懒，就直接用Resnet50了
先写个残差块

class Bottleneck(nn.Module):

    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        #1*1
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        #3*3
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)

        # channels*4
        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

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

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

        return out

整个网络，输出C2~C5特征层

class ResNet(nn.Module):
    def __init__(self, num_classes, block, layers):
        self.inplanes = 64
        super(ResNet, self).__init__()
        # 7*7
        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)
        # 3*3
        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)

        # 初始化权重
        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 = [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 freeze_bn(self):
        ‘‘‘Freeze BatchNorm layers.‘‘‘
        for layer in self.modules():
            if isinstance(layer, nn.BatchNorm2d):
                layer.eval()
                
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        # 特征提取C2~C5
        x1 = self.layer1(x)
        x2 = self.layer2(x1)
        x3 = self.layer3(x2)
        x4 = self.layer4(x3)

        return x2, x3, x4

实例化

def resnet50(num_classes, pretrained=False, **kwargs):
    model = ResNet(num_classes, Bottleneck, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(torch.load(path), strict=False)
    return model

RetinaNet pytorch implement from scratch 01--Backbone