##### 运行此脚本
export BERT_BASE_DIR = ./chinese_L-12_H-768_A-12 ## 模型地址
exprot Data_Dir = ./data
python bert-master/extract_features.py \
--input_file=$Data_Dir/train_ch.txt \
--output_file=$Data_dir/output.json \
--vocab_file=$BERT_BASE_DIR/vocab.txt \
--bert_config_file=$BERT_BASE_DIR/bert_config.json \
--init_checkpoint=$BERT_BASE_DIR/bert_model.ckpt \
--layers=-1,-2,-3,-4 \
--max_seq_length=128 \
--batch_size=8
{"linex_index": 0, "features":[{"token": "[CLS]", "layers": [{"index": -1, "values":[-0.919886, 0.656876, -0.58464654]}]}]}
import re
import json
src = ‘‘
tgt = ‘‘
def fun(file1,file2):
with open(file1,‘r‘,encoding=‘utf-8‘) as fl1:
with open(file2,‘w‘,encoding=‘utf-8‘) as fl2:
k=0
for line in fl1.readlines():
k+=1
line = json.loads(line)
temp = line.get(‘features‘)
temp = temp[1]
temp = temp.get(‘layers‘)
temp = temp[1]
temp = temp.get("values")
fl2.write(str(temp)+‘\n‘+‘\n‘) ## 好看一些
if k%1000==0:
print("Done"+‘ ‘+str(k))
fun(src,tgt)
原文:https://www.cnblogs.com/hanouba/p/11912107.html