def __init__(self, layers, cost, updater='Adam', verbose=2, Y=T.matrix(), iterator='SortedPadded'):
self.settings = locals()
del self.settings['self']
self.layers = layers
if isinstance(cost, basestring):
self.cost = case_insensitive_import(costs, cost)
else:
self.cost = cost
if isinstance(updater, basestring):
self.updater = case_insensitive_import(updates, updater)()
else:
self.updater = updater
if isinstance(iterator, basestring):
self.iterator = case_insensitive_import(iterators, iterator)()
else:
self.iterator = iterator
# True if output is a padded sequence
# Padded elements should not contribute to the loss
# and should be removed before returning predictions.
self.is_padseq_output = self.cost.__name__ in ['CategoricalPaddedSequenceCrossEntropy']
self.verbose = verbose
for i in range(1, len(self.layers)):
self.layers[i].connect(self.layers[i-1])
self.params = flatten([l.params for l in layers])
self.X = self.layers[0].input
self.y_tr = self.layers[-1].output(dropout_active=True)
self.y_te = self.layers[-1].output(dropout_active=False)
self.Y = Y
if self.is_padseq_output:
# P codes whether a sequence element was created by padding
# so that it can be ignored in the loss computation.
# 0 for padded elements, 1 for not-padded elements
self.P = T.matrix()
cost = self.cost(self.Y, self.y_tr, self.P)
else:
cost = self.cost(self.Y, self.y_tr)
self.updates = self.updater.get_updates(self.params, cost)
if self.is_padseq_output:
self._train = theano.function([self.X, self.Y, self.P], cost, updates=self.updates)
self._cost = theano.function([self.X, self.Y, self.P], cost)
else:
self._train = theano.function([self.X, self.Y], cost, updates=self.updates)
self._cost = theano.function([self.X, self.Y], cost)
self._predict = theano.function([self.X], self.y_te)
def __init__(self,
layers,
cost,
updater='Adam',
verbose=2,
Y=T.matrix(),
iterator='SortedPadded'):
self.settings = locals()
del self.settings['self']
self.layers = layers
if isinstance(cost, basestring):
self.cost = case_insensitive_import(costs, cost)
else:
self.cost = cost
if isinstance(updater, basestring):
self.updater = case_insensitive_import(updates, updater)()
else:
self.updater = updater
if isinstance(iterator, basestring):
self.iterator = getattr(iterators, iterator)()
else:
self.iterator = iterator
self.verbose = verbose
for i in range(1, len(self.layers)):
self.layers[i].connect(self.layers[i - 1])
self.params = flatten([l.params for l in layers])
self.X = self.layers[0].input
self.y_tr = self.layers[-1].output(dropout_active=True)
self.y_te = self.layers[-1].output(dropout_active=False)
self.Y = Y
cost = self.cost(self.Y, self.y_tr)
self.updates = self.updater.get_updates(self.params, cost)
self._train = theano.function([self.X, self.Y],
cost,
updates=self.updates)
self._params = theano.function([], self.params[0])
self._cost = theano.function([self.X, self.Y], cost)
self._predict = theano.function([self.X], self.y_te)
def __init__(self, layers, cost, updater='Adam', verbose=2, Y=T.matrix(), iterator='SortedPadded'):
self.settings = locals()
del self.settings['self']
self.layers = layers
if isinstance(cost, basestring):
self.cost = case_insensitive_import(costs, cost)
else:
self.cost = cost
if isinstance(updater, basestring):
self.updater = case_insensitive_import(updates, updater)()
else:
self.updater = updater
if isinstance(iterator, basestring):
self.iterator = case_insensitive_import(iterators, iterator)()
else:
self.iterator = iterator
self.verbose = verbose
for i in range(1, len(self.layers)):
self.layers[i].connect(self.layers[i-1])
self.params = flatten([l.params for l in layers])
self.X = self.layers[0].input
self.y_tr = self.layers[-1].output(dropout_active=True)
self.y_te = self.layers[-1].output(dropout_active=False)
self.Y = Y
cost = self.cost(self.Y, self.y_tr)
self.updates = self.updater.get_updates(self.params, cost)
self._train = theano.function([self.X, self.Y], cost, updates=self.updates)
self._cost = theano.function([self.X, self.Y], cost)
self._predict = theano.function([self.X], self.y_te)
