VGG系列(Pytorch实现)

最新推荐文章于 2025-06-23 10:01:55 发布

zh3389

最新推荐文章于 2025-06-23 10:01:55 发布

阅读量1.6w

点赞数 16

CC 4.0 BY-SA版权

分类专栏： PyTorch相关文章标签： VGG

本文链接：https://blog.youkuaiyun.com/zhanghao3389/article/details/85038252

PyTorch相关专栏收录该内容

7 篇文章

订阅专栏

本文详细介绍了VGG网络的结构及其在大规模图像识别中的应用，提供了PyTorch实现代码，包括网络配置、权重初始化及前向传播过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

github博客传送门
 博客园传送门

论文在此:VERY DEEP CONVOLUTIONA NETWORK FO LARGE-SCAL IMAG RECOGNITION

下载地址:https://arxiv.org/pdf/1409.1556.pdf

网络结构图:

VGG
VGG参数

Pytorch代码实现:

import torch.nn as nn
import math


class VGG(nn.Module):

    def __init__(self, features, num_classes=1000, init_weights=True):
        super(VGG, self).__init__()
        self.features = features
        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),
        )
        if init_weights:
            self._initialize_weights()

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

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(0, 0.01)
                m.bias.data.zero_()


def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)


cfg = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


def vgg11(**kwargs):
    model = VGG(make_layers(cfg['A']), **kwargs)
    return model


def vgg11_bn(**kwargs):
    model = VGG(make_layers(cfg['A'], batch_norm=True), **kwargs)
    return model


def vgg13(**kwargs):
    model = VGG(make_layers(cfg['B']), **kwargs)
    return model


def vgg13_bn(**kwargs):
    model = VGG(make_layers(cfg['B'], batch_norm=True), **kwargs)
    return model


def vgg16(**kwargs):
    model = VGG(make_layers(cfg['D']), **kwargs)
    return model


def vgg16_bn(**kwargs):
    model = VGG(make_layers(cfg['D'], batch_norm=True), **kwargs)
    return model


def vgg19(**kwargs):
    model = VGG(make_layers(cfg['E']), **kwargs)
    return model


def vgg19_bn(**kwargs):
    model = VGG(make_layers(cfg['E'], batch_norm=True), **kwargs)
    return model


if __name__ == '__main__':
    # 'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn', 'vgg19_bn', 'vgg19'
    # Example
    net11 = vgg11()
    print(net11)