ResNet 代码阅读笔记

ResNet 代码阅读笔记

论文笔记可以查看这篇博客。

先来回顾以下网络的框架:

可以看到，ResNet主要分为四个block。而对于层数不一样的结构，block也不一样。

因此在代码中，需要定义两个block类，分别为BasicBlock和Bottleneck，如下所示:

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


class BasicBlock(nn.Module):
  expansion = 1 # block内通道数不改变

  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 # element-wise addition
    out = self.relu(out)

    return out


class Bottleneck(nn.Module):
  expansion = 4 # block内通道数扩大四倍

  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  # element-wise addition
    out = self.relu(out)

    return out

接下来，编写一个ResNet类，来构建整体的ResNet网络，具体如下:

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)
    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

使用不同ResNet网络的API，具体如下:

def resnet18(pretrained=False):
  """Constructs a ResNet-18 model.
  Args:
    pretrained (bool): If True, returns a model pre-trained on ImageNet
  """
  model = ResNet(BasicBlock, [2, 2, 2, 2])
  if pretrained:
    model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
  return model


def resnet34(pretrained=False):
  """Constructs a ResNet-34 model.
  Args:
    pretrained (bool): If True, returns a model pre-trained on ImageNet
  """
  model = ResNet(BasicBlock, [3, 4, 6, 3])
  if pretrained:
    model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
  return model


def resnet50(pretrained=False):
  """Constructs a ResNet-50 model.
  Args:
    pretrained (bool): If True, returns a model pre-trained on ImageNet
  """
  model = ResNet(Bottleneck, [3, 4, 6, 3])
  if pretrained:
    model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
  return model


def resnet101(pretrained=False):
  """Constructs a ResNet-101 model.
  Args:
    pretrained (bool): If True, returns a model pre-trained on ImageNet
  """
  model = ResNet(Bottleneck, [3, 4, 23, 3])
  if pretrained:
    model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
  return model


def resnet152(pretrained=False):
  """Constructs a ResNet-152 model.
  Args:
    pretrained (bool): If True, returns a model pre-trained on ImageNet
  """
  model = ResNet(Bottleneck, [3, 8, 36, 3])
  if pretrained:
    model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
  return model

if __name__ == '__main__':
    model = resnet18() # 调用API
    print(model)

Conclusion

代码结构较为简单，需要注意的是expansion参数，BN添加在ReLU前。