Predict a categorical variable and then embed it (one-hot?)

@tom what is the best way to code this, if I have many categorical variables?

If I split the categoricals into an array of one-hot tensors, then it is a little easier to construct the net. However, I am concerned this would not be performant.

If I have all the values together, then I might need to have the dataset provide a list of ranges to slice. It’s a little trickier, but is that much faster?