def get_pipeline(period, data_path, target_inclusion_prob, windows, appliances,
target_appliance, activations, seq_length, num_seq_per_batch):
# Adding a and b to be coherent with buildings chosen in WINDOWS
num_seq_per_batch = num_seq_per_batch
filtered_activations = filter_activations(windows, appliances, activations)
real_agg_source = RealAggregateSource(
activations=filtered_activations,
target_appliance=target_appliance,
seq_length=seq_length,
filename=data_path,
windows=windows,
sample_period=period,
target_inclusion_prob=target_inclusion_prob)
sample = real_agg_source.get_batch(num_seq_per_batch=seq_length).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
pipeline = DataPipeline(
[real_agg_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std),
IndependentlyCenter()],
target_processing=[DivideBy(target_std)])
return pipeline
def get_pipeline(target_appliance, activations):
num_seq_per_batch = 64
if target_appliance == 'kettle':
seq_length = 128
train_buildings = [1, 2, 4]
unseen_buildings = [5]
elif target_appliance == 'microwave':
seq_length = 288
train_buildings = [1, 2]
unseen_buildings = [5]
elif target_appliance == 'washing machine':
seq_length = 1024
train_buildings = [1, 5]
unseen_buildings = [2]
elif target_appliance == 'fridge':
seq_length = 512
train_buildings = [1, 2, 4]
unseen_buildings = [5]
elif target_appliance == 'dish washer':
seq_length = 1024 + 512
train_buildings = [1, 2]
unseen_buildings = [5]
filtered_windows = select_windows(train_buildings, unseen_buildings)
filtered_activations = filter_activations(filtered_windows, activations)
synthetic_agg_source = SyntheticAggregateSource(
activations=filtered_activations,
target_appliance=target_appliance,
seq_length=seq_length,
sample_period=SAMPLE_PERIOD)
real_agg_source = RealAggregateSource(activations=filtered_activations,
target_appliance=target_appliance,
seq_length=seq_length,
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD)
stride_source = StrideSource(target_appliance=target_appliance,
seq_length=seq_length,
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD,
stride=STRIDE)
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source, stride_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std),
IndependentlyCenter()],
target_processing=[DivideBy(target_std)])
return pipeline
def get_pipeline(self, num_seq_per_batch, start_date, building_id,
valid_range, validate_length):
valid_agg_source = []
for task_appliance in self.appliances:
# buildings
buildings = self.building[task_appliance]
train_buildings = buildings['train_buildings']
unseen_buildings = buildings['unseen_buildings']
# windows
filtered_windows = select_windows(train_buildings,
unseen_buildings, self.window)
# data sources
valid_agg_source.append(
ValidationSource(appliances=self.appliances,
filename=self.nilm_filename,
windows=filtered_windows,
sample_period=self.sample_period,
start_date=start_date,
valid_range=valid_range,
building_id=building_id,
validate_length=validate_length,
format=self.format))
# look for existing processing parameters only when OVERRIDE is not on; if
# none, generate new ones
print('Looking for existing processing parameters ... ')
proc_params_filename = os.path.join(
dirs.MODELS_DIR, 'proc_params_' + self.model_name + '.npz')
print('Found; using them ...')
multi_input_std = np.load(proc_params_filename)['multi_input_std']
multi_target_std = np.load(proc_params_filename)['multi_target_std']
"""multi_input_std = 1000
multi_target_std = 400"""
# generate pipeline
pipeline = DataPipeline(valid_agg_source,
num_seq_per_batch=num_seq_per_batch,
input_processing=[
DivideBy(multi_input_std),
IndependentlyCenter()
],
target_processing=[DivideBy(multi_target_std)])
return pipeline, multi_input_std, multi_target_std
def get_pipeline(activations):
# sequence periods
seq_period = SEQ_PERIODS[TARGET_APPLIANCE]
seq_length = seq_period // SAMPLE_PERIOD
# buildings
buildings = BUILDINGS[TARGET_APPLIANCE]
train_buildings = buildings['train_buildings']
unseen_buildings = buildings['unseen_buildings']
# windows
filtered_windows = select_windows(
train_buildings, unseen_buildings, WINDOWS)
filtered_activations = filter_activations(
filtered_windows, activations, [TARGET_APPLIANCE])
# data sources
synthetic_agg_source = SyntheticAggregateSource(
activations=filtered_activations,
target_appliance=TARGET_APPLIANCE,
seq_length=seq_length,
sample_period=SAMPLE_PERIOD
)
real_agg_source = realaggregatesource.RealAggregateSource(
activations=filtered_activations,
target_appliance=TARGET_APPLIANCE,
seq_length=seq_length,
filename=NILMTK_FILENAME,
windows=filtered_windows,
allow_multiple_target_activations_in_aggregate=True,
sample_period=SAMPLE_PERIOD
)
stride_source = stridesource.StrideSource(
target_appliance=TARGET_APPLIANCE,
seq_length=seq_length,
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD,
stride=None
)
# look for existing processing parameters only when OVERRIDE is not on; if
# none, generate new ones
print('Looking for existing processing parameters ... ', end='')
proc_params_filename = os.path.join(dirs.MODELS_DIR, 'proc_params_' + DATASET + '_' + TARGET_APPLIANCE + '_' + strftime('%Y-%m-%d_%H_%m') + '.npz')
if not OVERRIDE and os.path.exists(proc_params_filename):
print('Found; using them ...')
input_std, target_std = np.load(proc_params_filename)['arr_0']
else:
if OVERRIDE:
print('Overridden; generating new ones ...')
else:
print('Not found; generating new ones ...')
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
print('Saving the processing parameters ...')
np.savez(proc_params_filename, [input_std, target_std])
# generate pipeline
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source, stride_source],
num_seq_per_batch=NUM_SEQ_PER_BATCH,
input_processing=[DivideBy(input_std), IndependentlyCenter()],
target_processing=[DivideBy(target_std)]
)
return pipeline, input_std, target_std
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD)
# ------------
# needed to rescale the input aggregated data
# rescaling is done using the a first batch of num_seq_per_batch sequences
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
# ------------
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std),
IndependentlyCenter()],
target_processing=[DivideBy(target_std)])
num_test_seq = 101
# create a validation set
X_valid = np.empty((num_test_seq * num_seq_per_batch, seq_length))
Y_valid = np.empty((num_test_seq * num_seq_per_batch, 3))
for i in range(num_test_seq):
(x_valid, y_valid) = pipeline.train_generator(fold='unseen_appliances',
source_id=1).next()
X_valid[i * num_seq_per_batch:(i + 1) *
num_seq_per_batch, :] = x_valid[:, :, 0]
Y_valid[i * num_seq_per_batch:(i + 1) * num_seq_per_batch, :] = y_valid
# ------------
# needed to rescale the input aggregated data
# rescaling is done using the a first batch of num_seq_per_batch sequences
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
# ------------
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std), IndependentlyCenter()],
target_processing=[DivideBy(target_std)]
)
num_test_seq = 101
# create a validation set
X_valid = np.empty((num_test_seq*num_seq_per_batch, seq_length))
Y_valid = np.empty((num_test_seq*num_seq_per_batch, 3))
for i in range(num_test_seq):
(x_valid,y_valid) = pipeline.train_generator(fold = 'unseen_appliances', source_id = 1).next()
# ------------
# needed to rescale the input aggregated data
# rescaling is done using the a first batch of num_seq_per_batch sequences
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
# ------------
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std), IndependentlyCenter()],
target_processing=[DivideBy(target_std)]
)
from keras.layers import Input, Dense, Flatten
from keras.models import Model
starting_time = time.time()
# define the network architecture = Conv Net
input_seq = Input(shape = (1, seq_length))
conv1_layer = Convolution1D(nb_filter = 16, filter_length = 3, border_mode='same',
init = 'normal', activation = 'relu')
conv1 = conv1_layer(input_seq)
conv2 = Convolution1D(nb_filter = 16, filter_length = 3, border_mode='same',
def run_experiment(dataset, INPUT_MEAN, INPUT_STD, SOURCE_TYPES,
VALIDATION_SOURCE_TYPES, DOWNSAMPLE_FACTOR, SEQ_LENGTH,
TARGET_SEQ_LENGTH, MAX_TARGET_POWER, TARGET_APPLIANCE,
TRAINING_SEED, VERBOSE_TRAINING, LEARNING_RATE,
NUM_SEQ_PER_BATCH, EPOCHS, STEPS_PER_EPOCH, USE_CUDA,
CHECKPOINT_BEST_MSE, CHECKPOINTING_EVERY_N_EPOCHS,
TEST_DISAGGREGATE_EVERY_N_EPOCHS, _run):
torch.manual_seed(TRAINING_SEED)
OUTPUT_FOLDER = os.path.join(ex.get_experiment_info()['name'], "output")
for observer in _run.observers:
if type(observer) is FileStorageObserver:
OUTPUT_FOLDER = os.path.join(observer.basedir, str(_run._id))
VERBOSE_TRAINING = 0
os.makedirs(OUTPUT_FOLDER, exist_ok=True)
writer = SummaryWriter(log_dir=OUTPUT_FOLDER)
# From dataset Ingredient
TRAIN_BUILDINGS = dataset["TRAIN_BUILDINGS"]
ON_POWER_THRESHOLD = dataset["ON_POWER_THRESHOLD"]
##############################################################################################
#PREPARE DATASET (DATALOADERs)
##############################################################################################
running_data_processes = [] # stop these at the end
sources, validation_sources = get_sources(
training_source_names=SOURCE_TYPES,
validation_source_names=VALIDATION_SOURCE_TYPES,
seq_length=SEQ_LENGTH,
sources_seed=TRAINING_SEED,
validation_stride=128)
input_processing_steps = [
Add(-INPUT_MEAN),
DivideBy(INPUT_STD),
Transpose((0, 2, 1))
]
target_processing_steps = [
Add(-INPUT_MEAN),
DivideBy(INPUT_STD),
Transpose((0, 2, 1))
]
if DOWNSAMPLE_FACTOR > 1:
downsample_rng = np.random.RandomState(TRAINING_SEED)
input_processing_steps_training = [
DownSample(DOWNSAMPLE_FACTOR, downsample_rng)
] + input_processing_steps
else:
input_processing_steps_training = input_processing_steps
validation_pipeline = DataPipeline(
sources=validation_sources,
num_seq_per_batch=NUM_SEQ_PER_BATCH,
input_processing=input_processing_steps_training,
target_processing=target_processing_steps)
validation_batches = get_validation_batches(validation_pipeline)
print("appliance {} has {} validation batches".format(
TARGET_APPLIANCE,
sum([len(v) for k, v in validation_batches.items()])))
data_pipeline = DataPipeline(
sources=sources,
num_seq_per_batch=NUM_SEQ_PER_BATCH,
input_processing=input_processing_steps_training,
target_processing=target_processing_steps)
data_thread = DataProcess(data_pipeline)
data_thread.start()
running_data_processes.append(data_thread)
net = _Net(SEQ_LENGTH)
print(net)
metrics_accu = MetricsAccumulator(on_power_threshold=ON_POWER_THRESHOLD,
max_power=MAX_TARGET_POWER)
# note: MSE - Mean Squared Error
criterion = torch.nn.MSELoss()
stop_training = False
best_mse = None
# PREPARE TEST DISAGGREGATOR
if TEST_DISAGGREGATE_EVERY_N_EPOCHS is not None:
test_disaggregator = Disaggregator(
EVALUATION_DATA_PATH=dataset['EVALUATION_DATA_PATH'],
TARGET_APPLIANCE=TARGET_APPLIANCE,
ON_POWER_THRESHOLD=ON_POWER_THRESHOLD,
MAX_TARGET_POWER=MAX_TARGET_POWER,
pad_mains=True,
pad_appliance=False,
disagg_func=disag_seq2seq,
downsample_factor=DOWNSAMPLE_FACTOR,
disagg_kwargs=dict(model=net,
input_processing=input_processing_steps,
target_processing=target_processing_steps,
n_seq_per_batch=NUM_SEQ_PER_BATCH,
seq_length=SEQ_LENGTH,
target_seq_length=TARGET_SEQ_LENGTH,
USE_CUDA=USE_CUDA,
stride=1))
# PREPARE TENSORS, WHICH WILL BE FED USED DURING TRAINING AND VALIDATION
input = torch.FloatTensor(NUM_SEQ_PER_BATCH, 1, SEQ_LENGTH)
target = torch.FloatTensor(NUM_SEQ_PER_BATCH, 1, TARGET_SEQ_LENGTH)
if USE_CUDA:
# note: push to GPU
net.cuda()
criterion.cuda()
input, target = input.cuda(), target.cuda()
# setup optimizer. TODO: Should we use 'Adam' for disaggregator?
optimizer = optim.Adam(net.parameters(),
lr=LEARNING_RATE,
betas=(0.9, 0.999))
#optimizer = optim.SGD(net.parameters(), momentum=0.9, nesterov=True, lr=LEARNING_RATE)
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=[50, 75],
gamma=0.1)
history = {}
csvpath = os.path.join(OUTPUT_FOLDER, "history.csv")
if os.path.exists(csvpath):
print("Already exists: {}".format(csvpath))
return -1
progbar_epoch = tqdm(desc="Epoch",
total=EPOCHS,
unit="epoch",
disable=(not VERBOSE_TRAINING))
for epoch in range(EPOCHS):
# TRAINING
metrics_log = {'training': {}}
training_loss = 0.0
progbar = tqdm(desc="Train",
total=STEPS_PER_EPOCH,
leave=False,
disable=(not VERBOSE_TRAINING))
for i in range(STEPS_PER_EPOCH):
net.zero_grad()
batch = data_thread.get_batch()
while batch is None:
batch = data_thread.get_batch()
qsize = data_thread._queue.qsize()
aggregated_signal = torch.from_numpy(batch.after_processing.input)
target_signal = torch.from_numpy(batch.after_processing.target)
if USE_CUDA:
aggregated_signal = aggregated_signal.cuda()
target_signal = target_signal.cuda()
input.resize_as_(aggregated_signal).copy_(aggregated_signal)
target.resize_as_(target_signal).copy_(target_signal)
inputv = Variable(input, requires_grad=False)
targetv = Variable(target, requires_grad=False)
output = net(inputv)
loss = criterion(output, targetv)
loss.backward()
optimizer.step()
training_loss += loss.item()
progbar.set_postfix(dict(loss="{:.4f}".format(loss.item()),
qsize=qsize),
refresh=False)
progbar.update()
metrics_log['training']['loss'] = float(training_loss /
STEPS_PER_EPOCH)
metrics_log['training']['lr'] = optimizer.param_groups[0]['lr']
# VALIDATION
#pr_num_thresholds = 127
for fold in validation_batches:
metrics_accu.reset_accumulator()
#accumulated_pr = {}
#for cl in ["tp", "tn", "fp", "fn"]:
# accumulated_pr[cl] = torch.LongTensor(pr_num_thresholds).zero_()
for batch in validation_batches[fold]:
aggregated_signal = torch.from_numpy(
batch.after_processing.input)
target_signal = torch.from_numpy(batch.after_processing.target)
if USE_CUDA:
aggregated_signal = aggregated_signal.cuda()
target_signal = target_signal.cuda()
input.resize_as_(aggregated_signal).copy_(aggregated_signal)
target.resize_as_(target_signal).copy_(target_signal)
with torch.no_grad():
inputv = Variable(input)
targetv = Variable(target)
output = net(inputv)
val_loss = criterion(output, targetv)
loss_value = val_loss.item()
# other metrics
pred_y = data_pipeline.apply_inverse_processing(
output.cpu().data.numpy(), 'target')
true_y = batch.before_processing.target
metrics_accu.accumulate_metrics(true_y,
pred_y,
val_loss=loss_value)
#calculate_pr_curve_torch(accumulated_pr, MAX_TARGET_POWER, true_y, pred_y, num_thresholds=pr_num_thresholds)
for key, value in metrics_accu.finalize_metrics().items():
metrics_log.setdefault(fold[0],
{}).setdefault(key, {})[fold[1]] = value
#precision = accumulated_pr["tp"] / (accumulated_pr["tp"] + accumulated_pr["fp"])
#recall = accumulated_pr["tp"] / (accumulated_pr["tp"] + accumulated_pr["fn"])
#writer.add_pr_curve_raw("pr_{}/{}".format(fold[0], fold[1]),
# true_positive_counts=accumulated_pr["tp"],
# false_positive_counts=accumulated_pr["fp"],
# true_negative_counts=accumulated_pr["tn"],
# false_negative_counts=accumulated_pr["fn"],
# precision=precision, recall=recall,
# global_step=(epoch+1)*STEPS_PER_EPOCH, num_thresholds=pr_num_thresholds)
# LR Scheduler
val_loss = metrics_log['unseen_activations']['val_loss']['rss']
#val_loss = metrics_log['mean_squared_error']['unseen_activations']['rss']
#scheduler.step(val_loss)
scheduler.step()
# PRINT STATS
if not VERBOSE_TRAINING:
print('[{:d}/{:d}] {}'.format(epoch + 1, EPOCHS,
metrics_log['training']))
else:
progbar_epoch.set_postfix(
dict(loss=metrics_log['training']['loss']), refresh=False)
progbar_epoch.update()
progbar.close()
# store in history / tensorboard
for fold, metrics_for_fold in metrics_log.items():
for metric_name, value in metrics_for_fold.items():
if type(value) == dict:
SW_add_scalars2(writer, "{}/{}".format(fold, metric_name),
value, (epoch + 1) * STEPS_PER_EPOCH)
for k, v in value.items():
name = "{}/{}/{}".format(fold, metric_name, k)
history.setdefault(name, []).append(v)
else:
name = "{}/{}".format(fold, metric_name)
writer.add_scalar(name, value,
(epoch + 1) * STEPS_PER_EPOCH)
history.setdefault(name, []).append(value)
# CHECKPOINTING
if CHECKPOINT_BEST_MSE:
mse = val_loss
if best_mse is None:
best_mse = mse
if best_mse > mse:
msg = "[{:d}/{:d}] MSE improved from {:.4f} to {:.4f} (d={:f}), saving model...".format(
epoch + 1, EPOCHS, best_mse, mse, best_mse - mse)
if not VERBOSE_TRAINING:
print(msg)
else:
progbar_epoch.write(msg)
torch.save(
{
'epoch': epoch + 1,
'step': (epoch + 1) * STEPS_PER_EPOCH,
'mse': mse,
'model': net.state_dict()
}, '{}/net_best_mse.pth.tar'.format(OUTPUT_FOLDER))
best_mse = mse
if CHECKPOINTING_EVERY_N_EPOCHS is not None:
if (epoch + 1) % CHECKPOINTING_EVERY_N_EPOCHS == 0:
torch.save(
net.state_dict(), '{}/net_step_{:06d}.pth'.format(
OUTPUT_FOLDER, (epoch + 1) * STEPS_PER_EPOCH))
if TEST_DISAGGREGATE_EVERY_N_EPOCHS is not None:
if (epoch + 1) % TEST_DISAGGREGATE_EVERY_N_EPOCHS == 0:
scores = test_disaggregator.calculate_metrics()
scores_by_metric = {}
for building_i, building in scores.items():
for metric, value in building.items():
scores_by_metric.setdefault(metric,
{})[building_i] = value
for metric, building_d in scores_by_metric.items():
SW_add_scalars2(writer, "test_score/{}".format(metric),
building_d, (epoch + 1) * STEPS_PER_EPOCH)
if stop_training:
break
# CHECKPOINTING at end
torch.save(
{
'epoch': epoch + 1,
'step': (epoch + 1) * STEPS_PER_EPOCH,
'model': net.state_dict(),
'optimizer': optimizer.state_dict(),
#'scheduler': scheduler.state_dict()
# TODO: scheduler is not saved this way, scheduler.state_dict() does not exist
},
'{}/net_step_{:06d}.pth.tar'.format(OUTPUT_FOLDER,
(epoch + 1) * STEPS_PER_EPOCH))
df = pd.DataFrame(history)
df.to_csv(csvpath)
for p in running_data_processes:
p.stop()
writer.close()
#return 42
return metrics_log['training']['loss']
def get_pipeline(activations):
global seq_length
agg_source = []
prob = []
target_inclusion_prob = 0.48 + len(APPLIANCES) * 0.1
for task_appliance in APPLIANCES:
seq_period = SEQ_PERIODS[task_appliance]
seq_length = seq_period // SAMPLE_PERIOD
# buildings
buildings = BUILDINGS[task_appliance]
train_buildings = buildings['train_buildings']
unseen_buildings = buildings['unseen_buildings']
# windows
filtered_windows = select_windows(train_buildings, unseen_buildings,
WINDOWS)
filtered_activations = filter_activations(filtered_windows,
activations,
BUILDINGS_APPLIANCES)
# data sources
real_source_prob = min(0.82, target_inclusion_prob)
if task_appliance == 'fridge':
real_source_prob = 1.0
agg_source.append(
RealAggregateSource(activations=filtered_activations,
target_appliance=task_appliance,
appliances=APPLIANCES,
target_inclusion_prob=real_source_prob,
seq_length=seq_length,
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD))
prob.append(1.0 / NUM_APPLIANCE)
"""agg_source.append(SyntheticAggregateSource(
activations=filtered_activations,
appliances=APPLIANCES,
seq_length=seq_length,
distractor_inclusion_prob=0.3,
target_inclusion_prob=min(0.5, target_inclusion_prob),
sample_period=SAMPLE_PERIOD
))
agg_source.append(StrideSource(
target_appliance=task_appliance,
appliances=APPLIANCES,
seq_length=seq_length,
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD,
stride=None
))
prob.append(0.5/NUM_APPLIANCE)"""
# look for existing processing parameters only when OVERRIDE is not on; if
# none, generate new ones
print('Looking for existing processing parameters ... ')
proc_params_filename = path.join(
dirs.MODELS_DIR, 'proc_params_' + DATASET + '_[' + TARGET_APPLIANCE +
']_' + strftime('%Y-%m-%d_%H_%m') + '.npz')
if not OVERRIDE and path.exists(proc_params_filename):
print('Found; using them ...')
multi_input_std = np.load(proc_params_filename)['multi_input_std']
multi_target_std = np.load(proc_params_filename)['multi_target_std']
else:
if OVERRIDE:
print('Overridden; generating new ones ...')
else:
print('Not found; generating new ones ...')
multi_input_std = np.array([])
multi_target_std = np.array([])
for sample_source in agg_source:
batch_size = 1024
sample = sample_source.get_batch(
num_seq_per_batch=batch_size).next()
sample = sample.before_processing
multi_input_std = np.append(multi_input_std,
sample.input.flatten().std())
multi_target_std = np.append(multi_target_std, [
sample.target[:, idx].flatten().std()
for idx in range(NUM_APPLIANCE)
])
multi_input_std = np.mean(multi_input_std)
multi_target_std = multi_target_std.reshape(-1, NUM_APPLIANCE)
multi_target_std = np.mean(multi_target_std, axis=0)
print('=' * 10)
print('Input std = ', multi_input_std)
for idx, appliance in enumerate(APPLIANCES):
print(appliance, 'std = ', multi_target_std[idx])
print('=' * 10)
print('Saving the processing parameters ...')
np.savez(proc_params_filename,
multi_input_std=[multi_input_std],
multi_target_std=multi_target_std)
# generate pipeline
pipeline = DataPipeline(
agg_source,
num_seq_per_batch=NUM_SEQ_PER_BATCH,
input_processing=[DivideBy(multi_input_std),
IndependentlyCenter()],
target_processing=[DivideBy(multi_target_std)],
source_probabilities=prob,
)
return pipeline, multi_input_std, multi_target_std
filename=NILMTK_FILENAME,
windows=filtered_windows,
sample_period=SAMPLE_PERIOD)
# ------------
# needed to rescale the input aggregated data
# rescaling is done using the a first batch of num_seq_per_batch sequences
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
# ------------
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std),
IndependentlyCenter()],
target_processing=[DivideBy(target_std)])
# get the shape of X_train
(X_train, Y_train) = pipeline.train_generator().next()
starting_time = time.time()
nb_epoch = 1
# define the network architecture = Conv Net
model = Sequential()
model.add(
Convolution1D(64,
3,
border_mode='same',
input_shape=(1, X_train.shape[2]),
# ------------
# needed to rescale the input aggregated data
# rescaling is done using the a first batch of num_seq_per_batch sequences
sample = real_agg_source.get_batch(num_seq_per_batch=1024).next()
sample = sample.before_processing
input_std = sample.input.flatten().std()
target_std = sample.target.flatten().std()
# ------------
pipeline = DataPipeline(
[synthetic_agg_source, real_agg_source],
num_seq_per_batch=num_seq_per_batch,
input_processing=[DivideBy(input_std), IndependentlyCenter()],
target_processing=[DivideBy(target_std)]
)
# get the shape of X_train
(X_train, Y_train) = pipeline.train_generator().next()
starting_time = time.time()
nb_epoch = 1
