MXNet.jl - weighted classes in SoftmaxOutput

mxnetjl

#1

I’m using MXNet.jl to write a binary classifier for a problem with class imbalance. I’d like to weight the two classes unequally when calculating the loss (i.e. a false positive would be weighted differently than a false negative). Is it possible to pass mx.SoftmaxOutput a vector of weights to use when calculating the loss?