卷积操作和conv2d使用

CNN中的卷积运算是为了做特征提取。

卷积操作：

import torch
import torchvision
import torch.nn.functional as F
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

# 输入数据
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]])
# 尺寸变换
input = torch.reshape(input,(1,1,5,5)) # 5*5
kernel = torch.reshape(kernel,(1,1,3,3)) # 3*3

print(input.shape)
print(kernel.shape)

# 卷积操作  stride表示一次移动几格
output = F.conv2d(input,kernel,stride=1)
print(output)
# tensor([[[[10, 12, 12],
#          [18, 16, 16],
#          [13,  9,  3]]]])


output2 = F.conv2d(input,kernel,stride=2)
print(output2)
# tensor([[[[10, 12],
#          [13,  3]]]])

# padding=1 表示四边各加一行或一列 全部由0填充
output3 = F.conv2d(input,kernel,stride=1,padding=1)
print(output3)
# tensor([[[[ 1,  3,  4, 10,  8],
#          [ 5, 10, 12, 12,  6],
#          [ 7, 18, 16, 16,  8],
#          [11, 13,  9,  3,  4],
#          [14, 13,  9,  7,  4]]]])

图片展示卷积操作流程：

---

 Conv2d函数的使用：(二维卷积，处理二维数据)

原型：Conv2d(in_channels, out_channels, kernel_size, stride=1,padding=0, dilation=1, groups=1,bias=True, padding_mode=‘zeros’)

参数：

• in_channels：输入的通道数目

• 
  
  out_channels： 输出的通道数目

• 
  
  kernel_size：卷积核的大小

# conv2d的使用
dataset = torchvision.datasets.CIFAR10(root="./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset,batch_size=64)

class NnModule(nn.Module):
    def __init__(self):
        super(NnModule, self).__init__()
        # kernel_size:卷积核大小
        self.conv1=Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)

    def forward(self,x):
        x = self.conv1(x) # 对x进行卷积操作
        return x

nnModule = NnModule()

writer = SummaryWriter("logs")
step=0
for data in dataloader:
    imgs,targets = data
    output = nnModule(imgs)  # imgs是网络的输入
    print(imgs.shape)
    # torch.Size([64, 3, 32, 32])
    print(output.shape)
    # torch.Size([64, 6, 30, 30]) -> [xxx,3,30,30] 否则报错

    writer.add_images("input",imgs,step)
    output = torch.reshape(output,(-1,3,30,30))
    writer.add_images("output", output, step)
    step=step+1