keras-bert:BERT的实现可以加载官方的预训练模型以进行特征提取和预测-源码
凯拉斯·伯特
[| ]
实现。 可以加载官方的预训练模型以进行特征提取和预测。
安装
pip install keras-bert
用法
使用热身
下载预先训练的检查点
提取功能
外部链接
Kashgari是可用于文本标签和文本分类的生产就绪NLP转移学习框架
凯拉斯·阿尔伯特
加载官方预训练模型
在特征提取演示中，您应该能够获得与官方模型chinese_L-12_H-768_A-12相同的提取结果。 并且在预测演示中，可以预测句子中丢失的单词。
在TPU上运行
提取演示演示了如何转换为在TPU上运行的模型。
分类演示显示了如何将模型应用于简单的分类任务。
分词器
Tokenizer类用于拆分文本并生成索引：
from keras_bert import Tokenizer
token_dict = {
'[CLS]' : 0 ,
'[SEP]' : 1
文件下载
资源详情
[{"title":"（ 70 个子文件 1.22MB ） keras-bert:BERT的实现可以加载官方的预训练模型以进行特征提取和预测-源码","children":[{"title":"keras-bert-master","children":[{"title":"MANIFEST.in <span style='color:#111;'> 88B </span>","children":null,"spread":false},{"title":".github","children":[{"title":"stale.yml <span style='color:#111;'> 36B </span>","children":null,"spread":false},{"title":"ISSUE_TEMPLATE","children":[{"title":"bug_report.md <span style='color:#111;'> 310B </span>","children":null,"spread":false},{"title":"question.md <span style='color:#111;'> 103B </span>","children":null,"spread":false},{"title":"feature_request.md <span style='color:#111;'> 610B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"keras_bert","children":[{"title":"tokenizer.py <span style='color:#111;'> 11.03KB </span>","children":null,"spread":false},{"title":"util.py <span style='color:#111;'> 5.92KB </span>","children":null,"spread":false},{"title":"layers","children":[{"title":"inputs.py <span style='color:#111;'> 355B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 273B </span>","children":null,"spread":false},{"title":"task_embed.py <span style='color:#111;'> 3.20KB </span>","children":null,"spread":false},{"title":"embedding.py <span style='color:#111;'> 3.69KB </span>","children":null,"spread":false},{"title":"pooling.py <span style='color:#111;'> 550B </span>","children":null,"spread":false},{"title":"masked.py <span style='color:#111;'> 1.36KB </span>","children":null,"spread":false},{"title":"conv.py <span style='color:#111;'> 674B </span>","children":null,"spread":false},{"title":"extract.py <span style='color:#111;'> 660B </span>","children":null,"spread":false}],"spread":true},{"title":"backend.py <span style='color:#111;'> 890B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 169B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"__init__.py <span style='color:#111;'> 26B </span>","children":null,"spread":false},{"title":"pretrained.py <span style='color:#111;'> 1.72KB </span>","children":null,"spread":false}],"spread":true},{"title":"bert.py <span style='color:#111;'> 11.72KB </span>","children":null,"spread":false},{"title":"loader.py <span style='color:#111;'> 7.74KB </span>","children":null,"spread":false},{"title":"optimizers","children":[{"title":"util.py <span style='color:#111;'> 718B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 20B </span>","children":null,"spread":false},{"title":"warmup_v2.py <span style='color:#111;'> 7.66KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"requirements-dev.txt <span style='color:#111;'> 83B </span>","children":null,"spread":false},{"title":"README.zh-CN.md <span style='color:#111;'> 10.41KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 45B </span>","children":null,"spread":false},{"title":"publish.sh <span style='color:#111;'> 83B </span>","children":null,"spread":false},{"title":"demo","children":[{"title":"load_model","children":[{"title":"load_and_extract.py <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"load_and_get_attention_map.py <span style='color:#111;'> 1.13KB </span>","children":null,"spread":false},{"title":"load_and_predict.py <span style='color:#111;'> 2.17KB </span>","children":null,"spread":false},{"title":"keras_bert_load_and_extract_tpu.ipynb <span style='color:#111;'> 11.88KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"keras_bert_load_and_predict.ipynb <span style='color:#111;'> 44.03KB </span>","children":null,"spread":false},{"title":"load_and_pool.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"keras_bert_load_and_extract.ipynb <span style='color:#111;'> 38.04KB </span>","children":null,"spread":false}],"spread":true},{"title":"tune","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"keras_bert_classification_tpu.ipynb <span style='color:#111;'> 13.67KB </span>","children":null,"spread":false}],"spread":true},{"title":"visualization","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"vis.py <span style='color:#111;'> 1.22KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":".travis.yml <span style='color:#111;'> 897B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"test.sh <span style='color:#111;'> 211B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 1.33KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 7.69KB </span>","children":null,"spread":false},{"title":"tests","children":[{"title":"test_tokenizer.py <span style='color:#111;'> 3.79KB </span>","children":null,"spread":false},{"title":"layers","children":[{"title":"test_pooling.py <span style='color:#111;'> 1.66KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"test_conv.py <span style='color:#111;'> 1.07KB </span>","children":null,"spread":false},{"title":"test_embedding.py <span style='color:#111;'> 1.02KB </span>","children":null,"spread":false},{"title":"test_masked.py <span style='color:#111;'> 3.49KB </span>","children":null,"spread":false},{"title":"test_extract.py <span style='color:#111;'> 942B </span>","children":null,"spread":false},{"title":"test_task_embed.py <span style='color:#111;'> 747B </span>","children":null,"spread":false},{"title":"test_inputs.py <span style='color:#111;'> 257B </span>","children":null,"spread":false}],"spread":false},{"title":"test_util.py <span style='color:#111;'> 4.07KB </span>","children":null,"spread":false},{"title":"test_loader.py <span style='color:#111;'> 3.13KB </span>","children":null,"spread":false},{"title":"test_checkpoint","children":[{"title":"bert_config.json <span style='color:#111;'> 490B </span>","children":null,"spread":false},{"title":"bert_model.ckpt.meta <span style='color:#111;'> 847.44KB </span>","children":null,"spread":false},{"title":"bert_model.ckpt.index <span style='color:#111;'> 4.39KB </span>","children":null,"spread":false},{"title":"vocab.txt <span style='color:#111;'> 73B </span>","children":null,"spread":false},{"title":"bert_model.ckpt.data-00000-of-00001 <span style='color:#111;'> 8.22KB </span>","children":null,"spread":false}],"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"test_bert.py <span style='color:#111;'> 4.86KB </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"test_get_pretrained.py <span style='color:#111;'> 304B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":false},{"title":"test_bert_fit.h5 <span style='color:#111;'> 1.65MB </span>","children":null,"spread":false},{"title":"optimizers","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"test_warmup.py <span style='color:#111;'> 2.89KB </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":".gitignore <span style='color:#111;'> 1.25KB </span>","children":null,"spread":false},{"title":"CHANGELOG.md <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- OrcaFlex 说明书
- testlink使用教程
- VISIO素材库（IBM完全版）
- RBF网络simulink程序
- 正点原子STM32F407 AD封装库
- Pyqt5 Qpainter绘制基础图形.doc
- ip数据包捕获程序设计实验 mfc
- web大作业.rar
- ssm的网上商城项目
- 使用3D RC网络建模异质材料中的介电响应
- 鼠标右键管理工具.zip
- Unreal-4.22-SetAnimInstanceClassFix：一种变通办法插件，可修复Unreal 4.22中的崩溃-源码
- trans 翻译前端
- 华南理工《编译原理》2020期末试题.pdf
- VB毕业论文：学生成绩及考评管理系统 答辩PPT.rar
- 票务系统架构设计案例分析
- 毕业设计完整版纺织外贸订单管理系统
- 山东省行政区划图
- 《Python进阶》中文版 pdf
- 微信小程序-后台搭建源码
- TCP与串口间的通信方式。Socket通信
- 适用于嵌入式的AES128加密（耗内存极小）
- ValidateCode.jar
- poi 解析excel生成html
- doxygen中文手册
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明