torch常用操作—— torch.nn.functional.pad

torch.nn.functional.pad

作用：填充tensor
目前为止，只支持2d和3d填充
用法：

 torch.nn.functional.pad(input, pad, mode='constant', value=0)[source]

input需要填充的tensor
pad决定填充的方向
以下面的例子观察可知：
pad为tuple (pad_l, pad_r, pad_t, pad_b )
其中四个元素的位置代表了填充的位置，大小为填充的行数，如果需要填充指定数值的话，可以指定values为你想要的数据

code1:

import torch
import torch.nn.functional as F
a = torch.rand(1, 3, 3)
print(a)
b = F.pad(a, [0, 0, 0, 1])
print(b)

output:

code2:

import torch
import torch.nn.functional as F
a = torch.rand(1, 3, 3)
print(a)
b = F.pad(a, [0, 0, 1, 0])
print(b)

output:

code3:

import torch
import torch.nn.functional as F
a = torch.rand(1, 3, 3)
print(a)
b = F.pad(a, [0, 1, 0, 0])
print(b)

output:

code4:

import torch
import torch.nn.functional as F
a = torch.rand(1, 3, 3)
print(a)
b = F.pad(a, [1, 0, 0, 0])
print(b)

output: