VGG细节

2024-03-14 21:57:41

参考

1.Very Deep Convolutional Networks for Large-Scale Image Recognition
2.VGG16学习笔记

1. 模型组成

  1. input: 224 x 224 RGB image
  2. preprocessing: the mean RGB value, computed ont the training set, from each pixel
  3. 组件： 3 x 3 convolution filters, 1 x 1 convolution filters
  4. In one of the configurations we also utilise 1 x 1 convolution filters, which can be seen as a linear transformation of the input channels(followed by non-linearity)
  5. the convolution stride is fixed to 1 pixel; the spatial padding of conv.layer input is such that the spatial resolution is preserved after convolution, i.e the padding is 1 pixel for 3 x 3 conv.layers.
  6. Spatial pooling is carried out by five max-pooling layers, which follow some of the conv.layers(not all the conv.layers are followed by max-pooling).Max-pooling is performed over a 2 x 2 pixel window, wit stride 2.
  7. A stack of convolutional layers(which has a different depth in different architectures) if followed by three Fully-Connected(FC) lyaers: the first two have 4096 channels each, the final layer is the soft-max layer.
  8. the configuration of the fully connected layers is the same in all networks
  9. all hidden layers ate equipped with the rectification(ReLU) non-linearity.

2. 模型详细结构

VGG中根据卷积核大小和卷积层数目的不同，可分为A，A-LRN,B,C,D,E共6个配置(ConvNet Configuration)，其中以D,E两种配置较为常用，分别称为VGG16和VGG19。

下图给出了VGG的六种结构配置：
VGG细节

上图中，每一列对应一种结构配置。例如，图中绿色部分即指明了VGG16所采用的结构。

我们针对VGG16进行具体分析发现，VGG16共包含：

  • 13个卷积层（Convolutional Layer），分别用conv3-XXX表示

  • 3个全连接层（Fully connected Layer）,分别用FC-XXXX表示

  • 5个池化层（Pool layer）,分别用maxpool表示
    其中，卷积层和全连接层具有权重系数，因此也被称为权重层，总数目为13+3=16，这即是

VGG16中16的来源。(池化层不涉及权重，因此不属于权重层，不被计数)。

3. 特点

VGG16的突出特点是简单，体现在：

卷积层均采用相同的卷积核参数

  1. 卷积层均表示为conv3-XXX，其中conv3说明该卷积层采用的卷积核的尺寸(kernel size)是3，即宽（width）和高（height）均为3，3*3是很小的卷积核尺寸，结合其它参数（步幅stride=1，填充方式padding=same），这样就能够使得每一个卷积层(张量)与前一层（张量）保持相同的宽和高。XXX代表卷积层的通道数。

  2. 池化层均采用相同的池化核参数

  3. 池化层的参数均为2×

模型是由若干卷积层和池化层堆叠（stack）的方式构成，比较容易形成较深的网络结构（在2014年，16层已经被认为很深了）。

综合上述分析，可以概括VGG的优点为: Small filters, Deeper networks.
VGG细节

4. 块结构

下面给出按照块划分的VGG16的结构图：
VGG细节

VGG的输入图像是 224x224x3

  • 通道数翻倍，由64依次增加到128，再到256，直至512保持不变，不再翻倍
  • 高和宽变减半，由 224→112→56→28→14→7

5. 权重参数

尽管VGG的结构简单，但是所包含的权重数目却很大，达到了惊人的139，357，544个参数。这些参数包括卷积核权重和全连接层权重。

  • 例如，对于第一层卷积，由于输入图的通道数是3，网络必须学习大小为3x3，通道数为3的的卷积核，这样的卷积核有64个，因此总共有（3x3x3）x64 = 1728个参数
  • 计算全连接层的权重参数数目的方法为：前一层节点数×本层的节点数前一层节点数×本层的节点数。因此，全连接层的参数分别为：
    • 7x7x512x4096 = 1027,645,444
    • 4096x4096 = 16,781,321
    • 4096x1000 = 4096000
      FeiFei Li在CS231的课件中给出了整个网络的全部参数的计算过程（不考虑偏置），如下图所示：

VGG细节

图中蓝色是计算权重参数数量的部分；红色是计算所需存储容量的部分。

VGG16具有如此之大的参数数目，可以预期它具有很高的拟合能力；但同时缺点也很明显：

  • 即训练时间过长，调参难度大。
  • 需要的存储容量大，不利于部署。例如存储VGG16权重值文件的大小为500多MB，不利于安装到嵌入式系统中。
import torch
import torch.nn as nn
from typing import Union, List, Dict, Any, cast

__all__ = [
    'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
    'vgg19_bn', 'vgg19',
]

model_urls = {
    'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
    'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
    'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
    'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
    'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
    'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
    'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
    'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}

class VGG(nn.Module):
    
    def __init__(
        self,
        features: nn.Module,
        num_classes: int = 1000,
        init_weights: bool = True
    ) -> None:
        super(VGG, self).__init__()
        self.features = features
        self.avgpool = nn.AdaptiveAvgPool2d((7,7))
        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: torch.Tensor) -> torch.Tensor:
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)
        return x
    
    def _initialize_weights(self) -> None:
        for m  in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)
                
def make_layers(cfg: List[Union[str, int]], batch_norm: bool = False) -> nn.Sequential:
    layers: List[nn.Module] = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size = 2, stride = 2)]
        else:
            v = cast(int, v)
            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)

cfgs: Dict[str, List[Union[str, int]]] = {
    '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 _vgg(arch: str, cfg: str, batch_norm: bool, pretrained: bool, progress: bool, **kwargs: Any) -> VGG:
    if pretrained:
        kwargs['init_weights'] = False
    model = VGG(make_layers(cfgs[cfg], batch_norm=batch_norm), **kwargs)
    if pretrained:
        state_dict = torch.hub.load_state_dict_from_url(model_urls[arch],
                                              progress=progress)
        model.load_state_dict(state_dict)
    return model

def vgg11(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 11-layer model (configuration "A") from
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg11', 'A', False, pretrained, progress, **kwargs)


def vgg11_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 11-layer model (configuration "A") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg11_bn', 'A', True, pretrained, progress, **kwargs)


def vgg13(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 13-layer model (configuration "B")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg13', 'B', False, pretrained, progress, **kwargs)


def vgg13_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 13-layer model (configuration "B") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg13_bn', 'B', True, pretrained, progress, **kwargs)


def vgg16(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 16-layer model (configuration "D")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)


def vgg16_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 16-layer model (configuration "D") with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg16_bn', 'D', True, pretrained, progress, **kwargs)


def vgg19(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 19-layer model (configuration "E")
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg19', 'E', False, pretrained, progress, **kwargs)


def vgg19_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
    r"""VGG 19-layer model (configuration 'E') with batch normalization
    `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        progress (bool): If True, displays a progress bar of the download to stderr
    """
    return _vgg('vgg19_bn', 'E', True, pretrained, progress, **kwargs)

model = vgg11(pretrained= False)
上一篇：使用这 6个Vue加载动画库来减少我们网站的跳出率


下一篇：ubuntu软件商店提示has install-snap change in progress问题