Python Pytorch eye() method

PyTorch is an open-source machine learning library developed by Facebook. It is used for deep neural network and natural language processing purposes.

The function torch.eye() returns a returns a 2-D tensor of size n*m with ones on the diagonal and zeros elsewhere.

Syntax: torch.eye(n, m, out=None)

Parameters:
n: the number of rows
m: the number of columns. Default – n
out (Tensor, optional): the output tensor

Return type: A 2-D tensor

Code #1:

# Importing the PyTorch library
import torch


# Applying the eye function and
# storing the resulting tensor in 'a'
a = torch.eye(3, 4)
print("a = ", a)

b = torch.eye(3, 3)
print("b = ", b)

c = torch.eye(5, 1)
print("c = ", c)

Output:

a =  tensor([[1., 0., 0., 0.],
        [0., 1., 0., 0.],
        [0., 0., 1., 0.]])
b =  tensor([[1., 0., 0.],
        [0., 1., 0.],
        [0., 0., 1.]])
c =  tensor([[1.],
        [0.],
        [0.],
        [0.],
        [0.]])