pytorch深度学习基础（十一）——常用结构化CNN模型构建

前言

在本专栏的上一篇博客中我们介绍了常用的线性模型，在本文中我们将介绍GoogleNet、resNet、denseNet这类结构化的模型的构建方式。

GoogLeNet

结构

整体的结构似乎有些吓人，但其实他也是用了块的思维，仔细观察可以发现，他中间一段很多层的结构都是相似的

Inception块

这个块就是其中重复的块，这个块分成了四个分支：1x1卷积、1x1卷积+3x3卷积、1x1卷积+5x5卷积、3x3卷积+1x1卷积，最后将这四个分支通道合并

class Inception(nn.Module):
    def __init__(self, in_channels, c1, c2, c3, c4, **kwargs):
        super(Inception, self).__init__(**kwargs)
        self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
        
        self.p2_1 = nn.Conv2d(in_channels, c2[0], kernel_size=1)
        self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
        
        self.p3_1 = nn.Conv2d(in_channels, c3[0], kernel_size=1)
        self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
        
        self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        self.p4_2 = nn.Conv2d(in_channels, c4, kernel_size=1)
        
    def forward(self, x):
        p1 = F.relu(self.p1_1(x))
        p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
        p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
        p4 = F.relu(self.p4_2(self.p4_1(x)))
        
        return torch.cat((p1, p2, p3, p4), dim=1)

模型构建

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
                  )
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1),
                   nn.ReLU(),
                   nn.Conv2d(64, 192, kernel_size=3, padding=1),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
                  )

b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
                   Inception(256, 128, (128, 192), (32, 96), 64),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
                  )

b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
                   Inception(512, 160, (112, 224), (24, 64), 64),
                   Inception(512, 128, (128, 256), (24, 64), 64),
                   Inception(512, 112, (144, 288), (32, 64), 64),
                   Inception(528, 256, (160, 320), (32, 128), 128),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
                  )

b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
                   Inception(832, 384, (192, 384), (48, 128), 128),
                   nn.AdaptiveAvgPool2d((1, 1)),
                   nn.Flatten()
                  )

net = nn.Sequential(b1, b2, b3, b4, b5, nn.Linear(1024, 10))

resNet18

模型结构

这个模型似乎要更加简洁一些，因为这里只有两个分支，但是他有两种分支方式，一种是卷积+残差，另外一种是卷积+经过1x1卷积处理过的残差

残差块

class Residual(nn.Module):
    def __init__(self, input_channels, num_channels, use_1x1conv=False, strides=1):
        super().__init__()
        self.conv1 = nn.Conv2d(input_channels, num_channels, kernel_size=3, padding=1, stride=strides)
        self.conv2 = nn.Conv2d(num_channels, num_channels, kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(input_channels, num_channels, kernel_size=1, stride=strides)
            
        else:
            self.conv3 = None
            
        self.bn1 = nn.BatchNorm2d(num_channels)
        self.bn2 = nn.BatchNorm2d(num_channels)
        
    def forward(self, X):
        Y = F.relu(self.bn1(self.conv1(X)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            X = self.conv3(X)
            
        Y += X
        return F.relu(Y)

构建时依次使用两种分支方式

def resnet_block(input_channels, num_channels, num_residuals, first_block=False):
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(input_channels, num_channels, use_1x1conv=True, strides=2))
        else:
            blk.append(Residual(num_channels, num_channels))
            
    return blk

模型构建

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
                  )
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))

net = nn.Sequential(b1, b2, b3, b4, b5, 
                    nn.AdaptiveAvgPool2d((1, 1)),
                    nn.Flatten(),
                    nn.Linear(512, 10)
                   )

denseNet

模型结构

这个模型的主要思路就是把每一次的输出和输入合并起来，同时作为下一层的输入，具体的细节还要结合代码解释

DenseBlock

我们看下面的代码，注意init中的循环以及forward时对于X的处理。我们可以发现，每经过一个conv_block都会将conv_block的输出并入到输入，以此作为下一层的输入

def conv_block(input_channels, num_channels):
    return nn.Sequential(nn.BatchNorm2d(input_channels), nn.ReLU(),
                         nn.Conv2d(input_channels, num_channels, kernel_size=3, padding=1)
                        )
                        
class DenseBlock(nn.Module):
    def __init__(self, num_convs, input_channels, num_channels):
        super(DenseBlock, self).__init__()
        layer = []
        for i in range(num_convs):
            layer.append(conv_block(
                num_channels * i + input_channels, num_channels
            ))
        self.net = nn.Sequential(*layer)
        
    def forward(self, X):
        for blk in self.net:
            Y = blk(X)
            X = torch.cat((X, Y), dim=1)
        
        return X

transition_block

这个块的主要作用是减少通道，因为在前面的块中，通道数会持续的增长，考虑到计算量，需要在中间加入减少通道的块

def transition_block(input_channels, num_channels):
    return nn.Sequential(nn.BatchNorm2d(input_channels), nn.ReLU(),
                         nn.Conv2d(input_channels, num_channels, kernel_size=1),
                         nn.AvgPool2d(kernel_size=2, stride=2)
                        )

模型构建

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
                  )
                  
num_channels, growth_rate = 64, 32
num_convs_in_dense_blocks = [4, 4, 4, 4]
blks = []
for i, num_convs in enumerate(num_convs_in_dense_blocks):
    blks.append(DenseBlock(num_convs, num_channels, growth_rate))
    num_channels += num_convs * growth_rate
    if i != len(num_convs_in_dense_blocks) - 1:
        blks.append(transition_block(num_channels, num_channels // 2))
        num_channels = num_channels // 2

net = nn.Sequential(b1, *blks,
                    nn.BatchNorm2d(num_channels), nn.ReLU(),
                    nn.AdaptiveAvgPool2d((1, 1)),
                    nn.Flatten(),
                    nn.Linear(num_channels, 10)
                   )

结尾

我们到现在模型就已经构建好了，测试的过程可以参照本专栏的上一篇博客
pytorch深度学习基础（十）——常用线性CNN模型的结构与训练