bert4keras、transformers 加载预训练bert模型、句向量cls，字向量提取；tokenizer使用_bert4keras预训练模型

1、bert4keras

分词器 Tokenizer

from bert4keras.models import build_transformer_model
from bert4keras.tokenizers import Tokenizer
import numpy as np

config_path = '/Users/lonng/Desktop/v+/xl/chinese_L-12_H-768_A-12/bert_config.json'
checkpoint_path = '/Users/lonng/Desktop/v+/xl/chinese_L-12_H-768_A-12/bert_model.ckpt'
dict_path = '/Users/lonng/Desktop/v+/xl/chinese_L-12_H-768_A-12/vocab.txt'

tokenizer = Tokenizer(dict_path, do_lower_case=True)  # 建立分词器
model = build_transformer_model(config_path, checkpoint_path)  # 建立模型，加载权重

# 编码测试
token_ids, segment_ids = tokenizer.encode('语言模型')

print('\n ===== predicting 
1
2
3
4
5
6
7
8
9
10
11
12
13
14