It is now easily possible to use any pgn as training data! First, use this pgn-extract command: pgn-extract: pgn-extract --fencomments -Wlalg --nochecks --nomovenumbers --noresults -w500000 -N -V -o output_file_name input_file_name
and then: learn convert_bin_from_pgn-extract output_file_name output_file_name input_file_name
Use this binary (bmi2) with the latest commit from nodchip/ttak (current release doesn't have that change last time I checked): https://cdn.discordapp.com/attachments/ ... ev_blas.7z
Stockfish NN release (NNUE)
Moderators: hgm, Rebel, chrisw
-
- Posts: 154
- Joined: Sun Jan 20, 2019 11:23 am
- Full name: kek w
-
- Posts: 364
- Joined: Mon May 14, 2007 8:20 pm
- Full name: Boban Stanojević
Re: Stockfish NN release (NNUE)
Guys, I just want to thank you for this interesting project! I think it is the right way to go in engines' development.
Re: Stockfish NN release (NNUE)
There's a guy on Leela Discord who generated 1 million Stockfish v Leela games for NN training. So these too could be used for NNUE and maybe produce a better result than using SF games or leela games alone.
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
Re: Stockfish NN release (NNUE)
where is the discord link ?
-
- Posts: 2129
- Joined: Thu May 29, 2008 10:43 am
Re: Stockfish NN release (NNUE)
Is that the one you want?
https://discord.com/channels/4359437104 ... 6266188890
It's for Stockfish-NNUE (not Leela)
https://discord.com/channels/4359437104 ... 6266188890
It's for Stockfish-NNUE (not Leela)
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
Re: Stockfish NN release (NNUE)
yes thats it thx
-
- Posts: 364
- Joined: Mon May 14, 2007 8:20 pm
- Full name: Boban Stanojević
Re: Stockfish NN release (NNUE)
Norm,
You uploaded popc binaries on the 26th, 27th and 29th of this month. But something is strange: the binaries from the 27th are three times faster than the binaries from the other days on my laptop.
You uploaded popc binaries on the 26th, 27th and 29th of this month. But something is strange: the binaries from the 27th are three times faster than the binaries from the other days on my laptop.
-
- Posts: 2129
- Joined: Thu May 29, 2008 10:43 am
Re: Stockfish NN release (NNUE)
yes, strange..
If you're using bench
I believe I did read somewhere (nnue discord?) from the author, that bench is not reliable/functional in this implementation.
I'll try to verify.
Thanks Boban
-
- Posts: 2129
- Joined: Thu May 29, 2008 10:43 am
Re: Stockfish NN release (NNUE)
Thanks, I found the issue.
I'll upload new binaries soon.
-
- Posts: 364
- Joined: Mon May 14, 2007 8:20 pm
- Full name: Boban Stanojević
Re: Stockfish NN release (NNUE)
Norm, I am not using bench: you know that it is too complicated for me. I was surprised when I noticed a surge in performance with the new binaries, two days ago -- on my old AMD A8, SF is achieves 550kn/s, the binaries from the 26th were ten times slower, about 53kn/s, and those of the 27th were achieving 155 kn/s. The new one are slower again. I also checked the number of positions after one mn, the depth, and it seems coherent with the nodes's count. Anyway, thank you for the popcount binaries -- it allowed me to finally try this new engine. It is similar to Winter, and recently Jonathan tried with two NN for the eval. I see a lot of intriguing, new possibilities arising.