Python – tensorflow.get_static_value()

TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning  neural networks. 

get_static_value() is used to calculate the static value of Tensor. If static value can’t be calculated it will return None.

Synatx: tensorflow.get_static_value(tensor, partial)

Parameters:

  • tensor: It is the input Tensor whose static value need to be calculated.
  • partial: Either True of False with default value set to False. It is set to True to allow returned array to have partially calculated values.

Returns: It returns a numpy ndarray that contains the calculated result.



Example 1:

Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# Importing the library
import tensorflow as tf
  
# Initializing the input
data = tf.constant([[1, 2, 3], [3, 4, 5], [5, 6, 7]])
  
# Printing the input
print('data: ',data)
  
# Calculating result
res = tf.get_static_value(data)
  
# Printing the result
print('res: ',res)

chevron_right


Output:

data:  tf.Tensor(
[[1 2 3]
 [3 4 5]
 [5 6 7]], shape=(3, 3), dtype=int32)
res:  [[1 2 3]
 [3 4 5]
 [5 6 7]]

Example 2:

Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# Importing the library
import tensorflow as tf
  
# Initializing the input
data = tf.Variable([[1, 2, 3], [3, 4, 5], [5, 6, 7]])
  
# Printing the input
print('data: ',data)
  
# Calculating result
res = tf.get_static_value(data)
  
# Printing the result
print('res: ',res)

chevron_right


Output:

data:  <tf.Variable 'Variable:0' shape=(3, 3) dtype=int32, numpy=
array([[1, 2, 3],
       [3, 4, 5],
       [5, 6, 7]], dtype=int32)>
res:  None





My Personal Notes arrow_drop_up

Check out this Author's contributed articles.

If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to contribute@geeksforgeeks.org. See your article appearing on the GeeksforGeeks main page and help other Geeks.

Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.