Pytorch 实现DenseNet网络

DenseNet的特性：

（1）神经网络一般需要使用池化操作缩小特征图尺寸来提取语义特征。而Dense Block需要保持每一个Block内的特征图尺寸一致来进行Concatnate操作，因此Dense Block被分成多个Block。Block的数量一般为4.

（2）两个相邻的Dense Block之间的部分被称为Transition层，具体包括BN，ReLU、1x1卷积、2x2平均池化操作。1x1的作用是降维，起到压缩模型的作用，而平均池化则是降低特征图的尺寸。

DenseNet的结构图：

网络四个优点

• 减轻梯度消失
• 提高了特征的传播效率
• 提高了特征的利用效率
• 减小了网络的参数量

Pytorch实现：

 

import torch
from torch import nn
import torch.nn.functional as F

#实现一个Bottleneck的类，初始化需要输入通道数与GrowthRate这两个参数
class Bottleneck(nn.Module):
    def __init__(self,nChannels,growthRate):
        super(Bottleneck,self).__init__()
    #通常1x1卷积的通道数为GrowthRate的4倍
        interChannels=4*growthRate
        self.bn1=nn.BatchNorm2d(nChannels)
        self.conv1=nn.Conv2d(nChannels,interChannels,kernel_size=1,bias=False)
        self.bn2=nn.BatchNorm2d(interChannels)
        self.conv2=nn.Conv2d(interChannels,growthRate,kernel_size=3,padding=1,bias=False)
    
    def forward(self,x):
        out=self.conv1(F.relu(self.bn1(x)))
        out=self.conv2(F.relu(self.bn2(out)))
        #将输入x同计算的结果out进行通道拼接
        out=torch.cat((x,out),1)
        return out
class Denseblock(nn.Module):
    def __init__(self,nChannels,growthRate,nDenseBlocks):
        super(Denseblock,self).__init__()
        layers=[]
        #将每一个Bottleneck利用nn.Sequential()整合起来，输入通道数需要线性增长
        for i in range(int(nDenseBlocks)):
            layers.append(Bottleneck(nChannels,growthRate))
            nChannels+=growthRate
        self.denseblock=nn.Sequential(*layers)
    def forward(self,x):
        return self.denseblock(x)

module=Denseblock(64,32,6).cuda()
module

结构： 

Denseblock(
  (denseblock): Sequential(
    (0): Bottleneck(
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    )
    (1): Bottleneck(
      (bn1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    )
    (2): Bottleneck(
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    )
    (3): Bottleneck(
      (bn1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    )
    (4): Bottleneck(
      (bn1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    )
    (5): Bottleneck(
      (bn1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
    )
  )
)