Python – tensorflow.math.log1p()

TensorFlow is open-source python library designed by Google to develop Machine Learning models and deep learning  neural networks. TensorFlow raw_ops provides low level access to all TensorFlow operations. Log1p() is used to find element wise logarithm of (1+x) for input x.

Syntax: tf.math.log1p(x, name)

Parameters:

  • x: It’s the input tensor. Allowed dtype for this tensor are bfloat16, half, float32, float64, complex64, complex128.
  •  name(optional): It’s defines the name for the operation.

   

Returns:  It returns a tensor of same dtype as x.



Example 1:

Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# Importing the library
import tensorflow as tf
   
# Initializing the input tensor
a = tf.constant([1, 2, 3, 4, 5], dtype = tf.float64)
   
# Printing the input tensor
print('Input: ', a)
   
# Calculating logarithm(1 + x)
res = tf.math.log1p(x = a)
   
# Printing the result
print('Result: ', res)

chevron_right


Output:

Input:  tf.Tensor([1. 2. 3. 4. 5.], shape=(5, ), dtype=float64)
Result:  tf.Tensor([0.69314718 1.09861229 1.38629436 1.60943791 1.79175947], shape=(5, ), dtype=float64)


Example 2: Visualization

Python3

filter_none

edit
close

play_arrow

link
brightness_4
code

# importing the library
import tensorflow as tf
import matplotlib.pyplot as plt
   
# Initializing the input tensor
a = tf.constant([1, 2, 3, 4, 5], dtype = tf.float64)
   
# Calculating logarithm(1 + x)
res = tf.math.log1p(x = a)
   
# Plotting the graph
plt.plot(a, res, color ='green')
plt.title('tensorflow.math.log1p')
plt.xlabel('Input')
plt.ylabel('Result')
plt.show()

chevron_right


Output:




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.