bert编码突袭了NLP各大榜单,为了让大家更方便的在自己的数据集合上测试bert的威力,在此分享一下,keras版本的nert编码层。直接上代码了。
class b_embeding_layer_b(keras.layers.Layer):
"""自定义层"""
def __init__(self, max_seq_len=50,model_dir = r"F:\glove.6B\chinese_L-12_H-768_A-12",mode="word", **kwargs):
self.max_seq_len = max_seq_len
self.model_dir = model_dir
self.mode = mode
super(b_embeding_layer_b, self).__init__(**kwargs)
def build(self, input_shape):
pass
def call(self, x, mask=None):
base_location = 'F:/glove.6B/chinese_L-12_H-768_A-12/'
bert_config = BertConfig.from_json_file(base_location + 'bert_config.json')
init_checkpoint = base_location + 'bert_model.ckpt'
model = BertModel(
config=bert_config,
is_training=True,
input_ids=tf.cast(x[0], tf.int32),
input_mask=tf.cast(x[1], tf.int32),
token_type_ids=tf.cast(x[2], tf.int32),
use_one_hot_embeddings=False)
tvars = tf.trainable_variables()
scaffold_fn = None
(assignment_map, _) = get_assignment_map_from_checkpoint(
tvars, init_checkpoint)
tf.train.init_from_checkpoint(init_checkpoint, assignment_map)
embedding = None
if self.mode == "sent":
embedding = model.get_pooled_output()
if self.mode == "word":
embedding = model.get_sequence_output()
return embedding
def compute_output_shape(self, input_shape):
if self.mode == "word":
return input_shape[0][0], self.max_seq_len,768
if self.mode == "sent":
return input_shape[0][0], 768
def get_config(self):
config = {'mode': self.mode,
"max_seq_len":self.max_seq_len
}
base_config = super(b_embeding_layer_b, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
调用方式,在前面分享的NER模型中有相应内容,在这里不在赘述了。