forked from animatedread/Warrior_EA
- Introduce per-bar feature cache to avoid redundant recomputation of input vectors during training. - Rename EnsureLabelCacheCapacity to EnsureBarCachesCapacity to reflect management of both label and feature caches. - Fix oversampling logic to maintain balanced representation among minority classes, replacing independent 5x caps that caused relative bias.
8.6 MiB
8.6 MiB