0 votes
1 view
in Machine Learning by (47.7k points)

How to convert a tensor into a numpy array when using Tensorflow with Python bindings?

1 Answer

0 votes
by (33.1k points)

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]))))

 <class 'numpy.ndarray'>

Or

>>> sess = tf.InteractiveSession() 

>>> print(type(tf.constant([1,2,3]).eval())) 

<class 'numpy.ndarray'>

Or

>>> sess = tf.Session() 

>>> with sess.as_default():

>>> print(type(tf.constant([1,2,3]).eval())) 

<class 'numpy.ndarray'>

Hope this answer helps.

Welcome to Intellipaat Community. Get your technical queries answered by top developers !


Categories

...