Thanks! Using isready made it work. nn.bin was in the eval folder, just suggested maybe easier for users to default location to engine directory.cdani wrote: ↑Fri Jun 26, 2020 9:31 amPut the net in "eval" folder under the folder of the engine, or change the EvalDir parameter.JohnS wrote: ↑Fri Jun 26, 2020 7:32 am Trying to understand this but not much luck so far.
I run sf-nnue run (halfkp-256x2-32-32) x64-bmi2 from the command line and then used
go depth 20
The engine just stopped after some time without any output, is this expected.
Suggestion - allow nn.bin to be in same directory as the exe, this seems simpler to me for using the engine.
What happens if nn.bin is missing, is it just normal stockfish.
Also you need to send an
isready
command
for the engine to load the eval file.
My strongest NNUE net (yet)
Moderators: hgm, Rebel, chrisw
-
- Posts: 215
- Joined: Sun Feb 24, 2008 2:08 am
Re: My strongest NNUE net (yet)
-
- Posts: 50
- Joined: Tue Jul 19, 2016 10:19 am
Re: My strongest NNUE net (yet)
What does option SkipLoadingEval do?
Kind regards.
Antonio
Kind regards.
Antonio
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
Re: My strongest NNUE net (yet)
The binaries we use have the learning function still in them.thunderstruck wrote: ↑Fri Jun 26, 2020 9:09 pm What does option SkipLoadingEval do?
Kind regards.
Antonio
Skiploadingeval is used when we want to train a net from scratch.
If you use it to play a game it plays like Stockfish without an evaluation function.
You can also download binaries without the learn fuction:
https://github.com/nodchip/Stockfish/releases
Those won't have the "skiploadingeval" option.
They're smaller in size, but otherwise play identical.
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
Re: My strongest NNUE net (yet)
I've updated the net again:cdani wrote: ↑Thu Jun 25, 2020 12:43 am Problably new best net, also from Gekkehenker:Here the net:Code: Select all
40+0.3 # PLAYER : RATING ERROR POINTS PLAYED (%) 1 stnnuegk2 : 2860.6 3.9 930.5 1814 51.3% 2 stnnuegk1 : 2851.4 3.9 883.5 1814 48.7%
https://cdn.discordapp.com/attachments/ ... 24_june.7z
Thanks to Gekkehenker and also to the community that is helping to improve this engine bit a bit!
Tested +25 +/-8 elo vs stnnuegk2 after 2000 games.
TC:10s+0.1s. 1 thread. Slowmover 50 for both
-
- Posts: 2204
- Joined: Sat Jan 18, 2014 10:24 am
- Location: Andorra
Re: My strongest NNUE net (yet)
Thanks.
I have done two tests:
Code: Select all
40 seconds + 0.3 against previous version:
# PLAYER : RATING ERROR POINTS PLAYED (%)
1 stnnuegk3 : 2863.5 4.9 650.5 1248 52.1%
2 stnnuegk2 : 2848.5 4.9 597.5 1248 47.9%
200 seconds + 1 against same version of Stockfish that I used previously:
# PLAYER : RATING ERROR POINTS PLAYED (%)
1 st200617 : 2882.2 6.7 377.0 657 57.4%
2 stnnuegk3 : 2829.8 6.7 280.0 657 42.6%
Daniel José - http://www.andscacs.com