Resnet 残差神经网络代码解读
代码根据torchvision.models中的源码
Resnet结构
resnet由building block和bottleneck组成,building block的结构如下:
比传统的卷积结构多了一个short-cut支路,用于传递底层的信息使得网络能够很深
bottleneck的结构如下:
这个结构主要是能够减少参数的数目,第一个1×1卷积把256维的channel降到64维,然后最后通过1×1卷积恢复256的通道数,整体上参数的数目1×1×256×64 + 3×3×64×64 + 1×1×64×256 = 69632,而用类似之前的block的话就是两个3×3×256的卷积,参数数目为3×3×256×256×2 = 1179648,差了16.94倍
Resnet总共有五组卷积,其中输入的size为224×224,第五组卷积输出为7×7.
代码解读
代码中,主要的结构有两个:BasicBlock和Bottlenneck,即上述所说的
Resnet18
先拿Resnet18举例
函数定义的部分
model为一个叫做Resnet的类,后面的[2, 2, 2, 2]可以看到正好是卷积组的个数。
再看ResNet类:
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)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
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
根据forward函数来看数据的流动,主要的部分就是中间的layer1-layer4
如果planes*block.expansion不等于inplanes或步长不为1,则进行下采样将通道数改为 planes*block.expansion,步长改为新的步长。叫下采样的原因是要调整input和残差的步长都一直(大于1),但其实还是有改变通道数。
再看到BasicBlock类:
可以看到,downsample就是为残差而准备的identity = self.downsample(x),其中只有第一层的conv1的步长是根据输入来的,举个例子,如果是2,那么输入x同时也经过同样的下采样,即使得残差和output一致。
Resnet18和Resnet34都是只用到了BasicBlock,就类似普通的CNN,但是更深的残差网络使用的是Bottleneck模块,如上述说到的主要目的是减小参数的数量
Resnet 50
定义部分:
Bottleneck部分
总结
Resnet是一个很有名的网络,它为搭建深层次的神经网络提供了一种可行方法。之前一直觉得这个网络好复杂,但是仔细去读源码的时候,发现很容易理解。