sabaki配置katago

https://github.com/lightvector/KataGo

最新版本是katago-v1.12.3-opencl-windows-x64   【2023-02-10】

打开命令,先切换到目录C:\workspace\KaTrainWindows-1.9.2\KaTrain\katrain\KataGo,然后执行命令

Run this command to have KataGo generate a custom gtp config for you based on answering some questions:

./katago.exe genconfig -model <NEURALNET>.bin.gz -output gtp_custom.cfg

 

C:\workspace\KaTrainWindows-1.9.2\KaTrain\katrain\KataGo>katago.exe genconfig -model ../models/g170e-b15c192-s1672170752-d466197061.bin.gz -output gtp_custom.cfg

执行配置命令,然后按照提示,进行配置

=========================================================================
RULES

What rules should KataGo use by default for play and analysis?
(chinese, japanese, korean, tromp-taylor, aga, chinese-ogs, new-zealand, bga, stone-scoring, aga-button):
chinese

=========================================================================
SEARCH LIMITS

When playing games, KataGo will always obey the time controls given by the GUI/tournament/match/online server.
But you can specify an additional limit to make KataGo move much faster. This does NOT affect analysis/review,
only affects playing games. Add a limit? (y/n) (default n):

 

NOTE: No limits configured for KataGo. KataGo will obey time controls provided by the GUI or server or match script
but if they don't specify any, when playing games KataGo may think forever without moving. (press enter to continue)


When playing games, KataGo can optionally ponder during the opponent's turn. This gives faster/stronger play
in real games but should NOT be enabled if you are running tests with fixed limits (pondering may exceed those
limits), or to avoid stealing the opponent's compute time when testing two bots on the same machine.
Enable pondering? (y/n, default n):

 

=========================================================================
GPUS AND RAM

Finding available GPU-like devices...
Found OpenCL Device 0: Intel(R) HD Graphics 530 (Intel(R) Corporation) (score 6000300)

Specify devices/GPUs to use (for example "0,1,2" to use devices 0, 1, and 2). Leave blank for a default SINGLE-GPU config:

 

 

Based on some test data, each speed doubling gains perhaps ~250 Elo by searching deeper.
Based on some test data, each thread costs perhaps 7 Elo if using 800 visits, and 2 Elo if using 5000 visits (by making MCTS worse).
So APPROXIMATELY based on this benchmark, if you intend to do a 5 second search:
numSearchThreads = 3: (baseline)
numSearchThreads = 5: +36 Elo
numSearchThreads = 6: +59 Elo
numSearchThreads = 8: +64 Elo
numSearchThreads = 10: +81 Elo (recommended)
numSearchThreads = 12: +28 Elo

Using 10 numSearchThreads!
2021-07-10 18:12:31+0800: GPU 0 finishing, processed 14038 rows 4164 batches

=========================================================================
DONE

Writing new config file to gtp_custom.cfg
You should be now able to run KataGo with this config via something like:
katago.exe gtp -model '../models/g170e-b15c192-s1672170752-d466197061.bin.gz' -config 'gtp_custom.cfg'

Feel free to look at and edit the above config file further by hand in a txt editor.
For more detailed notes about performance and what options in the config do, see:
https://github.com/lightvector/KataGo/blob/master/cpp/configs/gtp_example.cfg

 

作者:Chuck Lu    GitHub    
posted @   ChuckLu  阅读(1446)  评论(0编辑  收藏  举报
编辑推荐:
· 记一次.NET内存居高不下排查解决与启示
· 探究高空视频全景AR技术的实现原理
· 理解Rust引用及其生命周期标识(上)
· 浏览器原生「磁吸」效果!Anchor Positioning 锚点定位神器解析
· 没有源码,如何修改代码逻辑?
阅读排行:
· 全程不用写代码,我用AI程序员写了一个飞机大战
· DeepSeek 开源周回顾「GitHub 热点速览」
· MongoDB 8.0这个新功能碉堡了,比商业数据库还牛
· 记一次.NET内存居高不下排查解决与启示
· 白话解读 Dapr 1.15:你的「微服务管家」又秀新绝活了
历史上的今天:
2020-07-10 FlagsAttribute Class
2020-07-10 serilog Debugging and Diagnostics
2020-07-10 Configuration error of serilog
2020-07-10 Serilog settings appsetting 配置的加载
2020-07-10 Kibana Query Language
2019-07-10 your current language level is ecmascript 5
2019-07-10 How to correctly use preventDefault(), stopPropagation(), or return false; on events
点击右上角即可分享
微信分享提示