Git Product home page Git Product logo

lizzieyzy's Introduction

LizzieYzy - 围棋引擎界面(中文,English,日本語,한국어)

screenshot

LizzieYzy 是一个引擎界面,修改自Lizzie,可加载围棋引擎:KatagoLeelaZeroLeelaZenGTPSAIPachi以及其他标准GTP引擎。

在Lizzie的基础上增加了一些新功能:鹰眼分析,闪电分析,批量分析,形势判断,棋盘同步,引擎对局,死活题分析,双引擎模式,可视化KataGo分布式训练,以及一些细节修改,可完美支持高分辨率,不会因为系统缩放而显示模糊

  • 新功能

    • 鹰眼分析: 根据AI的选点胜率、计算量、目差,与棋谱中实际落子做比较,得出吻合度,胜率波动,目差波动,失误手等信息并以图表化的形式展示

    • 闪电分析: 使用Katago的analysis模式,并行分析整个棋谱,快速得出胜率图,选点等信息,支持批量分析

    • 批量分析: 支持打包棋谱按顺序使用GTP引擎分析,或使用Katago的analysis模式分析

    • 形式判断: 使用Katago(默认)的kata-raw-nn命令或ZenGTP的territory命令获取粗略的领地判断,支持每一步自动形势判断

    • 棋盘同步(C#): 相关仓库前台(不可移动,遮挡)/后台(不占用鼠标,可遮挡)两种模式,特别优化了野狐、弈城、新浪平台可一键同步,其他平台或图片动画等需框选棋盘(将棋盘选在内即可,比棋盘大很多也没关系),支持双向同步、自动落子(溜狗),采用C#语言,因此只支持Windows

    • 棋盘同步(Java): 相关仓库仅前台,需框选棋盘(选择比棋盘大一些的区域),支持双向同步、自动落子(溜狗)

    • 引擎对局: 两个引擎之间的单盘/多盘对局,可加载多个SGF作为开局,支持使用不同命令获取引擎选点:lz-analyzekata-analyzegenmove,多盘对局将会自动计算elo、标准差区间等信息

    • 死活题分析: 支持抓取局部棋盘上的死活题,并自动生成死活题框架以便AI在正确的范围内思考,详见[菜单]-[分析]-[死活题]以及[抓取死活题],或工具栏的最右侧[死活]按钮

    • 双引擎模式: 支持同时加载两个引擎并同步分析对比

    • 可视化KataGo分布式训练: 将KataGo官方的分布式训练可视化,可以看到每一局正在进行和已经训练完成的对局

LizzieYzy - GUI for Game of Go

screenshot_en

LizzieYzy is a graphical interface modified from Lizzie, allows loading various engines like: KatagoLeelaZeroLeelaZenGTPSAIPachi or other GTP engines.

We have added some new features on Lizzie's basis: Hawk Eye, Flash Analyze, Batch Analyze, Estimate, Board Synchronization(only windows), Engine Game, Tsumego Frame, Double Engine Mode, Visualized KataGo Distributed Training and adjusted some details, supported retina monitor, avoided getting fuzzy by scaled.

  • New features

    • Hawk Eye: Get accuracy, winrate difference, score difference and blunder moves based on the differences between engine candidates and actual moves and display in chart.

    • Flash Analyze: Depend on Katago's analysis mode, analyze all kifus in parallel and get winrate graph candidates rapidly, support batch analyze.

    • Batch Analyze: Support batch analyze kifus by GTP engine or Katago's analysis mode.

    • Estimate: Use Katago(default)'s command:kata-raw-nn or ZenGTP's command territory to get raw territory, support automatically estimate after each move.

    • Board Synchronization(C#): Repository Two mode: foreground(board can't be moved or covered)/backgorund. Special optimizations have been made for FoxWQ、TYGEM、SINA platforms, allowing one-click synchronization, while synchronizing from other platforms or from a picture or gif you need to select the region of the board. Support automatically carrying moves for both sides(developed by C#, only support Windows).

    • Board Synchronization(Java): Repository Foreground only, need to select the region contains the board. Support automatically carrying moves for both sides.

    • Engine Game: Allow a game or multiple games bettween two engines. Support loading some SGF files as opening books. Support various commands:lz-analyze, kata-analyze, genmove to get moves. For multiple games it will automatically calculate some statistics: elo, stdev interval and etc.

    • Tsumego Analysis: Support capture tsumego in part of goban, and automatically generate other part of stones help engine analyze in right area, refer to [Analyze]-[Tsumego frame] or [Capture tsumego] or [Tsumego] button in toolbar.

    • Double Engine Mode: Support loading two engines and analyze synchronously, which is convenient for comparison.

    • Visualized KataGo Distributed Training: Visualized official KataGo training, all games(playing or completed) can be watched.

LizzieYzy - 바둑 엔진용 GUI

screenshot_ko

LizzieYzy는 Lizzie를 기반으로 KatagoLeelaZeroLeelaZenGTPSAIPachi 등의 다른 GTP engine들을 로드할 수 있도록 수정된 그래픽 인터페이스입니다.

Lizzie 기반에 몇 가지 새로운 기능 추가: Hawk Eye, Flash Analyze, Batch Analyze, Estimate, Board Synchronization(only windows), Engine Game, Tsumego Analysis, Double Engine Mode, Visualized KataGo Distributed Training 및 몇몇 세부 사항 조정, 고해상도를 완벽하게 지원하여 시스템 스케일링으로 인해 흐릿하게 표시되지 않습니다.

  • 새로운 기능

    • Hawk Eye: 정확도, 승률 차이, 점수 차이, 엔진 후보 수와 실제 착수의 차이를 기반으로 한 실착수를 찾아서 차트에 표시.

    • Flash Analyze: Katago의 분석 모드를 사용함. 모든 기보를 병렬로 분석. 승률 그래프 후보를 빠르게 획득. 일괄 분석 지원.

    • Batch Analyze: GTP engine 또는 Katago의 분석 모드를 사용한 다수 기보 일괄 분석 지원.

    • Estimate: Katago(기본값)의 kata-raw-nn 명령 또는 ZenGTP의 territory 명령을 사용하여 현재 집 수 계산. 각 착수 후의 집 수 자동 예측을 지원.

    • Board Synchronization(C#): Repository 두 가지 모드: 전경(바둑판을 이동하거나 덮을 수 없음)/배경. FoxWQ, TYGEM, SINA 플랫폼에 최적화. 버튼을 클릭하여 동기화를 허용. 다른 플랫폼이나 사진 또는 착수를 통한 동기화 시 바둑판이 포함된 영역을 선택해야 함. 양방향 자동 착수 전달 지원. C#으로 개발되어서 Windows만 지원.

    • Board Synchronization(Java): Repository 전경 전용. 바둑판이 포함된 영역을 선택해야 함. 양방향 자동 착수 전달 지원.

    • Engine Game: 두 엔진 간의 1회(또는 다회) 대국을 수행. 대국 시작점으로 일부 sgf를 사용할 수 있습니다. 착수를 위한 다양한 명령 지원: lz-analyze, kata-analyze, genmove. 다회 대국시에 몇 가지 통계를 수집합니다: elo, stdev 간격 등.

    • Tsumego Analysis: Support capture tsumego in part of goban, and automatically generate other part of stones help engine analyze in right area, refer to [Analyze]-[Tsumego frame] or [Capture tsumego] or [Tsumego] button in toolbar.

    • Double Engine Mode: 2개 엔진을 로드하여 동시 분석을 지원. 비교에 편리합니다.

    • Visualized KataGo Distributed Training: 시각화된 공식 KataGo 훈련. 모든 대국(진행중이거나 완료된)을 시청할 수 있습니다.

lizzieyzy's People

Contributors

yzyray avatar hope366 avatar wonsiks avatar gro00 avatar awerty-noob avatar zyckk4 avatar

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.