Convnext前传----resnext及pytorch实现

套娃一下，resnext又与VGG，inception，resnet相关联

VGG

亮点:通过堆叠多个3*3的卷积核来替代大卷积核，比如两个3*3替换5*5，三个3*3替换7*7，这样他们拥有的感受野相同，并提出感受野。

 

 

 通过堆叠可以大大减小所需参数，假设输入与输出的通道数都是C

 inception

GoogLeNet:通过inception模块来获取多尺度信息，并可以通过1*1的卷积核进行映射和降维从而减少参数。以及辅助分类器。

 

 

resnet

 Resnet:通过残差防止梯度消失，梯度爆炸和模型退化。提出residual模块，加深网络结构，使用BN加速训练。残差的原理是随着层数的增加梯度会越来越小，那我直接将上一层加到这一层的输出从而提高梯度，达到加速训练和防止模型退化，梯度消失的作用。并且Resnet block在通道数上采用宽-窄-宽的设计，这个在等会的convnext会很重要。

resnext

组卷积：减少了参数，但同时与后面通道的联系被切断了。

resnext与resnet的区别就在于这个组卷积，而组卷积涉及到inception和VGG的卷积堆积

 

 代码

主要注意的我已经放在代码注释中了

class Bottleneck(nn.Module):
    """
    注意：原论文中，在虚线残差结构的主分支上，第一个1x1卷积层的步距是2，第二个3x3卷积层步距是1。
    但在pytorch官方实现过程中是第一个1x1卷积层的步距是1，第二个3x3卷积层步距是2，
    这么做的好处是能够在top1上提升大概0.5%的准确率。
    可参考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch
    """
    expansion = 4    # layer的第一个卷积通道数是最后一个卷积通道数的几倍

    def __init__(self, in_channel, out_channel, stride=1, downsample=None,
                 groups=1, width_per_group=64):
        # 1、下采样是指残差需不需要维度变换才能和卷积处理后的结果相加
        # 2、stride=1代表高宽不需要改变，stride=2代表高宽需要改变。并且见注释，stride=2在第一个3*3的卷积层
        # 3、groups和width_per_group用于resnext。groups是有多少个组，width_per_group是每个组的有多少个卷积
        # 4、resnext vs resnet：每一个block的输出维度一样，但是每一个block的前两个卷积的输出维度resnext是resnet的二倍
        # 5、因此，in_channel, out_channel是resnet中的数值，out_channel是block中前两个卷积的通道数，后面通过乘expansion得到block的输出维度
        # 6、注意conv2中的groups参数
        super(Bottleneck, self).__init__()

        width = int(out_channel * (width_per_group / 64.)) * groups
        # 如果是resnet，按默认值 (width_per_group / 64.) * groups等于1,所以width=out_channel
        # 如果是resnext，并用resnext中的32和4，得出width=2*out_channel，对应注释4

        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):
    # block对应BasicBlock还是Bottleneck
    # blocks_num是一个列表，对应每个layer中有多少个block
    # groups和width_per_group代表resnext
    # include_top是全局平均池化
    def __init__(self,
                 block,
                 blocks_num,
                 num_classes=1000,
                 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)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        # 以上所有的resnet都一样，conv2不需要改变高宽
        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
        # stride=2表示一定下采样，self.in_channel != channel * block.expansion是用来区分resnet18,34和其余的，因为resnet18,34在conv2不需要下采样
        if stride != 1 or self.in_channel != channel * block.expansion:
            # 在Bottleneck的conv2的第一个block的下采样只用改变通道，不需要改变高宽，所以stride=1，后面的stride都是2
            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
        # 非第一个block的stride必为1
        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 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)

resnext50_32x4d()