resnet中最中重要的就是代码残差块，
def forward(self,x)
identity = 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:
identity = self.downsample
out += identity
out = self.relu(out)
return out残差块结构:
左边的就叫做BasicBlock,右边就叫bottleneck
BasicBlock
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)
identity = 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:
identity = self.downsample
out += identity
out = self.relu(out)
return outbottleneck
注意Res18、Res34用的是BasicBlock，其余用的是Bottleneck
resnet18： ResNet(BasicBlock, [2, 2, 2, 2])
resnet34： ResNet(BasicBlock, [3, 4, 6, 3])
resnet50：ResNet(Bottleneck, [3, 4, 6, 3])
resnet101:ResNet(Bottleneck, [3, 4, 23, 3])
resnet152:ResNet(Bottleneck, [3, 8, 36, 3])
expansion = 4，因为Bottleneck中每个残差结构输出维度都是输入维度的4倍
class Bottleneck(nn.Module):
expansion = 4 def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(inplanes, planes)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = conv1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride def forward(self, x):
identity = 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:
identity = self.downsample(x) out += identity
out = self.relu(out) return out
ResNet类
几个关键点：
1.在残差结构之前，先对原始224 x 224的图片处理，在经过7 x 7的大卷积核、BN、ReLU、最大池化之后得到56 x 56 x 64的feature map
2.从layer1、layer2、layer3、layer4的定义可以看出，第一个stage不会减小feature map，其余都会在stage的第一层用步长2的3 x 3卷积进行feature map长和宽减半
3._make_layer函数中downsample对残差结构的输入进行升维，直接1 x 1卷积再加上BN即可，后面BasicBlock类和Bottleneck类用得到
4.最后的池化层使用的是自适应平均池化，而非论文中的全局平均池化
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False):
super(ResNet, self).__init__()
self.inplanes = 64
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=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)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes) def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion),
) layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ 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
