Skip to content
Related Articles

Related Articles

Python – tensorflow.GradientTape.watch()

View Discussion
Improve Article
Save Article
  • Last Updated : 16 Jul, 2020

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

watch()  is used to start tracing Tensor by the Tape.

Syntax: watch( tensor )

Parameter:

  • tensor: It is a Tensor or list of tensors to be watched.

Returns: None

Raise:

  • ValueError: It will raise ValueError if the passes parameter is not Tensor.

Example 1:

Python3




# Importing the library
import tensorflow as tf
  
x = tf.constant(4.0)
  
# Using GradientTape
with tf.GradientTape() as gfg:
  
  # Starting the recording x
  gfg.watch(x)
  y = x * x
  
# Computing gradient
res = gfg.gradient(y, x) 
  
# Printing result
print("res: ", res)


Output:

res:  tf.Tensor(8.0, shape=(), dtype=float32)

Example 2:

Python3




# Importing the library
import tensorflow as tf
  
x = tf.constant(4.0)
z = tf.constant(5.0)
  
# Using GradientTape
with tf.GradientTape(persistent = True) as gfg:
  
  # Starting the recording x and z
  gfg.watch([x, z])
  y = z * z
  u = x * x
  
# Computing gradient
grad_y = gfg.gradient(y, z) 
grad_u = gfg.gradient(u, x)
  
# Printing result
print("grad_y: ", grad_y)
print("grad_u: ", grad_u)


Output:

grad_y:  tf.Tensor(10.0, shape=(), dtype=float32)
grad_u:  tf.Tensor(8.0, shape=(), dtype=float32)



My Personal Notes arrow_drop_up
Recommended Articles
Page :

Start Your Coding Journey Now!