def exp_b(name):
# ReLU 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'] = [{
'type': BidirectionalRecurrentLayer,
'num_units': 50,
'W_in_to_hid': Normal(std=1),
'W_hid_to_hid': Identity(scale=0.5),
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'learn_init': False,
'precompute_input': False
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': Conv1DLayer,
'num_filters': 50,
'filter_length': 4,
'stride': 4,
'nonlinearity': rectify,
'W': Normal(std=1 / sqrt(50))
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 100,
'W_in_to_hid': Normal(std=1 / sqrt(50)),
'W_hid_to_hid': Identity(scale=0.5),
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'learn_init': False,
'precompute_input': False
}, {
'type': DenseLayer,
'num_units': source.n_outputs,
'nonlinearity': None,
'W': Normal(std=1 / sqrt(100))
}]
net = Net(**net_dict_copy)
return net
def exp_b(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)
}, {
'type': Conv1DLayer,
'num_filters': 10,
'filter_length': 2,
'stride': 1,
'nonlinearity': rectify,
'border_mode': 'same'
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'W_hid_to_hid': Identity(scale=0.5)
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': Conv1DLayer,
'num_filters': 40,
'filter_length': 4,
'stride': 4,
'nonlinearity': rectify
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'W_hid_to_hid': Identity(scale=0.5)
}, {
'type': DenseLayer,
'num_units': source.n_outputs,
'nonlinearity': T.nnet.softplus
}]
net = Net(**net_dict_copy)
return net
def exp_a(name):
# ReLU 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']= [
{
'type': BidirectionalRecurrentLayer,
'num_units': 50,
'W_in_to_hid': Normal(std=1),
'W_hid_to_hid': Identity(scale=0.9),
'nonlinearity': rectify,
'learn_init': False,
'precompute_input': True
},
{
'type': DenseLayer,
'num_units': source.n_outputs,
'nonlinearity': None,
'W': Normal(std=1/sqrt(50))
}
]
net = Net(**net_dict_copy)
return net
# 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=MDNPlotter
layers_config=[{
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'W_hid_to_hid': Identity(scale=0.1),
'batch_norm': True
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'W_hid_to_hid': Identity(scale=0.1),
'batch_norm': True
}])
def exp_a(name):
global source
source_dict_copy = deepcopy(source_dict)
source = RealApplianceSource(**source_dict_copy)
def exp_c(name):
"""
tanh all the way through. Identity init of RNNs
"""
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)
},
{
'type': Conv1DLayer,
'num_filters': 40,
'filter_length': 2,
'stride': 1,
'nonlinearity': identity,
'b': None,
'border_mode': 'same'
},
{
'type': BatchNormLayer,
'nonlinearity': tanh
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
},
{
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': identity,
'b': None,
'W_hid_to_hid': Identity(scale=0.5),
'learn_init': True, 'precompute_input': False
},
{
'type': BatchNormLayer,
'axes': (0, 1),
'nonlinearity': tanh
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
},
{
'type': Conv1DLayer,
'num_filters': 40,
'filter_length': 4,
'stride': 4,
'nonlinearity': identity,
'b': None
},
{
'type': BatchNormLayer,
'nonlinearity': tanh
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
},
{
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': identity,
'b': None,
'W_hid_to_hid': Identity(scale=0.5),
'learn_init': True, 'precompute_input': False
},
{
'type': BatchNormLayer,
'axes': (0, 1),
'nonlinearity': tanh
},
{
'type': DenseLayer,
'num_units': source.n_outputs,
'nonlinearity': T.nnet.softplus
}
]
net = Net(**net_dict_copy)
return net
# 7000: 5e-06,
# 10000: 1e-06,
# 15000: 5e-07,
# 50000: 1e-07
},
do_save_activations=True,
# auto_reshape=False,
# plotter=CentralOutputPlotter
# plotter=MDNPlotter
layers_config=[{
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': identity,
'b': None,
'W_hid_to_hid': Identity(scale=0.5)
}, {
'type': BatchNormLayer,
'axes': (0, 1),
'nonlinearity': rectify
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': identity,
'b': None,
'W_hid_to_hid': Identity(scale=0.5)
}, {
'type': BatchNormLayer,
'axes': (0, 1),
'nonlinearity': rectify
}, {
'type': Conv1DLayer,
'num_filters': 20,
'filter_length': 2,
'stride': 1,
'nonlinearity': rectify,
'border_mode': 'same'
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'W_hid_to_hid': Identity()
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': Conv1DLayer,
'num_filters': 40,
'filter_length': 4,
'stride': 4,
'nonlinearity': rectify
}, {
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
}, {
'type': BidirectionalRecurrentLayer,
'num_units': 40,
def exp_b(name):
# e59 but ReLU
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,
learning_rate=1e-3,
learning_rate_changes_by_iteration={
1000: 1e-4,
2000: 1e-5
}
))
net_dict_copy['layers_config']= [
{
'type': DenseLayer,
'num_units': 50,
'nonlinearity': rectify,
'W': Uniform(25),
'b': Uniform(25)
},
{
'type': DenseLayer,
'num_units': 50,
'nonlinearity': rectify,
'W': Uniform(10),
'b': Uniform(10)
},
{
'type': BidirectionalRecurrentLayer,
'num_units': 40,
'W_in_to_hid': Uniform(5),
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'learn_init': False,
'precompute_input': False,
'W_hid_to_hid': Identity(0.5)
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
},
{
'type': Conv1DLayer,
'num_filters': 20,
'filter_length': 4,
'stride': 4,
'nonlinearity': rectify
},
{
'type': DimshuffleLayer,
'pattern': (0, 2, 1)
},
{
'type': BidirectionalRecurrentLayer,
'num_units': 80,
'W_in_to_hid': Uniform(5),
'W_hid_to_hid': Identity(0.5),
'gradient_steps': GRADIENT_STEPS,
'nonlinearity': rectify,
'learn_init': False,
'precompute_input': False
},
{
'type': DenseLayer,
'num_units': source.n_outputs,
'nonlinearity': sigmoid
}
]
net = Net(**net_dict_copy)
return net