How to not generate the 'is_training' variable?

[yurivict]

The 'is_training' variable is added to the model and unnecessarily overcomplicates it.

The documentation suggests to add tflearn.is_training(False). However, this causes the failure:

  File "firenet-to-protobuf.py", line 30, in <module>
    tflearn.is_training(False)
  File "/usr/local/lib/python3.6/site-packages/tflearn/config.py", line 97, in is_training
    tf.get_collection('is_training_ops')[1].eval(session=session)
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 731, in eval
    return _eval_using_default_session(self, feed_dict, self.graph, session)
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 5565, in _eval_using_default_session
    raise ValueError("Cannot evaluate tensor using `eval()`: No default "
ValueError: Cannot evaluate tensor using `eval()`: No default session is registered. Use `with sess.as_default()` or pass an explicit session to `eval(session=sess)`

So how to eliminate is_training?