ValueError: Variable embedding_attention_seq2seq/rnn/embedding_wrapper/embedding already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at

Question

with tf.Session() as sess:
encoder_inputs, decoder_inputs, target_weights, outputs, loss, update, saver, learning_rate_decay_op, learning_rate = get_model(feed_previous=True)
saver.restore(sess, './model/demo')
sys.stdout.write("> ")
sys.stdout.flush()
input_seq = sys.stdin.readline()

            报的是这个get_model这一行的错误，请问大家要怎么改

Answer 1

get_model的代码检查下，存在重复定义张量的问题，搜索下代码中的embedding