pytorch（3）--VGG block和 Resnet block

最新推荐文章于 2024-09-04 09:48:16 发布

ForeverYang2015

最新推荐文章于 2024-09-04 09:48:16 发布

阅读量4k

点赞数 1

分类专栏： pytorch

本文链接：https://blog.csdn.net/AP1005834/article/details/115093973

版权

深度学习 VGGBlock ResNetBlock 卷积神经网络残差连接

关键词由CSDN通过智能技术生成

pytorch 专栏收录该内容

11 篇文章 1 订阅

订阅专栏

一、前言

本篇记录 VGG Block和Resnet Block 经典结构

二、VGGblock

VGG Block 可由两层conv3或三层conv3组成，两层的感受野和一层conv5一样，三层conv3的感受野和一层conv7是一样的，但是能够减少计算量，以下为不同的VGGblock搭配的VGG网络

包含两层conv3的VGG block 代码如下，CBR-CBR，无池化层

class VGGBlock(nn.Module):
    def __init__(self, in_channels, middle_channels, out_channels, act_func=nn.ReLU(inplace=True)):
        super(VGGBlock, self).__init__()
        self.act_func = act_func
        self.conv1 = nn.Conv2d(in_channels, middle_channels, 3, padding=1)
        self.bn1 = nn.BatchNorm2d(middle_channels)
        self.conv2 = nn.Conv2d(middle_channels, out_channels, 3, padding=1)
        self.bn2 = nn.BatchNorm2d(out_channels)

    def forward(self, x):
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.act_func(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.act_func(out)

        return out

三、Resnet block

resnet 有2种网络结构

BasicBlock结构和 BottleNeck 结构

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-K7OrudiF-1595851424230)(C:\Users\Administrator\Desktop\Resnet\7.png)]$ $[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-JbMevQsR-1595851424232)(C:\Users\Administrator\Desktop\Resnet\8.png)]$

5种不同层数的ResNet结构图，如下所示：

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-yDZdjc2t-1595851424234)(C:\Users\Administrator\Desktop\Resnet\1.png)]$

#代码参考自pytorch 官方 https://pytorch.org/docs/0.4.0/_modules/torchvision/models/resnet.html

import torch.nn as nn
import math
import torch


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        #self.avgpool = nn.AvgPool2d(7, stride=1)  
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        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))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x


def resnet18(pretrained=False, num_classes = 1000  ):
    """Constructs a ResNet-18 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2] )
    if pretrained:
        model.load_state_dict( torch.load("resnet18-5c106cde.pth") )
    num_features=model.fc.in_features
    model.fc=nn.Linear(num_features,num_classes)        
    
    return model

def resnet50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
    return model



def resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
    return model



def resnet152(pretrained=False, **kwargs):
    """Constructs a ResNet-152 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
    return model


model = resnet18(  pretrained = True, num_classes = 7 )