从训练有素的RNN模型生成单词:“变量已经存在,不允许。您是不是要在VarScope中设置reuse = True?”

时间:2017-08-24 20:52:38

标签: machine-learning tensorflow deep-learning ipython-notebook rnn

所以我在jupytor笔记本中实现了RNN字生成器模型。 当我尝试使用训练过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']))

它首次运行,但如果我再次运行代码则会出现错误:

    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文件然后运行代码以获取新样本。 如何更改代码以避免这种情况?

1 个答案:

答案 0 :(得分:1)

您可以多次调用model.sample函数而不会出现问题,但其他所有内容(创建会话,构建模型,加载检查点)应该只运行一次。如果您重构代码,那么您将不再看到该错误消息。