seq2seq模型运行时错误：ValueError: too many values to unpack (expected 2) about zhihu

[NELSONZHAO]

我重新跑了一遍，问题主要在于TensorFlow的版本问题，我当时写代码的版本是1.1，1.3的部分接口发生改变，这种问题修改调用接口的代码就可以。解决方案：
1.使用TensorFlow1.1版本重新跑。
2.decoding_layer函数里修改代码：
training_decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(training_decoder, impute_finished=True, maximum_iterations=max_target_sequence_length)
为
training_decoder_output, _, _ = tf.contrib.seq2seq.dynamic_decode(training_decoder, impute_finished=True, maximum_iterations=max_target_sequence_length)

修改：
predicting_decoder_output, _ = tf.contrib.seq2seq.dynamic_decode(predicting_decoder, impute_finished=True, maximum_iterations=max_target_sequence_length)
为：
predicting_decoder_output, _, _ = tf.contrib.seq2seq.dynamic_decode(predicting_decoder, impute_finished=True, maximum_iterations=max_target_sequence_length)

1和2方案我都试过了，可以正常运行