Python Pytorch one() 方法

PyTorch 是 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目的。

函数torch.ones()返回一个用标量值 1 填充的张量，其形状由变量参数大小定义。

Syntax: torch.ones(size, out=None)

Parameters:
size: a sequence of integers defining the shape of the output tensor
out (Tensor, optional): the output tensor

Return type: A tensor filled with scalar value 1, of same shape as size.

代码#1：

# Importing the PyTorch library
import torch
  
  
# Applying the ones function and
# storing the resulting tensor in 't'
a = torch.ones([3, 4])
print("a = ", a)
  
b = torch.ones([1, 5])
print("b = ", b)
  
c = torch.ones([5, 1])
print("c = ", c)
  
d = torch.ones([3, 3, 2])
print("d = ", d)

输出：

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

        [[1., 1.],
         [1., 1.],
         [1., 1.]],

        [[1., 1.],
         [1., 1.],
         [1., 1.]]])