def __init__(self, dataset_path, batch_size=500, instance_weights_path=None):
L.info("Initializing dataset from: " + os.path.abspath(dataset_path))
# Reading parameters from the mmap file
fp = np.memmap(dataset_path, dtype='int32', mode='r')
self.num_samples = fp[0]
self.ngram = fp[1]
fp = fp.reshape((self.num_samples + 3, self.ngram))
self.vocab_size = fp[1,0]
self.num_classes = fp[2,0]
# Setting minibatch size and number of mini batches
self.batch_size = batch_size
self.num_batches = int(M.ceil(self.num_samples / self.batch_size))
# Reading the matrix of samples
x = fp[3:,0:self.ngram - 1] # Reading the context indices
y = fp[3:,self.ngram - 1] # Reading the output word index
self.shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
self.shared_y = T.cast(theano.shared(y, borrow=True), 'int32')
self.is_weighted = False
if instance_weights_path:
instance_weights = np.loadtxt(instance_weights_path)
U.xassert(instance_weights.shape == (self.num_samples,), "The number of lines in weights file must be the same as the number of samples.")
self.shared_w = T.cast(theano.shared(instance_weights, borrow=True), theano.config.floatX)
self.is_weighted = True
L.info(' #samples: %s, ngram size: %s, vocab size: %s, #classes: %s, batch size: %s, #batches: %s' % (
U.red(self.num_samples), U.red(self.ngram), U.red(self.vocab_size), U.red(self.num_classes), U.red(self.batch_size), U.red(self.num_batches)
)
)
def __init__(self,
rng,
input,
vocab_size,
emb_dim,
emb_matrix=None,
concat=True,
emb_path=None,
vocab_path=None,
add_weights=False):
L.info("Lookup Table layer, #words: %s, #dims: %s" %
(U.red(vocab_size), U.red(emb_dim)))
self.input = input
self.emb_matrix = emb_matrix
if self.emb_matrix is None:
self.emb_matrix = numpy.asarray(
rng.uniform(
low=-0.01, #low=-1,
high=0.01, #high=1,
size=(vocab_size, emb_dim)),
dtype=theano.config.floatX)
if emb_path:
U.xassert(vocab_path,
'When emb_path is given, vocab must be given too.')
self.initialize(emb_path, vocab_path)
self.embeddings = theano.shared(value=self.emb_matrix,
name='embeddings',
borrow=True)
if add_weights:
weights_vec = numpy.ones(vocab_size, dtype=theano.config.floatX)
self.weights = theano.shared(value=weights_vec,
name='word_weights',
borrow=True)
# Check if the speed can be improved
self.output = (self.weights.dimshuffle(0, 'x') *
self.embeddings)[input]
#self.output = self.weights.dimshuffle(0, 'x')[input] * self.embeddings[input]
#self.output = self.weights[input].dimshuffle(0, 'x') * self.embeddings[input]
self.params = [self.embeddings, self.weights]
else:
self.output = self.embeddings[input]
self.params = [self.embeddings]
if concat:
self.output = self.output.reshape(
(input.shape[0], emb_dim * input.shape[1]))
def __init__(self,
rng,
input,
n_in,
n_out,
W_values=None,
init_method=0,
b_values=None,
no_bias=False,
suffix=None):
L.info("Linear layer, #inputs: %s, #outputs: %s" %
(U.red(n_in), U.red(n_out)))
self.input = input
if W_values is None:
if init_method == 0: # Useful for Relu activation
high = 0.01
elif init_method == 1: # Useful for Tanh activation
high = numpy.sqrt(6. / (n_in + n_out))
elif init_method == 2: # Useful for Sigmoid activation
high = 4 * numpy.sqrt(6. / (n_in + n_out))
else:
L.error('Invalid initialization method')
W_values = numpy.asarray(rng.uniform(low=-high,
high=high,
size=(n_in, n_out)),
dtype=theano.config.floatX)
if b_values is None and not no_bias:
b_values = numpy.zeros((n_out, ), dtype=theano.config.floatX)
W_name = 'W'
if suffix is not None:
W_name += '.' + str(suffix)
W = theano.shared(value=W_values, name=W_name, borrow=True)
self.W = W
if no_bias:
self.output = T.dot(input, self.W)
self.params = [self.W]
else:
b_name = 'b'
if suffix is not None:
b_name += '.' + str(suffix)
b = theano.shared(value=b_values, name=b_name, borrow=True)
self.b = b
self.output = T.dot(input, self.W) + self.b
self.params = [self.W, self.b]
def __init__(self, dataset_path, batch_size=500, instance_weights_path=None):
L.info("Initializing dataset from: " + os.path.abspath(dataset_path))
# Reading parameters from the mmap file
print K.get_platform()
fp = np.memmap(dataset_path, dtype='int32', mode='r')
self.num_samples = fp[0]
self.ngram = fp[1]
fp = fp.reshape((self.num_samples + 3, self.ngram))
self.vocab_size = fp[1,0]
self.num_classes = fp[2,0]
# Setting minibatch size and number of mini batches
self.batch_size = batch_size
self.num_batches = int(M.ceil(self.num_samples / self.batch_size))
# Reading the matrix of samples
x = fp[3:,0:self.ngram - 1] # Reading the context indices
y = fp[3:,self.ngram - 1] # Reading the output word index
#self.shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
#self.shared_y = T.cast(theano.shared(y, borrow=True), 'int32')
# What is T.cast :))
L.info("Initialize a simple variable")
val = np.random.random((4, 2))
tmp = K.variable(val)
L.info("Initialize a real variable")
tmp = K.variable(x)
L.info("Initialize two casted variables")
self.shared_x = K.cast(K.variable(x), 'int32')
self.shared_y = K.cast(K.variable(y), 'int32')
L.info("Create two variable without borrow=True")
self.is_weighted = False
if instance_weights_path:
instance_weights = np.loadtxt(instance_weights_path)
U.xassert(instance_weights.shape == (self.num_samples,), "The number of lines in weights file must be the same as the number of samples.")
# what is borrow=True
# self.shared_w = T.cast(theano.shared(instance_weights, borrow=True), theano.config.floatX)
self.shared_w = K.cast(K.variable(instance_weights), K._FLOATX)
self.is_weighted = True
L.info(' #samples: %s, ngram size: %s, vocab size: %s, #classes: %s, batch size: %s, #batches: %s' % (
U.red(self.num_samples), U.red(self.ngram), U.red(self.vocab_size), U.red(self.num_classes), U.red(self.batch_size), U.red(self.num_batches)
)
)
def __init__(self, rng, input, n_in, n_out, W_values=None, init_method=0, b_values=None, no_bias=False, suffix=None):
L.info("Linear layer, #inputs: %s, #outputs: %s" % (U.red(n_in), U.red(n_out)))
self.input = input
if W_values is None:
if init_method == 0: # Useful for Relu activation
high = 0.01
elif init_method == 1: # Useful for Tanh activation
high = numpy.sqrt(6. / (n_in + n_out))
elif init_method == 2: # Useful for Sigmoid activation
high = 4 * numpy.sqrt(6. / (n_in + n_out))
else:
L.error('Invalid initialization method')
W_values = numpy.asarray(
rng.uniform(
low=-high,
high=high,
size=(n_in, n_out)
),
dtype=theano.config.floatX
)
if b_values is None and not no_bias:
b_values = numpy.zeros((n_out,), dtype=theano.config.floatX)
W_name = 'W'
if suffix is not None:
W_name += '.' + str(suffix)
W = theano.shared(value=W_values, name=W_name, borrow=True)
self.W = W
if no_bias:
self.output = T.dot(input, self.W)
self.params = [self.W]
else:
b_name = 'b'
if suffix is not None:
b_name += '.' + str(suffix)
b = theano.shared(value=b_values, name=b_name, borrow=True)
self.b = b
self.output = T.dot(input, self.W) + self.b
self.params = [self.W, self.b]
def __init__(self, rng, input, vocab_size, emb_dim, emb_matrix=None, concat=True, emb_path=None, vocab_path=None, add_weights=False, suffix=None, high=0.01):
L.info("Lookup Table layer, #words: %s, #dims: %s" % (U.red(vocab_size), U.red(emb_dim)))
self.input = input
self.emb_matrix = emb_matrix
if self.emb_matrix is None:
self.emb_matrix = numpy.asarray(
rng.uniform(
low=-high, #low=-1,
high=high, #high=1,
size=(vocab_size, emb_dim)
),
dtype=theano.config.floatX
)
if emb_path:
U.xassert(vocab_path, 'When emb_path is given, vocab must be given too.')
self.initialize(emb_path, vocab_path)
embeddings_name = 'embeddings'
if suffix is not None:
embeddings_name += '.' + str(suffix)
self.embeddings = theano.shared(value=self.emb_matrix, name=embeddings_name, borrow=True)
if add_weights:
weights_vec = numpy.ones(vocab_size, dtype=theano.config.floatX)
self.weights = theano.shared(value=weights_vec, name='word_weights', borrow=True)
# Check if the speed can be improved
self.output = (self.weights.dimshuffle(0, 'x') * self.embeddings)[input]
#self.output = self.weights.dimshuffle(0, 'x')[input] * self.embeddings[input]
#self.output = self.weights[input].dimshuffle(0, 'x') * self.embeddings[input]
self.params = [self.embeddings, self.weights]
else:
self.output = self.embeddings[input]
self.params = [self.embeddings]
if concat:
self.output = self.output.reshape((input.shape[0], emb_dim * input.shape[1]))
def __init__(self, rng, input, vocab_size, emb_dim, emb_matrix=None, concat=True, emb_path=None, vocab_path=None, add_weights=False):
L.info("Lookup Table layer, #words: %s, #dims: %s" % (U.red(vocab_size), U.red(emb_dim)))
self.input = input
L.info("Input " + str(input))
L.info("Add weightes " + str(add_weights))
self.emb_matrix = emb_matrix
if self.emb_matrix is None:
self.emb_matrix = numpy.asarray(
rng.uniform(
low=-0.01, #low=-1,
high=0.01, #high=1,
size=(vocab_size, emb_dim)
),
dtype=K._FLOATX
)
if emb_path:
U.xassert(vocab_path, 'When emb_path is given, vocab must be given too.')
self.initialize(emb_path, vocab_path)
#self.embeddings = theano.shared(value=self.emb_matrix, name='embeddings', borrow=True)
self.embeddings = K.variable(self.emb_matrix, name='embeddings')
if add_weights:
weights_vec = numpy.ones(vocab_size, dtype=K._FLOATX)
#self.weights = theano.shared(value=weights_vec, name='word_weights', borrow=True)
self.weights = K.variable(weights_vec, name='word_weights')
# Check if the speed can be improved
self.output = (self.weights.dimshuffle(0, 'x') * self.embeddings)[input]
#self.output = self.weights.dimshuffle(0, 'x')[input] * self.embeddings[input]
#self.output = self.weights[input].dimshuffle(0, 'x') * self.embeddings[input]
self.params = [self.embeddings, self.weights]
else:
self.output = self.embeddings[input]
self.params = [self.embeddings]
if concat:
self.output = self.output.reshape((input.shape[0], emb_dim * input.shape[1]))
def __init__(self,
dataset_path,
batch_size=500,
instance_weights_path=None):
L.info("Initializing dataset from: " + os.path.abspath(dataset_path))
# Reading parameters from the mmap file
print K.get_platform()
fp = np.memmap(dataset_path, dtype='int32', mode='r')
self.num_samples = fp[0]
self.ngram = fp[1]
fp = fp.reshape((self.num_samples + 3, self.ngram))
self.vocab_size = fp[1, 0]
self.num_classes = fp[2, 0]
# Setting minibatch size and number of mini batches
self.batch_size = batch_size
self.num_batches = int(M.ceil(self.num_samples / self.batch_size))
# Reading the matrix of samples
x = fp[3:, 0:self.ngram - 1] # Reading the context indices
y = fp[3:, self.ngram - 1] # Reading the output word index
#self.shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
#self.shared_y = T.cast(theano.shared(y, borrow=True), 'int32')
# What is T.cast :))
L.info("Initialize a simple variable")
val = np.random.random((4, 2))
tmp = K.variable(val)
L.info("Initialize a real variable")
tmp = K.variable(x)
L.info("Initialize two casted variables")
self.shared_x = K.cast(K.variable(x), 'int32')
self.shared_y = K.cast(K.variable(y), 'int32')
L.info("Create two variable without borrow=True")
self.is_weighted = False
if instance_weights_path:
instance_weights = np.loadtxt(instance_weights_path)
U.xassert(
instance_weights.shape == (self.num_samples, ),
"The number of lines in weights file must be the same as the number of samples."
)
# what is borrow=True
# self.shared_w = T.cast(theano.shared(instance_weights, borrow=True), theano.config.floatX)
self.shared_w = K.cast(K.variable(instance_weights), K._FLOATX)
self.is_weighted = True
L.info(
' #samples: %s, ngram size: %s, vocab size: %s, #classes: %s, batch size: %s, #batches: %s'
% (U.red(self.num_samples), U.red(
self.ngram), U.red(self.vocab_size), U.red(self.num_classes),
U.red(self.batch_size), U.red(self.num_batches)))
def __init__(self,
dataset_path,
batch_size=500,
instance_weights_path=None):
L.info("Initializing dataset from: " + os.path.abspath(dataset_path))
# Reading parameters from the mmap file
fp = np.memmap(dataset_path, dtype='int32', mode='r')
self.num_samples = fp[0]
self.ngram = fp[1]
fp = fp.reshape((self.num_samples + 3, self.ngram))
self.vocab_size = fp[1, 0]
self.num_classes = fp[2, 0]
# Setting minibatch size and number of mini batches
self.batch_size = batch_size
self.num_batches = int(M.ceil(self.num_samples / self.batch_size))
# Reading the matrix of samples
x = fp[3:, 0:self.ngram - 1] # Reading the context indices
y = fp[3:, self.ngram - 1] # Reading the output word index
self.shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
self.shared_y = T.cast(theano.shared(y, borrow=True), 'int32')
self.is_weighted = False
if instance_weights_path:
instance_weights = np.loadtxt(instance_weights_path)
U.xassert(
instance_weights.shape == (self.num_samples, ),
"The number of lines in weights file must be the same as the number of samples."
)
self.shared_w = T.cast(
theano.shared(instance_weights, borrow=True),
theano.config.floatX)
self.is_weighted = True
L.info(
' #samples: %s, ngram size: %s, vocab size: %s, #classes: %s, batch size: %s, #batches: %s'
% (U.red(self.num_samples), U.red(
self.ngram), U.red(self.vocab_size), U.red(self.num_classes),
U.red(self.batch_size), U.red(self.num_batches)))
def __init__(self, dataset_path, batch_size=500, instance_weights_path=None):
L.info("Initializing dataset (with features) from: " + os.path.abspath(dataset_path))
# Reading parameters from the mmap file
fp = np.memmap(dataset_path, dtype='int32', mode='r')
#print type(fp1)
#fp = np.empty(fp1.shape, dtype='int32')
#fp[:] = fp1
#print type(fp)
self.num_samples = fp[0]
self.ngram = fp[1]
fp = fp.reshape((len(fp)/self.ngram, self.ngram))
num_header_lines = fp[1,0]
self.features_info = [] # Format (vocab_size, num_of_elements)
for i in xrange(num_header_lines-1):
self.features_info.append( (fp[i+2,0], fp[i+2,1]) )
self.num_classes = fp[(num_header_lines+2)-1,0]
# Setting minibatch size and number of mini batches
self.batch_size = batch_size
self.num_batches = int(M.ceil(self.num_samples / self.batch_size))
# Reading the matrix of samples
# x is list
'''
self.shared_x_list = []
last_start_pos = 0
for i in xrange(len(self.features_info)):
vocab_size, num_elems = self.features_info[i]
x = fp[num_header_lines+2:,last_start_pos:last_start_pos + num_elems] # Reading the context indices
last_start_pos += num_elems
shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
self.shared_x_list.append(shared_x)
'''
x = fp[num_header_lines+2:,0:self.ngram - 1] # Reading the context indices
self.shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
y = fp[num_header_lines+2:,self.ngram - 1] # Reading the output word index
self.shared_y = T.cast(theano.shared(y, borrow=True), 'int32')
## Untested instance weighting
self.is_weighted = False
if instance_weights_path:
instance_weights = np.loadtxt(instance_weights_path)
U.xassert(instance_weights.shape == (self.num_samples,), "The number of lines in weights file must be the same as the number of samples.")
self.shared_w = T.cast(theano.shared(instance_weights, borrow=True), theano.config.floatX)
self.is_weighted = True
L.info(' #samples: %s, #classes: %s, batch size: %s, #batches: %s' % (
U.red(self.num_samples), U.red(self.num_classes), U.red(self.batch_size), U.red(self.num_batches)
))
for feature in enumerate(self.features_info):
L.info("Feature %s: #ngrams= %s vocab_size= %s" %( U.red(feature[0]), U.red(feature[1][1]), U.red(feature[1][0])))
def train(classifier, criterion, args, trainset, devset, testset=None):
if args.algorithm == "sgd":
from dlm.algorithms.sgd import SGD as Trainer
else:
L.error("Invalid training algorithm: " + args.algorithm)
# Get number of minibatches from the training file
num_train_batches = trainset.get_num_batches()
# Initialize the trainer object
trainer = Trainer(classifier, criterion, args.learning_rate, trainset, clip_threshold=args.clip_threshold)
# Initialize the Learning Rate tuner, which adjusts learning rate based on the development/validation file
lr_tuner = LRTuner(low=0.01*args.learning_rate, high=10*args.learning_rate, inc=0.01*args.learning_rate)
validation_frequency = 5000 # minibatches
# Logging and statistics
total_num_iter = args.num_epochs * num_train_batches
hook = Hook(classifier, devset, testset, total_num_iter, args.out_dir)
L.info('Training')
start_time = time.time()
verbose_freq = 1000 # minibatches
epoch = 0
hook.evaluate(0)
a = time.time()
classifier.save_model(args.out_dir + '/model.epoch_0.gz', zipped=True)
while (epoch < args.num_epochs):
epoch = epoch + 1
L.info("Epoch: " + U.red(epoch))
minibatch_avg_cost_sum = 0
for minibatch_index in xrange(num_train_batches):
# Makes an update of the paramters after processing the minibatch
minibatch_avg_cost, gparams = trainer.step(minibatch_index)
minibatch_avg_cost_sum += minibatch_avg_cost
if minibatch_index % verbose_freq == 0:
grad_norms = [np.linalg.norm(gparam) for gparam in gparams]
L.info(U.blue("[" + time.ctime() + "] ") + '%i/%i, cost=%.2f, lr=%f'
% (minibatch_index, num_train_batches, minibatch_avg_cost_sum/(minibatch_index+1), trainer.get_learning_rate()))
L.info('Grad Norms: [' + ', '.join(['%.6f' % gnorm for gnorm in grad_norms]) + ']')
curr_iter = (epoch - 1) * num_train_batches + minibatch_index
if curr_iter > 0 and curr_iter % validation_frequency == 0:
hook.evaluate(curr_iter)
L.info(U.blue("[" + time.ctime() + "] ") + '%i/%i, cost=%.2f, lr=%f'
% (num_train_batches, num_train_batches, minibatch_avg_cost_sum/num_train_batches, trainer.get_learning_rate()))
dev_ppl = hook.evaluate(curr_iter)
lr = trainer.get_learning_rate()
if args.enable_lr_adjust:
lr = lr_tuner.adapt_lr(dev_ppl, lr)
trainer.set_learning_rate(lr)
classifier.save_model(args.out_dir + '/model.epoch_' + str(epoch) + '.gz', zipped=True)
end_time = time.time()
hook.evaluate(total_num_iter)
L.info('Optimization complete')
L.info('Ran for %.2fm' % ((end_time - start_time) / 60.))
def train(classifier, criterion, args, trainset, devset, testset=None):
if args.algorithm == "sgd":
from dlm.algorithms.sgd import SGD as Trainer
else:
L.error("Invalid training algorithm: " + args.algorithm)
# Get number of minibatches from the training file
num_train_batches = trainset.get_num_batches()
# Initialize the trainer object
trainer = Trainer(classifier, criterion, args.learning_rate, trainset, clip_threshold=args.clip_threshold)
# Initialize the Learning Rate tuner, which adjusts learning rate based on the development/validation file
lr_tuner = LRTuner(low=0.01*args.learning_rate, high=10*args.learning_rate, inc=0.01*args.learning_rate)
validation_frequency = 5000 # minibatches
# Logging and statistics
total_num_iter = args.num_epochs * num_train_batches
hook = Hook(classifier, devset, testset, total_num_iter, args.out_dir)
L.info('Training')
start_time = time.time()
verbose_freq = 1000 # minibatches
epoch = 0
hook.evaluate(0)
a = time.time()
classifier.save_model(args.out_dir + '/model.epoch_0.gz', zipped=True)
while (epoch < args.num_epochs):
epoch = epoch + 1
L.info("Epoch: " + U.red(epoch))
minibatch_avg_cost_sum = 0
for minibatch_index in xrange(num_train_batches):
# Makes an update of the paramters after processing the minibatch
minibatch_avg_cost, gparams = trainer.step(minibatch_index)
minibatch_avg_cost_sum += minibatch_avg_cost
if minibatch_index % verbose_freq == 0:
grad_norms = [np.linalg.norm(gparam) for gparam in gparams]
L.info(U.blue("[" + time.ctime() + "] ") + '%i/%i, cost=%.2f, lr=%f'
% (minibatch_index, num_train_batches, minibatch_avg_cost_sum/(minibatch_index+1), trainer.get_learning_rate()))
L.info('Grad Norms: [' + ', '.join(['%.6f' % gnorm for gnorm in grad_norms]) + ']')
curr_iter = (epoch - 1) * num_train_batches + minibatch_index
if curr_iter > 0 and curr_iter % validation_frequency == 0:
hook.evaluate(curr_iter)
L.info(U.blue("[" + time.ctime() + "] ") + '%i/%i, cost=%.2f, lr=%f'
% (num_train_batches, num_train_batches, minibatch_avg_cost_sum/num_train_batches, trainer.get_learning_rate()))
dev_ppl = hook.evaluate(curr_iter)
lr = trainer.get_learning_rate()
if args.enable_lr_adjust:
lr = lr_tuner.adapt_lr(dev_ppl, lr)
trainer.set_learning_rate(lr)
classifier.save_model(args.out_dir + '/model.epoch_' + str(epoch) + '.gz', zipped=True)
end_time = time.time()
hook.evaluate(total_num_iter)
L.info('Optimization complete')
L.info('Ran for %.2fm' % ((end_time - start_time) / 60.))
def __init__(self,
dataset_path,
batch_size=500,
instance_weights_path=None):
L.info("Initializing dataset (with features) from: " +
os.path.abspath(dataset_path))
# Reading parameters from the mmap file
fp = np.memmap(dataset_path, dtype='int32', mode='r')
#print type(fp1)
#fp = np.empty(fp1.shape, dtype='int32')
#fp[:] = fp1
#print type(fp)
self.num_samples = fp[0]
self.ngram = fp[1]
fp = fp.reshape((len(fp) / self.ngram, self.ngram))
num_header_lines = fp[1, 0]
self.features_info = [] # Format (vocab_size, num_of_elements)
for i in xrange(num_header_lines - 1):
self.features_info.append((fp[i + 2, 0], fp[i + 2, 1]))
self.num_classes = fp[(num_header_lines + 2) - 1, 0]
# Setting minibatch size and number of mini batches
self.batch_size = batch_size
self.num_batches = int(M.ceil(self.num_samples / self.batch_size))
# Reading the matrix of samples
# x is list
'''
self.shared_x_list = []
last_start_pos = 0
for i in xrange(len(self.features_info)):
vocab_size, num_elems = self.features_info[i]
x = fp[num_header_lines+2:,last_start_pos:last_start_pos + num_elems] # Reading the context indices
last_start_pos += num_elems
shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
self.shared_x_list.append(shared_x)
'''
x = fp[num_header_lines + 2:,
0:self.ngram - 1] # Reading the context indices
self.shared_x = T.cast(theano.shared(x, borrow=True), 'int32')
y = fp[num_header_lines + 2:,
self.ngram - 1] # Reading the output word index
self.shared_y = T.cast(theano.shared(y, borrow=True), 'int32')
## Untested instance weighting
self.is_weighted = False
if instance_weights_path:
instance_weights = np.loadtxt(instance_weights_path)
U.xassert(
instance_weights.shape == (self.num_samples, ),
"The number of lines in weights file must be the same as the number of samples."
)
self.shared_w = T.cast(
theano.shared(instance_weights, borrow=True),
theano.config.floatX)
self.is_weighted = True
L.info(' #samples: %s, #classes: %s, batch size: %s, #batches: %s' %
(U.red(self.num_samples), U.red(self.num_classes),
U.red(self.batch_size), U.red(self.num_batches)))
for feature in enumerate(self.features_info):
L.info("Feature %s: #ngrams= %s vocab_size= %s" % (U.red(
feature[0]), U.red(feature[1][1]), U.red(feature[1][0])))
def __init__(self, input, func_name):
L.info("Activation layer, function: " + U.red(func_name))
self.input = input
self.func = self.get_function(func_name)
self.output = self.func(input)