介绍
Resnet分类网络是当前应用最为广泛的CNN特征提取网络。
我们的一般印象当中,深度学习愈是深(复杂,参数多)愈是有着更强的表达能力。凭着这一基本准则CNN分类网络自Alexnet的7层发展到了VGG的16乃至19层,后来更有了Googlenet的22层。可后来我们发现深度CNN网络达到一定深度后再一味地增加层数并不能带来进一步地分类性能提高,反而会招致网络收敛变得更慢,test dataset的分类准确率也变得更差。排除数据集过小带来的模型过拟合等问题后,我们发现过深的网络仍然还会使分类准确度下降(相对于较浅些的网络而言)。
简单地增加网络层数会导致梯度消失和梯度爆炸,因此,人们提出了正则化初始化和中间的正则化层(Batch Normalization),但是 又引发了另外一个问题——退化问题,即随着网络层数地增加,训练集上的准确率却饱和甚至下降。这个问题并不是由过拟合(overfit)造成的,因为过拟合表现应该表现为在训练集上变现更好。
residual learning的block是通过使用多个有参层来学习输入输出之间的残差表示,而非像一般CNN网络(如Alexnet/VGG等)那样使用有参层来直接尝试学习输入、输出之间的映射。实验表明使用一般意义上的有参层来直接学习残差比直接学习输入、输出间映射要容易得多(收敛速度更快),也有效得多(可通过使用更多的层来达到更高的分类精度)。
Resnet网络
残差:观测值与估计值之间的差。
在网络中增加直连通道,允许原始输入信息直接传到后面的层中,当前网络不需要学习整个的输出,只学习上一个网络输出的残差,拷贝一个浅层网络的输出加给深层的输出,直接将输入信息绕道传到输出,让深度学习后面的层至少实现恒等快捷连接(identity shortcut connection)的作用,保护信息完整性,整个网络只需要学习输入、输出差别的那部分,简化了学习目标和难度。
\(F(x)=H(x)-x\).\(x\)是估计值(也就是上一层ResNet输出的特征映射),一般称x为identity Function,它是一个跳跃连接;\(F(x)\)是ResNet Function,\(H(x)\)是深层输出,观测值。当\(x\)代表的特征已经足够成熟,\(F(x)\)会自动趋向于使学习成为0.
residual模块改变了前向和后向信息传递的方式,从而促进了网络的优化,在反向传播过程中梯度的传导多了更简便的路径。会明显减小模块中参数的值从而让网络中的参数对反向传导的损失值有更敏感的响应能力,虽然从根本上没有解决回传损失小的问题,但却让参数减小,相对而言增加了回传损失的效果,也产生了一定的正则化作用。
网络结构
- basic模式:简单地将X相对Y缺失的通道直接补零从而使其能够相对齐的方式,以两个3*3的卷积网络串接在一起作为一个残差块;
- bottleneck模式:通过使用1x1的conv来表示\(W_s\)映射从而使得最终输入与输出的通道达到一致的方式。1*1,3*3,11三个卷积网络串接在一起作为一个残差模块。加入11的卷积核巧妙地缩减或扩张feature map维度从而使得我们的3x3 conv的filters数目不受外界即上一层输入的影响,自然它的输出也不会影响到下一层module,增加非线性和减小输出的深度以减小计算成本。不过它纯是为了节省计算时间进而缩小整个模型训练所需的时间而设计的,对最终的模型精度并无影响。
代码实现
import torch import torch.nn as nn class BasicBlock(nn.Module): """Basic Block for resnet 18 and resnet 34 """ #BasicBlock and BottleNeck block #have different output size #we use class attribute expansion #to distinct expansion = 1 def __init__(self, in_channels, out_channels, stride=1): super().__init__() #residual function self.residual_function = nn.Sequential( nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels * BasicBlock.expansion, kernel_size=3, padding=1, bias=False), nn.BatchNorm2d(out_channels * BasicBlock.expansion) ) #shortcut self.shortcut = nn.Sequential() #the shortcut output dimension is not the same with residual function #use 1*1 convolution to match the dimension if stride != 1 or in_channels != BasicBlock.expansion * out_channels: self.shortcut = nn.Sequential( nn.Conv2d(in_channels, out_channels * BasicBlock.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(out_channels * BasicBlock.expansion) ) def forward(self, x): return nn.ReLU(inplace=True)(self.residual_function(x) + self.shortcut(x)) class BottleNeck(nn.Module): """Residual block for resnet over 50 layers """ expansion = 4 def __init__(self, in_channels, out_channels, stride=1): super().__init__() self.residual_function = nn.Sequential( nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels, stride=stride, kernel_size=3, padding=1, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True), nn.Conv2d(out_channels, out_channels * BottleNeck.expansion, kernel_size=1, bias=False), nn.BatchNorm2d(out_channels * BottleNeck.expansion), ) self.shortcut = nn.Sequential() if stride != 1 or in_channels != out_channels * BottleNeck.expansion: self.shortcut = nn.Sequential( nn.Conv2d(in_channels, out_channels * BottleNeck.expansion, stride=stride, kernel_size=1, bias=False), nn.BatchNorm2d(out_channels * BottleNeck.expansion) ) def forward(self, x): return nn.ReLU(inplace=True)(self.residual_function(x) + self.shortcut(x)) class ResNet(nn.Module): def __init__(self, block, num_block, num_classes=100): super().__init__() self.in_channels = 64 self.conv1 = nn.Sequential( nn.Conv2d(3, 64, kernel_size=3, padding=1, bias=False), nn.BatchNorm2d(64), nn.ReLU(inplace=True)) #we use a different inputsize than the original paper #so conv2_x's stride is 1 self.conv2_x = self._make_layer(block, 64, num_block[0], 1) self.conv3_x = self._make_layer(block, 128, num_block[1], 2) self.conv4_x = self._make_layer(block, 256, num_block[2], 2) self.conv5_x = self._make_layer(block, 512, num_block[3], 2) self.avg_pool = nn.AdaptiveAvgPool2d((1, 1)) self.fc = nn.Linear(512 * block.expansion, num_classes) def _make_layer(self, block, out_channels, num_blocks, stride): """make resnet layers(by layer i didnt mean this 'layer' was the same as a neuron netowork layer, ex. conv layer), one layer may contain more than one residual block Args: block: block type, basic block or bottle neck block out_channels: output depth channel number of this layer num_blocks: how many blocks per layer stride: the stride of the first block of this layer Return: return a resnet layer """ # we have num_block blocks per layer, the first block # could be 1 or 2, other blocks would always be 1 strides = [stride] + [1] * (num_blocks - 1) layers = [] for stride in strides: layers.append(block(self.in_channels, out_channels, stride)) self.in_channels = out_channels * block.expansion return nn.Sequential(*layers) def forward(self, x): output = self.conv1(x) output = self.conv2_x(output) output = self.conv3_x(output) output = self.conv4_x(output) output = self.conv5_x(output) output = self.avg_pool(output) output = output.view(output.size(0), -1) output = self.fc(output) return output def resnet18(): """ return a ResNet 18 object """ return ResNet(BasicBlock, [2, 2, 2, 2]) def resnet34(): """ return a ResNet 34 object """ return ResNet(BasicBlock, [3, 4, 6, 3]) def resnet50(): """ return a ResNet 50 object """ return ResNet(BottleNeck, [3, 4, 6, 3]) def resnet101(): """ return a ResNet 101 object """ return ResNet(BottleNeck, [3, 4, 23, 3]) def resnet152(): """ return a ResNet 152 object """ return ResNet(BottleNeck, [3, 8, 36, 3])
引用: