Python - tensorflow.GradientTape.reset()

Last Updated : 10 Jul, 2020

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

reset() is used to clear all information that is stored by the Tape.

Syntax: reset()

Parameters: It doesn't accept any parameters.

Returns: It returns none.

Example 1:

Python3

# Importing the library
import tensorflow as tf

x = tf.constant(4.0)

# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  y = x * x * x
  y+=x*x

# Computing gradient without reset
res  = gfg.gradient(y, x) 

# Printing result
print("res(y = x*x*x + x*x): ",res)

# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  y = x * x * x

  # Resetting the Tape
  gfg.reset()
  
  gfg.watch(x)
  y+=x*x

# Computing gradient with reset
res  = gfg.gradient(y, x) 

# Printing result
print("res(y = x*x): ",res)

Output:


res(y = x*x*x + x*x):  tf.Tensor(56.0, shape=(), dtype=float32)
res(y = x*x):  tf.Tensor(8.0, shape=(), dtype=float32)

Example 2:

Python3

# Importing the library
import tensorflow as tf

x = tf.constant(3.0)

# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  y = x * x
  y+=x*x

# Computing gradient without reset
res  = gfg.gradient(y, x) 

# Printing result
print("res(y = x*x + x*x): ",res)

# Using GradientTape
with tf.GradientTape() as gfg:
  gfg.watch(x)
  y = x * x

  # Resetting the Tape
  gfg.reset()
  gfg.watch(x)
  y+=x

# Computing gradient with reset
res  = gfg.gradient(y, x) 

# Printing result
print("res(y = x): ",res)

Output:


res(y = x*x + x*x):  tf.Tensor(12.0, shape=(), dtype=float32)
res(y = x):  tf.Tensor(1.0, shape=(), dtype=float32)

Python Introduction

aman neekhara

Improve

Article Tags :

Practice Tags :

python

Python - tensorflow.GradientTape.reset()

Similar Reads

Python Fundamentals

Python Data Structures

Advanced Python

Data Science with Python

Web Development with Python

Python Practice

Thank You!

What kind of Experience do you want to share?