How to perform element-wise addition on tensors in PyTorch?

In this article, we are going to see how to perform element-wise addition on tensors in PyTorch in Python. We can perform element-wise addition using torch.add() function. 

This function also allows us to perform addition on the same or different dimensions of tensors. If tensors are different in dimensions so it will return the higher dimension tensor. 

Syntax: torch.add(inp, c, out=None)

Parameters:

• inp: This is input tensor.
• c: The value that is to be added to every element of tensor.
• out: This is optional parameter and it is the output tensor.

Return: returns a new modified tensor..

Example 1: The following program is to perform addition on two single dimension tensors.

Python3

# import torch library
import torch

# define two tensors
tens_1 = torch.Tensor([10, 20, 30, 40, 50])
tens_2 = torch.Tensor([1, 2, 3, 4, 5])

# display tensors
print("\nFirst Tensor \n", tens_1)
print("\nsecond Tensor \n", tens_2)

# Add both the tensor
tens = torch.add(tens_1, tens_2)
print("\n After Element-wise Addition\n", tens)

Output:

Example 2: The following program is to perform elements-wise addition on 2D tensors.

Python3

# import the torch library
import torch

# define 2D tensors
tens_1 = torch.Tensor([[1, 2], [3, 4]])
tens_2 = torch.Tensor([[10, 20], [20, 40]])

# display these tensors
print("First Tensor \n", tens_1)
print("second Tensor \n", tens_2)

# perform addition on these tensors
tens = torch.add(tens_1, tens_2)

# display final result
print("\n After Element-wise Addition\n", tens)

Output:

Example 3: The following program is to shows how to perform elements-wise addition on two different dimension tensors.

Python3

# import torch library
import torch

# define 1D tensor
tens_1 = torch.Tensor([1, 2])

# define 2D tensor
tens_2 = torch.Tensor([[10, 20], [20, 40]])

# display tensors
print("\nFirst Tensor \n", tens_1)
print("\nsecond Tensor \n", tens_2)

# perform addition on tensors
tens = torch.add(tens_1, tens_2)

# display final output
print("\n After Element-wise Addition\n", tens)

Output:

Example 4: The following program is to know how to add a scalar quantity to a tensor.

Python3

# Python program to perform element-wise Addition
# import the required library
import torch

# define a tensor
tens_1 = torch.Tensor([1, 2, 3, 4])

# define 2D tensor
tens_2 = torch.Tensor([[10, 20], [30, 40]])

# display tensors
print("\nFirst Tensor \n", tens_1)
print("second Tensor \n", tens_2)

# perform addition on 1D tensors
t1 = torch.add(tens_1, 10)
# display final output
print("\n After adding scalar quantity to 1D tensor: \n", t1)

# perform addition on 2D tensors
t2 = torch.add(tens_2, 20)
# display final output
print("\n After adding scalar quantity to 2D tensor: \n", t2)

Output: