Python Pytorch eye()用法及代码示例

PyTorch是由Facebook开发的开源机器学习库。它用于深度神经网络和自然语言处理。

函数torch.eye()返回a返回大小为n * m的2-D张量，对角线为1，其他位置为零。

用法:torch.eye(n, m, out=None)

代码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)

输出：

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.]])