NLP/nlp_xiaojiang
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update readme.md

Browse Source
This commit is contained in:
yongzhuo 2019-05-10 16:42:27 +08:00 committed by GitHub
parent af0a8d7a7c
commit 74fafb1e1e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
FeatureProject/bert/readme.md
View File

@ -3,14 +3,14 @@
# usage:
this bert you need not fine tuning for common target
step1:github项目中只是上传部分数据，需要的前往链接: 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
* step1:github项目中只是上传部分数据，需要的前往链接: 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
* 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