4.1、知识补充，VGG-16结构实现

梦在黎明破晓时啊

已于 2023-06-14 23:03:06 修改

阅读量89

点赞数

分类专栏：深度学习入门学习文章标签：深度学习人工智能神经网络

于 2023-03-18 20:56:13 首次发布

本文链接：https://blog.csdn.net/qq_39522016/article/details/129642693

版权

深度学习入门学习专栏收录该内容

15 篇文章 1 订阅

订阅专栏

手写VGG-16网络结构视频
 参考备注

1.网络结构图及对应输出结果

在这里插入图片描述

2.代码结构

import torch.nn as nn
from torchsummary import summary
import torch

class VGG16(nn.Module):
    def __init__(self):
        super(VGG16, self).__init__()
        self.maxpool1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 64, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)
            )
        
        self.maxpool2 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(128, 128, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)
            )
        
        self.maxpool3 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)
            )
        
        self.maxpool4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)
            )
        
        self.maxpool5= nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(512, 512, kernel_size=3,stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)
            )
        
        self.dense = nn.Sequential(
            nn.Linear(512 * 5 * 5, 4096),
            nn.ReLU(),
            nn.Linear(4096, 4096),
            nn.ReLU(),
            nn.Linear(4096, 1000)
        )
 
    def forward(self, x):
        pool1=self.maxpool1(x)
        pool2=self.maxpool2(pool1)
        pool3=self.maxpool3(pool2)
        pool4=self.maxpool4(pool3)
        pool5=self.maxpool5(pool4)
        
        flat = pool5.view(pool5.size(0), -1)
        class_ = self.dense(flat)
        return class_
if __name__ == "__main__": 
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    vgg_model=VGG16().to(device)
    summary(vgg_model, (3,160, 160)) #打印网络结构