Hi Matt,
it is not possible to share an object across different task of the same
operator or even different operators.
This would be globally mutable state which is in general hard to get
efficient in distributed systems.
Something that might work is to use a CoFlatMapOperator with one input
Errata: How can an *object (such as the classifier, line 1)* be accessed by
any Flink node [...]
Just in case, the classifier itself can't be serialized I believe, it's
part of a framework which I can't modify. In any case, even if it's
serialized, I guess the cost of moving it to one node and
