>>> final_embedding=normalized_embeddings.eval()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 569, in eval
    return _eval_using_default_session(self, feed_dict, self.graph, session)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3727, 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)`

Solve it by defining a session like below,

sess = tf.Session()

and then running above command as follows,

>>> final_embedding=normalized_embeddings.eval(session=sess)

or run it as follows,

>>>with tf.Session().as_default():
       final_embedding=normalized_embeddings.eval()

or run it as follows,

>>>sess=tf.InteractiveSession()
>>>final_embedding=normalized_embeddings.eval()