def train_single_sent_id(self, sentences, iteration, work=None, neu1=None):
if work is None: work = zeros(self.layer1_size, dtype=REAL)
if neu1 is None:
neu1 = matutils.zeros_aligned(self.layer1_size, dtype=REAL)
num_of_grad = 0
if (self.update_mode == 1): num_of_grad = self.layer1_size
elif (self.update_mode == 2): num_of_grad = 2 * self.layer1_size
elif (self.update_mode == 3): num_of_grad = 2 * self.layer1_size + 3
sent_grad = zeros(num_of_grad, dtype=REAL)
if self.init_adjust:
denom = sqrt(self.layer1_size)
else:
denom = self.layer1_size
new_sent = (random.rand(self.layer1_size).astype(REAL) - 0.5) / denom
for i in range(iteration):
alpha = max(self.min_alpha, self.alpha * (1 - 1.0 * i / iteration)
) if self.update_mode == 0 else self.alpha
for sentence in sentences:
sampled = [self.vocab.get(word, None) for word in sentence]
train_sent_vec(self, new_sent, sampled, alpha, work, neu1,
sent_grad)
return new_sent
def worker_train():
"""Train the model, lifting lists of sentences from the jobs queue."""
work = matutils.zeros_aligned(
self.layer1_size + 8,
dtype=REAL) # each thread must have its own work memory
neu1 = matutils.zeros_aligned(self.layer1_size + 8, dtype=REAL)
while True:
job = jobs.get()
if job is None: # data finished, exit
break
# update the learning rate before every job
if self.update_mode == 0:
alpha = max(
self.min_alpha,
self.alpha * (1 - 1.0 * word_count[0] / total_words))
else:
alpha = self.alpha
job_words = sum(
train_sent_vec(self, self.sents[sent_no], sentence, alpha,
work, neu1, self.sents_grad[sent_no])
for sent_no, sentence in job)
with lock:
word_count[0] += job_words
sent_count[0] += chunksize
elapsed = time.time() - start
if elapsed >= next_report[0]:
logger.info(
"PROGRESS: at %.2f%% sents, alpha %.05f, %.0f words/s"
% (100.0 * sent_count[0] / total_sents, alpha,
word_count[0] / elapsed if elapsed else 0.0))
next_report[
0] = elapsed + 1.0 # don't flood the log, wait at least a second between progress reports
def train_single_sent_id(self, sentences, iteration, work=None, neu1=None):
if work is None: work = zeros(self.layer1_size, dtype=REAL)
if neu1 is None: neu1 = matutils.zeros_aligned(self.layer1_size, dtype=REAL)
num_of_grad = 0
if (self.update_mode == 1): num_of_grad = self.layer1_size
elif (self.update_mode == 2): num_of_grad = 2 * self.layer1_size
elif (self.update_mode == 3): num_of_grad = 2 * self.layer1_size + 3
sent_grad = zeros(num_of_grad, dtype=REAL)
if self.init_adjust:
denom = sqrt(self.layer1_size)
else:
denom = self.layer1_size
new_sent = (random.rand(self.layer1_size).astype(REAL) - 0.5) / denom
for i in range(iteration):
alpha = max(self.min_alpha, self.alpha * (1 - 1.0 * i / iteration)) if self.update_mode == 0 else self.alpha
for sentence in sentences:
sampled = [self.vocab.get(word, None) for word in sentence]
train_sent_vec(self, new_sent, sampled, alpha, work, neu1, sent_grad)
return new_sent
def worker_train():
"""Train the model, lifting lists of sentences from the jobs queue."""
work = matutils.zeros_aligned(self.layer1_size + 8, dtype=REAL) # each thread must have its own work memory
neu1 = matutils.zeros_aligned(self.layer1_size + 8, dtype=REAL)
while True:
job = jobs.get()
if job is None: # data finished, exit
break
# update the learning rate before every job
if self.update_mode == 0:
alpha = max(self.min_alpha, self.alpha * (1 - 1.0 * word_count[0] / total_words))
else:
alpha = self.alpha
job_words = sum(train_sent_vec(self, self.sents[sent_no], sentence, alpha, work, neu1, self.sents_grad[sent_no])
for sent_no, sentence in job)
with lock:
word_count[0] += job_words
sent_count[0] += chunksize
elapsed = time.time() - start
if elapsed >= next_report[0]:
logger.info("PROGRESS: at %.2f%% sents, alpha %.05f, %.0f words/s" %
(100.0 * sent_count[0] / total_sents, alpha, word_count[0] / elapsed if elapsed else 0.0))
next_report[0] = elapsed + 1.0 # don't flood the log, wait at least a second between progress reports
