pytorch从零实现resnet50_人群计数resnet50代码

pytorch从零实现resnet_pytorch实现resnet_两只蜡笔的小新的博客-CSDN博客

前言：

之前博主写过一个ResNet34, ResNet18的实现方法，对于ResNet50的实现方法有点不太一样，之前的实现方法参考上面的链接。下面介绍ResNet50的实现方法。

基本结构示意图

 发现ResNet50，其基本模块是三个，1*1 3*3 1*1 的卷积层，在向前推进的时候，需要特征图的通道数降维，所以与ResNet34不同的地方是BasicBlock，和make_layer

二、构建BasicBlock

class Bottleneck(nn.Module):
    expansion: int = 4
    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample = None,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer = None
    ) -> None:
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.))
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, stride=1, bias=False)
        self.bn1 = norm_layer(width)
        self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride,
                     padding=dilation, bias=False, dilation=dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = nn.Conv2d(width, planes * self.expansion, kernel_size=1, stride=1, bias=False)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride
 
    def forward(self, x):
        identity = 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:
            identity = self.downsample(x)
 
        out += identity
        out = self.relu(out)
 
        return out

三、残差块的实现，

由于renset残差单元可能连接两个不同维度的特征图，所以要接一个降采样操作self.downsample = shortcut，有没有取决于输入维度与输出维度是否相同,还取决于特征图的尺寸是否发生变化。

    def _make_layer(self, block, planes: int, blocks: int,
                    stride: int = 1):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        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),
                norm_layer(planes * block.expansion),)
        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample,
                            self.base_width, previous_dilation, norm_layer))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes,
                                base_width=self.base_width, dilation=self.dilation,
                                norm_layer=norm_layer))
        return nn.Sequential(*layers)

四、下面构造类class ResNet50(nn.Module)

1.构造类方法1

class ResNet50_src(nn.Module):
    def __init__(self,block =  Bottleneck,
        layers = [3, 4, 6, 3],
        num_classes: int = 1000,
        width_per_group: int = 64,
        norm_layer = None
    ):
        super(ResNet50_src, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer
 
        self.inplanes = 64
        self.dilation = 1
        self.base_width = width_per_group
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = norm_layer(self.inplanes)
        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.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)
 
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
 
 
    def _make_layer(self, block, planes: int, blocks: int,
                    stride: int = 1):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        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),
                norm_layer(planes * block.expansion),)
        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample,
                            self.base_width, previous_dilation, norm_layer))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes,
                                base_width=self.base_width, dilation=self.dilation,
                                norm_layer=norm_layer))
        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 = torch.flatten(x, 1)
        x = self.fc(x)
        return x

运行对比测试

if __name__ == '__main__':
    from torchsummary import summary
    from torchvision import models
 
    resnet = models.resnet50(pretrained=False)
    summary(ResNet50_src().cuda(),(3,512,512))
    # summary(resnet.cuda(),(3,512,512))