logger.setLevel(logging.WARN)
else:
logger.setLevel(logging.INFO)
print >> stderr, 'Instances file: %s' % instances_file
print >> stderr, 'Model file: %s' % model
print >> stderr, 'Word vector file: %s' % word_vector_file
print >> stderr, 'lambda_reg: %20.18f' % lambda_reg
print >> stderr, 'Max iterations: %d' % maxiter
if _seed:
print >> stderr, 'Random seed: %s' % _seed
print >> stderr, ''
print >> stderr, 'load Word2Vec Model...'
word_vectors = WordVectors.load_vectors(word_vector_file)
embsize = word_vectors.embsize()
print >> stderr, 'preparing data...'
instances, _, total_internal_node = prepare_data(word_vectors, instances_file)
print >> stderr, 'init. RAE parameters...'
timer = Timer()
timer.tic()
if _seed != None:
_seed = int(_seed)
else:
_seed = None
print >> stderr, 'seed: %s' % str(_seed)
theta0 = init_theta(embsize, _seed=_seed)
print >> stderr, "Source Word vector file: %s" % source_word_vector_file
print >> stderr, "Target Word vector file: %s" % target_word_vector_file
print >> stderr, "lambda_reg: %20.18f" % lambda_reg
print >> stderr, "lambda_reg_L: %20.18f" % lambda_reg_L
print >> stderr, "lambda_reg_rec: %20.18f" % lambda_reg_rec
print >> stderr, "lambda_reg_sem: %20.18f" % lambda_reg_sem
print >> stderr, "alpha: %20.18f" % alpha
print >> stderr, "Max iterations: %d" % maxiter
print >> stderr, "Max iterations_la: %d" % maxiter_la
if _seed:
print >> stderr, "Random seed: %s" % _seed
print >> stderr, ""
print >> stderr, "load word vectors..."
# 载入词向量的输入放入word_vectors中
source_word_vectors = WordVectors.load_vectors(source_word_vector_file)
target_word_vectors = WordVectors.load_vectors(target_word_vector_file)
# embsize为词向量的维度
source_embsize = source_word_vectors.embsize()
target_embsize = target_word_vectors.embsize()
print >> stderr, "preparing data..."
# 载入训练短语数据，将短语转化为instance的数组放入instances中
source_instances, _, source_total_internal_node = prepare_data(source_word_vectors, source_instances_file)
target_instances, _, target_total_internal_node = prepare_data(target_word_vectors, target_instances_file)
print >> stderr, "init. RAE parameters..."
timer = Timer()
timer.tic()
if _seed != None:
_seed = int(_seed)
else:
print >> stderr, 'Source Word vector file: %s' % src_word_vector_file
print >> stderr, 'Target Word vector file: %s' % trg_word_vector_file
print >> stderr, 'lambda_reg: %20.18f' % lambda_reg
print >> stderr, 'lambda_reg_L: %20.18f' % lambda_reg_L
print >> stderr, 'lambda_reg_rec: %20.18f' % lambda_reg_rec
print >> stderr, 'lambda_reg_sem: %20.18f' % lambda_reg_sem
print >> stderr, 'alpha: %20.18f' % alpha
print >> stderr, 'Max iterations: %d' % maxiter
print >> stderr, 'Max iterations_la: %d' % maxiter_la
if _seed:
print >> stderr, 'Random seed: %s' % _seed
print >> stderr, ''
print >> stderr, 'load word vectors...'
# 载入词向量的输入放入word_vectors中
src_word_vectors = WordVectors.load_vectors( src_word_vector_file )
trg_word_vectors = WordVectors.load_vectors( trg_word_vector_file )
#embsize为词向量的维度
src_embsize = src_word_vectors.embsize()
trg_embsize = trg_word_vectors.embsize()
print >> stderr, 'preparing data...'
#载入训练短语数据，将短语转化为instance的数组放入instances中
src_instances, _, src_total_internal_node = prepare_data( src_word_vectors, src_instances_file )
trg_instances, _, trg_total_internal_node = prepare_data( trg_word_vectors, trg_instances_file )
print >> stderr, 'init. RAE parameters...'
timer = Timer()
timer.tic()
if _seed != None:
_seed = int(_seed)
else:
if checking_grad:
logger.setLevel(logging.WARN)
else:
logger.setLevel(logging.INFO)
print >> stderr, 'Instances file: %s' % instances_file
print >> stderr, 'Model file: %s' % model
print >> stderr, 'Word vector file: %s' % word_vector_file
print >> stderr, 'lambda_reg: %20.18f' % lambda_reg
print >> stderr, 'Max iterations: %d' % maxiter
if _seed:
print >> stderr, 'Random seed: %s' % _seed
print >> stderr, ''
print >> stderr, 'load word vectors...'
word_vectors = WordVectors.load_vectors(word_vector_file)
embsize = word_vectors.embsize()
print >> stderr, 'preparing data...'
instances, _, total_internal_node = prepare_data(
word_vectors, instances_file)
print >> stderr, 'init. RAE parameters...'
timer = Timer()
timer.tic()
if _seed != None:
_seed = int(_seed)
else:
_seed = None
print >> stderr, 'seed: %s' % str(_seed)
