p17土堆说卷积操作

weight权重，就是就是卷积核


先看所需要的参数


发现input不符合要求，可使用pytorch提供的变换

import torch
import torch.nn.functional as F

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]])

kernal = torch.tensor([[1, 2,  0],
                       [0, 1, 0],
                       [2, 1, 0]])

input = torch.reshape(input, (1, 1, 5, 5))
# input – input tensor of shape (\text{minibatch} , \text{in\_channels} , iH , iW)(minibatch,in_channels,iH,iW)
kernal = torch.reshape(kernal, (1, 1, 3, 3))
print(input.shape)
print(kernal.shape)

output = F.conv2d(input, kernal, stride=1)
print(output)

D:\anaconda\python.exe C:/Users/ASUS/Desktop/tudui/nn_conv.py
torch.Size([1, 1, 5, 5])
torch.Size([1, 1, 3, 3])
tensor([[[[10,  9, 11],
          [16, 13, 15],
          [12,  9,  3]]]])

Process finished with exit code 0