Giter Site home page Giter Site logo

barryzm's Projects

transformer-xl-chinese icon transformer-xl-chinese

transformer xl在中文文本生成上的尝试(效果意外的好,可写小说、古诗)(transformer xl for text generation of chinese)

transformers icon transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

tsunami-security-scanner icon tsunami-security-scanner

Tsunami is a general purpose network security scanner with an extensible plugin system for detecting high severity vulnerabilities with high confidence.

tt_fund icon tt_fund

天天基金网爬虫:北向资金、基金每日净值涨跌、大盘涨跌、基金公司信息

ttbot icon ttbot

今日头条机器人,支持用户登陆、关注、取消关注、获取关注粉丝、发文、发悟空问答、点赞、评论、采集各种类型新闻讯息等,使用今日头条网页版API实现

two icon two

😏随机一句「中二」的台词!

uda icon uda

Unsupervised Data Augmentation (UDA)

uvloger icon uvloger

基于深度学习的视频配乐自动剪辑系统

v9porn icon v9porn

9*Porn Android 客户端,突破游客每天观看10次视频的限制,还可以下载视频

vecstack icon vecstack

Python package for stacking (machine learning technique)

video-editing-auxiliary-tool-based-on-barrage-analysis- icon video-editing-auxiliary-tool-based-on-barrage-analysis-

原理是这样子的: 假设观众的弹幕是大众趣味的正确反馈,在精彩时刻就会有大量特定弹幕, 那么可以反向通过统计一段时间内特定弹幕的数量,来识别出一个长视频中受欢迎的部分。 统计是通过输入关键词来进行的,例如对于特别有趣的片段,观众倾向于发送“草”这一弹幕。 假设在一段时间内,草的弹幕超出了预设的限制(limit),工具应当记下该时间轴,并提供给剪辑者一个参考时间轴。 在一段时间内,由于网络延迟的问题,弹幕的出现不是同步的, 观众见证一个亮点时刻时,作为反应的弹幕也会分散在数秒之中。 因此将统计的范围放到当前时刻开始的5秒之内。只要总计的弹幕达到了阈值(limit) 就记下当前时刻,并且从20秒间隔(interval)后重新开始新一轮判定。 若当前时刻并不达标,将当前时间往后推进1秒。 之所以设置了20秒的冷却间隔(interval),是为了减少重复记轴—— 精彩镜头从来不是瞬间,而是从某个时间点开始的时间段 如果不设置冷却时间,那么相邻的数秒都会被纳入统计。 这样输出的数个结果的参考意义是很有限的。 统计开始容易,统计结束位置很难,但是结束位置可以人为判断,未必要越厨代庖。 因此这个工具旨在提供一个“精彩片段的开始大致时间”, 给剪辑者、补长视频的观众作为跳转参考。 这样一来工具的运行时间也能一定程度上减少。

video_analyst icon video_analyst

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

videoauidt icon videoauidt

:video_camera: minitrill 视频审核模块(一个短视频app视频审核的思路及实现汇总)

videocaption icon videocaption

视频的文本摘要(标注),输入一段视频,通过深度学习网络和人工智能程序识别视频主要表达的意思(Input a video output a txt decribing the video)。

vits_chinese icon vits_chinese

vits chinese, tts chinese, tts mandarin 史上训练最简单,音质最好的语音合成系统,兼容性非常好的合成框架

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.