6.Vgg16--CNN经典网络模型详解（pytorch实现）

最新推荐文章于 2025-05-30 21:15:41 发布

原创

最新推荐文章于 2025-05-30 21:15:41 发布 · 668 阅读

4 ·

CC 4.0 BY-SA版权

文章标签：

#cnn #pytorch #人工智能 #VGG16 #目标检测

1.首先建立一个model.py文件，用来写神经网络，代码如下：

import torch
import torch.nn as nn
class My_VGG16(nn.Module):
    def __init__(self,num_classes=5,init_weight=True):
        super(My_VGG16, self).__init__()
        # 特征提取层
        self.features = nn.Sequential(
            nn.Conv2d(in_channels=3,out_channels=64,kernel_size=3,stride=1,padding=1),
            nn.Conv2d(in_channels=64,out_channels=64,kernel_size=3,stride=1,padding=1),
            nn.MaxPool2d(kernel_size=2,stride=2),
            nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=1, padding=1),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),
            nn.MaxPool2d(kernel_size=2,stride=2),
            nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_siz