def train(self, model, dataset):
minibatch = tensor.matrix()
cost = SquaredError(model)(minibatch, model.reconstruct(minibatch)).mean()
trainer = SGDOptimizer(model, self.base_lr, self.anneal_start)
updates = trainer.cost_updates(cost)
train_fn = function([minibatch], cost, updates = updates)
data = dataset.get_design_matrix()
for epoch in xrange(self.num_epochs):
for offset in xrange(0, data.shape[0], self.batch_size):
minibatch_err = train_fn(data[offset:(offset+self.batch_size)])
print "epoch %d, batch %d-%d: %f" % (epoch, offset, offset + self.batch_size -1, minibatch_err)
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)
# 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['sparsity_target'],
conf['sparsity_target_penalty'])
# 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 20
batchsize = 20
# Here's a manual training loop. I hope to have some classes that
# automate this a litle bit.
for epoch in xrange(5):
for offset in xrange(0, data.shape[0], batchsize):
minibatch_err = train_fn(data[offset:(offset + batchsize)])
print "epoch %d, batch %d-%d: %f" % \
(epoch, offset, offset + batchsize - 1, minibatch_err)
MyCorruptor = framework.corruption.get(name)
corruptor = MyCorruptor(layer.get('corruption_level', 0))
# Allocate an denoising or contracting autoencoder
MyAutoencoder = framework.autoencoder.get(clsname)
ae = MyAutoencoder.fromdict(layer, corruptor=corruptor)
# Allocate an optimizer, which tells us how to update our model.
MyCost = framework.cost.get(layer['cost_class'])
varcost = MyCost(ae)(minibatch, ae.reconstruct(minibatch))
if isinstance(ae, ContractingAutoencoder):
alpha = layer.get('contracting_penalty', 0.1)
penalty = alpha * ae.contraction_penalty(minibatch)
varcost = varcost + penalty
varcost = varcost.mean()
trainer = SGDOptimizer(ae, layer['base_lr'], layer['anneal_start'])
updates = trainer.cost_updates(varcost)
# Finally, build a Theano function out of all this.
train_fn = theano.function([minibatch], varcost,
updates=updates,
name='train_fn')
# Here's a manual training loop.
print '... training layer:', clsname
start_time = time.clock()
proba = utils.getboth(layer, conf, 'proba')
iterator = BatchIterator(data, proba, layer['batch_size'])
saving_counter = 0
saving_rate = utils.getboth(layer, conf, 'saving_rate', 0)
for epoch in xrange(layer['epochs']):
}
print '== training =='
# A symbolic input representing your minibatch.
minibatch = tensor.matrix()
# Allocate a denoising autoencoder with binomial noise corruption.
corruptor = GaussianCorruptor(corruption_level=conf['corruption_level'])
da = DenoisingAutoencoder(corruptor, conf['nvis'], conf['nhid'],
conf['act_enc'], conf['act_dec'],
tied_weights=conf['tied_weights'],
irange=conf['irange'])
# 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.params(), conf['base_lr'], conf['anneal_start'])
# Finally, build a Theano function out of all this.
train_fn = theano.function([minibatch], cost,
updates=trainer.cost_updates(cost))
# Suppose we want minibatches of size 10
batchsize = 10
# Here's a manual training loop. I hope to have some classes that
# automate this a litle bit.
for epoch in xrange(10):
for offset in xrange(0, train_data.shape[0], batchsize):
minibatch_err = train_fn(train_data[offset:(offset + batchsize)])
#print "epoch %d, batch %d-%d: %f" % \
#(epoch, offset, offset + batchsize - 1, minibatch_err)