type=float,
default=0.0,
required=False,
help="Components with variance below this threshold"
" will be discarded")
parser.add_argument('-w',
'--whiten',
action='store_const',
default=False,
const=True,
required=False,
help='Divide projected features by their '
'standard deviation')
args = parser.parse_args()
# Load dataset.
data = load_data({'dataset': args.dataset})
# TODO: this can be done more efficiently and readably by list
# comprehensions
train_data, valid_data, test_data = map(
lambda (x): x.get_value(borrow=True), data)
print >> sys.stderr, "Dataset shapes:", map(
lambda (x): get_constant(x.shape), data)
# PCA base-class constructor arguments.
conf = {
'num_components': args.num_components,
'min_variance': args.min_variance,
'whiten': args.whiten
}
# Set PCA subclass from argument.
if args.algorithm == 'cov_eig':
help='This many most components will be preserved')
parser.add_argument('-v', '--min-variance', action='store',
type=float,
default=0.0,
required=False,
help="Components with variance below this threshold"
" will be discarded")
parser.add_argument('-w', '--whiten', action='store_const',
default=False,
const=True,
required=False,
help='Divide projected features by their '
'standard deviation')
args = parser.parse_args()
# Load dataset.
data = load_data({'dataset': args.dataset})
# TODO: this can be done more efficiently and readably by list
# comprehensions
train_data, valid_data, test_data = map(lambda(x):
x.get_value(borrow=True), data)
logger.info("Dataset shapes: {0}".format(map(lambda(x):
x.get_value().shape, data)))
# PCA base-class constructor arguments.
conf = {
'num_components': args.num_components,
'min_variance': args.min_variance,
'whiten': args.whiten
}
# Set PCA subclass from argument.
if args.algorithm == 'cov_eig':
def main_train(epochs, batchsize, solution='',sparse_penalty=0,sparsityTarget=0,sparsityTargetPenalty=0):
# Experiment specific arguments
conf_dataset = {'dataset' : 'avicenna',
'expname' : 'dummy', # Used to create the submission file
'transfer' : True,
'normalize' : True, # (Default = True)
'normalize_on_the_fly' : False, # (Default = False)
'randomize_valid' : True, # (Default = True)
'randomize_test' : True, # (Default = True)
'saving_rate': 0, # (Default = 0)
'savedir' : './outputs',
}
# First layer = PCA-75 whiten
pca_layer = {'name' : '1st-PCA',
'num_components': 75,
'min_variance': -50,
'whiten': True,
'pca_class' : 'CovEigPCA',
# Training properties
'proba' : [1, 0, 0],
'savedir' : './outputs',
}
# Load the dataset
data = utils.load_data(conf_dataset)
if conf_dataset['transfer']:
# Data for the ALC proxy
label = data[3]
data = data[:3]
# First layer : train or load a PCA
pca = create_pca(conf_dataset, pca_layer, data, model=pca_layer['name'])
data = [utils.sharedX(pca.function()(set.get_value(borrow=True)),borrow=True) for set in data]
'''
if conf_dataset['transfer']:
data_train, label_train = utils.filter_labels(data[0], label)
alc = embed.score(data_train, label_train)
print '... resulting ALC on train (for PCA) is', alc
'''
nvis = utils.get_constant(data[0].shape[1]).item()
conf = {
'corruption_level': 0.1,
'nhid': 200,
'nvis': nvis,
'anneal_start': 100,
'base_lr': 0.001,
'tied_weights': True,
'act_enc': 'sigmoid',
'act_dec': None,
#'lr_hb': 0.10,
#'lr_vb': 0.10,
'tied_weights': True ,
'solution': solution,
'sparse_penalty': sparse_penalty,
'sparsityTarget': sparsityTarget ,
'sparsityTargetPenalty': sparsityTargetPenalty,
'irange': 0,
}
# A symbolic input representing your minibatch.
minibatch = tensor.matrix()
# Allocate a denoising autoencoder with binomial noise corruption.
corruptor = GaussianCorruptor(conf['corruption_level'])
da = DenoisingAutoencoder(corruptor, conf['nvis'], conf['nhid'],
conf['act_enc'], conf['act_dec'], conf['tied_weights'], conf['solution'], conf['sparse_penalty'],
conf['sparsityTarget'], conf['sparsityTargetPenalty'])
# Allocate an optimizer, which tells us how to update our model.
# TODO: build the cost another way
cost = SquaredError(da)(minibatch, da.reconstruct(minibatch)).mean()
trainer = SGDOptimizer(da, conf['base_lr'], conf['anneal_start'])
updates = trainer.cost_updates(cost)
# Finally, build a Theano function out of all this.
train_fn = theano.function([minibatch], cost, updates=updates)
# Suppose we want minibatches of size 10
proba = utils.getboth(conf, pca_layer, 'proba')
iterator = BatchIterator(data, proba, batchsize)
# Here's a manual training loop. I hope to have some classes that
# automate this a litle bit.
final_cost = 0
for epoch in xrange(epochs):
c = []
for minibatch_data in iterator:
minibatch_err = train_fn(minibatch_data)
c.append(minibatch_err)
final_cost = numpy.mean(c)
print "epoch %d, cost : %f" % (epoch , final_cost)
print '############################## Fin de l\'experience ############################'
print 'Calcul de l\'ALC : '
if conf_dataset['transfer']:
data_train, label_train = utils.filter_labels(data[0], label)
alc = embed.score(data_train, label_train)
print 'Solution : ',solution
print 'sparse_penalty = ',sparse_penalty
print 'sparsityTarget = ',sparsityTarget
print 'sparsityTargetPenalty = ',sparsityTargetPenalty
print 'Final denoising error is : ',final_cost
print '... resulting ALC on train is', alc
return (alc,final_cost)
def main_train(epochs,
batchsize,
solution='',
sparse_penalty=0,
sparsityTarget=0,
sparsityTargetPenalty=0):
# Experiment specific arguments
conf_dataset = {
'dataset': 'avicenna',
'expname': 'dummy', # Used to create the submission file
'transfer': True,
'normalize': True, # (Default = True)
'normalize_on_the_fly': False, # (Default = False)
'randomize_valid': True, # (Default = True)
'randomize_test': True, # (Default = True)
'saving_rate': 0, # (Default = 0)
'savedir': './outputs',
}
# First layer = PCA-75 whiten
pca_layer = {
'name': '1st-PCA',
'num_components': 75,
'min_variance': -50,
'whiten': True,
'pca_class': 'CovEigPCA',
# Training properties
'proba': [1, 0, 0],
'savedir': './outputs',
}
# Load the dataset
data = utils.load_data(conf_dataset)
if conf_dataset['transfer']:
# Data for the ALC proxy
label = data[3]
data = data[:3]
# First layer : train or load a PCA
pca = create_pca(conf_dataset, pca_layer, data, model=pca_layer['name'])
data = [
utils.sharedX(pca.function()(set.get_value(borrow=True)), borrow=True)
for set in data
]
'''
if conf_dataset['transfer']:
data_train, label_train = utils.filter_labels(data[0], label)
alc = embed.score(data_train, label_train)
print '... resulting ALC on train (for PCA) is', alc
'''
nvis = utils.get_constant(data[0].shape[1]).item()
conf = {
'corruption_level': 0.1,
'nhid': 200,
'nvis': nvis,
'anneal_start': 100,
'base_lr': 0.001,
'tied_weights': True,
'act_enc': 'sigmoid',
'act_dec': None,
#'lr_hb': 0.10,
#'lr_vb': 0.10,
'tied_weights': True,
'solution': solution,
'sparse_penalty': sparse_penalty,
'sparsityTarget': sparsityTarget,
'sparsityTargetPenalty': sparsityTargetPenalty,
'irange': 0,
}
# A symbolic input representing your minibatch.
minibatch = tensor.matrix()
# Allocate a denoising autoencoder with binomial noise corruption.
corruptor = GaussianCorruptor(conf['corruption_level'])
da = DenoisingAutoencoder(corruptor, conf['nvis'], conf['nhid'],
conf['act_enc'], conf['act_dec'],
conf['tied_weights'], conf['solution'],
conf['sparse_penalty'], conf['sparsityTarget'],
conf['sparsityTargetPenalty'])
# Allocate an optimizer, which tells us how to update our model.
# TODO: build the cost another way
cost = SquaredError(da)(minibatch, da.reconstruct(minibatch)).mean()
trainer = SGDOptimizer(da, conf['base_lr'], conf['anneal_start'])
updates = trainer.cost_updates(cost)
# Finally, build a Theano function out of all this.
train_fn = theano.function([minibatch], cost, updates=updates)
# Suppose we want minibatches of size 10
proba = utils.getboth(conf, pca_layer, 'proba')
iterator = BatchIterator(data, proba, batchsize)
# Here's a manual training loop. I hope to have some classes that
# automate this a litle bit.
final_cost = 0
for epoch in xrange(epochs):
c = []
for minibatch_data in iterator:
minibatch_err = train_fn(minibatch_data)
c.append(minibatch_err)
final_cost = numpy.mean(c)
print "epoch %d, cost : %f" % (epoch, final_cost)
print '############################## Fin de l\'experience ############################'
print 'Calcul de l\'ALC : '
if conf_dataset['transfer']:
data_train, label_train = utils.filter_labels(data[0], label)
alc = embed.score(data_train, label_train)
print 'Solution : ', solution
print 'sparse_penalty = ', sparse_penalty
print 'sparsityTarget = ', sparsityTarget
print 'sparsityTargetPenalty = ', sparsityTargetPenalty
print 'Final denoising error is : ', final_cost
print '... resulting ALC on train is', alc
return (alc, final_cost)
# Experiment specific arguments
conf = {
'dataset': 'avicenna',
'expname': 'dummy', # Used to create the submission file
'transfer': True,
'normalize': True, # (Default = True)
'normalize_on_the_fly': False, # (Default = False)
'randomize_valid': True, # (Default = True)
'randomize_test': True, # (Default = True)
'saving_rate': 0, # (Default = 0)
'savedir': './outputs',
}
# Load the dataset
data = utils.load_data(conf)
if conf['transfer']:
# Data for the ALC proxy
label = data[3]
data = data[:3]
# First layer : train or load a PCA
pca1 = create_pca(conf, layer1, data, model=layer1['name'])
data = [
utils.sharedX(pca1.function()(set.get_value(borrow=True)), borrow=True)
for set in data
]
# Second layer : train or load a DAE or CAE
ae = create_ae(conf, layer2, data, model=layer2['name'])
default=0.0,
required=False,
help="Components with variance below this threshold" " will be discarded",
)
parser.add_argument(
"-w",
"--whiten",
action="store_const",
default=False,
const=True,
required=False,
help="Divide projected features by their " "standard deviation",
)
args = parser.parse_args()
# Load dataset.
data = load_data({"dataset": args.dataset})
# TODO: this can be done more efficiently and readably by list
# comprehensions
train_data, valid_data, test_data = map(lambda (x): x.get_value(borrow=True), data)
print >> sys.stderr, "Dataset shapes:", map(lambda (x): x.get_value().shape, data)
# PCA base-class constructor arguments.
conf = {"num_components": args.num_components, "min_variance": args.min_variance, "whiten": args.whiten}
# Set PCA subclass from argument.
if args.algorithm == "cov_eig":
PCAImpl = CovEigPCA
elif args.algorithm == "svd":
PCAImpl = SVDPCA
elif args.algorithm == "online":
PCAImpl = OnlinePCA
conf["minibatch_size"] = args.minibatch_size
def main_train(epochs, batchsize, solution="", sparse_penalty=0, sparsityTarget=0, sparsityTargetPenalty=0):
# Experiment specific arguments
conf_dataset = {
"dataset": "avicenna",
"expname": "dummy", # Used to create the submission file
"transfer": True,
"normalize": True, # (Default = True)
"normalize_on_the_fly": False, # (Default = False)
"randomize_valid": True, # (Default = True)
"randomize_test": True, # (Default = True)
"saving_rate": 0, # (Default = 0)
"savedir": "./outputs",
}
# First layer = PCA-75 whiten
pca_layer = {
"name": "1st-PCA",
"num_components": 75,
"min_variance": -50,
"whiten": True,
"pca_class": "CovEigPCA",
# Training properties
"proba": [1, 0, 0],
"savedir": "./outputs",
}
# Load the dataset
data = utils.load_data(conf_dataset)
if conf_dataset["transfer"]:
# Data for the ALC proxy
label = data[3]
data = data[:3]
# First layer : train or load a PCA
pca = create_pca(conf_dataset, pca_layer, data, model=pca_layer["name"])
data = [utils.sharedX(pca.function()(set.get_value(borrow=True)), borrow=True) for set in data]
"""
if conf_dataset['transfer']:
data_train, label_train = utils.filter_labels(data[0], label)
alc = embed.score(data_train, label_train)
print '... resulting ALC on train (for PCA) is', alc
"""
nvis = utils.get_constant(data[0].shape[1]).item()
conf = {
"corruption_level": 0.1,
"nhid": 200,
"nvis": nvis,
"anneal_start": 100,
"base_lr": 0.001,
"tied_weights": True,
"act_enc": "sigmoid",
"act_dec": None,
#'lr_hb': 0.10,
#'lr_vb': 0.10,
"tied_weights": True,
"solution": solution,
"sparse_penalty": sparse_penalty,
"sparsityTarget": sparsityTarget,
"sparsityTargetPenalty": sparsityTargetPenalty,
"irange": 0,
}
# A symbolic input representing your minibatch.
minibatch = tensor.matrix()
# Allocate a denoising autoencoder with binomial noise corruption.
corruptor = GaussianCorruptor(conf["corruption_level"])
da = DenoisingAutoencoder(
corruptor,
conf["nvis"],
conf["nhid"],
conf["act_enc"],
conf["act_dec"],
conf["tied_weights"],
conf["solution"],
conf["sparse_penalty"],
conf["sparsityTarget"],
conf["sparsityTargetPenalty"],
)
# Allocate an optimizer, which tells us how to update our model.
# TODO: build the cost another way
cost = SquaredError(da)(minibatch, da.reconstruct(minibatch)).mean()
trainer = SGDOptimizer(da, conf["base_lr"], conf["anneal_start"])
updates = trainer.cost_updates(cost)
# Finally, build a Theano function out of all this.
train_fn = theano.function([minibatch], cost, updates=updates)
# Suppose we want minibatches of size 10
proba = utils.getboth(conf, pca_layer, "proba")
iterator = BatchIterator(data, proba, batchsize)
# Here's a manual training loop. I hope to have some classes that
# automate this a litle bit.
final_cost = 0
for epoch in xrange(epochs):
c = []
for minibatch_data in iterator:
minibatch_err = train_fn(minibatch_data)
c.append(minibatch_err)
final_cost = numpy.mean(c)
print "epoch %d, cost : %f" % (epoch, final_cost)
print "############################## Fin de l'experience ############################"
print "Calcul de l'ALC : "
if conf_dataset["transfer"]:
data_train, label_train = utils.filter_labels(data[0], label)
alc = embed.score(data_train, label_train)
print "Solution : ", solution
print "sparse_penalty = ", sparse_penalty
print "sparsityTarget = ", sparsityTarget
print "sparsityTargetPenalty = ", sparsityTargetPenalty
print "Final denoising error is : ", final_cost
print "... resulting ALC on train is", alc
return (alc, final_cost)