ResNet¶

# convolutional layers

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


def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d:
    """1x1 convolution"""
    return nn.Conv2d(
        in_planes, 
        out_planes, 
        kernel_size=1, 
        stride=stride, 
        bias=False)

class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
        groups: int = 1,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer: Optional[Callable[..., nn.Module]] = None,
    ) -> None:
        super().__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError("BasicBlock only supports groups=1 and base_width=64")
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x: Tensor) -> Tensor:
        identity = x  # x  给自己先备份一份

        out = self.conv1(x)  # 对x做卷积 
        out = self.bn1(out)  # 对x归一化 
        out = self.relu(out)  # 对x用激活函数

        out = self.conv2(out)  # 对x做卷积
        out = self.bn2(out)  # 归一化

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

        out += identity  # 进行downsample
        out = self.relu(out)

        return out

class Bottleneck(nn.Module):
    # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
    # while original implementation places the stride at the first 1x1 convolution(self.conv1)
    # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
    # This variant is also known as ResNet V1.5 and improves accuracy according to
    # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.

    expansion: int = 4  # 对输出通道进行倍增

    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
        groups: int = 1,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer: Optional[Callable[..., nn.Module]] = None,
    ) -> None:
        super().__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.0)) * groups
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

        # Bottleneckd forward函数和BasicBlock类似
    def forward(self, x: Tensor) -> Tensor:
        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

class ResNet(nn.Module):
    def __init__(
        self,
        block: Type[Union[BasicBlock, Bottleneck]], # 选择基本模块
        layers: List[int], # 每一层block的数目构成 -> [3,4,6,3]
        num_classes: int = 1000, # 分类数目
        zero_init_residual: bool = False, # 初始化
        
        #######其他卷积构成，与本文ResNet无关######
        groups: int = 1,
        width_per_group: int = 64,
        replace_stride_with_dilation: Optional[List[bool]] = None,
        #########################################
        
        norm_layer: Optional[Callable[..., nn.Module]] = None, # norm 层
    ) -> None:
        super().__init__()
        _log_api_usage_once(self)
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer
		
        self.inplanes = 64 # 输入通道
        
        #######其他卷积构成，与本文ResNet无关######
        self.dilation = 1 # 空洞卷积
        if replace_stride_with_dilation is None:
            # each element in the tuple indicates if we should replace
            # the 2x2 stride with a dilated convolution instead
            replace_stride_with_dilation = [False, False, False]
        if len(replace_stride_with_dilation) != 3:
            raise ValueError(
                "replace_stride_with_dilation should be None "
                f"or a 3-element tuple, got {replace_stride_with_dilation}"
            )
        self.groups = groups
        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)
        # 通过_make_layer带到层次化设计的效果
        self.layer1 = self._make_layer(block, 64, layers[0])  # 对应着conv2_x
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dilate=replace_stride_with_dilation[0])  # 对应着conv3_x
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dilate=replace_stride_with_dilation[1])  # 对应着conv4_x
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dilate=replace_stride_with_dilation[2])  # 对应着conv5_x
        # 分类头
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)
		
        # 模型初始化
        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)

        # Zero-initialize the last BN in each residual branch,
        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck) and m.bn3.weight is not None:
                    nn.init.constant_(m.bn3.weight, 0)  # type: ignore[arg-type]
                elif isinstance(m, BasicBlock) and m.bn2.weight is not None:
                    nn.init.constant_(m.bn2.weight, 0)  # type: ignore[arg-type]
	# 层次化设计，创建由多个块构成的序列层
    def _make_layer(
        self,
        block: Type[Union[BasicBlock, Bottleneck]], # 基本构成模块选择
        planes: int,  # 输入的通道
        blocks: int, # 模块数目
        stride: int = 1, # 步长
        dilate: bool = False, # 空洞卷积，与本文无关
    ) -> nn.Sequential:
        norm_layer = self._norm_layer
        downsample = None # 是否采用下采样
        ####################无关#####################
        previous_dilation = self.dilation 
        if dilate:
            self.dilation *= stride
            stride = 1
        #############################################
        # 当步长不为 1 或者 输入通道不等于预期输出通道数时，进行下采样，基于序列层构建下采样模块
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                norm_layer(planes * block.expansion),
            )
		
        # 使用layers存储每个layer
        layers = []
        # 添加第一个块，包含下采样操作
        layers.append(
            block(
                self.inplanes, 
                planes, 
                stride, 
                downsample, 
                self.groups, 
                self.base_width, 
                previous_dilation, 
                norm_layer
            )
        )
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(
                block(
                    self.inplanes,
                    planes,
                    groups=self.groups,
                    base_width=self.base_width,
                    dilation=self.dilation,
                    norm_layer=norm_layer,
                )
            )
		# 将layers通过nn.Sequential转化为网络
        return nn.Sequential(*layers)

    def _forward_impl(self, x: Tensor) -> Tensor:
        # See note [TorchScript super()]
        x = self.conv1(x)  # conv1   x shape [1 64 112 112]
        x = self.bn1(x)   # 归一化处理   
        x = self.relu(x)  # 激活函数
        x = self.maxpool(x)  # conv2_x的3x3 maxpool        x shape [1 64 56 56]

        x = self.layer1(x) # layer 1
        x = self.layer2(x) # layer 2
        x = self.layer3(x) # layer 3
        x = self.layer4(x) # layer 4

        x = self.avgpool(x) # 自适应池化
        x = torch.flatten(x, 1) 
        x = self.fc(x) # 分类

        return x

    def forward(self, x: Tensor) -> Tensor:
        return self._forward_impl(x)