def create_crf_model(bert_config, is_training, input_ids, input_mask, segment_ids, labels, num_labels, use_one_hot_embeddings):
"""
create model
:param bert_config: bert config
:param is_training:
:param input_ids: idx of input data
:param input_mask:
:param segment_ids:
:param labels: idx of labels
:param num_labels: type of labels
:param use_one_hot_embeddings:
:return:
"""
# representation
model = modeling.BertModel(
config=bert_config,
is_training=is_training,
input_ids=input_ids,
input_mask=input_mask,
token_type_ids=segment_ids,
use_one_hot_embeddings=use_one_hot_embeddings
)
embedding = model.get_sequence_output()
max_seq_length = embedding.shape[1].value
used = tf.sign(tf.abs(input_ids))
lengths = tf.reduce_sum(used, reduction_indices=1)
crf = CRF(embedded_chars=embedding,droupout_rate=0.5,initializers=initializers, num_labels=num_labels,
seq_length=max_seq_length, labels=labels, lengths=lengths,
is_training=is_training)
(total_loss, logits, trans, pred_ids) = crf.add_crf_layer()
return (total_loss, logits, trans, pred_ids)
def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
labels, num_labels, use_one_hot_embeddings):
"""
创建X模型
:param bert_config: bert 配置
:param is_training:
:param input_ids: 数据的idx 表示
:param input_mask:
:param segment_ids:
:param labels: 标签的idx 表示
:param num_labels: 类别数量
:param use_one_hot_embeddings:
:return:
"""
# 使用数据加载BertModel,获取对应的字embedding
model = modeling.BertModel(config=bert_config,
is_training=is_training,
input_ids=input_ids,
input_mask=input_mask,
token_type_ids=segment_ids,
use_one_hot_embeddings=use_one_hot_embeddings)
# 获取对应的embedding 输入数据[batch_size, seq_length, embedding_size]
embedding = model.get_sequence_output()
max_seq_length = embedding.shape[1].value
used = tf.sign(tf.abs(input_ids))
lengths = tf.reduce_sum(
used, reduction_indices=1) # [batch_size] 大小的向量，包含了当前batch中的序列长度
blstm_crf = CRF(embedded_chars=embedding,
hidden_unit=FLAGS.lstm_size,
cell_type=FLAGS.cell,
num_layers=FLAGS.num_layers,
droupout_rate=FLAGS.droupout_rate,
initializers=initializers,
num_labels=num_labels,
seq_length=max_seq_length,
labels=labels,
lengths=lengths,
is_training=is_training)
rst = blstm_crf.add_crf_layer()
return rst
def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
labels, num_labels, use_one_hot_embeddings):
"""
create model
:param bert_config: bert cofig
:param is_training:
:param input_ids: idx of data
:param input_mask:
:param segment_ids:
:param labels: idx of label
:param num_labels: number of categories
:param use_one_hot_embeddings:
:return:
"""
# load BertModel, and acuqire the corresponding embedding
model = modeling.BertModel(config=bert_config,
is_training=is_training,
input_ids=input_ids,
input_mask=input_mask,
token_type_ids=segment_ids,
use_one_hot_embeddings=use_one_hot_embeddings)
# acuqire the corresponding embedding
embedding = model.get_sequence_output()
max_seq_length = embedding.shape[1].value
used = tf.sign(tf.abs(input_ids))
lengths = tf.reduce_sum(used, reduction_indices=1) # [batch_size]
crf = CRF(embedded_chars=embedding,
droupout_rate=FLAGS.droupout_rate,
initializers=initializers,
num_labels=num_labels,
seq_length=max_seq_length,
labels=labels,
lengths=lengths,
is_training=is_training)
rst = crf.add_crf_layer()
return rst
