nlp_xiaojiang/FeatureProject/bert
2019-11-12 19:59:53 +08:00
..
__init__.py bert feature and sim 2019-05-10 10:11:35 +08:00
extract_keras_bert_feature.py fix sim 2019-11-12 19:59:53 +08:00
layers_keras.py Add files via upload 2019-05-10 15:35:46 +08:00
readme.md Update readme.md 2019-05-12 09:12:29 +08:00
tet_bert_keras_sim.py fix sim 2019-11-12 19:59:53 +08:00

BERT

usage:

this bert you need not fine tuning for common target

  • step1:github只上传部分数据前往链接: https://pan.baidu.com/s/1I3vydhmFEQ9nuPG2fDou8Q 提取码: rket download chinese_L-12_H-768_A-12谷歌预训练好的模型 解压到Data/chinese_L-12_H-768_A-12
  • step2-1: 运行 FeatureProject/bert/extract_keras_bert_feature.py then you can get vector of bert encoding
  • step2-2: 运行 FeatureProject/bert/tet_bert_keras_sim.py then you can get sim of bert vector of two sentence and get avg time of run a sentence of encode

thanks