kate/BadFish
1
0
Fork 0
mirror of https://github.com/sockspls/badfish synced 2025-04-29 16:23:09 +00:00
Code Issues Releases Wiki Activity

Re-evaluate some small net positions for more accurate evals

Browse source 
Use main net evals when small net evals hint that higher eval
accuracy may be worth the slower eval speeds. With Finny caches,
re-evals with the main net are less expensive than before.

Original idea by mstembera who I've added as co-author to this PR.

Based on reEval tests by mstembera:
https://tests.stockfishchess.org/tests/view/65e69187b6345c1b934866e5
https://tests.stockfishchess.org/tests/view/65e863aa0ec64f0526c3e991

A few variants of this patch also passed LTC:
https://tests.stockfishchess.org/tests/view/663d2108507ebe1c0e91f407
https://tests.stockfishchess.org/tests/view/663e388c3a2f9702074bc152

Passed STC:
https://tests.stockfishchess.org/tests/view/663dadbd1a61d6377f190e2c
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 92320 W: 23941 L: 23531 D: 44848
Ptnml(0-2): 430, 10993, 22931, 11349, 457

Passed LTC:
https://tests.stockfishchess.org/tests/view/663ef48b2948bf9aa698690c
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 98934 W: 24907 L: 24457 D: 49570
Ptnml(0-2): 48, 10952, 27027, 11382, 58

closes https://github.com/official-stockfish/Stockfish/pull/5238

bench 1876282

Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com>
This commit is contained in:
Linmiao Xu 2024-05-09 14:03:35 -04:00 • committed by Joost VandeVondele
parent 53f363041c
commit 0b08953174
2 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
src/evaluate.cpp
View file

@ -62,6 +62,9 @@ Value Eval::evaluate(const Eval::NNUE::Networks& networks,
Value nnue = smallNet ? networks.small.evaluate(pos, &caches.small, true, &nnueComplexity)
: networks.big.evaluate(pos, &caches.big, true, &nnueComplexity);
if (smallNet && (nnue * simpleEval < 0 || std::abs(nnue) < 500))
nnue = networks.big.evaluate(pos, &caches.big, true, &nnueComplexity);
const auto adjustEval = [&](int nnueDiv, int pawnCountMul, int evalDiv, int shufflingConstant) {
// Blend optimism and eval with nnue complexity and material imbalance
optimism += optimism * (nnueComplexity + std::abs(simpleEval - nnue)) / 584;

2
src/evaluate.h
View file

@ -29,7 +29,7 @@ class Position;
namespace Eval {
constexpr inline int SmallNetThreshold = 1274;
constexpr inline int SmallNetThreshold = 1174;
// The default net name MUST follow the format nn-[SHA256 first 12 digits].nnue
// for the build process (profile-build and fishtest) to work. Do not change the