nodchip Stockfish issues

nodchip / Stockfish

UCI chess engine

http://www.stockfishchess.com/

GNU General Public License v3.0

100 stars 25 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Failure to load nnue trained by https://github.com/glinscott/nnue-pytorch

#329 arashesfahany closed 2 years ago
1
What is the master neural network referred to in SF source code near SF12 (first NNue)

#328 Dboingue opened 3 years ago
1
Merge with official-stockfish/Stockfish/master of 2021-05-13

#327 Sopel97 opened 3 years ago
0
Merge with official-stockfish/Stockfish/master of 2021-05-13

#326 Sopel97 closed 3 years ago
0
master and tools branches...

#325 Sopel97 opened 3 years ago
4
Shorter write_maxply and inaccurate result

#324 fsmosca opened 3 years ago
2
Tools after merge 2

#323 Sopel97 closed 3 years ago
0
Fix ranking of root moves by TB

#322 fsmosca closed 3 years ago
0
Fixes on include paths in tbprobe

#321 fsmosca closed 3 years ago
1
Fix stats.md docs.

#320 Sopel97 closed 3 years ago
0
More stats

#319 Sopel97 closed 3 years ago
2
Revert "Add additional checks for en-passant possiblity when fixing the erroneus ep flag from a fen."

#318 Sopel97 closed 3 years ago
0
Fix segfault and end the game by 3-fold repetitions

#317 fsmosca closed 3 years ago
0
Add additional checks for en-passant possiblity when fixing the erroneus ep flag from a fen.

#316 Sopel97 closed 3 years ago
1
Invalid EP results in bad binpack conversion

#315 borg323 opened 3 years ago
6
Would be nice if issue is labelled bug if it is a bug

#314 fsmosca closed 3 years ago
4
Add optional warmup step for training.

#313 Sopel97 closed 3 years ago
1
Add random move accuracy for comparison.

#312 Sopel97 closed 3 years ago
1
Segmentation fault on gensfen with ensure_quiet and random_multi_pv

#311 fsmosca closed 3 years ago
7
Change some `learn` parameter naming. Update docs.

#310 Sopel97 closed 3 years ago
1
Fix relation between halfmove and fullmove clocks.

#309 Sopel97 closed 3 years ago
1
12:35 AM] J.H. Ellis: Could discard draws from data so that they make up a maximum of x%, then tune x.

#308 Sopel97 opened 3 years ago
0
Fix minor typo in documentation for gensfen

#307 QuackQuackBlah closed 3 years ago
1
Add `gather_statistics` command

#306 Sopel97 closed 3 years ago
0
http://talkchess.com/forum3/viewtopic.php?f=2&t=76736&p=885254#p885254

#305 Sopel97 closed 3 years ago
2
binpack stats

#304 Sopel97 closed 3 years ago
1
docs smart_fen_skipping

#303 Sopel97 closed 3 years ago
0
move accuracy

#302 Sopel97 closed 3 years ago
0
Clarify some learn option names and behaviour.

#301 Sopel97 closed 3 years ago
0
Warmup step

#300 Sopel97 closed 3 years ago
0
uninit value with TB

#299 vondele closed 3 years ago
9
2 fold adjudicated as a draw

#298 Sopel97 closed 3 years ago
9
optimizer state is not being saved

#297 Sopel97 opened 3 years ago
0
Fix wrong multipv depth range. Fixes #291

#296 Sopel97 closed 3 years ago
1
document .bin and .plain

#295 Sopel97 opened 3 years ago
0
compile errors on mac

#294 kennyfrc opened 3 years ago
0
reduction depends on thread count

#293 Sopel97 opened 3 years ago
0
hash dedup removes book position

#292 Sopel97 opened 3 years ago
0
incorrect multipv depth

#291 Sopel97 closed 3 years ago
0
Correctly handle the last batch of data in sfen_reader

#290 Sopel97 closed 3 years ago
1
Don't unload evalfile on set nnue false

#289 Sopel97 closed 3 years ago
1
Add split_count argument to shuffle_binpack.py

#288 vondele closed 3 years ago
1
Reduce the amount of sfens buffered for the validation step.

#287 Sopel97 closed 3 years ago
1
Correctly account for factors when computing the average absolute weight of the feature transformer.

#286 Sopel97 closed 3 years ago
1
Add thread sanitized run for instrumented_learn

#285 Sopel97 closed 3 years ago
3
Accumulate clipping statistics to a 64 bit integer to prevent overflow for larger batch sizes.

#284 Sopel97 closed 3 years ago
1
Prevent q_ in loss calculation from reaching values that would produce NaN

#283 Sopel97 closed 3 years ago
1
[WIP] Correct feature_transformer sgd and do ADA-like lr scaling per feature

#282 Sopel97 closed 3 years ago
0
[WIP] Automatic sigmoid scaling for the data eval to perf. Separate scaling for data and player.

#281 Sopel97 closed 3 years ago
2
allow for repeated searches in rescoring

#280 vondele closed 3 years ago
1