liudicsu's repositories

AllDataPackages

中文、分词、词表、核心词典、事件词表、停用词、敏感词、问答、问答数据、知识图谱、文本语料。

Stargazers:0Issues:0Issues:0
Language:ShellStargazers:0Issues:1Issues:0

ape210k

This is the repository of the Ape210K dataset and baseline models.

Language:PythonStargazers:0Issues:0Issues:0

bert-extractive-summarizer

Easy to use extractive text summarization with BERT

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

chaizi

漢語拆字字典

License:NOASSERTIONStargazers:0Issues:0Issues:0

CheatSheetSeries

The OWASP Cheat Sheet Series was created to provide a concise collection of high value information on specific application security topics.

License:NOASSERTIONStargazers:0Issues:0Issues:0

competition-baseline

数据科学竞赛各种baseline代码、思路分享

License:GPL-3.0Stargazers:0Issues:0Issues:0

couplet-clean-dataset

Chinese Couplets Dataset without vulgar words. 不包含敏感内容的对联数据集。

License:MITStargazers:0Issues:0Issues:0

Crawler_Illegal_Cases_In_China

Collection of China illegal cases about web crawler 本项目用来整理所有**大陆爬虫开发者涉诉与违规相关的新闻、资料与法律法规。致力于帮助在**大陆工作的爬虫行业从业者了解我国相关法律,避免触碰数据合规红线。

Language:HTMLStargazers:0Issues:0Issues:0

fuzzychinese

A small package to fuzzy match chinese words

License:BSD-3-ClauseStargazers:0Issues:0Issues:0

gpt-explorer

GPT-3 Explorer

Language:TypeScriptLicense:NOASSERTIONStargazers:0Issues:0Issues:0

GPT2-Chinese

Chinese version of GPT2 training code, using BERT tokenizer.

License:MITStargazers:0Issues:0Issues:0

GPT2-chitchat

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型

Stargazers:0Issues:0Issues:0

gpt2-ml

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

License:Apache-2.0Stargazers:0Issues:0Issues:0

HanLP

自然语言处理 中文分词 词性标注 命名实体识别 依存句法分析 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁

License:Apache-2.0Stargazers:0Issues:0Issues:0

home-assistant

:house_with_garden: Open source home automation that puts local control and privacy first

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

KnowledgeGraphData

史上最大规模1.4亿中文知识图谱开源下载

Language:PythonStargazers:0Issues:0Issues:0

math_seq2tree

Seq2Tree model for Solving Math Word Problems

License:GPL-3.0Stargazers:0Issues:0Issues:0

milvus

Milvus is an open source vector search engine.

Language:C++License:Apache-2.0Stargazers:0Issues:0Issues:0

Poetry

非常全的古诗词数据,收录了从先秦到现代的共计85万余首古诗词。

License:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

Reading-List

Reading list on deep learning

Stargazers:0Issues:1Issues:0

RLexample

Some basic examples of playing with RL

Language:PythonStargazers:0Issues:0Issues:0

seeprettyface-generator-wanghong

这是一个用StyleGAN训练出的网红脸生成器

Stargazers:0Issues:0Issues:0

sent2vec

General purpose unsupervised sentence representations

Language:C++License:NOASSERTIONStargazers:0Issues:0Issues:0

simbert

a bert for retrieval and generation

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

the-most-complete-dictionary-ever

The most complete Chinese dictionaries ever. 史上最全的中文分类词库,包含地理信息、电子游戏、工程应用、农林牧渔、人文科学、社会科学、生活百科、医学医药、艺术设计、娱乐休闲、运动休闲、自然科学等12大类的超级字典。

Stargazers:0Issues:0Issues:0

TRN-pytorch

Temporal Relation Networks

License:NOASSERTIONStargazers:0Issues:0Issues:0

Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

Language:PythonLicense:LGPL-3.0Stargazers:0Issues:0Issues:0

youtube-dl

Command-line program to download videos from YouTube.com and other video sites

License:UnlicenseStargazers:0Issues:0Issues:0