TensorFlow is open-source Python library designed by Google to develop Machine Learning models and deep learning neural networks.
grad_pass_through() is used to create grad-pass-through operation with forward behavior passes by function.
Syntax: tensorflow.grad_pass_through( f )
Parameters:
- f: It is a function which returns a Tensor or nested structure of Tensor.
Returns: It returns a function h(x) which returns the same values as f(x) and whose gradients are the same as those of an identity function.
Example 1:
Python3
# Importing the libraryimport tensorflow as tf# Initializing the Tensorx = tf.Variable(2.0, name ="x")z = tf.Variable(4.0, name ="z")with tf.GradientTape() as gfg: # y will evaluate to 16.0 i.e 4**2 y = tf.grad_pass_through(x.assign)(z**2)# res will evaluate to 8.0res = gfg.gradient(y, z)# Printing resultprint("y: ", y)print("res: ", res) |
Output:
y: tf.Tensor(16.0, shape=(), dtype=float32) res: tf.Tensor(8.0, shape=(), dtype=float32)
Example 2:
Python3
# Importing the libraryimport tensorflow as tf# Initializing the Tensorx = tf.Variable(3.0, name ="x")with tf.GradientTape() as gfg: # y will evaluate to 9.0 i.e 3**2 y = tf.grad_pass_through(x.assign)(x**2)# res will evaluate to 6.0res = gfg.gradient(y, x)# Printing resultprint("y: ", y)print("res: ", res) |
Output:
y: tf.Tensor(9.0, shape=(), dtype=float32) res: tf.Tensor(6.0, shape=(), dtype=float32)
