Python - PyTorch trunc() method

PyTorch torch.trunc() method returns a new tensor with the truncated integer values of the elements of input/ after removing the decimal portion of the number.

Syntax: torch.trunc(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: Python3

# Importing the PyTorch library 
import torch 
  
# A constant tensor of size n
a = torch.randn(6)
print(a)

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

Output:

 1.1257
 0.4493
-0.7309
 1.5523
-0.2877
 0.1155
[torch.FloatTensor of size 6]
 1
 0
-0
 1
-0
 0
[torch.FloatTensor of size 6]

Example 2: Python3

# Importing the PyTorch library 
import torch 
  
# A constant tensor of size n
a = torch.FloatTensor([1.5, 3.9, -6.9, 3.678])
print(a)

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

Output:

 1.5000
 3.9000
-6.9000
 3.6780
[torch.FloatTensor of size 4]
 1
 3
-6
 3
[torch.FloatTensor of size 4]