（四）卷积操作

从左到右，从上到下

import torch

input = torch.tensor([[1,2,0,3,1],
                      [0,1,2,3,1],
                      [1,2,1,0,0],
                      [5,2,3,1,1],
                      [2,1,0,1,1]])

kernel = torch.tensor([[1,2,1],
                       [0,1,0],
                       [2,1,0]])
print(input.shape)
print(kernel.shape)

结果：没有通道

进行尺寸变换

卷积时，需要将图像转换为四维来表示

#进行尺寸变换
input = torch.reshape(input,(1,1,5,5))
kernel = torch.reshape(kernel,(1,1,3,3))

结果：batch，channel，h, w

import torch.nn.functional as F
#stride为1
output = F.conv2d(input,kernel,stride=1)
print(output)
#stride为2
output = F.conv2d(input,kernel,stride=2)
print(output)

结果：

---

 padding：默认为0

上下左右进行扩充，默认为0

 

'''padding'''
output3 = F.conv2d(input,kernel,stride=1,padding=1)
print(output3)

结果

完整代码

import torch
import torch.nn.functional as F
#图像
input = torch.tensor([[1,2,0,3,1],
                      [0,1,2,3,1],
                      [1,2,1,0,0],
                      [5,2,3,1,1],
                      [2,1,0,1,1]])
#卷积核
kernel = torch.tensor([[1,2,1],
                       [0,1,0],
                       [2,1,0]])
#进行尺寸变换
input = torch.reshape(input,(1,1,5,5))
kernel = torch.reshape(kernel,(1,1,3,3))
#打印形状
print(input.shape)
print(kernel.shape)
#stride为1
output = F.conv2d(input,kernel,stride=1)
print(output)
#stride为2
output = F.conv2d(input,kernel,stride=2)
print(output)

'''padding'''
output3 = F.conv2d(input,kernel,stride=1,padding=1)
print(output3)