VGG有6種子模型，分別是A、A-LRN、B、C、D、E，我們?？吹降幕臼荄、E這兩種模型，即VGG16，VGG19


為了方便閱讀，并沒有加上激活函數(shù)層

from torch import nn import torch from torchsummary import summaryclass VGG16(nn.Module):def __init__(self):super(VGG16, self).__init__()self.sum_Module = 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(2, 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(2, 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(2, 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(2, 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_size=3, stride=1, padding=1),nn.MaxPool2d(2, 2),nn.Flatten(),nn.Linear(7 * 7*512, 4096),#nn.Dropout(0.5),nn.Linear(4096, 4096),#nn.Dropout(0.5),nn.Linear(4096, 1000))def forward(self, x):x = self.sum_Module(x),return xif __name__ == '__main__':YOLO = VGG16()device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')inputs = YOLO.to(device)summary(inputs, (3, 224, 224),batch_size=1, device="cuda") # 分別是輸入數(shù)據(jù)的三個維度

總結(jié)

以上是生活随笔為你收集整理的VGG16网络结构复现（Pytorch版）的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。