def train(self, X, XY, V, VY, count_dict, word_dict, embed_map):
"""
Trains the LBL
"""
self.start = self.seed
self.init_params(embed_map, count_dict, XY)
inds = np.arange(len(X))
numbatches = len(inds) / self.batchsize
curr = 1e20
counter = 0
target=None
num = 15000
# Main loop
stop.display_phase(1)
for epoch in range(self.maxepoch):
self.epoch = epoch
tic = time.time()
prng = RandomState(self.seed + epoch + 1)
prng.shuffle(inds)
for minibatch in range(numbatches):
batchX = X[inds[minibatch::numbatches]]
batchY = XY[inds[minibatch::numbatches]]
(words, acts, preds) = self.forward(batchX)
self.backward(batchY, preds, acts, words, batchX)
self.update_params(batchX)
self.update_hyperparams()
toc = time.time()
# Results and stopping criteria
obj = self.compute_obj(X[:num], XY[:num])
obj_val = self.compute_obj(V[:num], VY[:num])
if self.verbose > 0:
stop.display_results(epoch, toc-tic, obj, obj_val)
(curr, counter) = stop.update_result(curr, obj_val, counter)
if counter == 0:
stop.save_model(self, self.loc)
stopping_target = obj
if stop.criteria_complete(self, epoch, curr, obj, counter,
self.k, obj_val, target):
if self.criteria == 'maxepoch':
break
elif self.criteria == 'validation_pp':
self = stop.load_model(self.loc)
counter = 0
X = np.r_[X, V]
XY = vstack([XY, VY]).tocsr()
self.criteria = 'll_train_heldout'
target = stopping_target #obj
stop.display_phase(2)
inds = range(X.shape[0])
prng.shuffle(inds)
numbatches = len(inds) / self.batchsize
elif self.criteria == 'll_train_heldout':
break
def train(self, X, XY, V, VY, count_dict, word_dict, embed_map):
"""
Trains the LBL
"""
self.start = self.seed
self.init_params(embed_map, count_dict, XY)
inds = np.arange(len(X))
numbatches = len(inds) / self.batchsize
curr = 1e20
counter = 0
target = None
num = 15000
# Main loop
stop.display_phase(1)
for epoch in range(self.maxepoch):
self.epoch = epoch
tic = time.time()
prng = RandomState(self.seed + epoch + 1)
prng.shuffle(inds)
for minibatch in range(numbatches):
batchX = X[inds[minibatch::numbatches]]
batchY = XY[inds[minibatch::numbatches]]
(words, acts, preds) = self.forward(batchX)
self.backward(batchY, preds, acts, words, batchX)
self.update_params(batchX)
self.update_hyperparams()
toc = time.time()
# Results and stopping criteria
obj = self.compute_obj(X[:num], XY[:num])
obj_val = self.compute_obj(V[:num], VY[:num])
if self.verbose > 0:
stop.display_results(epoch, toc - tic, obj, obj_val)
(curr, counter) = stop.update_result(curr, obj_val, counter)
if counter == 0:
stop.save_model(self, self.loc)
stopping_target = obj
if stop.criteria_complete(self, epoch, curr, obj, counter, self.k,
obj_val, target):
if self.criteria == 'maxepoch':
break
elif self.criteria == 'validation_pp':
self = stop.load_model(self.loc)
counter = 0
X = np.r_[X, V]
XY = vstack([XY, VY]).tocsr()
self.criteria = 'll_train_heldout'
target = stopping_target #obj
stop.display_phase(2)
inds = range(X.shape[0])
prng.shuffle(inds)
numbatches = len(inds) / self.batchsize
elif self.criteria == 'll_train_heldout':
break
def train(self, X, indX, XY, V, indV, VY, IM, count_dict, word_dict,
embed_map):
"""
Trains the LBL
"""
self.start = self.seed
self.init_params(embed_map, count_dict, XY)
inds = np.arange(len(X))
numbatches = len(inds) / self.batchsize
curr = 1e20
counter = 0
target = None
num = 15000
x = T.matrix('x', dtype='int32')
y = T.matrix('y')
im = T.matrix('im')
lr = T.scalar('lr')
mom = T.scalar('mom')
(words, acts, IF, preds) = self.forward(x, im)
obj_T = self.compute_obj(x, im, y)
compute_obj_T = theano.function([x, im, y], obj_T)
train_batch = theano.function([x, im, y, lr, mom],
obj_T,
updates=self.update_params(
obj_T, x, lr, mom),
on_unused_input='warn')
log_file = open("train_valid_err.txt", 'w')
# Main loop
stop.display_phase(1)
for epoch in range(self.maxepoch):
self.epoch = epoch
tic = time.time()
prng = RandomState(self.seed + epoch + 1)
prng.shuffle(inds)
obj = 0.0
for minibatch in range(numbatches):
batchX = X[inds[minibatch::numbatches]].astype(np.int32)
batchY = XY[inds[minibatch::numbatches]].toarray().astype(
theano.config.floatX)
batchindX = indX[inds[minibatch::numbatches]].astype(
np.int32).flatten()
batchIm = IM[batchindX].astype(theano.config.floatX)
obj += train_batch(batchX, batchIm, batchY, self.eta_t,
self.p_t)
self.update_hyperparams()
toc = time.time()
# Results and stopping criteria
obj_val = compute_obj_T(
V[:num].astype(np.int32),
IM[indV[:num].astype(int).flatten()].astype(
theano.config.floatX),
VY[:num].toarray().astype(theano.config.floatX))
log_file.write('{} {}\n'.format(obj, obj_val))
if self.verbose > 0:
stop.display_results(epoch, toc - tic, obj, obj_val)
(curr, counter) = stop.update_result(curr, obj_val, counter)
if counter == 0:
stop.save_model_theano(self, self.loc)
stopping_target = obj
if stop.criteria_complete(self, epoch, curr, obj, counter, self.k,
obj_val, target):
if self.criteria == 'maxepoch':
break
elif self.criteria == 'validation_pp':
stop.load_model_theano(self, self.loc)
counter = 0
X = np.r_[X, V]
XY = vstack([XY, VY]).tocsr()
indX = np.r_[indX, indV]
self.criteria = 'll_train_heldout'
target = stopping_target #obj
stop.display_phase(2)
inds = range(X.shape[0])
prng.shuffle(inds)
numbatches = len(inds) / self.batchsize
elif self.criteria == 'll_train_heldout':
break
log_file.close()
def train(self, X, indX, XY, V, indV, VY, IM, count_dict, word_dict, embed_map):
"""
Trains the LBL
"""
self.start = self.seed
self.init_params(embed_map, count_dict, XY)
inds = np.arange(len(X))
numbatches = len(inds) / self.batchsize
curr = 1e20
counter = 0
target=None
num = 15000
x = T.matrix('x', dtype='int32')
y = T.matrix('y')
im = T.matrix('im')
lr = T.scalar('lr')
mom = T.scalar('mom')
(words, acts, IF, preds) = self.forward(x, im)
obj_T = self.compute_obj(x, im, y)
compute_obj_T = theano.function([x, im, y], obj_T)
train_batch = theano.function([x, im, y, lr, mom], obj_T,
updates=self.update_params(obj_T, x, lr, mom),
on_unused_input='warn')
log_file = open("train_valid_err.txt", 'w')
# Main loop
stop.display_phase(1)
for epoch in range(self.maxepoch):
self.epoch = epoch
tic = time.time()
prng = RandomState(self.seed + epoch + 1)
prng.shuffle(inds)
obj = 0.0
for minibatch in range(numbatches):
batchX = X[inds[minibatch::numbatches]].astype(np.int32)
batchY = XY[inds[minibatch::numbatches]].toarray().astype(theano.config.floatX)
batchindX = indX[inds[minibatch::numbatches]].astype(np.int32).flatten()
batchIm = IM[batchindX].astype(theano.config.floatX)
obj += train_batch(batchX, batchIm, batchY, self.eta_t, self.p_t)
self.update_hyperparams()
toc = time.time()
# Results and stopping criteria
obj_val = compute_obj_T(V[:num].astype(np.int32),
IM[indV[:num].astype(int).flatten()].astype(theano.config.floatX),
VY[:num].toarray().astype(theano.config.floatX))
log_file.write('{} {}\n'.format(obj, obj_val))
if self.verbose > 0:
stop.display_results(epoch, toc-tic, obj, obj_val)
(curr, counter) = stop.update_result(curr, obj_val, counter)
if counter == 0:
stop.save_model_theano(self, self.loc)
stopping_target = obj
if stop.criteria_complete(self, epoch, curr, obj, counter,
self.k, obj_val, target):
if self.criteria == 'maxepoch':
break
elif self.criteria == 'validation_pp':
stop.load_model_theano(self, self.loc)
counter = 0
X = np.r_[X, V]
XY = vstack([XY, VY]).tocsr()
indX = np.r_[indX, indV]
self.criteria = 'll_train_heldout'
target = stopping_target #obj
stop.display_phase(2)
inds = range(X.shape[0])
prng.shuffle(inds)
numbatches = len(inds) / self.batchsize
elif self.criteria == 'll_train_heldout':
break
log_file.close()
