Page 19 of 34
Re: KataGo Distributed Training and new networks
Posted: Fri Nov 25, 2022 4:02 pm
by hope366
If anyone has a CUDA version of KataGo for the new architecture, could you please upload it?
I tried to compile using cmake before, but it didn't work in my environment.
Re: KataGo Distributed Training and new networks
Posted: Fri Nov 25, 2022 4:16 pm
by And
and the version of eigenavx2 for Windows please!
Re: KataGo Distributed Training and new networks
Posted: Fri Nov 25, 2022 10:24 pm
by And
KataGo 18b, playouts 10 - 60b, playouts 10
Re: KataGo Distributed Training and new networks
Posted: Sat Nov 26, 2022 4:43 am
by And
PC_Screen wrote:Katago Eigen, same process, drop it inside the katago 1.11 eigen folder and replace the old katago.exe.
https://drive.google.com/file/d/18XJHc8 ... sp=sharing
As for the speed being lower, try running the benchmark in the command prompt (./katago.exe benchmark -model <NEURALNET>.bin.gz) and adjust the number of search threads based on it
many thanks! it works, with different networks, and 18b works. but the speed compared to eigen, eigenavx2 1.11.0 is tens times slower. something's wrong.
visits: 1
10b eigen 1.11 Time taken: 0.281
10b your file Time taken: 15.21
60b eigen 1.11 Time taken: 2.605
60b your file Time taken: 160.166
18b your file Time taken: 56.941
Re: KataGo Distributed Training and new networks
Posted: Sat Nov 26, 2022 10:05 am
by And
second game KataGo 18b, playouts 10 - 60b, playouts 10
(60b-s665)
Re: KataGo Distributed Training and new networks
Posted: Sat Nov 26, 2022 8:13 pm
by And
KataGo 18b, playouts 100 - CS Zero 9d H4
Re: KataGo Distributed Training and new networks
Posted: Sun Nov 27, 2022 8:16 am
by And
KataGo 18b, playouts 100 - CS Zero 9d H5
after 347 moves CS Zero: winrate 64.3, B+32
Re: KataGo Distributed Training and new networks
Posted: Sun Nov 27, 2022 6:23 pm
by PC_Screen
New KataGo 18b out, supposed to as strong as 60b at equal visits while also being faster than 40b, which means it should be stronger than both in an actual game.
https://cdn.discordapp.com/attachments/ ... 21b.bin.gz
Also test game: KataGo 1.11 18b (W) vs KataGo 1.3.5 40b (B) with 2H and 0.5 Komi, Japanese Rules. The time setting is 10s/move for both which gave them around 1-2k visits per move on average.
The new 18b KataGo managed a convincing win against a 2 year old KataGo despite the 2 handicap stones.
Re: KataGo Distributed Training and new networks
Posted: Sun Nov 27, 2022 6:27 pm
by And
"UEC finished this weekend...KataGo placed 2nd in the final (and first in the preliminaries)."
https://discord.com/channels/4170221623 ... 4930181303
Re: KataGo Distributed Training and new networks
Posted: Mon Nov 28, 2022 12:47 pm
by And
KataGo (18b-uec, playouts 1) - CS Zero 9d
Re: KataGo Distributed Training and new networks
Posted: Mon Nov 28, 2022 9:37 pm
by And
100 games 19x19 KataGo 18b-uec (playouts 1) - 60b-s665 (playouts 1):
18b (B) - 60b (W) 21:29
18b (W) - 60b (B) 26:24
Re: KataGo Distributed Training and new networks
Posted: Tue Nov 29, 2022 12:05 am
by And
100 games 19x19 KataGo 18b-uec (playouts 2) - 60b-s665 (playouts 1):
18b (B) - 60b (W) 32:18
18b (W) - 60b (B) 35:15
Re: KataGo Distributed Training and new networks
Posted: Tue Nov 29, 2022 6:32 am
by And
10 games KataGo 18b-uec (playouts 10) - 60b-s665 (playouts 5):
18b (W) - 60b (B) 8:2
Re: KataGo Distributed Training and new networks
Posted: Tue Nov 29, 2022 10:52 am
by And
10 games KataGo 18b-uec (playouts 10) - 60b-s665 (playouts 5):
18b (B) - 60b (W) 9:1
Re: KataGo Distributed Training and new networks
Posted: Tue Nov 29, 2022 11:28 am
by And
in the position from here
viewtopic.php?p=244851#p244851, I turned on the analysis mode, the network 18b-uec. the move h1 was immediately highlighted. after ~200 visits, katago showed white winning, but then decided that there no winning and the winrate continued to fall
EDIT after 10K visits - 39.4
$$Wc White to play
$$ ---------------------------------------
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . X . . . . . . . . . |
$$ | . X O O . . . X X O X X X . X X X . . |
$$ | . . X , O . O X O O . O . . . O X O . |
$$ | . X . X X X O O X O . . . . . . . . . |
$$ | . . O . . . O . X O . . X . . . O . . |
$$ | . . . . . O . . X . O O X . . O . . . |
$$ | . . X . . . O X X X O X X . X O . . . |
$$ | . . . . . . O O X O O X . O . X O . . |
$$ | . . . , . . O O O X X O . . . X O . . |
$$ | . . . . . . X O O X . O . . . X . . . |
$$ | . . O . . X . X X X O . . . . . X . . |
$$ | . . . . . X O . . X . . . . . . . . . |
$$ | . . . X . X O O O X . . . . . . . . . |
$$ | . . X O X X X O X O . O . . . . O . . |
$$ | . . O O O . X O X O . . . O . O . O . |
$$ | . . . O . O O X X O . . X X X X O X . |
$$ | . . . . . . X . . . . . . . . . X . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ ---------------------------------------
- Click Here To Show Diagram Code
[go]$$Wc White to play
$$ ---------------------------------------
$$ | . . . . . . . . . . . . . . . . . . . |
$$ | . . . . . . O . . X . . . . . . . . . |
$$ | . X O O . . . X X O X X X . X X X . . |
$$ | . . X , O . O X O O . O . . . O X O . |
$$ | . X . X X X O O X O . . . . . . . . . |
$$ | . . O . . . O . X O . . X . . . O . . |
$$ | . . . . . O . . X . O O X . . O . . . |
$$ | . . X . . . O X X X O X X . X O . . . |
$$ | . . . . . . O O X O O X . O . X O . . |
$$ | . . . , . . O O O X X O . . . X O . . |
$$ | . . . . . . X O O X . O . . . X . . . |
$$ | . . O . . X . X X X O . . . . . X . . |
$$ | . . . . . X O . . X . . . . . . . . . |
$$ | . . . X . X O O O X . . . . . . . . . |
$$ | . . X O X X X O X O . O . . . . O . . |
$$ | . . O O O . X O X O . . . O . O . O . |
$$ | . . . O . O O X X O . . X X X X O X . |
$$ | . . . . . . X . . . . . . . . . X . . |
$$ | . . . . . . . . . . . . . . . . . . . |
$$ ---------------------------------------[/go]