tf.contrib.seq2seq.prepare_attention(attention_states, attention_option, num_units, reuse=False)
Prepare keys/values/functions for attention.
attention_states: hidden states to attend over.
attention_option: how to compute attention, either "luong" or "bahdanau".
num_units: hidden state dimension.
reuse: whether to reuse variable scope.
attention_keys: to be compared with target states.
attention_values: to be used to construct context vectors.
attention_score_fn: to compute similarity between key and target states.
attention_construct_fn: to build attention states.