【VGG11】VGG11 网络结构

Enzo 想砸电脑

已于 2023-03-03 23:06:44 修改

阅读量601

点赞数 1

文章标签：人工智能 python 深度学习

于 2023-01-08 21:23:01 首次发布

本文链接：https://blog.csdn.net/weixin_37804469/article/details/128605843

版权

传统图像处理同时被 2 个专栏收录

4 篇文章 0 订阅

订阅专栏

图片分类

4 篇文章 1 订阅

订阅专栏

class VGG11(nn.Module):
    def __init__(self):
        super(VGG11, self).__init__()

        self.conv_block1 = nn.Sequential(
            nn.Conv2d(in_channels=1, out_channels=8, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.conv_block2 = nn.Sequential(
            nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.conv_block3 = nn.Sequential(
            nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.Conv2d(in_channels=32, out_channels=32, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.conv_block4 = nn.Sequential(
            nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.conv_block5 = nn.Sequential(
            nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)
        )

        self.linear1 = nn.Sequential(
            nn.Linear(in_features=3136, out_features=512),
            nn.ReLU(),
            nn.Dropout(p=0.5)
        )

        self.linear2 = nn.Sequential(
            nn.Linear(in_features=512, out_features=512),
            nn.ReLU(),
            nn.Dropout(p=0.5)
        )

        self.linear3 = nn.Linear(in_features=512, out_features=120)


    def forward(self, x):
        x = self.conv_block1(x)
        x = self.conv_block2(x)
        x = self.conv_block3(x)
        x = self.conv_block4(x)
        x = self.conv_block5(x)
        x = x.view(x.shape[0], -1)
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.linear3(x)
        return x


net = VGG11()
summary(net, input_size=(1, 224, 224))

输出：

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1          [-1, 8, 224, 224]              80
              ReLU-2          [-1, 8, 224, 224]               0
         MaxPool2d-3          [-1, 8, 112, 112]               0
            Conv2d-4         [-1, 16, 112, 112]           1,168
              ReLU-5         [-1, 16, 112, 112]               0
         MaxPool2d-6           [-1, 16, 56, 56]               0
            Conv2d-7           [-1, 32, 56, 56]           4,640
              ReLU-8           [-1, 32, 56, 56]               0
            Conv2d-9           [-1, 32, 56, 56]           9,248
             ReLU-10           [-1, 32, 56, 56]               0
        MaxPool2d-11           [-1, 32, 28, 28]               0
           Conv2d-12           [-1, 64, 28, 28]          18,496
             ReLU-13           [-1, 64, 28, 28]               0
           Conv2d-14           [-1, 64, 28, 28]          36,928
             ReLU-15           [-1, 64, 28, 28]               0
        MaxPool2d-16           [-1, 64, 14, 14]               0
           Conv2d-17           [-1, 64, 14, 14]          36,928
             ReLU-18           [-1, 64, 14, 14]               0
           Conv2d-19           [-1, 64, 14, 14]          36,928
             ReLU-20           [-1, 64, 14, 14]               0
        MaxPool2d-21             [-1, 64, 7, 7]               0
           Linear-22                  [-1, 512]       1,606,144
             ReLU-23                  [-1, 512]               0
          Dropout-24                  [-1, 512]               0
           Linear-25                  [-1, 512]         262,656
             ReLU-26                  [-1, 512]               0
          Dropout-27                  [-1, 512]               0
           Linear-28                  [-1, 120]          61,560
================================================================
Total params: 2,074,776
Trainable params: 2,074,776
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.19
Forward/backward pass size (MB): 15.65
Params size (MB): 7.91
Estimated Total Size (MB): 23.75