从经过训练的 RNN 模型生成单词："Variable already exists, disallowed. Did you mean to set reuse=True in VarScope? "

Question

所以我在jupytor notebook中实现了一个RNN词生成器模型。当我尝试使用经过训练的模型生成一些单词时：

    with open(os.path.join(cfgs['save_dir'], 'config.pkl'), 'rb') as f:
       saved_args = cPickle.load(f)

    with open(os.path.join(cfgs['save_dir'], 'words_vocab.pkl'), 'rb') as f:
       words, vocab = cPickle.load(f)

    with tf.Session() as sess:
       model = Model(saved_args, True)
       tf.global_variables_initializer().run()
       saver = tf.train.Saver(tf.global_variables())
       ckpt = tf.train.get_checkpoint_state(cfgs['save_dir'])
       if ckpt and ckpt.model_checkpoint_path:
           saver.restore(sess, ckpt.model_checkpoint_path)
           print(model.sample(sess, words, vocab, cfgs['n'], cfgs['prime'], cfgs['sample'], cfgs['pick'], cfgs['width']))

它是第一次工作，但是如果我运行代码再次出现错误：

    ValueError: Variable rnnlm/softmax_w already exists, disallowed. Did you mean to set reuse=True in VarScope?

现在我必须关闭 ipynb 文件，然后运行代码才能获得新样本。如何更改代码避免这种情况？

Answer 1

您可以多次调用 model.sample 函数而不会出现问题，但其他一切（创建会话、构造模型、加载检查点）应该只运行一次。如果您重构代码，您将不会再看到该错误消息。

从经过训练的 RNN 模型生成单词："Variable already exists, disallowed. Did you mean to set reuse=True in VarScope? "

Generating words from trained RNN model: "Variable already exists, disallowed. Did you mean to set reuse=True in VarScope? "

machine-learning

tensorflow

deep-learning

ipython-notebook

rnn