KataGo
KataGo copied to clipboard
lightvector
GTP engine and self-play learning in Go
I leave this here FYI, maybe this is helpful. I managed to run KataGo on rasberry pi 4 inside a docker container using [this approach](https://github.com/miliar/saiboard/blob/main/software/backend/katago/Dockerfile_rasp) This is the output of...
When using the katago analysis engine, I attempt to set the `allowMoves` field (and I set the untilDepth field to 1000000000). However, I find that sometimes the engine will generate...
Why is katago on an 11 way board, where the thread count only goes up to 60 max, and then it doesn't analyze when it's cranked up further
I am currently using an older version of KataGo, and when running larger networks such as b40 or b60, they are clearly stronger and more reliable at high playouts than...
I'm trying to use Katago with a GPU to find very interesting / clever moves and games played by pros (or even Katago). One approach is to search through modern...
I know that GPU is more important than CPU for Katago performance. But, I'm curious if there is a performance decrease when using a low-end CPU with High-end GPU. ex)...
When I use the "analyse" sub-command to analyse the current board state, I find that the whiteOwnerMap looks like the result that AI has make a next move. However, what...
I analyzed a game by Katago. Kata-genmove_analyze B ownership true = info move A1 .... ...... ownership ...... play B1 What is different from A1 and B1? The game was...
I tested 400 games at 1000 maxplayouts 7.5 komi between two identical versions of Katago 1.12 running TensorRT using LizzieYZY GUI on a 4 GPUs system I noticed from task...
