Minic 2.51 is available.
https://github.com/tryingsomestuff/Mini ... s/tag/2.51
NNUE performance is just crazy with this release, as shown in previous post.
Have fun.
Minic version 2
Moderators: hgm, Rebel, chrisw
-
xr_a_y
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
-
chysiddh14
- Posts: 38
- Joined: Tue Jan 01, 2019 9:34 am
- Full name: Siddhartha Chaudhary
Re: Minic version 2
same android binary can be used in arm7 and arm8 device ,thanks
-
xr_a_y
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 2
Great news ! I must say I don't test that by myself.chysiddh14 wrote: ↑Wed Oct 14, 2020 3:33 pm same android binary can be used in arm7 and arm8 device ,thanks
If you can post some figures about Minic on android speed and strength it would be great !
-
Rebel
- Posts: 6991
- Joined: Thu Aug 18, 2011 12:04 pm
Re: Minic version 2
SRL 1000ms, quite some differences between the 4 nets I tested with version 2.51xr_a_y wrote: ↑Wed Oct 14, 2020 10:50 am Minic 2.51 is available.
https://github.com/tryingsomestuff/Mini ... s/tag/2.51
NNUE performance is just crazy with this release, as shown in previous post.
Have fun.
Code: Select all
The SRL rating list of : Wed Oct 14 17:06:37 2020
EPD : epd\lc1.epd
Time : 1000ms
Max Time Hash
Engine Points Used Time Found Pos Elo Score Score ms Mb Cpu Errors NNUE
1 Stockfish 12 341638 11:34:09.7 25383 40000 3416 400000 85.41% 1000 128 1 0 SV-2257
2 Ethereal-NNUE 334327 11:37:45.7 24676 40000 3343 400000 83.58% 1000 128 1 0 nn-baeb9ef2d183
3 RubiChess 1.8 NNUE 328244 11:30:21.7 23651 40000 3282 400000 82.06% 1000 128 1 0 nn-97f742aaefcd
4 Minic 2.51 SV-2257 327917 11:02:37.3 23628 40000 3279 400000 81.98% 1000 128 1 0 SV-2257
5 Minic 2.51 NNUE 325905 11:01:15.1 23441 40000 3259 400000 81.48% 1000 128 1 0 nn-97f742aaefcd
6 Minic 2.50 NNUE 322147 11:06:22.6 22986 40000 3221 400000 80.54% 1000 128 1 0 nn-97f742aaefcd
7 Nemorino 6.00 319148 10:36:00.7 22853 40000 3191 400000 79.79% 1000 128 1 42
8 Orion 0.7 NNUE_Player 318886 11:43:55.1 22654 40000 3188 400000 79.72% 1000 128 1 0 SV-2257
9 Ethereal 12.62 317128 11:37:07.9 22428 40000 3171 400000 79.28% 1000 128 1 0
10 Komodo 14 317110 11:09:21.4 22398 40000 3171 400000 79.28% 1000 128 1 0
11 igel 2.80 NNUE 316831 11:32:02.3 22679 40000 3168 400000 79.21% 1000 128 1 0
12 Minic 2.51 nexus 315288 11:01:57.0 22397 40000 3152 400000 78.82% 1000 128 1 0 napping_nexus
13 Houdini 6.03 314596 11:27:54.8 22218 40000 3146 400000 78.65% 1000 128 1 0
14 SlowChess 2.2 313139 10:30:56.4 21860 40000 3131 400000 78.28% 1000 128 1 0
15 Minic 2.51 nutrient 312407 11:02:18.3 21729 40000 3124 400000 78.10% 1000 128 1 0 nascent_nutrient
16 rofChade 2.3 309642 11:24:20.2 21587 40000 3096 400000 77.41% 1000 128 1 41
17 Ethereal 12 309088 11:30:20.9 21840 40000 3090 400000 77.27% 1000 128 1 0
18 Laser 1.7 308178 11:29:30.5 21320 40000 3081 400000 77.04% 1000 128 1 0
19 Schooner 2.2 306808 10:22:01.9 21335 40000 3068 400000 76.70% 1000 128 1 0
20 Xiphos 0.6 306796 10:03:55.9 21333 40000 3068 400000 76.70% 1000 128 1 0
21 Booot 6.4 305082 12:56:19.6 21267 40000 3050 400000 76.27% 1000 128 1 124
22 Defenchess 2.2 303754 10:12:00.7 21208 40000 3037 400000 75.94% 1000 128 1 41
23 Andscacs 0.95 301560 12:10:30.8 20745 40000 3015 400000 75.39% 1005 128 1 41
24 Shredder 13 300619 11:28:47.0 20946 40000 3006 400000 75.15% 1000 128 1 0
25 Wasp 4.00 299925 11:45:50.1 20727 40000 2999 400000 74.98% 1000 128 1 0
26 Senpai 2 299279 11:36:50.5 20615 40000 2992 400000 74.82% 1000 128 1 42
27 Winter 0.9 298713 10:06:38.6 20518 40000 2987 400000 74.68% 1000 128 1 0
28 Arasan 22 298663 11:27:32.7 20460 40000 2986 400000 74.67% 1000 128 1 0
29 ice 4.0 297995 11:49:51.1 20767 40000 2980 400000 74.50% 1000 128 1 0
30 Critter 1.6 297939 11:38:55.1 20654 40000 2979 400000 74.48% 1000 128 1 22
31 Fire 7.1 296996 11:26:35.7 20356 40000 2970 400000 74.25% 1000 128 1 0
32 Vajolet 2.8 296269 11:25:51.6 20327 40000 2962 400000 74.07% 1000 128 1 0
33 Demolito 200514 295686 10:53:58.5 20429 40000 2956 400000 73.92% 1000 128 1 0
34 Gogobello 2.2 293824 11:44:24.1 20296 40000 2938 400000 73.46% 1000 128 1 41
35 Nemorino 5.00 291649 10:05:27.4 19882 40000 2916 400000 72.91% 1000 128 1 41
36 Rodent 4 291647 11:45:03.3 19774 40000 2916 400000 72.91% 1000 128 1 0
37 Winter 0.8 291596 10:02:03.0 20057 40000 2916 400000 72.90% 1000 128 1 41
38 Hannibal 1.7 291446 11:39:04.6 19985 40000 2914 400000 72.86% 1000 128 1 0
39 Combusken 1.2 291389 12:25:31.9 19902 40000 2914 400000 72.85% 1000 128 1 41
40 Texel 1.7 291164 11:27:40.3 20064 40000 2911 400000 72.79% 1000 128 1 0
41 Monolith 2 290807 11:31:27.5 19972 40000 2908 400000 72.70% 1000 128 1 0
42 Topple 0.7.5 290649 12:13:57.0 19696 40000 2906 400000 72.66% 1000 128 1 0
43 Deuterium 2019 290578 11:31:42.7 19819 40000 2905 400000 72.64% 1000 128 1 0
44 Chiron 4 290250 11:46:17.8 19978 40000 2902 400000 72.56% 1000 128 1 0
45 Godel 7.0 290222 12:52:57.9 19758 40000 2902 400000 72.56% 1000 128 1 42
46 Amoeba 3.1 289712 09:40:26.2 19682 40000 2897 400000 72.43% 1000 128 1 0
47 FabChess 1.15 289296 11:50:40.2 19849 40000 2892 400000 72.32% 1000 128 1 41
48 sting-sf-21 288904 11:31:56.3 19905 40000 2889 400000 72.23% 1000 128 1 0
49 Marvin 3.60 288732 10:48:52.8 19848 40000 2887 400000 72.18% 1000 128 1 41
50 Bobcat 8 287527 10:54:11.9 19486 40000 2875 400000 71.88% 1000 128 1 0
51 Invictus r305 285355 10:16:08.6 19227 40000 2853 400000 71.34% 1000 128 1 0
52 Counter 3.5 285137 11:25:20.1 19329 40000 2851 400000 71.28% 1000 128 1 0
53 Weiss 1.0 284693 11:23:14.3 19241 40000 2846 400000 71.17% 1000 128 1 0
54 Asymptote 0.8 284305 12:19:43.9 19245 40000 2843 400000 71.08% 1000 128 1 41
55 Tucano 8.0 280426 04:46:55.0 18777 40000 2804 400000 70.11% 1000 128 1 0
56 RuyDos 1.1.11 278666 10:25:44.5 18567 40000 2786 400000 69.67% 1000 128 1 0
57 Cheese 2.1 277252 11:28:33.3 18763 40000 2772 400000 69.31% 1000 128 1 0
58 GreKo 2020.03 276482 11:29:35.7 18694 40000 2764 400000 69.12% 1000 128 1 0
59 Fruit 2.3 275618 11:30:55.1 18270 40000 2756 400000 68.90% 1000 128 1 0
60 ProDeo 2.2 273793 11:29:46.3 18263 40000 2738 400000 68.45% 1000 128 1 0
61 Benjamin 271801 11:29:55.8 17985 40000 2718 400000 67.95% 1000 128 1 0
62 Fridolin 3.10 271357 11:40:42.9 18030 40000 2713 400000 67.84% 1000 128 1 0
63 Fruit 2.1 270830 11:29:45.7 17982 40000 2708 400000 67.71% 1000 128 1 0
64 Devel 3.0.0b 269433 12:22:53.0 17986 40000 2694 400000 67.36% 1000 128 1 65
65 Ruffian 2 265592 11:13:01.7 17740 40000 2656 400000 66.40% 1000 128 1 0
66 Stash 18.0 253693 11:10:20.4 16848 40000 2536 400000 63.42% 1000 128 1 0
67 CT800 1.40 253449 10:45:20.4 16533 40000 2534 400000 63.36% 1000 128 1 0
68 Ares 005-2 243380 04:42:01.1 15937 40000 2433 400000 60.84% 1000 128 1 0
69 FoxSee 3.3.3 240244 11:08:18.3 15505 40000 2402 400000 60.06% 1000 128 1 0
Code: Select all
Max Time Hash
Engine Points Used Time Found Pos Elo Score Score ms Mb Cpu Errors NNUE
4 Minic 2.51 SV-2257 327917 11:02:37.3 23628 40000 3279 400000 81.98% 1000 128 1 0 SV-2257
5 Minic 2.51 NNUE 325905 11:01:15.1 23441 40000 3259 400000 81.48% 1000 128 1 0 nn-97f742aaefcd
12 Minic 2.51 nexus 315288 11:01:57.0 22397 40000 3152 400000 78.82% 1000 128 1 0 napping_nexus
15 Minic 2.51 nutrient 312407 11:02:18.3 21729 40000 3124 400000 78.10% 1000 128 1 0 nascent_nutrient
90% of coding is debugging, the other 10% is writing bugs.
-
Gabor Szots
- Posts: 1362
- Joined: Sat Jul 21, 2018 7:43 am
- Location: Szentendre, Hungary
- Full name: Gabor Szots
Re: Minic version 2
Vivien, please enlighten me. If the NNUE used is not from SF but your own work why don't you want it to be tested?
Gabor Szots
CCRL testing group
CCRL testing group
-
xr_a_y
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 2
NNUE merge was too easyGabor Szots wrote: ↑Wed Oct 14, 2020 5:36 pm Vivien, please enlighten me. If the NNUE used is not from SF but your own work why don't you want it to be tested?
NNUE technology is from SF.
But yes I built my own net (nascent nutrient).
Please see this
http://talkchess.com/forum3/viewtopic.p ... fe#p863067
-
xr_a_y
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 2
Thanks for this test. Order and strength of nets is well respected. Very good tool you have !Rebel wrote: ↑Wed Oct 14, 2020 5:22 pmSRL 1000ms, quite some differences between the 4 nets I tested with version 2.51xr_a_y wrote: ↑Wed Oct 14, 2020 10:50 am Minic 2.51 is available.
https://github.com/tryingsomestuff/Mini ... s/tag/2.51
NNUE performance is just crazy with this release, as shown in previous post.
Have fun.
Code: Select all
The SRL rating list of : Wed Oct 14 17:06:37 2020 EPD : epd\lc1.epd Time : 1000ms Max Time Hash Engine Points Used Time Found Pos Elo Score Score ms Mb Cpu Errors NNUE 1 Stockfish 12 341638 11:34:09.7 25383 40000 3416 400000 85.41% 1000 128 1 0 SV-2257 2 Ethereal-NNUE 334327 11:37:45.7 24676 40000 3343 400000 83.58% 1000 128 1 0 nn-baeb9ef2d183 3 RubiChess 1.8 NNUE 328244 11:30:21.7 23651 40000 3282 400000 82.06% 1000 128 1 0 nn-97f742aaefcd 4 Minic 2.51 SV-2257 327917 11:02:37.3 23628 40000 3279 400000 81.98% 1000 128 1 0 SV-2257 5 Minic 2.51 NNUE 325905 11:01:15.1 23441 40000 3259 400000 81.48% 1000 128 1 0 nn-97f742aaefcd 6 Minic 2.50 NNUE 322147 11:06:22.6 22986 40000 3221 400000 80.54% 1000 128 1 0 nn-97f742aaefcd 7 Nemorino 6.00 319148 10:36:00.7 22853 40000 3191 400000 79.79% 1000 128 1 42 8 Orion 0.7 NNUE_Player 318886 11:43:55.1 22654 40000 3188 400000 79.72% 1000 128 1 0 SV-2257 9 Ethereal 12.62 317128 11:37:07.9 22428 40000 3171 400000 79.28% 1000 128 1 0 10 Komodo 14 317110 11:09:21.4 22398 40000 3171 400000 79.28% 1000 128 1 0 11 igel 2.80 NNUE 316831 11:32:02.3 22679 40000 3168 400000 79.21% 1000 128 1 0 12 Minic 2.51 nexus 315288 11:01:57.0 22397 40000 3152 400000 78.82% 1000 128 1 0 napping_nexus 13 Houdini 6.03 314596 11:27:54.8 22218 40000 3146 400000 78.65% 1000 128 1 0 14 SlowChess 2.2 313139 10:30:56.4 21860 40000 3131 400000 78.28% 1000 128 1 0 15 Minic 2.51 nutrient 312407 11:02:18.3 21729 40000 3124 400000 78.10% 1000 128 1 0 nascent_nutrient 16 rofChade 2.3 309642 11:24:20.2 21587 40000 3096 400000 77.41% 1000 128 1 41 17 Ethereal 12 309088 11:30:20.9 21840 40000 3090 400000 77.27% 1000 128 1 0 18 Laser 1.7 308178 11:29:30.5 21320 40000 3081 400000 77.04% 1000 128 1 0 19 Schooner 2.2 306808 10:22:01.9 21335 40000 3068 400000 76.70% 1000 128 1 0 20 Xiphos 0.6 306796 10:03:55.9 21333 40000 3068 400000 76.70% 1000 128 1 0 21 Booot 6.4 305082 12:56:19.6 21267 40000 3050 400000 76.27% 1000 128 1 124 22 Defenchess 2.2 303754 10:12:00.7 21208 40000 3037 400000 75.94% 1000 128 1 41 23 Andscacs 0.95 301560 12:10:30.8 20745 40000 3015 400000 75.39% 1005 128 1 41 24 Shredder 13 300619 11:28:47.0 20946 40000 3006 400000 75.15% 1000 128 1 0 25 Wasp 4.00 299925 11:45:50.1 20727 40000 2999 400000 74.98% 1000 128 1 0 26 Senpai 2 299279 11:36:50.5 20615 40000 2992 400000 74.82% 1000 128 1 42 27 Winter 0.9 298713 10:06:38.6 20518 40000 2987 400000 74.68% 1000 128 1 0 28 Arasan 22 298663 11:27:32.7 20460 40000 2986 400000 74.67% 1000 128 1 0 29 ice 4.0 297995 11:49:51.1 20767 40000 2980 400000 74.50% 1000 128 1 0 30 Critter 1.6 297939 11:38:55.1 20654 40000 2979 400000 74.48% 1000 128 1 22 31 Fire 7.1 296996 11:26:35.7 20356 40000 2970 400000 74.25% 1000 128 1 0 32 Vajolet 2.8 296269 11:25:51.6 20327 40000 2962 400000 74.07% 1000 128 1 0 33 Demolito 200514 295686 10:53:58.5 20429 40000 2956 400000 73.92% 1000 128 1 0 34 Gogobello 2.2 293824 11:44:24.1 20296 40000 2938 400000 73.46% 1000 128 1 41 35 Nemorino 5.00 291649 10:05:27.4 19882 40000 2916 400000 72.91% 1000 128 1 41 36 Rodent 4 291647 11:45:03.3 19774 40000 2916 400000 72.91% 1000 128 1 0 37 Winter 0.8 291596 10:02:03.0 20057 40000 2916 400000 72.90% 1000 128 1 41 38 Hannibal 1.7 291446 11:39:04.6 19985 40000 2914 400000 72.86% 1000 128 1 0 39 Combusken 1.2 291389 12:25:31.9 19902 40000 2914 400000 72.85% 1000 128 1 41 40 Texel 1.7 291164 11:27:40.3 20064 40000 2911 400000 72.79% 1000 128 1 0 41 Monolith 2 290807 11:31:27.5 19972 40000 2908 400000 72.70% 1000 128 1 0 42 Topple 0.7.5 290649 12:13:57.0 19696 40000 2906 400000 72.66% 1000 128 1 0 43 Deuterium 2019 290578 11:31:42.7 19819 40000 2905 400000 72.64% 1000 128 1 0 44 Chiron 4 290250 11:46:17.8 19978 40000 2902 400000 72.56% 1000 128 1 0 45 Godel 7.0 290222 12:52:57.9 19758 40000 2902 400000 72.56% 1000 128 1 42 46 Amoeba 3.1 289712 09:40:26.2 19682 40000 2897 400000 72.43% 1000 128 1 0 47 FabChess 1.15 289296 11:50:40.2 19849 40000 2892 400000 72.32% 1000 128 1 41 48 sting-sf-21 288904 11:31:56.3 19905 40000 2889 400000 72.23% 1000 128 1 0 49 Marvin 3.60 288732 10:48:52.8 19848 40000 2887 400000 72.18% 1000 128 1 41 50 Bobcat 8 287527 10:54:11.9 19486 40000 2875 400000 71.88% 1000 128 1 0 51 Invictus r305 285355 10:16:08.6 19227 40000 2853 400000 71.34% 1000 128 1 0 52 Counter 3.5 285137 11:25:20.1 19329 40000 2851 400000 71.28% 1000 128 1 0 53 Weiss 1.0 284693 11:23:14.3 19241 40000 2846 400000 71.17% 1000 128 1 0 54 Asymptote 0.8 284305 12:19:43.9 19245 40000 2843 400000 71.08% 1000 128 1 41 55 Tucano 8.0 280426 04:46:55.0 18777 40000 2804 400000 70.11% 1000 128 1 0 56 RuyDos 1.1.11 278666 10:25:44.5 18567 40000 2786 400000 69.67% 1000 128 1 0 57 Cheese 2.1 277252 11:28:33.3 18763 40000 2772 400000 69.31% 1000 128 1 0 58 GreKo 2020.03 276482 11:29:35.7 18694 40000 2764 400000 69.12% 1000 128 1 0 59 Fruit 2.3 275618 11:30:55.1 18270 40000 2756 400000 68.90% 1000 128 1 0 60 ProDeo 2.2 273793 11:29:46.3 18263 40000 2738 400000 68.45% 1000 128 1 0 61 Benjamin 271801 11:29:55.8 17985 40000 2718 400000 67.95% 1000 128 1 0 62 Fridolin 3.10 271357 11:40:42.9 18030 40000 2713 400000 67.84% 1000 128 1 0 63 Fruit 2.1 270830 11:29:45.7 17982 40000 2708 400000 67.71% 1000 128 1 0 64 Devel 3.0.0b 269433 12:22:53.0 17986 40000 2694 400000 67.36% 1000 128 1 65 65 Ruffian 2 265592 11:13:01.7 17740 40000 2656 400000 66.40% 1000 128 1 0 66 Stash 18.0 253693 11:10:20.4 16848 40000 2536 400000 63.42% 1000 128 1 0 67 CT800 1.40 253449 10:45:20.4 16533 40000 2534 400000 63.36% 1000 128 1 0 68 Ares 005-2 243380 04:42:01.1 15937 40000 2433 400000 60.84% 1000 128 1 0 69 FoxSee 3.3.3 240244 11:08:18.3 15505 40000 2402 400000 60.06% 1000 128 1 0Code: Select all
Max Time Hash Engine Points Used Time Found Pos Elo Score Score ms Mb Cpu Errors NNUE 4 Minic 2.51 SV-2257 327917 11:02:37.3 23628 40000 3279 400000 81.98% 1000 128 1 0 SV-2257 5 Minic 2.51 NNUE 325905 11:01:15.1 23441 40000 3259 400000 81.48% 1000 128 1 0 nn-97f742aaefcd 12 Minic 2.51 nexus 315288 11:01:57.0 22397 40000 3152 400000 78.82% 1000 128 1 0 napping_nexus 15 Minic 2.51 nutrient 312407 11:02:18.3 21729 40000 3124 400000 78.10% 1000 128 1 0 nascent_nutrient
Code: Select all
13 Houdini 6.03 314596 11:27:54.8 22218 40000 3146 400000 78.65% 1000 128 1 0
14 SlowChess 2.2 313139 10:30:56.4 21860 40000 3131 400000 78.28% 1000 128 1 0
15 Minic 2.51 nutrient 312407 11:02:18.3 21729 40000 3124 400000 78.10% 1000 128 1 0 nascent_nutrient
16 rofChade 2.3 309642 11:24:20.2 21587 40000 3096 400000 77.41% 1000 128 1 41
17 Ethereal 12 309088 11:30:20.9 21840 40000 3090 400000 77.27% 1000 128 1 0
18 Laser 1.7 308178 11:29:30.5 21320 40000 3081 400000 77.04% 1000 128 1 0
19 Schooner 2.2 306808 10:22:01.9 21335 40000 3068 400000 76.70% 1000 128 1 0
20 Xiphos 0.6 306796 10:03:55.9 21333 40000 3068 400000 76.70% 1000 128 1 0
21 Booot 6.4 305082 12:56:19.6 21267 40000 3050 400000 76.27% 1000 128 1 124
22 Defenchess 2.2 303754 10:12:00.7 21208 40000 3037 400000 75.94% 1000 128 1 41
Another example is what is currently happening in Graham division 2 (with nascent nutrient also)
Code: Select all
1. MINIC 2.50 64-BIT 34 21.0 **** ===. 101. 0=0. ===. 10=. 11=. ==1. 1=1. =1=1 1=0. 11=.
2. DEFENCHESS 2.2 64-BIT 34 20.0 ===. **** 1==. =0=. =1=. =1=. ==== 01=. =1=. ==1. ===. 11=.
3. RUBICHESS 1.8 64-BIT 34 19.0 010. 0==. **** 1=1. ===. 0==. =0=. 11=. 1=1. 1==. ===. ==1=
4. ANDSCACS 0.95 64-BIT 34 18.5 1=1. =1=. 0=0. **** ===. =1=0 =0=. =1=. 0=1. 11=. 0==. =1=.
5. ARASAN 22.1 64-BIT 33 18.0 ===. =0=. ===. ===. **** 11=. 10=. ==1. 01=. =1=. 10=. ===.
For now, I'm learning about NN and that's enough.
-
nabildanial
- Posts: 126
- Joined: Thu Jun 05, 2014 5:29 am
- Location: Malaysia
Re: Minic version 2
NNUE is no different than every single technique/technology used in chess (LMR, null move etc.) except that all of them are related to search. Is it something about NNUE being an eval-based technology that makes it undeserved to be recognized by you?xr_a_y wrote: ↑Wed Oct 14, 2020 5:54 pmNNUE merge was too easyGabor Szots wrote: ↑Wed Oct 14, 2020 5:36 pm Vivien, please enlighten me. If the NNUE used is not from SF but your own work why don't you want it to be tested?
NNUE technology is from SF.
But yes I built my own net (nascent nutrient).
Please see this
http://talkchess.com/forum3/viewtopic.p ... fe#p863067
-
xr_a_y
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Minic version 2
I not only borrow the technology, but also the code itself (a code bigger in number of lines than Minic code itself !).nabildanial wrote: ↑Wed Oct 14, 2020 8:47 pmNNUE is no different than every single technique/technology used in chess (LMR, null move etc.) except that all of them are related to search. Is it something about NNUE being an eval-based technology that makes it undeserved to be recognized by you?xr_a_y wrote: ↑Wed Oct 14, 2020 5:54 pmNNUE merge was too easyGabor Szots wrote: ↑Wed Oct 14, 2020 5:36 pm Vivien, please enlighten me. If the NNUE used is not from SF but your own work why don't you want it to be tested?
NNUE technology is from SF.
But yes I built my own net (nascent nutrient).
Please see this
http://talkchess.com/forum3/viewtopic.p ... fe#p863067
Moreover NNUE merging inside Minic (both evaluation code and learning code) was very easy, because the code was already well cleaned by Stockfish contributors.
I'll rethink my position for example if NNUE and associated learning tools become a shared lib for the community. Or if like 30 engines is going for NNUE and uses SF nets ... (a situation I will dislike a lot ...)
I did this NNUE experiment for fun, for learning, not for position in rating list.
Of course anyone can use it ! And I'll try to build net for it. Think of it as an option, not a way to climb the ladder. (a ladder that Minic is already climbing quite fast anyway http://ccrl.chessdom.com/ccrl/404/cgi/c ... +opponents, thanks to the forum, to CPW, to advices, to discord channel, to code reading, ...)
-
nabildanial
- Posts: 126
- Joined: Thu Jun 05, 2014 5:29 am
- Location: Malaysia
Re: Minic version 2
I get it if the used net to rank Minic is SF nets, but I don't quite get why you don't want to recognize your own homebrew nets that are created from Minic own eval as a part of Minic.xr_a_y wrote: ↑Wed Oct 14, 2020 8:59 pmI not only borrow the technology, but also the code itself (a code bigger in number of lines than Minic code itself !).nabildanial wrote: ↑Wed Oct 14, 2020 8:47 pmNNUE is no different than every single technique/technology used in chess (LMR, null move etc.) except that all of them are related to search. Is it something about NNUE being an eval-based technology that makes it undeserved to be recognized by you?xr_a_y wrote: ↑Wed Oct 14, 2020 5:54 pmNNUE merge was too easyGabor Szots wrote: ↑Wed Oct 14, 2020 5:36 pm Vivien, please enlighten me. If the NNUE used is not from SF but your own work why don't you want it to be tested?
NNUE technology is from SF.
But yes I built my own net (nascent nutrient).
Please see this
http://talkchess.com/forum3/viewtopic.p ... fe#p863067
Moreover NNUE merging inside Minic (both evaluation code and learning code) was very easy, because the code was already well cleaned by Stockfish contributors.