def train():
# 加载数据集
train_sentences = dl.load_sentences(FLAGS.train_file)
dev_sentences = dl.load_sentences(FLAGS.dev_file)
test_sentences = dl.load_sentences(FLAGS.test_file)
# 转换编码 bio转bioes
dl.update_tag_scheme(train_sentences, FLAGS.tag_schema)
dl.update_tag_scheme(test_sentences, FLAGS.tag_schema)
dl.update_tag_scheme(dev_sentences, FLAGS.tag_schema)
# 创建单词映射及标签映射
if not os.path.isfile(FLAGS.map_file):
_, word_to_id, id_to_word = dl.word_mapping(train_sentences)
_, tag_to_id, id_to_tag = dl.tag_mapping(train_sentences)
with open(FLAGS.map_file, 'wb') as f:
pickle.dump([word_to_id, id_to_word, tag_to_id, id_to_tag], f)
else:
with open(FLAGS.map_file, 'rb') as f:
unpickler = pickle.Unpickler(f)
scores = unpickler.load()
word_to_id, id_to_word, tag_to_id, id_to_tag = scores
train_data = dl.prapare_dataset(train_sentences, word_to_id, tag_to_id)
dev_data = dl.prapare_dataset(train_sentences, word_to_id, tag_to_id)
test_data = dl.prapare_dataset(train_sentences, word_to_id, tag_to_id)
print('train_data %i, dev_data_num %i, test_data_num %i' %
(len(train_data), len(dev_data), len(test_data)))
mu.make_path(FLAGS)
if os.path.isfile(FLAGS.config_file):
config = mu.load_config(FLAGS.config_file)
else:
config = mu.config_model(FLAGS, word_to_id, tag_to_id)
mu.save_config(config, FLAGS.config_file)
log_path = os.path.join('log', FLAGS.log_file)
logger = mu.get_log(log_path)
mu.print_config(config, logger)
print('aa')
def train():
# 加载数据集
train_sentences = data_loader.load_sentences(FLAGS.train_file)
dev_sentences = data_loader.load_sentences(FLAGS.dev_file)
test_sentences = data_loader.load_sentences(FLAGS.test_file)
# 转换编码
data_loader.update_tag_scheme(train_sentences, FLAGS.tag_schema)
data_loader.update_tag_scheme(dev_sentences, FLAGS.tag_schema)
data_loader.update_tag_scheme(test_sentences, FLAGS.tag_schema)
# 创建单词和词典映射
if not os.path.isfile(FLAGS.map_file):
if FLAGS.pre_emb:
dico_words_train = data_loader.word_mapping(train_sentences)[0]
dico_word, word_to_id, id_to_word = data_utils.augment_with_pretrained(
dico_words_train.copy(), FLAGS.emb_file,
list(
itertools.chain.from_iterable([[w[0] for w in s]
for s in test_sentences])))
else:
_, word_to_id, id_to_word = data_loader.word_mapping(
train_sentences)
_, tag_to_id, id_to_tag = data_loader.tag_mapping(train_sentences)
with open(FLAGS.map_file, 'wb') as f:
pickle.dump([word_to_id, id_to_word, tag_to_id, id_to_tag], f)
else:
with open(FLAGS.map_file, 'rb') as f:
word_to_id, id_to_word, tag_to_id, id_to_tag = pickle.load(f)
# 准备数据
train_data = data_loader.prepare_dataset(train_sentences, word_to_id,
tag_to_id)
dev_data = data_loader.prepare_dataset(dev_sentences, word_to_id,
tag_to_id)
test_data = data_loader.prepare_dataset(test_sentences, word_to_id,
tag_to_id)
# 将数据分批处理
train_manager = data_utils.BatchManager(train_data, FLAGS.batch_size)
dev_manager = data_utils.BatchManager(dev_data, FLAGS.batch_size)
test_manager = data_utils.BatchManager(test_data, FLAGS.batch_size)
# 创建不存在的文件夹
model_utils.make_path(FLAGS)
# 判断配置文件
if os.path.isfile(FLAGS.config_file):
config = model_utils.load_config(FLAGS.config_file)
else:
config = model_utils.config_model(FLAGS, word_to_id, tag_to_id)
model_utils.save_config(config, FLAGS.config_file)
# 配置印logger
log_path = os.path.join('log', FLAGS.log_file)
logger = model_utils.get_logger(log_path)
model_utils.print_config(config, logger)
tf_config = tf.ConfigProto(allow_soft_placement=True)
tf_config.gpu_options.allow_growth = True
step_per_epoch = train_manager.len_data
with tf.Session(config=tf_config) as sess:
model = model_utils.create(sess, Model, FLAGS.ckpt_path, load_word2vec,
config, id_to_word, logger)
logger.info('开始训练')
loss = []
start = time.time()
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.setps_chech == 0:
iteration = step // step_per_epoch + 1
logger.info(
"iteration{}: step{}/{}, NER loss:{:>9.6f}".format(
iteration, step % step_per_epoch, step_per_epoch,
np.mean(loss)))
loss = []
best = evaluate(sess, model, 'dev', dev_manager, id_to_tag, logger)
if best:
model_utils.save_model(sess, model, FLAGS.ckpt_path, logger)
evaluate(sess, model, 'test', test_manager, id_to_tag, logger)
t = time.time() - start
logger.info('cost time: %f' % t)
config = model_utils.load_config(FLAGS.config_file)
else:
config = model_utils.config_model(FLAGS, word_to_id, tag_to_id)
model_utils.save_config(config, FLAGS.config_file)
log_path = os.path.join("log", FLAGS.log_file)
logger = model_utils.get_logger(log_path)
model_utils.print_config(config, logger)
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 = model_utils.create(sess, Model, FLAGS.ckpt_path, load_word2vec, config, id_to_word, logger)
logger.info("开始训练")
def train():
# 加载数据集
train_sentences = data_loader.load_sentences(FLAGS.train_file)
dev_sentences = data_loader.load_sentences(FLAGS.dev_file)
test_sentences = data_loader.load_sentences(FLAGS.test_file)
# 转换编码 bio转bioes
data_loader.update_tag_scheme(train_sentences, FLAGS.tag_schema)
data_loader.update_tag_scheme(test_sentences, FLAGS.tag_schema)
data_loader.update_tag_scheme(dev_sentences, FLAGS.tag_schema)
# 创建单词映射及标签映射
if not os.path.isfile(FLAGS.map_file):
if FLAGS.pre_emb:
dico_words_train = data_loader.word_mapping(train_sentences)[0]
dico_word, word_to_id, id_to_word = data_utils.augment_with_pretrained(
dico_words_train.copy(),
FLAGS.emb_file,
list(
itertools.chain.from_iterable(
[[w[0] for w in s] for s in test_sentences]
)
)
)
else:
_, word_to_id, id_to_word = data_loader.word_mapping(train_sentences)
_, tag_to_id, id_to_tag = data_loader.tag_mapping(train_sentences)
with open(FLAGS.map_file, "wb") as f:
pickle.dump([word_to_id, id_to_word, tag_to_id, id_to_tag], f)
else:
with open(FLAGS.map_file, 'rb') as f:
word_to_id, id_to_word, tag_to_id, id_to_tag = pickle.load(f)
train_data = data_loader.prepare_dataset(
train_sentences, word_to_id, tag_to_id
)
dev_data = data_loader.prepare_dataset(
dev_sentences, word_to_id, tag_to_id
)
test_data = data_loader.prepare_dataset(
test_sentences, word_to_id, tag_to_id
)
train_manager = data_utils.BatchManager(train_data, FLAGS.batch_size)
dev_manager = data_utils.BatchManager(dev_data, FLAGS.batch_size)
test_manager = data_utils.BatchManager(test_data, FLAGS.batch_size)
print('train_data_num %i, dev_data_num %i, test_data_num %i' % (len(train_data), len(dev_data), len(test_data)))
model_utils.make_path(FLAGS)
if os.path.isfile(FLAGS.config_file):
config = model_utils.load_config(FLAGS.config_file)
else:
config = model_utils.config_model(FLAGS, word_to_id, tag_to_id)
model_utils.save_config(config, FLAGS.config_file)
log_path = os.path.join("log", FLAGS.log_file)
logger = model_utils.get_logger(log_path)
model_utils.print_config(config, logger)
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 = model_utils.create(sess, Model, FLAGS.ckpt_path, load_word2vec, config, id_to_word, logger)
logger.info("开始训练")
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.setps_chech== 0:
iterstion = step // steps_per_epoch + 1
logger.info("iteration:{} step{}/{},NER loss:{:>9.6f}".format(iterstion, step%steps_per_epoch, steps_per_epoch, np.mean(loss)))
loss = []
best = evaluate(sess,model,"dev", dev_manager, id_to_tag, logger)
if best:
model_utils.save_model(sess, model, FLAGS.ckpt_path, logger)
evaluate(sess, model, "test", test_manager, id_to_tag, logger)
if __name__ == '__main__':
FLAGS = parse_args()
# tensorflow config
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
sess = tf.Session(config=tf_config)
# model config
make_path(FLAGS)
config = config_model()
save_config(config, FLAGS.config_file)
log_path = os.path.join("log", FLAGS.log_file)
logger = get_logger(log_path)
print_config(config, logger)
with open(FLAGS.necessary, 'rb') as f:
word_to_id, id_to_word, char_to_id, id_to_char, pumsa_to_id, id_to_pumsa, tag_to_id, id_to_tag, ner_morph_tag = pickle.load(
f)
# ner_morph_tag = {"1걸":[0]*15}
embedding_matrix = load_word_embedding_matrix(config, FLAGS.EMBEDDING_PATH,
word_to_id)
if config['elmo']:
# elmo_dict = load_elmo_dict(config["elmo_dict"])
elmo_dict = load_elmo_dict(FLAGS.elmo_dict)
else:
elmo_dict = None
