Python – PyTorch frac() method

PyTorch torch.frac() method computes the fractional portion of each element in input.

Syntax: torch.frac(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([-5.4, 6.6, -7.1099, 4.4567])
print(a)

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

Output:

-5.4000
 6.6000
-7.1099
 4.4567
[torch.FloatTensor of size 4]

-0.4000
 0.6000
-0.1099
 0.4567
[torch.FloatTensor of size 4]

Example 2:

# Importing the PyTorch library
import torch

# A constant tensor of size n
a = torch.randn(6)
print(a)

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

Output:

-0.5260
-1.8843
 0.8062
 1.2264
-0.1505
-0.3217
[torch.FloatTensor of size 6]

-0.5260
-0.8843
 0.8062
 0.2264
-0.1505
-0.3217
[torch.FloatTensor of size 6]