pytorch-VGG網絡

VGG網絡結構 

 

第一層: 3x3x3x64, 步長爲1, padding=1 

第二層: 3x3x64x64, 步長爲1, padding=1 

第三層: 3x3x64x128, 步長爲1, padding=1

第四層: 3x3x128x128, 步長爲1, padding=1

第五層: 3x3x128x256, 步長爲1, padding=1

第六層: 3x3x256x256, 步長爲1, padding=1

第七層: 3x3x256x256, 步長爲1, padding=1

第八層: 3x3x256x512, 步長爲1, padding=1 

第九層: 3x3x512x512, 步長爲1, padding=1 

第十層:3x3x512x512, 步長爲1, padding=1 

第十一層: 3x3x512x512, 步長爲1, padding=1 

第十二層: 3x3x512x512, 步長爲1, padding=1 

第十三層:3x3x512x512, 步長爲1, padding=1 

第十四層: 512*7*7, 4096的全鏈接操做

第十五層: 4096, 4096的全鏈接操做

第十六層: 4096, num_classes 的 全鏈接操做

import torch
from torch import nn

class VGG(nn.Module):
    def __init__(self, num_classes):
        super(VGG, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(64, 64, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(64, 128, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(128, 128, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(128, 256, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(256, 512, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(512, 512, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(512, 512, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(512, 512, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(512, 512, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.Conv2d(512, 512, kernel_size=3, padding=1),
            nn.ReLU(True),
            nn.MaxPool2d(kernel_size=2, stride=2),)
        self.classifier = nn.Sequential(
            nn.Linear(512*7*7, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(True),
            nn.Dropout(),
            nn.Linear(4096, num_classes)
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), -1)
        x = self.classifier(x)

        return x