Python PyTorch zeros() 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.zeros()返回一个用标量值 0 填充的张量，其形状由变量参数大小定义。

Syntax: torch.zeros(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 0, of same shape as size.

代码#1：

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

输出：

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

        [[0., 0.],
         [0., 0.],
         [0., 0.]],

        [[0., 0.],
         [0., 0.],
         [0., 0.]]])