ValueError Issu about indrnn

[batzner]

Hi, can you provide details on which code you ran? Was it the examples/addition_rnn.py script or the example code in the Readme? Did you run it on master or another branch?

I hope, we can find the problem.

[sam9211]

I think it's something related with tf.variable_scope. When I run the addition_rnn.py script directly using python everything is OK, but if I copy the code into my Jupyter Notebook and run the bug happened. I have fixed the bug by adding:
with tf.variable_scope("indrnn", reuse=None):
in front of
output, state = tf.nn.dynamic_rnn(cell, inputs_ph, dtype=tf.float32)
and make all the rest code within that with loop, then it started running.

[batzner]

The error usually occurs, when you run
output, state = tf.nn.dynamic_rnn(cell, inputs_ph, dtype=tf.float32)
twice. Then, it will create the variables again in the second call and complain that they already exist. It might be that you ran the cell Jupyter Notebook twice, so all the variables were already initialized. I have not used TensorFlow in Jupyter yet, but restarting the notebook would probably help in such cases. Apart from that you can also use the reuse parameter of a variable scope, as you mentioned above.

[sam9211]

Cool!
Tanks again!