You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi. I think you are confusing something here. The concept of "blocks" is used in deep residual CNNs as used in Alpha/LeelaZero style approaches. The NNUE in (Fairy-)Stockfish is a very shallow neural network without anything like blocks, also see the documentation and this .
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Discussion about technical issues during Xiangqi NNUE training, how to solve them, and sharing of links to generated training data.
See https://github.com/ianfab/variant-nnue-pytorch/wiki/%E4%B8%AD%E6%96%87 for documentation, and feel free to extend it if you have additional information.
Beta Was this translation helpful? Give feedback.
All reactions