Method generate_enqueue_ops

Generates the host-side Ops to enqueue the shards of a tuple. sharded_inputs is a list, one for each shard, of lists of Tensors. sharded_inputs[0] is the tuple of Tensors to use to feed shard 0 if the queue. Returns the host-side Ops that must be run to enqueue the sharded tuple. Th

(self,
                           sharded_inputs,
                           tpu_ordinal_function=None,
                           placement_function=None)