Python – PyTorch log() method

PyTorch torch.log() method gives a new tensor having the natural logarithm of the elements of input tensor.

Syntax: torch.log(input, out=None)

Arguments

• input: This is input tensor.
• out: The output tensor.

Return: It returns a Tensor.

Let’s see this concept with the help of few examples:
Example 1:

# Importing the PyTorch library
import torch

# A constant tensor of size n
a = torch.FloatTensor([5, 6, 7, 4])
print(a)

# Applying the log function and
# storing the result in 'out'
out = torch.log(a)
print(out)

Output:

5
 6
 7
 4
[torch.FloatTensor of size 4]

 1.6094
 1.7918
 1.9459
 1.3863
[torch.FloatTensor of size 4]

Example 2:

# Importing the PyTorch library
import torch

# A constant tensor of size n
a = torch.FloatTensor([1.45, 2.3, 10])
print(a)

# Applying the log function and
# storing the result in 'out'
out = torch.log(a)
print(out)

Output:

 1.4500
  2.3000
 10.0000
[torch.FloatTensor of size 3]

 0.3716
 0.8329
 2.3026
[torch.FloatTensor of size 3]