So any nn.Module fields are handled automatically, but beyond that then we need to used setup? e.g. say I have a CSV I read in using pandas in __init__, that field would only be present on the main thread and on the other threads?
So any nn.Module fields are handled automatically, but beyond that then we need to used setup? e.g. say I have a CSV I read in using pandas in __init__, that field would only be present on the main thread and on the other threads?