rnn.rnn is removed since Tensorflow 1.0, the demo doesn't work on it.

[doncat99]

After a little modification to the source code as to adapt to the Tensorflow 1.0, I found the following error:

ValueError: Attempt to reuse RNNCell <tensorflow.contrib.rnn.python.ops.core_rnn_cell_impl.BasicLSTMCell object at 0x1170bb710> with a different variable scope than its first use. First use of cell was with scope 'model/rnn/multi_rnn_cell/cell_0/basic_lstm_cell', this attempt is with scope 'model/rnn/multi_rnn_cell/cell_1/basic_lstm_cell'. Please create a new instance of the cell if you would like it to use a different set of weights. If before you were using: MultiRNNCell([BasicLSTMCell(...)] * num_layers), change to: MultiRNNCell([BasicLSTMCell(...) for _ in range(num_layers)]). If before you were using the same cell instance as both the forward and reverse cell of a bidirectional RNN, simply create two instances (one for forward, one for reverse). In May 2017, we will start transitioning this cell's behavior to use existing stored weights, if any, when it is called with scope=None (which can lead to silent model degradation, so this error will remain until then.)

And yet I have no idea how to fix it, hope anyone would hint me a little.
Below is my modification to the source.

    from tensorflow.contrib import rnn

    lstm_cell = rnn.BasicLSTMCell(hidden_size, forget_bias=0.0, state_is_tuple=True)
    
    if is_training and config.keep_prob < 1:
        lstm_cell = rnn.DropoutWrapper(lstm_cell, output_keep_prob=config.keep_prob)
    cell = rnn.MultiRNNCell([lstm_cell for _ in range(config.num_layers)], state_is_tuple=True)

    self._initial_state = cell.zero_state(batch_size, tf.float32)

    iw = tf.get_variable("input_w", [1, hidden_size])
    ib = tf.get_variable("input_b", [hidden_size])
    inputs = [tf.nn.xw_plus_b(i_, iw, ib) for i_ in tf.split(self._input_data, num_steps, 1)]

    if is_training and config.keep_prob < 1:
        inputs = [tf.nn.dropout(input_, config.keep_prob) for input_ in inputs]
    
    outputs, states = rnn.static_rnn(cell, inputs, initial_state=self._initial_state)

[hhuhhu]

it's ok now, i modify the code as above, it didn't come across this problem