接下来是一步一步看中的代码 。
参数说明：
block：表示传入或者层 。
:传入的是个列表，可以通过获取[index]来控制,以及是否采用空洞卷积 。
:分类数量
:初始化
:分组数
：表示是否传入空洞卷积参数 。如果不指定，则赋值为 [False, False, False]，表示不使用空洞卷积 。
:是否传入层，不传入的时候则为BN层 。
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,groups=1, width_per_group=64, replace_stride_with_dilation=None,norm_layer=None):
代码讲解将以为例，那么此时传入的block就为，layer=[3,4,6,3],=1000,其他系列可以看下面这张图 。在看代码的时候希望大家可以对着下面这个图来看，方便理解 。
先看下下面这几行代码，可以看到这三行代码是由一个输入通道为3，输出通道为64，k=7,s=2,=3,bn层，relu函数构成的，这正好就对应到上面图中的conv1 。
# conv1结构代码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)
然后再看 。是由一个最大池化，还有3个组成(你可以理解为图中的3，4，6，3就是这类结构重复次数) 。
# conv2_xself.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.layer1 = self._make_layer(block, 64, layers[0])
代码中的调用的是函数，
下面这张图为,表示为第一个结构 。在的每个中，只在第一个处的残差边会用1x1的卷积进行升维，其他的都是输入和输出直接相加，这个特点需要注意一下 。
【完整的ResNet代码】self.layer2 = self._make_layer(block, 128, layers[1], stride=2,dilate=replace_stride_with_dilation[0])#self.layer3 = self._make_layer(block, 256, layers[2], stride=2,dilate=replace_stride_with_dilation[1])self.layer4 = self._make_layer(block, 512, layers[3], stride=2,dilate=replace_stride_with_dilation[2])
然后看,3,4，过程和是一样的，只不过这里传入的=2.
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))self.fc = nn.Linear(512 * block.expansion, num_classes)
最后就是连接一个平均池化和全连接用来分类 。
完整的代码：
class ResNet(nn.Module):def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,groups=1, width_per_group=64, replace_stride_with_dilation=None,norm_layer=None):super(ResNet, self).__init__()if norm_layer is None:norm_layer = nn.BatchNorm2dself._norm_layer = norm_layerself.inplanes = 64self.dilation = 1if replace_stride_with_dilation is None:# each element in the tuple indicates if we should replace# the 2x2 stride with a dilated convolution insteadreplace_stride_with_dilation = [False, False, False]if len(replace_stride_with_dilation) != 3:raise ValueError("replace_stride_with_dilation should be None ""or a 3-element tuple, got {}".format(replace_stride_with_dilation))self.groups = groupsself.base_width = width_per_groupself.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,dilate=replace_stride_with_dilation[0])self.layer3 = self._make_layer(block, 256, layers[2], stride=2,dilate=replace_stride_with_dilation[1])self.layer4 = self._make_layer(block, 512, layers[3], stride=2,dilate=replace_stride_with_dilation[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)# 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/1706.02677if zero_init_residual:for m in self.modules():if isinstance(m, Bottleneck):nn.init.constant_(m.bn3.weight, 0)elif isinstance(m, BasicBlock):nn.init.constant_(m.bn2.weight, 0)def _make_layer(self, block, planes, blocks, stride=1, dilate=False):norm_layer = self._norm_layerdownsample = Noneprevious_dilation = self.dilationif dilate:self.dilation *= stridestride = 1if stride != 1 or self.inplanes != planes * block.expansion:downsample = nn.Sequential(conv1x1(self.inplanes, planes * block.expansion, stride),norm_layer(planes * block.expansion),)layers = []layers.append(block(self.inplanes, planes, stride, downsample, self.groups,self.base_width, previous_dilation, norm_layer))self.inplanes = planes * block.expansionfor _ 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))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