invalid factor level, na generated

For your problem, Tensor returned by Session.run() or tf.eval() is already a NumPy array, except for Sparse tensor, they return Sparse value.

For example:

>>> print(type(tf.Session().run(tf.constant([1,2,3]))))
 
Or
>>> sess = tf.InteractiveSession() 
>>> print(type(tf.constant([1,2,3]).eval())) 

Or
>>> sess = tf.Session() 
>>> with sess.as_default():
>>> print(type(tf.constant([1,2,3]).eval())) 

Hope this answer helps you convert tensor to NumPy array.