def pos(sequence):
"""
中文词性标注，调用深度学习模型
:param sequence:
:return:
"""
config = load_config(FLAGS.config_pos_path)
logger = get_logger(FLAGS.log_file)
# limit GPU memory
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
# load dict
with open(FLAGS.pos_dict_path, "rb") as f:
char_to_id, id_to_char, tag_to_id, id_to_tag = pickle.load(f)
# create graph and reload model
with tf.Session(config=tf_config) as sess:
model = create_model(sess, Model, FLAGS.pos_model_path,
load_word2vec, config, id_to_char, logger)
while True:
line = input("请输入测试句子:")
result = model.evaluate_line(sess,
input_from_line(line, char_to_id),
id_to_tag)
print(result)
def evaluate_line():
config = load_config(FLAGS.config_file)
logger = get_logger(FLAGS.log_file)
# limit GPU memory
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
with open(FLAGS.map_file, "rb") as f:
char_to_id, id_to_char, tag_to_id, id_to_tag = pickle.load(f)
with tf.Session(config=tf_config) as sess:
model = create_model(sess, Model, FLAGS.ckpt_path, load_word2vec, config, id_to_char, logger)
while True:
line = input("请输入测试句子:")
result = model.evaluate_line(sess, input_from_line(line, char_to_id), id_to_tag)
print(result)
def train():
# load data sets
train_sentences = load_sentences(FLAGS.train_file, FLAGS.lower,
FLAGS.zeros)
dev_sentences = load_sentences(FLAGS.dev_file, FLAGS.lower, FLAGS.zeros)
test_sentences = load_sentences(FLAGS.test_file, FLAGS.lower, FLAGS.zeros)
# Use selected tagging scheme (IOB / IOBES)
if FLAGS.tag_schema == 'iob':
update_tag_scheme(train_sentences, FLAGS.tag_schema)
update_tag_scheme(test_sentences, FLAGS.tag_schema)
# create maps if not exist 创建index-term 映射表，如果存在则加载，否则创建
if not os.path.isfile(FLAGS.map_file):
# create dictionary for word
if FLAGS.pre_emb:
dico_chars_train = char_mapping(train_sentences + dev_sentences,
FLAGS.lower)[0]
dico_chars, char_to_id, id_to_char = augment_with_pretrained(
dico_chars_train.copy(), FLAGS.emb_file,
list(
itertools.chain.from_iterable([[w[0] for w in s]
for s in test_sentences +
dev_sentences])))
else:
_c, char_to_id, id_to_char = char_mapping(
train_sentences + dev_sentences + test_sentences, FLAGS.lower)
# Create a dictionary and a mapping for tags
_t, tag_to_id, id_to_tag = tag_mapping(train_sentences +
dev_sentences + test_sentences)
with open(FLAGS.map_file, "wb") as f:
pickle.dump([char_to_id, id_to_char, tag_to_id, id_to_tag], f)
else:
with open(FLAGS.map_file, "rb") as f:
char_to_id, id_to_char, tag_to_id, id_to_tag = pickle.load(f)
# prepare data, get a collection of list containing index
train_data = prepare_dataset(train_sentences, char_to_id, tag_to_id,
FLAGS.lower)
dev_data = prepare_dataset(dev_sentences, char_to_id, tag_to_id,
FLAGS.lower)
test_data = prepare_dataset(test_sentences, char_to_id, tag_to_id,
FLAGS.lower)
print("%i / %i / %i sentences in train / dev / test." %
(len(train_data), len(dev_data), len(test_data)))
train_manager = BatchManager(train_data, FLAGS.batch_size)
dev_manager = BatchManager(dev_data, 100)
test_manager = BatchManager(test_data, 100)
# make path for store log and model if not exist
make_path(FLAGS)
config = config_model(char_to_id, tag_to_id)
log_path = FLAGS.log_file
logger = get_logger(log_path)
print_config(config, logger)
# limit GPU memory
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
steps_per_epoch = train_manager.len_data
with tf.Session(config=tf_config) as sess:
model = create_model(sess, Model, FLAGS.ckpt_path, load_word2vec,
config, id_to_char, logger)
logger.info("start training")
loss = []
for i in range(100):
for batch in train_manager.iter_batch(shuffle=True):
step, batch_loss = model.run_step(sess, True, batch)
loss.append(batch_loss)
if step % FLAGS.steps_check == 0:
iteration = step // steps_per_epoch + 1
logger.info("iteration:{} step:{}/{}, "
"NER loss:{:>9.6f}".format(
iteration, step % steps_per_epoch,
steps_per_epoch, np.mean(loss)))
loss = []
best = evaluate(sess, model, "dev", dev_manager, id_to_tag, logger)
if best:
save_model(sess, model, FLAGS.ckpt_path, logger)
evaluate(sess, model, "test", test_manager, id_to_tag, logger)
