ChanServ changed the topic of #mlpack to: "mlpack: a fast, flexible machine learning library :: We don't always respond instantly, but we will respond; please be patient :: Logs at http://www.mlpack.org/irc/
< KimSangYeon-DGU[>
zoq: In this PR (https://github.com/mlpack/mlpack/pull/2474), I suggested updating the initial values of the `runningVariance` of the `BatchNorm` class from `0`s to `1`s. So, the `runningVariance` will be slightly different. The reason we updated is to synchronize the values with PyTorch's.
< KimSangYeon-DGU[>
Is it okay to do that in view of the backward compatibility and library maintenance? If not, we'll revert that.
< KimSangYeon-DGU[>
CC: kartikdutt18
< zoq>
KimSangYeon-DGU[: Fine with me, sounds like it would resolve some confusions.
< KimSangYeon-DGU[>
zoq: Right, great 🙂
< kartikdutt18Gitt>
Great, Thanks.
< himanshu_pathak[>
Hey sakshamb189: are you there ??