wh20's repositories
GenIR-Survey
This is the repository for the GenIR survey.
KungFuHeroSimulator
武林英雄模拟器
Contrastive_Learning_Papers
A list of contrastive Learning papers
gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
entmax
The entmax mapping and its loss, a family of sparse softmax alternatives.
learn2018-autodown
清华大学新版网络学堂课程自动下载脚本 / A python script to clone all files from learn.tsinghua.edu.cn
resume
Software developer resume in Latex
building_KG
利用注释,构建唐诗知识图谱。
classification_GAT
用唐诗知识图谱、带标签的诗词作输入 2层GAT+attention 唐诗题材分类 Tensorflow框架
Historical-ranking-data-visualization-based-on-d3.js
这是一个数据可视化项目,能够将历史数据排名转化为动态柱状图图表
bert
TensorFlow code and pre-trained models for BERT
Tsinghua-CourseSpider
用于清华大学选课系统的爬虫及基于MS Excel的选课工具
os_course_exercises
Exercises for OS course
gvr-android-sdk
Google VR SDK for Android
ucore_os_docs
ucore os lab guide
ucore_os_lab
os kernel labs for operating systems course in Tsinghua University.
wechat_spider
微信爬虫,获取文章阅读量、点赞量、评论等,获取公众号所有历史文章链接。
daizhigev20
殆知阁古代文献
FLY_US
美国大学备考资料 How to apply US colleges
ClassHelper
清华选课助手
pyspider
知乎爬虫和v2ex爬虫的实现。使用python的pyspider爬虫进行开发,主要爬取知乎的问题和评论,以及v2ex的帖子。数据转储到mysql数据库,用于zhihu项目的使用。
MachineLearning
Basic Machine Learning and Deep Learning
OOPLRS
OOP狼人杀
weibo-spider
新浪微博爬虫,采用Java语言开发,基于HTTPClient 4.0,采用MySQL存储爬取数据,支持多进程并发执行。功能包括:爬取微博、评论、转发、关注列表(层次)。根据数据需求,持续更新...