This is my current net:
Trained on depth 8 data.
Validated with depth 19 data.
For use rename it to nn.bin and replace the original nn.bin in the "eval" folder.
For use with:
stockfish.nnue-learn-use-blas.halfkp_256x2-32-32.exe
And
stockfish.nnue.halfkp_256x2-32-32.exe
https://github.com/nodchip/Stockfish/re ... 2020-06-09
I'm currently generating new training data with it, will be able to release something new in a few days I hope.
Stockfish NN release (NNUE)
Moderators: hgm, Rebel, chrisw
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
-
- Posts: 106
- Joined: Tue Feb 07, 2012 11:14 am
Re: Stockfish NN release (NNUE)
May I ask how to use these engines? They don't run in the gui arena.
ty
ty
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
Re: Stockfish NN release (NNUE)
What CPU do you have.
The binaries I linked require BMI2 support (Haswell or newer, Ryzen or newer if AMD)
Are you installing the halfkp binaries, and did you put the 20mb nn in the eval folder? (And renamed it to nn.bin)
-
- Posts: 106
- Joined: Tue Feb 07, 2012 11:14 am
Re: Stockfish NN release (NNUE)
my cpu is a intel i7 4790k running on windows 10 Pro
I tried to install the halfkp binaries with the 20 mb nn, renamed as nn.bin.
But it looks like it's still not working
I tried to install the halfkp binaries with the 20 mb nn, renamed as nn.bin.
But it looks like it's still not working
-
- Posts: 584
- Joined: Fri Mar 30, 2018 7:20 am
- Full name: Andreas Matthies
Re: Stockfish NN release (NNUE)
I also tried your halfkp binary stockfish.nnue.halfkp_256x2-32-32.exe
Have replaced eval\nn.bin with the candidate one.
My system: Intel(R) Core(TM) i5-5257U CPU @ 2.70GHz
Crashes at "go" command with 0xc0000005 at offset 00000000000365d4 (if that helps).
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
-
- Posts: 106
- Joined: Tue Feb 07, 2012 11:14 am
Re: Stockfish NN release (NNUE)
great, thanks, now it works.
-
- Posts: 937
- Joined: Fri Mar 10, 2006 4:29 pm
- Location: Germany
Re: Stockfish NN release (NNUE)
Are you still training without draws?Raphexon wrote: ↑Fri Jun 12, 2020 11:14 pm This is my current net:
Trained on depth 8 data.
Validated with depth 19 data.
For use rename it to nn.bin and replace the original nn.bin in the "eval" folder.
For use with:
stockfish.nnue-learn-use-blas.halfkp_256x2-32-32.exe
And
stockfish.nnue.halfkp_256x2-32-32.exe
https://github.com/nodchip/Stockfish/re ... 2020-06-09
I'm currently generating new training data with it, will be able to release something new in a few days I hope.
Probably not a good idea, imho.
In my copy of SF-NNUE https://github.com/joergoster/Stockfish-NNUE I enabled to use draw results, as well.
Hopefully, I did everything right.
When compiling from source it will use halfkp_256x2-32-32 architecture by default.
I also think that the initial learning rate (eta = 1.0) might be too high.
Jörg Oster
-
- Posts: 144
- Joined: Sun Oct 14, 2018 8:21 pm
- Full name: JSmith
Re: Stockfish NN release (NNUE)
Can you share all of your binaries (gensfen, half-kp, half-kp learn, etc.,) on Google Drive or as GitHub releases? I know it's a lot to ask for, but I'd really appreciate it.Joerg Oster wrote: ↑Sat Jun 13, 2020 2:46 pmAre you still training without draws?Raphexon wrote: ↑Fri Jun 12, 2020 11:14 pm This is my current net:
Trained on depth 8 data.
Validated with depth 19 data.
For use rename it to nn.bin and replace the original nn.bin in the "eval" folder.
For use with:
stockfish.nnue-learn-use-blas.halfkp_256x2-32-32.exe
And
stockfish.nnue.halfkp_256x2-32-32.exe
https://github.com/nodchip/Stockfish/re ... 2020-06-09
I'm currently generating new training data with it, will be able to release something new in a few days I hope.
Probably not a good idea, imho.
In my copy of SF-NNUE https://github.com/joergoster/Stockfish-NNUE I enabled to use draw results, as well.
Hopefully, I did everything right.
When compiling from source it will use halfkp_256x2-32-32 architecture by default.
I also think that the initial learning rate (eta = 1.0) might be too high.
-
- Posts: 937
- Joined: Fri Mar 10, 2006 4:29 pm
- Location: Germany
Re: Stockfish NN release (NNUE)
Try these: https://www.file-upload.net/download-14 ... 20.7z.htmlcucumber wrote: ↑Sat Jun 13, 2020 3:28 pmCan you share all of your binaries (gensfen, half-kp, half-kp learn, etc.,) on Google Drive or as GitHub releases? I know it's a lot to ask for, but I'd really appreciate it.Joerg Oster wrote: ↑Sat Jun 13, 2020 2:46 pmAre you still training without draws?Raphexon wrote: ↑Fri Jun 12, 2020 11:14 pm This is my current net:
Trained on depth 8 data.
Validated with depth 19 data.
For use rename it to nn.bin and replace the original nn.bin in the "eval" folder.
For use with:
stockfish.nnue-learn-use-blas.halfkp_256x2-32-32.exe
And
stockfish.nnue.halfkp_256x2-32-32.exe
https://github.com/nodchip/Stockfish/re ... 2020-06-09
I'm currently generating new training data with it, will be able to release something new in a few days I hope.
Probably not a good idea, imho.
In my copy of SF-NNUE https://github.com/joergoster/Stockfish-NNUE I enabled to use draw results, as well.
Hopefully, I did everything right.
When compiling from source it will use halfkp_256x2-32-32 architecture by default.
I also think that the initial learning rate (eta = 1.0) might be too high.
Jörg Oster