深度学习作业——第三周

一.代码练习

1.Lenet网络

网络模型代码如下：

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

class LeNet(nn.Module):
    # 初始化方法：定义网络层结构
    def __init__(self):
        super(LeNet, self).__init__()  # 调用基类的构造函数
        self.conv1 = nn.Conv2d(3, 16, 5)  # （1）in_channel:图片RGB三通道（2）out_channel:filter组数（3）filter大小kernel_size:5x5  
        self.pool1 = nn.MaxPool2d(2, 2)  # (1)kernel_size:2 (2)stride:2
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)  # output(32, 5, 5)
        # 全连接层的输入是一个一维的向量，所以需要把得到的特征矩阵展平成一维向量
        self.fc1 = nn.Linear(32 * 5 * 5, 120)  # 第一层的节点个数是120（leNet定义的）
        self.fc2 = nn.Linear(120, 84)  # 第二层的节点个数是84（leNet定义的）
        self.fc3 = nn.Linear(84, 2)  # 最后一个全连接层的输出要根据训练集进行修改，这里使用的训练集有10个类别

    # 定义正向传播的过程
    def forward(self, x):
        x = F.relu(self.conv1(x))  # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)  # output(16, 14, 14)
        x = F.relu(self.conv2(x))  # output(32, 10, 10)
        x = self.pool2(x)  # output(32, 5, 5)
        x = x.view(-1, 32 * 5 * 5)  # output(32*5*5)  -1：第一个维度，进行自动推理 32*5*5：展平后的节点个数
        x = F.relu(self.fc1(x))  # output(120)
        x = F.relu(self.fc2(x))  # output(84)
        x = self.fc3(x)  # output(10)
        return x

最后将结果上传网络获得68.75分。

2.Resnet网络

网络模型代码如下：

import torch.nn as nn
import torch
 
class BasicBlock(nn.Module):
    expansion = 1
 
    def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
        #输入特征矩阵深度，输出特征矩阵深度，步长，下采样参数对应虚线残差结构
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
                               kernel_size=3, stride=stride, padding=1, bias=False)
        #卷积核大小kernel_size，bias为偏置，BN不需要使用
        self.bn1 = nn.BatchNorm2d(out_channel)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
                               kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channel)
        self.downsample = downsample
 
    def forward(self, x):
        identity = x
        if self.downsample is not None:#if=none对应实线部分则跳过，否则经过下采样，得到输出
            identity = self.downsample(x)
 
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
 
        out = self.conv2(out)
        out = self.bn2(out)
 
        out += identity
        out = self.relu(out)
 
        return out
 
 
class Bottleneck(nn.Module):
    expansion = 4
 
    def __init__(self, in_channel, out_channel, stride=1, downsample=None,
                 groups=1, width_per_group=64):
        super(Bottleneck, self).__init__()
 
        width = int(out_channel * (width_per_group / 64.)) * groups
 
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width,
                               kernel_size=1, stride=1, bias=False)  # squeeze channels
        self.bn1 = nn.BatchNorm2d(width)
        # -----------------------------------------
        self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups,
                               kernel_size=3, stride=stride, bias=False, padding=1)
        self.bn2 = nn.BatchNorm2d(width)
        # -----------------------------------------
        self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion,
                               kernel_size=1, stride=1, bias=False)  # unsqueeze channels
        self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
 
    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(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)
 
        out += identity
        out = self.relu(out)
 
        return out
 
 
class ResNet(nn.Module):
 
    def __init__(self,
                 block,#残差结构，basicblock或bottleneck
                 blocks_num,#一个列表参数对应每个残差结构个数
                 num_classes=1000,#训练集分类个数
                 include_top=True,
                 groups=1,
                 width_per_group=64):
        super(ResNet, self).__init__()
        self.include_top = include_top
        self.in_channel = 64
 
        self.groups = groups
        self.width_per_group = width_per_group
 
        self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
                               padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(self.in_channel)
        self.relu = nn.ReLU(inplace=True)#以上为第一层
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)#第二层
        self.layer1 = self._make_layer(block, 64, blocks_num[0])
        self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
        self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
        self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
        if self.include_top:
            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))  # output size = (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')
 
    def _make_layer(self, block, channel, block_num, stride=1):
        downsample = None
        if stride != 1 or self.in_channel != channel * block.expansion:#18层，34层会直接跳过
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(channel * block.expansion))
 
        layers = []
        layers.append(block(self.in_channel,
                            channel,
                            downsample=downsample,
                            stride=stride,
                            groups=self.groups,
                            width_per_group=self.width_per_group))
        self.in_channel = channel * block.expansion
 
        for _ in range(1, block_num):
            layers.append(block(self.in_channel,
                                channel,
                                groups=self.groups,
                                width_per_group=self.width_per_group))
 
        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)
 
        if self.include_top:
            x = self.avgpool(x)
            x = torch.flatten(x, 1)
            x = self.fc(x)
 
        return x
 
 
def resnet34(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet34-333f7ec4.pth
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
 
 
def resnet50(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet50-19c8e357.pth
    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)
 
 
def resnet101(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
    return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)
 
 
def resnext50_32x4d(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth
    groups = 32
    width_per_group = 4
    return ResNet(Bottleneck, [3, 4, 6, 3],
                  num_classes=num_classes,
                  include_top=include_top,
                  groups=groups,
                  width_per_group=width_per_group)
 
 
def resnext101_32x8d(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth
    groups = 32
    width_per_group = 8
    return ResNet(Bottleneck, [3, 4, 23, 3],
                  num_classes=num_classes,
                  include_top=include_top,
                  groups=groups,
                  width_per_group=width_per_group)

这个网络是我根据网课内容以及网上查阅到的资料仿写的，但是最后用resnet34训练出来的网络性能并不理想，将测试集输出的结果上传网络得分仅有50.75分，具体原因目前还不清楚，还在学习摸索中。 

二.问题总结

1.Residual learning 的基本原理？

对于一个堆积层结构，当输入为x时其学习到的特征记为H(x)，现将残差定义为F(x) = H(x)-x，这样其实原始的学习特征是H(x) = F(x)+x。由于残差F(x)≥0（我觉得应该不会为0）这使得堆积层在输入特征基础上学习到新的特征，从而拥有更好的性能。

2.Batch Normailization 的原理，思考 BN、LN、IN 的主要区别。

Batch Normalization的目的是使我们的一批（Batch）feature map满足均值为0，方差为1的分布规律。通过该方法能够加速网络的收敛并提升准确率。

LN是Layer Normalization，它适用于深度不固定的网络；IN是Instance Normalization，它适用于像素级别。

3.为什么分组卷积可以提升准确率？即然分组卷积可以提升准确率，同时还能降低计算量，分数数量尽量多不行吗？

将卷积分组后能够大大减少参数数量，从而在相同情况下加深网络深度。但由于分组后各组之间的信息将被分割，因此也不能分太多组。