VGG16 结构图 + pytorch代码

最新推荐文章于 2025-03-14 11:42:51 发布

Fire丶Chicken

最新推荐文章于 2025-03-14 11:42:51 发布

阅读量1.6k

点赞数 2

分类专栏：网络文章标签： pytorch 深度学习机器学习

本文链接：https://blog.youkuaiyun.com/qq_40374812/article/details/121746593

版权

网络专栏收录该内容

1 篇文章

订阅专栏

本文详细介绍了VGG16神经网络结构图，并提供了使用PyTorch编写的实现代码，包括conv_pool_block和conv_block模块，以及整个VGG16模型的构建过程。适合深度学习入门者理解卷积神经网络架构。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

VGG16 结构图

在这里插入图片描述

需要清晰一点的可以下PDF文件：
链接: https://pan.baidu.com/s/1RaEeupUKzEQPnfy02Idp3g.
密码是：cn0t

pytorch 网络代码

import torch
import torch.nn as nn
import torch.nn.functional as F

class conv_pool_block(nn.Module):
    def __init__(self, in_channels, out_channels,conv_size=(3,3), conv_stride=(1,1), pool_size=(2,2), pool_stride=(2,2)):
        super(conv_pool_block, self).__init__()

        self.block = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=conv_size, stride=conv_stride, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=pool_size, stride=pool_stride)
            # inplace = False 时,不会修改输入对象的值,而是返回一个新创建的对象,所以打印出对象存储地址不同,类似于C语言的值传递
            # inplace = True 时,会修改输入对象的值,所以打印出对象存储地址相同,类似于C语言的址传递
            # inplace = True ,会改变输入数据的值,节省反复申请与释放内存的空间与时间,只是将原来的地址传递,效率更好
        )

    def forward(self, x):
        x = self.block(x)
        return x


class conv_block(nn.Module):
    def __init__(self, in_channels, out_channels,conv_size=(3,3), conv_stride=(1,1)):
        super(conv_block, self).__init__()

        self.block = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=conv_size, stride=conv_stride, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        x = self.block(x)
        return x


class VGG16(nn.Module):
    def __init__(self, input_size, input_channels, class_num):
        super(VGG16, self).__init__()

        conv_c = [64, 128, 256, 512, 512]
        # if input_size//32 != 0:
        #     raise ValueError("图片Size不是32的倍数！")
        l_f_size = int(input_size/32)  # Last Feature Map Size

        self.layer1_conv_block = conv_block(input_channels, conv_c[0])
        self.layer1_conv_pool_block = conv_pool_block(conv_c[0], conv_c[0])

        self.layer2_conv_block = conv_block(conv_c[0], conv_c[1])
        self.layer2_conv_pool_block = conv_pool_block(conv_c[1], conv_c[1])

        self.layer3_conv_block = nn.Sequential(
            conv_block(conv_c[1], conv_c[2]),
            conv_block(conv_c[2], conv_c[2])
        )
        self.layer3_conv_pool_block = conv_pool_block(conv_c[2], conv_c[2])

        self.layer4_conv_block = nn.Sequential(
            conv_block(conv_c[2], conv_c[3]),
            conv_block(conv_c[3], conv_c[3])
        )
        self.layer4_conv_pool_block = conv_pool_block(conv_c[3], conv_c[3])

        self.layer5_conv_block = nn.Sequential(
            conv_block(conv_c[3], conv_c[4]),
            conv_block(conv_c[4], conv_c[4])
        )
        self.layer5_conv_pool_block = conv_pool_block(conv_c[4], conv_c[4])
        self.Flatten = nn.Flatten()
        self.layer6_fc = nn.Linear(512*l_f_size*l_f_size, 4096)
        self.layer7_fc = nn.Linear(4096, 4096)
        self.layer8_fc = nn.Linear(4096, class_num)

    def forward(self, x):
        in_size = x.size(0)

        x = self.layer1_conv_block(x)
        x = self.layer1_conv_pool_block(x)

        x = self.layer2_conv_block(x)
        x = self.layer2_conv_pool_block(x)

        x = self.layer3_conv_block(x)
        x = self.layer3_conv_pool_block(x)

        x = self.layer4_conv_block(x)
        x = self.layer4_conv_pool_block(x)

        x = self.layer5_conv_block(x)
        x = self.layer5_conv_pool_block(x)

        # 展平
        x = self.Flatten(x)

        x = self.layer6_fc(x)
        x = self.layer7_fc(x)
        x = self.layer8_fc(x)

        return x


if __name__ == "__main__":
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    a = VGG16(224, 3, 1000).to(device)
    from torchsummary import summary
    summary(a, input_size=(3, 224, 224)