彻底搞懂ResNet50

pytorch实现resnet50代码如下：
（1）一个block实现，如1x1，64，3x3，64，1x1，256。这段代码中，1x1的卷积核只是为了改变输出通道数，3x3的卷积可能改变卷积核大小，与参数stride有关。即定义Bottleneck(inplanes, planes, stride, downsample)时，改变的可能是卷积核大小。

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

(2) resnet实现：_make_layer()函数实现一个layer。
强调点1：
对于每个layer而言，每经过一个block之后，通道数变为了4planes，因此下一个block的输入通道数应为4planes，故定义self.inplanes = planes * block.expansion。planes不变，总是为传入的参数，如64，128，256，512。变得是每次经过一个block之后的输出通道数，也就意味着下一个block的输入通道数变了。
强调点2：
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)
可以看到，构建每个layer时传入的stride参数不一样，那么这个参数代表了什么呢？
进入_make_layer()函数中看看，这个stride影响的是第一个block的构建，其他block均不受stride影响。进入block的__init()函数中可以看到，stride影响的是第2个3x3的卷积，可能会影响此时的feature map大小。

总结一下，第一个layer(共3个block，每个block有3层，共9层，均不受stride的影响，即stride=1，故不改变feature map的大小)；第二个layer(共4个block，每个block有3层，共12层。第一个block的第2层受stride影响，可能会改变feature map的大小，其余11层均不改变feature map大小)；第三个layer(共6个block，每个block有3层，共18层。第一个block的第2层受stride影响，可能会改变feature map的大小，其余17层均不改变feature map大小)…第四个layer和上面类似，不做赘述。

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)   # different
    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

resnet50调用resnet类：

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