Faster R-CNN学习（1）：Res101网络详解

深度解析：Faster R-CNN中的Res101网络

最新推荐文章于 2025-11-08 10:31:05 发布

原创最新推荐文章于 2025-11-08 10:31:05 发布 · 1w 阅读

28 ·

CC 4.0 BY-SA版权

此文章版权归Xinyu_cheng所有, 若有参考，烦请标注

文章标签：

#ResNet #faster R-CNN #深度学习

本文深入探讨Faster R-CNN中的Res101网络结构，包括ResNet的基本和瓶颈结构，以及在faster R-CNN中的应用。通过代码分析了Res101的层构成，如conv1、layer1至layer4，以及downsample在瓶颈结构中的作用。

部署运行你感兴趣的模型镜像

代码地址：https://github.com/xinyu-ch/faster-rcnn.pytorch/blob/master/lib/model/faster_rcnn/resnet.py

前言

具体的理论知识可参考：https://www.cnblogs.com/shouhuxianjian/p/7766441.html

1 总结构

如下是ResNet的一个主题结构，通过__init__函数可设置对应的ResNet网络，block代表网络的结构（BasicBlock–基础结构， Bottleneck–瓶颈结构），layers代表选择不同的层（[2, 2, 2, 2]–res18， [3, 4, 6, 3]–res18, [3, 4, 6, 3]–res50, [3, 4, 23, 3]–res101，具体可参考ResNet详细结构），默认类别num_classes–1000。__make_layer用于创建结构类似的层，其中的downsample在稍后介绍的基础结构会用到，downsample在瓶颈结构中会用到。self.modules会返回模型的每一层参数，此处for循环是用于初始化卷积层和batch normalization层的参数。layer1, layer2, layer3, layer4 是输入输出层数不同但结构相同的resual网络层，后面详细解释。
Res101层构成：第1层–conv1卷积层+bn+relu+Maxpool; 第2~10层(33)–layer1; 第11～22层(43)–layer2；第23～91层(233)–layer3; 第92～100层(33)–layer4; 第101层：avgpool层+fc层。

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=0, ceil_mode=True)  # change
        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)
        # it is slightly better whereas slower to set stride = 1
        # self.layer4 = self._make_layer(block, 512, layers[3], stride=1)
        self.avgpool = nn.AvgPool2d(7)
        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

2 基础Resual 网络结构

ResNet网络中主要用到了两个结构：基础ResNet结构和瓶颈结构，如下图，左侧是基础结构，其一般用于层数小于30层的时候；右侧的是瓶颈结构，其一般用于大于30层的时候，可以大幅减少网络参数。由图可以看出，基础结构的相加部分维度相同，可直接相加，其expansion=1；而瓶颈结构的维度则不太一样，不能直接相加，需要进行downsample处理后才可直接相加，其expansion=4
在这里插入图片描述
基础结构代码：

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

瓶颈结构：

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, stride=stride, bias=False) # change
    self.bn1 = nn.BatchNorm2d(planes)
    self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, # change
                 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

这里的结构和上图描述的一致，可详细看看。瓶颈结构会用到downsample，但是layer1, layer2， layer3, layer4都只有最开始的时候有用到。

3 基于ResNet骨干网的faster R-CNN

__init__模型初始化，相关参数设置。__init_modules模型初始化，

class resnet(_fasterRCNN):
  def __init__(self, classes, num_layers=101, pretrained=False, class_agnostic=False):
    self.model_path = 'data/pretrained_model/resnet101_caffe.pth'
    self.dout_base_model = 1024
    self.pretrained = pretrained
    self.class_agnostic = class_agnostic

    _fasterRCNN.__init__(self, classes, class_agnostic)

  def _init_modules(self):
    resnet = resnet101()

    if self.pretrained == True:
      print("Loading pretrained weights from %s" %(self.model_path))
      state_dict = torch.load(self.model_path)
      resnet.load_state_dict({k:v for k,v in state_dict.items() if k in resnet.state_dict()})

    # Build resnet.
    self.RCNN_base = nn.Sequential(resnet.conv1, resnet.bn1,resnet.relu,
      resnet.maxpool,resnet.layer1,resnet.layer2,resnet.layer3)

    self.RCNN_top = nn.Sequential(resnet.layer4)

    self.RCNN_cls_score = nn.Linear(2048, self.n_classes)
    if self.class_agnostic:
      self.RCNN_bbox_pred = nn.Linear(2048, 4)
    else:
      self.RCNN_bbox_pred = nn.Linear(2048, 4 * self.n_classes)

    # Fix blocks
    for p in self.RCNN_base[0].parameters(): p.requires_grad=False
    for p in self.RCNN_base[1].parameters(): p.requires_grad=False

    assert (0 <= cfg.RESNET.FIXED_BLOCKS < 4)
    if cfg.RESNET.FIXED_BLOCKS >= 3:
      for p in self.RCNN_base[6].parameters(): p.requires_grad=False
    if cfg.RESNET.FIXED_BLOCKS >= 2:
      for p in self.RCNN_base[5].parameters(): p.requires_grad=False
    if cfg.RESNET.FIXED_BLOCKS >= 1:
      for p in self.RCNN_base[4].parameters(): p.requires_grad=False

    def set_bn_fix(m):
      classname = m.__class__.__name__
      if classname.find('BatchNorm') != -1:
        for p in m.parameters(): p.requires_grad=False

    self.RCNN_base.apply(set_bn_fix)
    self.RCNN_top.apply(set_bn_fix)

  def train(self, mode=True):
    # Override train so that the training mode is set as we want
    nn.Module.train(self, mode)
    if mode:
      # Set fixed blocks to be in eval mode
      self.RCNN_base.eval()
      self.RCNN_base[5].train()
      self.RCNN_base[6].train()

      def set_bn_eval(m):
        classname = m.__class__.__name__
        if classname.find('BatchNorm') != -1:
          m.eval()

      self.RCNN_base.apply(set_bn_eval)
      self.RCNN_top.apply(set_bn_eval)

  def _head_to_tail(self, pool5):
    fc7 = self.RCNN_top(pool5).mean(3).mean(2)
    return fc7

您可能感兴趣的与本文相关的镜像