How to compute the inverse of a square matrix in PyTorch

In this article, we are going to cover how to compute the inverse of a square matrix in PyTorch. 

torch.linalg.inv() method

we can compute the inverse of the matrix by using torch.linalg.inv() method. It accepts a square matrix and a batch of the square matrices as input. If the input is a batch of the square matrices then the output will also have the same batch dimensions. This method returns the inverse matrix.

Syntax: torch.linalg.inv(M)

Parameters:

• M – This is our square matrix or a batch of square matrix.

Returns: it will returns the inverse matrix.

Example 1:

In this example, we will understand how to compute the inverse of a 4×4 square matrix in PyTorch.

Python3

# import required library
import torch

# define a 4x4 square matrix
mat = torch.tensor([[ 1.00, -0.000, -0.00,  0.00],
        [ 4.00,  1.000,  2.00,  0.00],
        [ -9.00,  -3.00,  1.00,  8.00],
        [ -2.00, -0.00, -0.00,  1.00]])
print("Input Matrix M: \n", mat)

# compute the inverse of matrix
Mat_inv = torch.linalg.inv(mat)

# display result
print("\nInverse Matrix: \n", Mat_inv)

Output:

Example 2:

In this example, we will compute the inverse of a batch of square matrices in PyTorch.

Python3

# import required library
import torch

# define a batch of two 3x3 square matrix
mat = torch.tensor([[[1.0, 2.0, 3.0], [4.0, 1.0, 6.0],
                     [1.0, 1.0, 1.0]],
                    [[2.0, 2.0, 3.0], [4.0, 5.0, 6.0],
                     [2.0, 2.0, 2.0]]])
print("Input Matrix M: \n", mat)

# compute the inverse of matrix
Mat_inv = torch.linalg.inv(mat)

# display result
print("\nInverse Matrix: \n", Mat_inv)

Output: