def setup_model(p):
ladder = LadderAE(p)
# Setup inputs
input_type = TensorType('float32',
[False] * (len(p.encoder_layers[0]) + 1))
x_only = input_type('features_unlabeled')
if debug:
x_only.tag.test_value = numpy.random.normal(
size=(p.batch_size, ) + p.encoder_layers[0]).astype(floatX)
x = input_type('features_labeled')
if debug:
x.tag.test_value = numpy.random.normal(
size=(p.batch_size, ) + p.encoder_layers[0]).astype(floatX)
y = theano.tensor.lvector('targets_labeled')
if debug:
y.tag.test_value = numpy.random.randint(1,
int(p.encoder_layers[-1]) + 1,
(p.batch_size))
ladder.apply(x, y, x_only)
# Load parameters if requested
if p.get('load_from'):
with open(p.load_from + '/trained_params.npz') as f:
loaded = numpy.load(f)
cg = ComputationGraph([ladder.costs.total])
current_params = VariableFilter(roles=[PARAMETER])(cg.variables)
logger.info('Loading parameters: %s' % ', '.join(loaded.keys()))
for param in current_params:
assert param.get_value().shape == loaded[param.name].shape
param.set_value(loaded[param.name])
return ladder
def setup_model(p):
ladder = LadderAE(p)
# Setup inputs
input_type = TensorType('float32', [False] * (len(p.encoder_layers[0]) + 1))
x_only = input_type('features_unlabeled')
if debug:
x_only.tag.test_value = numpy.random.normal(size=(p.batch_size,)+p.encoder_layers[0]).astype(floatX)
x = input_type('features_labeled')
if debug:
x.tag.test_value = numpy.random.normal(size=(p.batch_size,)+p.encoder_layers[0]).astype(floatX)
y = theano.tensor.lvector('targets_labeled')
if debug:
y.tag.test_value = numpy.random.randint(1,int(p.encoder_layers[-1])+1,(p.batch_size))
ladder.apply(x, y, x_only)
# Load parameters if requested
if p.get('load_from'):
with open(p.load_from + '/trained_params.npz') as f:
loaded = numpy.load(f)
cg = ComputationGraph([ladder.costs.total])
current_params = VariableFilter(roles=[PARAMETER])(cg.variables)
logger.info('Loading parameters: %s' % ', '.join(loaded.keys()))
for param in current_params:
assert param.get_value().shape == loaded[param.name].shape
param.set_value(loaded[param.name])
return ladder
def setup_model(p):
ladder = LadderAE(p)
# Setup inputs
input_type = TensorType("float32", [False] * (len(p.encoder_layers[0]) + 1))
x_only = input_type("features_unlabeled")
x = input_type("features_labeled")
y = theano.tensor.lvector("targets_labeled")
ladder.apply(x, y, x_only)
# Load parameters if requested
if p.get("load_from"):
trained_params = ojoin(p.load_from, "trained_params_best.npz")
# trained_params = ojoin(p.load_from, 'trained_params_best.npz')
# if not file_exists(trained_params):
# trained_params = ojoin(p.load_from, 'trained_params.npz')
with open(trained_params) as f:
loaded = numpy.load(f)
cg = ComputationGraph([ladder.costs.total])
current_params = VariableFilter(roles=[PARAMETER])(cg.variables)
logger.info("Loading parameters: %s" % ", ".join(loaded.keys()))
for param in current_params:
assert param.get_value().shape == loaded[param.name].shape
param.set_value(loaded[param.name])
return ladder
def setup_model(p):
ladder = LadderAE(p)
# Setup inputs
input_type = TensorType('float32',
[False] * (len(p.encoder_layers[0]) + 1))
x_only = input_type('features_unlabeled')
x = input_type('features_labeled')
y = theano.tensor.lvector('targets_labeled')
ladder.apply(x, y, x_only)
# Load parameters if requested
if p.get('load_from'):
trained_params = ojoin(p.load_from, 'trained_params_best.npz')
# trained_params = ojoin(p.load_from, 'trained_params_best.npz')
# if not file_exists(trained_params):
# trained_params = ojoin(p.load_from, 'trained_params.npz')
with open(trained_params) as f:
loaded = numpy.load(f)
cg = ComputationGraph([ladder.costs.total])
current_params = VariableFilter(roles=[PARAMETER])(cg.variables)
logger.info('Loading parameters: %s' % ', '.join(loaded.keys()))
for param in current_params:
assert param.get_value().shape == loaded[param.name].shape
param.set_value(loaded[param.name])
return ladder
def setup_model():
ladder = LadderAE()
input_type = TensorType('float32', [False, False])
x_lb = input_type('features_labeled')
x_un = input_type('features_unlabeled')
y = theano.tensor.lvector('targets_labeled')
ladder.apply(x_lb, x_un, y)
return ladder
def setup_model():
ladder = LadderAE()
input_type = TensorType('float32', [False, False])
x_lb = input_type('features_labeled')
x_un = input_type('features_unlabeled')
y = theano.tensor.lvector('targets_labeled')
ladder.apply(x_lb, x_un, y)
return ladder
def setup_model(p):
ladder = LadderAE(p)
# Setup inputs
input_type = TensorType('float32', [False] * (len(p.encoder_layers[0]) + 1))
x_only = input_type('features_unlabeled')
x = input_type('features_labeled')
y = theano.tensor.lvector('targets_labeled')
ladder.apply(x, y, x_only)
# Load parameters if requested
if p.get('load_from'):
with numpy.load(p.load_from + '/trained_params.npz') as loaded:
cg = ComputationGraph([ladder.costs.total])
current_params = VariableFilter(roles=[PARAMETER])(cg.variables)
logger.info('Loading parameters: %s' % ', '.join(loaded.keys()))
for param in current_params:
assert param.get_value().shape == loaded[param.name].shape
param.set_value(loaded[param.name])
return ladder
