How to Pad the Input Tensor Boundaries with Zero in PyTorch

In this article, we will discuss how to pad the input tensor boundaries with zero in Python using PyTorch.

torch.nn.ZeroPad2D() method

This method has accepted the size of padding as input and returns a new tensor with boundaries. The boundaries may be the same or different from all sides (left, right, top, bottom). we can increase the height and width of a padded tensor by using top+bottom and left+right respectively. The below syntax is used to pad the input tensor boundaries with zero.

Syntax: torch.nn.ZeroPad2d(pad)

Parameter:

• pad (int, tuple): This is size of padding. The size of padding is an integer or a tuple.

Return: This method returns a new tensor with boundaries.

Example 1:

In this example, we will see how to pad the input tensor boundaries with zero.

# Import required library
import torch
import torch.nn as nn
# define a tensor
tens = torch.tensor([[[11, 12], [13, 14]]])
print("\n Input Tensor: \n", tens)
# give padding size same for all sides
pad = nn.ZeroPad2d(1)
output = pad(tens)
# display result
print("\n After Pad Input Tensor: \n", output)

Output:

Example 2:

In this example, we will see how to add unique padding sizes to all sides.

# Import required library
import torch
import torch.nn as nn
# define a tensor
tens = torch.tensor([[[11, 12], [13, 14]]])
print("\n Input Tensor: \n", tens)
# add unique padding sizes to all sides
# (left, right, top, bottom)
pad = nn.ZeroPad2d((1, 2, 3, 4))
output = pad(tens)
# display result
print("\n After Pad Input Tensor:\n", output)

Output: