神经网络--卷积层

卷积操作

torch.nn.functional.conv2d()：对由多个输入平面组成的输入信号进行二维卷积
stride：滑动步长
padding：对矩阵边缘进行填充

import torch
import torch.nn.functional as F

#输入图像5×5
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]])

#输入卷积核3×3
kernel = torch.tensor([[1, 2, 1],
                      [0, 1, 0],
                      [2, 1, 0]])

#输入input和卷积核kernel需要四个参数，要求相乘之后乘积不变
input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))

#对由多个输入平面组成的输入信号进行二维卷积
# stride：滑动步长
output1 = F.conv2d(input, kernel, stride=1)
print(output1)

output2 = F.conv2d(input, kernel, stride=2)
print(output2)

#padding：对矩阵边缘进行填充
output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)

结果：

tensor([[[[10, 12, 12],
          [18, 16, 16],
          [13,  9,  3]]]])
tensor([[[[10, 12],
          [13,  3]]]])
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]]]])

in_channels：输入图片通道
out_channels：由卷积产生的通道数
kernel_size：卷积核尺寸
stride：滑动步长
padding：边缘填充
经过卷积操作后原始图减小，例子中从32×32变成30×30

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

dataset = torchvision.datasets.CIFAR10("./data", train=False, transform=torchvision.transforms.ToTensor(), download=True)
dataloader = DataLoader(dataset, batch_size=64)

class Test(nn.Module):
    def __init__(self):
        super(Test, self).__init__()

        #in_channels=3：输入图片第三通道
        #out_channels=6：由卷积产生的通道数6
        #kernel_size=3：卷积核3×3
        #stride=1：滑动步长1
        #padding=0：边缘填充0
        self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0)

    def forward(self,x):
        #向卷积层传入参数
        x = self.conv1(x)
        return x


test1 = Test()
writer = SummaryWriter("./logs")
step = 0

for data in dataloader:
    imgs, targets = data
    output = test1(imgs)

    #torch.Size([64, 3 ,32, 32])
    writer.add_images("input", imgs, step)

    #torch.Size([64, 6, 30, 30])
    #彩色图像的channels需要为3
    #当不能确定第一个参数的值时填-1
    output = torch.reshape(output, (-1, 3, 30, 30))

    writer.add_images("input", imgs, step)

    step = step + 1

结果：