From 890eb8d7f4a8c46eae18283ca5ac9c61fd41ed97 Mon Sep 17 00:00:00 2001 From: tslil clingman Date: Wed, 10 Feb 2021 20:07:24 -0500 Subject: Change the training data generation a little Although it pains me to say it, ``label smoothing'' appears to be actually work. I'm also currently experimenting with training simply against _all_ games, instead of only bot matches. Once the training finishes i'll pit cttei against itself with old and new weights, hopefully there'll be a noticeable improvement. --- resources/extract.sh | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'resources') diff --git a/resources/extract.sh b/resources/extract.sh index fb2c30d..b413d46 100755 --- a/resources/extract.sh +++ b/resources/extract.sh @@ -2,7 +2,8 @@ db_file=games_anon.db -chosen_players="AaaarghBot Tiltak_Bot TakticianBot" +#chosen_players="AaaarghBot Tiltak_Bot TakticianBot" +chosen_players="" query() { query="(size == $1) and (result != '1-0') and (result != '0-1') and (result != '0-0') and (result != '1/2-1/2')" @@ -34,7 +35,10 @@ process() { ./pptdb "$size" "data/playtak-$size" > "data/check-$size" tail -n22 "data/check-$size" echo -ne "\tStripping overflows and illegal games... " - grep -Fvxf "data/check-$size" "data/playtak-$size" > "data/good-playtak-$size" + grep -Fvxf "data/check-$size" "data/playtak-$size" > "data/good-playtak-$size-all" + + shuf "data/good-playtak-$size-all" > "data/good-playtak-$size" + rm "data/good-playtak-$size-all" echo -en "Done.\n\tGenerating training data... " ./pptdb "$size" "data/good-playtak-$size" generate -- cgit v1.3.1