在这里https://github.com/tensorflow/models/blob/master/tutorials/rnn/translate/translate.py#L281-L282
# This is a greedy decoder - outputs are just argmaxes of output_logits.
outputs = [int(np.argmax(logit, axis=1)) for logit in output_logits]
最初很难理解,其实就是在所有词里选概率最大的