ValueError: Variable rnn/basic_rnn_cell/kernel already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?

Question

Any ideas how can I solve problem shown below? With the information that I found on the web it is associated with problem of reusing tensorflow scope however nothing works.

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

  File "/code/backend/management/commands/RNN.py", line 370, in predict
    states_series, current_state = tf.nn.dynamic_rnn(cell=cell, inputs=batchX_placeholder, dtype=tf.float32)
  File "/code/backend/management/commands/RNN.py", line 499, in Command
    predict("string")
  File "/code/backend/management/commands/RNN.py", line 12, in <module>
    class Command(BaseCommand):

I tried for instance something like this

with tf.variable_scope('scope'):
 states_series, current_state = tf.nn.dynamic_rnn(cell=cell, inputs=batchX_placeholder, dtype=tf.float32)

and this

with tf.variable_scope('scope', reuse = True ):
 states_series, current_state = tf.nn.dynamic_rnn(cell=cell, inputs=batchX_placeholder, dtype=tf.float32)

and this

with tf.variable_scope('scope', reuse = tf.AUTO_REUSE ):
 states_series, current_state = tf.nn.dynamic_rnn(cell=cell, inputs=batchX_placeholder, dtype=tf.float32)

Any ideas?

Solution

Does this happen when you run the model for the first time (upon opening a new python console)?

If not, you need to clear you computational graph. You can do that by putting this line at the beginning of your script.

tf.reset_default_graph()