Search found 269 matches

by Raphexon
Sat Jun 13, 2020 9:46 am
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

marsell wrote:
Sat Jun 13, 2020 9:29 am
May I ask how to use these engines? They don't run in the gui arena.
ty
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)
by Raphexon
Fri Jun 12, 2020 9:14 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

This is my current net: Trained on depth 8 data. Validated with depth 19 data. https://drive.google.com/file/d/1P7EJuWPm02tKXx_aLxo_xwFWMSN3A44B/view?usp=sharing 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...
by Raphexon
Fri Jun 12, 2020 8:32 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

Would anyone be willing to test this net? https://cdn.discordapp.com/attachments/496514663287095328/721073037100974211/nn.7z I've trained it off of fishtest games. I expect it to play endgames poorly (especially without TBs) since those don't appear much in training games. My code to go from PGNs t...
by Raphexon
Sun Jun 07, 2020 5:27 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

Is anyone able to get this to work on Linux? I get a segfault calling into wait_for_search_finished from ThreadPool::set almost immediately after running ./stockfish. The wait_for_search_finished is different from what I see in SF 11, so I tried replacing it with SF 11's. No dice. I have no idea wh...
by Raphexon
Sun Jun 07, 2020 1:25 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

The later one has the shallow depth pruning disabled so the fixed depth is stronger but in normal play it will cost a lot of elo - about 170 to 200. That's outright nonsense! This patch only disables the pruning for the very first 4 iterations of the search, which avoids outright blunders and stran...
by Raphexon
Sat Jun 06, 2020 11:07 am
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

This page also holds some information. http://qhapaq.hatenablog.com/entry/2018/06/02/221612 http://qhapaq.hatenablog.com/entry/2018/07/08/193316 hi, The BMI2 compiles are not running on AMD Ryzen box. Also I am not able to figure out how to use the nn.bin Please give a detailed instruction and popc...
by Raphexon
Sat Jun 06, 2020 9:12 am
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

This page also holds some information. http://qhapaq.hatenablog.com/entry/2018/06/02/221612 http://qhapaq.hatenablog.com/entry/2018/07/08/193316 hi, The BMI2 compiles are not running on AMD Ryzen box. Also I am not able to figure out how to use the nn.bin Please give a detailed instruction and popc...
by Raphexon
Fri Jun 05, 2020 1:30 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

I have 3 more games! 2 of which are against Lc0 running on my 980TI. I used the Stein 14.0 net at 2.5-3knps. SFNN is about 1/2 the speed of regular SF which means the Leela ratio, which usually favors SF on my setup is now about equal. The net SF uses is a new halfkp net trained on depth=6 instead ...
by Raphexon
Fri Jun 05, 2020 11:37 am
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 42727

Re: Stockfish NN release (NNUE)

Earlier info: 1. The trainer converts the searched score in a training sample to the winning percentage with the calculating formula below. https://twitter.com/issei_y/status/589642166818877440 2. The trainer converts the game result to the winning percentage. Win=1.0 Lose=0.0 3. The trainer calcula...