conversion from bnn.SpatialConvolution and bnn.binary to nn or cudnn

I was trying to convert this model into CPU supported device(nn), was able to convert some of the layers using cudnn.convert, but getting stuck at layers from bnn.torch, has anyone converted bnn layers to nn or cudnn.
any help would be appreciated.
Thank you

The issue mentions converting bnn.SpatialConvolution and bnn.binary layers to nn or cudnn for CPU support. Look at the model definition in the repository to identify where these bnn layers are used. Research the bnn.torch library to understand the layer interfaces and how they differ from standard nn layers. Check if there are existing conversion utilities or if manual reimplementation is needed, then test the converted model on CPU.

索引モデルが issue の本文から書いたものです。