Python – PyTorch floor() method

PyTorch torch.floor() method returns a new tensor which is floor of the elements of input, the largest integer less than or equal to each element.

Syntax: torch.floor(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([1.5, 4.2, 6.7, 3.9])
print(a)

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

Output:

 1.5000
 4.2000
 6.7000
 3.9000
[torch.FloatTensor of size 4]

 1
 4
 6
 3
[torch.FloatTensor of size 4]

Example 2:

# Importing the PyTorch library
import torch

# A constant tensor of size n
a = torch.FloatTensor([1.59, 4.5999, 6.78, 3.99999])
print(a)

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

Output:

1.5900
 4.5999
 6.7800
 4.0000
[torch.FloatTensor of size 4]

 1
 4
 6
 3
[torch.FloatTensor of size 4]