Search found 2165 matches

by cdani
Sat Jun 20, 2020 8:10 am
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

I have done a longer time control test. 600 seconds (10 minutes) + 2 seconds against latest Stockfish dev. So maybe 80 elo less than Stockfish. # PLAYER : RATING ERROR POINTS PLAYED (%) 1 st200617 : 2896.3 9.9 203.5 333 61.1% 2 stnnuecl1 : 2815.7 9.9 129.5 333 38.9% What value are you using for slo...
by cdani
Fri Jun 19, 2020 7:50 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

I have done a longer time control test. 600 seconds (10 minutes) + 2 seconds against latest Stockfish dev. So maybe 80 elo less than Stockfish. # PLAYER : RATING ERROR POINTS PLAYED (%) 1 st200617 : 2896.3 9.9 203.5 333 61.1% 2 stnnuecl1 : 2815.7 9.9 129.5 333 38.9% What value are you using for slo...
by cdani
Fri Jun 19, 2020 6:48 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

lkaufman wrote:
Fri Jun 19, 2020 6:46 pm
What value are you using for slowmover? My best result was with 70, with 60 close behind.
Default one.
by cdani
Fri Jun 19, 2020 6:43 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

I have done a longer time control test. 600 seconds (10 minutes) + 2 seconds against latest Stockfish dev. So maybe 80 elo less than Stockfish. # PLAYER : RATING ERROR POINTS PLAYED (%) 1 st200617 : 2896.3 9.9 203.5 333 61.1% 2 stnnuecl1 : 2815.7 9.9 129.5 333 38.9% Games: https://1drv.ms/u/s!Aj8wlS...
by cdani
Fri Jun 19, 2020 9:01 am
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

Quick test 30 + 0.2 of your net (stnnuecl1) against the previous best net known for me. Yours is a bit better: # PLAYER : RATING ERROR POINTS PLAYED (%) 1 stnnuecl1 : 2868.0 10.7 269.0 504 53.4% 2 stnnue : 2844.0 10.7 235.0 504 46.6% Now testing it against the latest one of Additional Pylon halfkp ...
by cdani
Thu Jun 18, 2020 9:41 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

lkaufman wrote:
Thu Jun 18, 2020 9:39 pm
I'm getting just about half the nodes per second of Stockfish 11, is that typical?
Yes. It's a neural net, very optimized, but slower than a typical eval function.
by cdani
Thu Jun 18, 2020 9:34 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

Quick test 30 + 0.2 of your net (stnnuecl1) against the previous best net known for me. Yours is a bit better: # PLAYER : RATING ERROR POINTS PLAYED (%) 1 stnnuecl1 : 2868.0 10.7 269.0 504 53.4% 2 stnnue : 2844.0 10.7 235.0 504 46.6% Now testing it against the latest one of Additional Pylon halfkp 2...
by cdani
Thu Jun 18, 2020 8:17 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

I put it and the half-k application in a folder, and tried to install in the Fritz-17 gui, but apparently there is something else I need to do as it won't load. I have a recent (1 year old) 8 core I-7 laptop, windows 10, with a good GPU (not needed for this I believe). What else do I have to do? Pu...
by cdani
Thu Jun 18, 2020 8:09 pm
Forum: Computer Chess Club: General Topics
Topic: My strongest NNUE net (yet)
Replies: 34
Views: 8395

Re: My strongest NNUE net (yet)

Many thanks!
Exciting times :-)
I'm testing it. I will post the results.
by cdani
Wed Jun 17, 2020 5:52 am
Forum: Computer Chess Club: General Topics
Topic: Stockfish NN release (NNUE)
Replies: 227
Views: 63000

Re: Stockfish NN release (NNUE)

Some more results with two nets from this thread against the latest sf dev. 1 thread, tc 1m+1s, the same 100 short normal openings for both matches. Bigger net is more solid. sf dev 150620 - sf nnue halfkp256 : 116,5/200 +57-24=119 sf dev 150620 - sf nnue halfkp384 : 109,5/200 +41-22=137 I also did...