net_dict_ae_rnn(seq_length):
NUM_FILTERS = 8
return dict(
epochs=None,
save_plot_interval=1000,
loss_function=lambda x, t: squared_error(x, t).mean(),
updates_func=nesterov_momentum,
learning_rate=1e-2,
learning_rate_changes_by_iteration={105000: 1e-3},
do_save_activations=True,
auto_reshape=False,
plotter=Plotter(n_seq_to_plot=32, n_training_examples_to_plot=16),
layers_config=[
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{
'label': 'conv0',
'type': Conv1DLayer, # convolve over the time axis
'num_filters': NUM_FILTERS,
'filter_size': 4,
'stride': 1,
'nonlinearity': None,
'border_mode': 'valid'
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # back to (batch, time, features)
},
{
'type': DenseLayer,
'num_units': (seq_length - 3) * NUM_FILTERS,
'nonlinearity': rectify
},
{
'type': DenseLayer,
'num_units': 128,
'nonlinearity': rectify
},
{
'type': DenseLayer,
'num_units': (seq_length - 3) * NUM_FILTERS,
'nonlinearity': rectify
},
{
'type': ReshapeLayer,
'shape': (-1, (seq_length - 3), NUM_FILTERS)
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{ # DeConv
'type': Conv1DLayer,
'num_filters': 1,
'filter_size': 4,
'stride': 1,
'nonlinearity': None,
'border_mode': 'full'
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1), # back to (batch, time, features)
'label': 'AE_output'
}
],
layer_changes={
100001: {
'new_layers': [{
'type': ConcatLayer,
'axis': 2,
'incomings': ['input', 'AE_output']
}, {
'type': BLSTMLayer,
'num_units': 128,
'merge_mode': 'concatenate',
'grad_clipping': 10.0,
'gradient_steps': 500
}, {
'type': BLSTMLayer,
'num_units': 256,
'merge_mode': 'concatenate',
'grad_clipping': 10.0,
'gradient_steps': 500
}, {
'type': ReshapeLayer,
'shape': (64 * seq_length, 512)
}, {
'type': DenseLayer,
'num_units': 128,
'nonlinearity': tanh
}, {
'type': DenseLayer,
'num_units': 1,
'nonlinearity': None
}]
}
})
def exp_a(name):
logger = logging.getLogger(name)
real_appliance_source1 = RealApplianceSource(
logger=logger,
filename=UKDALE_FILENAME,
appliances=[
TARGET_APPLIANCE, ['fridge freezer', 'fridge', 'freezer'],
'dish washer', 'kettle', ['washer dryer', 'washing machine']
],
max_appliance_powers=[MAX_TARGET_POWER, 300, 2500, 2600, 2400],
on_power_thresholds=[ON_POWER_THRESHOLD] + [10] * 4,
min_on_durations=[MIN_ON_DURATION, 60, 1800, 12, 1800],
min_off_durations=[MIN_OFF_DURATION, 12, 1800, 12, 600],
divide_input_by_max_input_power=False,
window_per_building=WINDOW_PER_BUILDING,
seq_length=SEQ_LENGTH,
output_one_appliance=True,
train_buildings=TRAIN_BUILDINGS,
validation_buildings=VALIDATION_BUILDINGS,
n_seq_per_batch=N_SEQ_PER_BATCH,
skip_probability=0.75,
skip_probability_for_first_appliance=SKIP_PROBABILITY_FOR_TARGET,
# target_is_start_and_end_and_mean=True,
standardise_input=True,
input_stats=INPUT_STATS,
independently_center_inputs=INDEPENDENTLY_CENTER_INPUTS)
# same_location_source1 = SameLocation(
# logger=logger,
# filename=UKDALE_FILENAME,
# target_appliance=TARGET_APPLIANCE,
# window_per_building=WINDOW_PER_BUILDING,
# seq_length=SEQ_LENGTH,
# train_buildings=TRAIN_BUILDINGS,
# validation_buildings=VALIDATION_BUILDINGS,
# n_seq_per_batch=N_SEQ_PER_BATCH,
# skip_probability=SKIP_PROBABILITY_FOR_TARGET,
# # target_is_start_and_end_and_mean=True,
# standardise_input=True,
# offset_probability=1,
# divide_target_by=MAX_TARGET_POWER,
# input_stats=INPUT_STATS,
# independently_center_inputs=INDEPENDENTLY_CENTER_INPUTS,
# on_power_threshold=ON_POWER_THRESHOLD,
# min_on_duration=MIN_ON_DURATION,
# min_off_duration=MIN_OFF_DURATION
# )
# multi_source = MultiSource(
# sources=[
# {
# 'source': real_appliance_source1,
# 'train_probability': 0.5,
# 'validation_probability': 0
# },
# {
# 'source': same_location_source1,
# 'train_probability': 0.5,
# 'validation_probability': 1
# }
# ],
# standardisation_source=same_location_source1
# )
net_dict_copy = deepcopy(net_dict)
net_dict_copy.update(
dict(experiment_name=name,
source=real_appliance_source1,
plotter=Plotter(n_seq_to_plot=32,
n_training_examples_to_plot=16)))
net = Net(**net_dict_copy)
return net
def net_dict_rnn(seq_length):
if seq_length <= 300:
learning_rate = 1e-2
learning_rate_changes_by_iteration = {1000: 1e-3, 10000: 1e-4}
elif seq_length < 1500:
learning_rate = 1e-4
learning_rate_changes_by_iteration = {5000: 1e-5, 9000: 1e-6}
else:
learning_rate = 1e-5
learning_rate_changes_by_iteration = {5000: 1e-6, 9000: 1e-7}
return dict(
epochs=10000,
save_plot_interval=1000,
loss_function=lambda x, t: squared_error(x, t).mean(),
updates_func=nesterov_momentum,
learning_rate=learning_rate,
learning_rate_changes_by_iteration=learning_rate_changes_by_iteration,
do_save_activations=True,
auto_reshape=True,
plotter=Plotter(n_seq_to_plot=32, n_training_examples_to_plot=16),
layers_config=[
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{
'type': Conv1DLayer, # convolve over the time axis
'num_filters': 16,
'filter_size': 4,
'stride': 1,
'nonlinearity': None,
'border_mode': 'same'
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1), # back to (batch, time, features)
'label': 'dimshuffle3'
},
{
'type': BLSTMLayer,
'num_units': 128,
'merge_mode': 'concatenate',
'grad_clipping': 10.0,
'gradient_steps': 500
},
{
'type': BLSTMLayer,
'num_units': 256,
'merge_mode': 'concatenate',
'grad_clipping': 10.0,
'gradient_steps': 500
},
{
'type': DenseLayer,
'num_units': 128,
'nonlinearity': tanh
},
{
'type': DenseLayer,
'num_units': 1,
'nonlinearity': None
}
])
def exp_g(name):
# conv at beginning
# b but with dropout
logger = logging.getLogger(name)
global multi_source
SEQ_LENGTH = 256
N_SEQ_PER_BATCH = 64
real_appliance_source1 = RealApplianceSource(
logger=logger,
filename=UKDALE_FILENAME,
appliances=[
TARGET_APPLIANCE, ['fridge freezer', 'fridge', 'freezer'],
'dish washer', 'kettle', ['washer dryer', 'washing machine']
],
max_appliance_powers=[MAX_TARGET_POWER, 300, 2500, 2600, 2400],
on_power_thresholds=[ON_POWER_THRESHOLD] + [10] * 4,
min_on_durations=[MIN_ON_DURATION, 60, 1800, 12, 1800],
min_off_durations=[MIN_OFF_DURATION, 12, 1800, 12, 600],
divide_input_by_max_input_power=False,
window_per_building=WINDOW_PER_BUILDING,
seq_length=SEQ_LENGTH,
output_one_appliance=True,
train_buildings=TRAIN_BUILDINGS,
validation_buildings=VALIDATION_BUILDINGS,
n_seq_per_batch=N_SEQ_PER_BATCH,
skip_probability=0.75,
skip_probability_for_first_appliance=SKIP_PROBABILITY_FOR_TARGET,
standardise_input=True,
input_stats=INPUT_STATS,
independently_center_inputs=INDEPENDENTLY_CENTER_INPUTS,
subsample_target=SUBSAMPLE_TARGET,
input_padding=INPUT_PADDING)
same_location_source1 = SameLocation(
logger=logger,
filename=UKDALE_FILENAME,
target_appliance=TARGET_APPLIANCE,
window_per_building=WINDOW_PER_BUILDING,
seq_length=SEQ_LENGTH,
train_buildings=TRAIN_BUILDINGS,
validation_buildings=VALIDATION_BUILDINGS,
n_seq_per_batch=N_SEQ_PER_BATCH,
skip_probability=SKIP_PROBABILITY_FOR_TARGET,
standardise_input=True,
offset_probability=1,
divide_target_by=MAX_TARGET_POWER,
input_stats=INPUT_STATS,
independently_center_inputs=INDEPENDENTLY_CENTER_INPUTS,
on_power_threshold=ON_POWER_THRESHOLD,
min_on_duration=MIN_ON_DURATION,
min_off_duration=MIN_OFF_DURATION,
include_all=True,
allow_incomplete=True,
subsample_target=SUBSAMPLE_TARGET,
input_padding=INPUT_PADDING)
multi_source = MultiSource(sources=[{
'source': real_appliance_source1,
'train_probability': 0.5,
'validation_probability': 0
}, {
'source': same_location_source1,
'train_probability': 0.5,
'validation_probability': 1
}],
standardisation_source=same_location_source1)
net_dict_copy = deepcopy(net_dict)
net_dict_copy.update(
dict(
auto_reshape=True,
experiment_name=name,
source=multi_source,
plotter=Plotter(n_seq_to_plot=32, n_training_examples_to_plot=16),
layers_config=[
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1) # (batch, features, time)
},
{
'type': Conv1DLayer, # convolve over the time axis
'num_filters': 16,
'filter_size': 4,
'stride': 1,
'nonlinearity': None,
'border_mode': 'same'
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1), # back to (batch, time, features)
'label': 'dimshuffle3'
},
{
'type': DropoutLayer
},
{
'type': BLSTMLayer,
'num_units': 128,
'merge_mode': 'concatenate'
},
{
'type': DropoutLayer
},
{
'type': BLSTMLayer,
'num_units': 256,
'merge_mode': 'concatenate'
},
{
'type': DropoutLayer
},
{
'type': DenseLayer,
'num_units': 128,
'nonlinearity': tanh
},
{
'type': DenseLayer,
'num_units': 1,
'nonlinearity': None
}
]))
net = Net(**net_dict_copy)
return net
def exp_a(name):
# longer seq length
logger = logging.getLogger(name)
global multi_source
SEQ_LENGTH = 2048
N_SEQ_PER_BATCH = 8
# real_appliance_source1 = RealApplianceSource(
# logger=logger,
# filename=UKDALE_FILENAME,
# appliances=[
# TARGET_APPLIANCE,
# ['fridge freezer', 'fridge', 'freezer'],
# 'dish washer',
# 'kettle',
# ['washer dryer', 'washing machine']
# ],
# max_appliance_powers=[MAX_TARGET_POWER, 300, 2500, 2600, 2400],
# on_power_thresholds=[ON_POWER_THRESHOLD] + [10] * 4,
# min_on_durations=[MIN_ON_DURATION, 60, 1800, 12, 1800],
# min_off_durations=[MIN_OFF_DURATION, 12, 1800, 12, 600],
# divide_input_by_max_input_power=False,
# window_per_building=WINDOW_PER_BUILDING,
# seq_length=SEQ_LENGTH,
# output_one_appliance=True,
# train_buildings=TRAIN_BUILDINGS,
# validation_buildings=VALIDATION_BUILDINGS,
# n_seq_per_batch=N_SEQ_PER_BATCH,
# skip_probability=0.75,
# skip_probability_for_first_appliance=SKIP_PROBABILITY_FOR_TARGET,
# standardise_input=True,
# input_stats=INPUT_STATS,
# independently_center_inputs=INDEPENDENTLY_CENTER_INPUTS,
# subsample_target=SUBSAMPLE_TARGET,
# input_padding=INPUT_PADDING
# )
# same_location_source1 = SameLocation(
# logger=logger,
# filename=UKDALE_FILENAME,
# target_appliance=TARGET_APPLIANCE,
# window_per_building=WINDOW_PER_BUILDING,
# seq_length=SEQ_LENGTH,
# train_buildings=TRAIN_BUILDINGS,
# validation_buildings=VALIDATION_BUILDINGS,
# n_seq_per_batch=N_SEQ_PER_BATCH,
# skip_probability=SKIP_PROBABILITY_FOR_TARGET,
# standardise_input=True,
# offset_probability=1,
# divide_target_by=MAX_TARGET_POWER,
# input_stats=INPUT_STATS,
# independently_center_inputs=INDEPENDENTLY_CENTER_INPUTS,
# on_power_threshold=ON_POWER_THRESHOLD,
# min_on_duration=MIN_ON_DURATION,
# min_off_duration=MIN_OFF_DURATION,
# include_all=True,
# allow_incomplete=True,
# subsample_target=SUBSAMPLE_TARGET,
# input_padding=INPUT_PADDING
# )
# multi_source = MultiSource(
# sources=[
# {
# 'source': real_appliance_source1,
# 'train_probability': 0.5,
# 'validation_probability': 0
# },
# {
# 'source': same_location_source1,
# 'train_probability': 0.5,
# 'validation_probability': 1
# }
# ],
# standardisation_source=same_location_source1
# )
net_dict_copy = deepcopy(net_dict)
net_dict_copy.update(
dict(
experiment_name=name,
source=multi_source,
plotter=Plotter(n_seq_to_plot=32, n_training_examples_to_plot=16),
learning_rate=1e-7,
learning_rate_changes_by_iteration={
1000: 1e-8,
10000: 1e-9
},
layers_config=[
{
'type': DenseLayer,
'num_units': 64,
'nonlinearity': tanh
},
{
'type': BLSTMLayer,
'num_units': 128,
'merge_mode': 'concatenate',
'grad_clipping': 1.0
# 'gradient_steps': 200
},
{
'type': BLSTMLayer,
'num_units': 256,
'merge_mode': 'concatenate',
'grad_clipping': 1.0
# 'gradient_steps': 200
},
{
'type': DenseLayer,
'num_units': 128,
'nonlinearity': tanh
},
{
'type': DenseLayer,
'num_units': 1,
'nonlinearity': None
}
]))
net = Net(**net_dict_copy)
return net