1.ResNeXt的介绍
ResNeXt是ResNet基础上的改进版本,改进的部分不多,主要将之前的残差结构换成了另外的一个block结构,并且使用了组卷积的概念。
性能参数指标
可以看见ResNeXt的性能还是有提升的。
在计算量相同的情况下,错误率更低
普通的卷积
假设输入矩阵的channel是Cin,而输出的channel的n,同时kernel size是k,那么卷积所需要的参数是Cin * n * k * k
组卷积
组卷积的概念是,将输入矩阵的channel平均分为group组,简称g组。那么对于这g组中的每一组的channel就变成了 Cin/g ,如果输出的channel同样是n时,那么对于每一组的channel就需要去卷积一个channel为 n/g 的卷积核,最后g个 n/g 的输出拼接为一个channel为n的最终输出。那么此时所需要的参数量是:((Cin/g) * (n/g) * k * k)*g
可以看见,对比所使用的的参数量,组卷积比普通的卷积少得多,只是原来的1/g。
需要注意:当分组的个数等于输入的channel数,而输出的channels也等于输入的channel时,此时就是MobileNet中的DW卷积。
对于以上的三个图,在数学的计算上是完全一致的,但是最后的一个图看起来比较的简洁。
残差结构的主要步骤:
- 首先对输入的矩阵进行1x1的卷积处理,实现了降维的效果,从channel为256,降到了128.
- 然后通过3x3的组卷积,分为32组,进行卷积处理,此时的channel不变,仍然是128.
- 最后再进行1x1的卷积处理,实现了升维的效果,从channel为128,升到了256.
- 而此时的输出在于输入作相加,实现残差结构。
RexNeXt与ResNet的主要变化就是结构变化:
其中ResNeXt-50(32x4d)的参数如图所示:
ResNeXt-50(32x4d)中的32值的是拆分出来的组数量,而4便是每个拆分出来的组的channels个数。其中group设置32的原因是,其效果最好。而对于浅层次的网络,比如18/34层,ResNeXt提出的改进结构并没有很明显的效果,所以不适用于浅层的网络。
2.ResNeXt的实现
1)自定义模型结构参考代码
import torch import torch.nn as nn num_class = 5 resnext50_32x4d_params = [3, 4, 6, 3] resnext101_32x8d_params = [3, 4, 23, 3] # 定义Conv1层 def Conv1(in_planes, places, stride=2): return nn.Sequential( nn.Conv2d(in_channels=in_planes,out_channels=places,kernel_size=7,stride=stride,padding=3, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=1) ) class ResNeXtBlock(nn.Module): def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 2, cardinality=32): super(ResNeXtBlock,self).__init__() self.expansion = expansion self.downsampling = downsampling # torch.Size([1, 256, 56, 56]) # torch.Size([1, 512, 28, 28]) # torch.Size([1, 1024, 14, 14]) # torch.Size([1, 2048, 7, 7]) self.bottleneck = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False, groups=cardinality), # 使用了组卷积 nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(places * self.expansion), ) if self.downsampling: self.downsample = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(places * self.expansion) ) self.relu = nn.ReLU(inplace=True) def forward(self, x): residual = x out = self.bottleneck(x) if self.downsampling: residual = self.downsample(x) out += residual out = self.relu(out) return out class ResNet(nn.Module): def __init__(self,blocks, blockkinds, num_classes=num_class): super(ResNet,self).__init__() self.blockkinds = blockkinds self.conv1 = Conv1(in_planes = 3, places= 64) if self.blockkinds == ResNeXtBlock: self.expansion = 2 # 64 -> 128 self.layer1 = self.make_layer(in_places=64, places=128, block=blocks[0], stride=1) # 256 -> 256 self.layer2 = self.make_layer(in_places=256, places=256, block=blocks[1], stride=2) # 512 -> 512 self.layer3 = self.make_layer(in_places=512, places=512, block=blocks[2], stride=2) # 1024 -> 1024 self.layer4 = self.make_layer(in_places=1024, places=1024, block=blocks[3], stride=2) self.fc = nn.Linear(2048, num_classes) self.avgpool = nn.AvgPool2d(7, stride=1) # 初始化网络结构 for m in self.modules(): if isinstance(m, nn.Conv2d): # 采用了何凯明的初始化方法 nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif isinstance(m, nn.BatchNorm2d): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) def make_layer(self, in_places, places, block, stride): layers = [] # torch.Size([1, 256, 56, 56]) layers.append(self.blockkinds(in_places, places, stride, downsampling =True)) for i in range(1, block): layers.append(self.blockkinds(places*self.expansion, places)) return nn.Sequential(*layers) def forward(self, x): # conv1层 x = self.conv1(x) # torch.Size([1, 64, 56, 56]) # conv2_x层 x = self.layer1(x) # torch.Size([1, 256, 56, 56]) # conv3_x层 x = self.layer2(x) # torch.Size([1, 512, 28, 28]) # conv4_x层 x = self.layer3(x) # torch.Size([1, 1024, 14, 14]) # conv5_x层 x = self.layer4(x) # torch.Size([1, 2048, 7, 7]) x = self.avgpool(x) # torch.Size([1, 2048, 1, 1]) / torch.Size([1, 512]) x = x.view(x.size(0), -1) # torch.Size([1, 2048]) / torch.Size([1, 512]) x = self.fc(x) # torch.Size([1, 5]) return x def ResNeXt50_32x4d(): return ResNet(resnext50_32x4d_params, ResNeXtBlock) def ResNeXt101_32x8d(): return ResNet(resnext101_32x8d_params, ResNeXtBlock) if __name__ =='__main__': # model = ResNeXtBlock(in_places=256, places=128) # print(model) # model = ResNeXt50_32x4d() model = ResNeXt101_32x8d() input = torch.randn(1, 3, 224, 224) out = model(input) print(out.shape)
2)迁移学习模型结构参考代码
from torchvision.models import resnext101_32x8d from utils import Flatten if __name__ =='__main__': # 迁移学习 trained_model = resnext101_32x8d(pretrained=True) model = nn.Sequential(*list(trained_model.children())[:-1], # torch.Size([32, 512, 1, 1]) Flatten(), # torch.Size([32, 512]) nn.Linear(2048, 5) # torch.Size([32, 5]) ) input = torch.randn(1, 3, 224, 224) out = model(input) print(out.shape) # output: # Downloading: "https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth" to C:\Users\Acer/.cache\torch\hub\checkpoints\resnext101_32x8d-8ba56ff5.pth # 100.0% # torch.Size([1, 5])
3.ResNet与ResNeXt实现完整代码
import torch import torch.nn as nn # 分类数目 num_class = 5 # 各层数目 resnet18_params = [2, 2, 2, 2] resnet34_params = [3, 4, 6, 3] resnet50_params = [3, 4, 6, 3] resnet101_params = [3, 4, 23, 3] resnet152_params = [3, 8, 36, 3] resnext50_32x4d_params = [3, 4, 6, 3] resnext101_32x8d_params = [3, 4, 23, 3] # 定义Conv1层 def Conv1(in_planes, places, stride=2): return nn.Sequential( nn.Conv2d(in_channels=in_planes,out_channels=places,kernel_size=7,stride=stride,padding=3, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=1) ) # 浅层的残差结构 class BasicBlock(nn.Module): def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 1): super(BasicBlock,self).__init__() self.expansion = expansion self.downsampling = downsampling # torch.Size([1, 64, 56, 56]), stride = 1 # torch.Size([1, 128, 28, 28]), stride = 2 # torch.Size([1, 256, 14, 14]), stride = 2 # torch.Size([1, 512, 7, 7]), stride = 2 self.basicblock = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=1, padding=1, bias=False), nn.BatchNorm2d(places * self.expansion), ) # torch.Size([1, 64, 56, 56]) # torch.Size([1, 128, 28, 28]) # torch.Size([1, 256, 14, 14]) # torch.Size([1, 512, 7, 7]) # 每个大模块的第一个残差结构需要改变步长 if self.downsampling: self.downsample = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places*self.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(places*self.expansion) ) self.relu = nn.ReLU(inplace=True) def forward(self, x): # 实线分支 residual = x out = self.basicblock(x) # 虚线分支 if self.downsampling: residual = self.downsample(x) out += residual out = self.relu(out) return out # 深层的残差结构 class Bottleneck(nn.Module): # 注意:默认 downsampling=False def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 4): super(Bottleneck,self).__init__() self.expansion = expansion self.downsampling = downsampling self.bottleneck = nn.Sequential( # torch.Size([1, 64, 56, 56]),stride=1 # torch.Size([1, 128, 56, 56]),stride=1 # torch.Size([1, 256, 28, 28]), stride=1 # torch.Size([1, 512, 14, 14]), stride=1 nn.Conv2d(in_channels=in_places,out_channels=places,kernel_size=1,stride=1, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), # torch.Size([1, 64, 56, 56]),stride=1 # torch.Size([1, 128, 28, 28]), stride=2 # torch.Size([1, 256, 14, 14]), stride=2 # torch.Size([1, 512, 7, 7]), stride=2 nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), # torch.Size([1, 256, 56, 56]),stride=1 # torch.Size([1, 512, 28, 28]), stride=1 # torch.Size([1, 1024, 14, 14]), stride=1 # torch.Size([1, 2048, 7, 7]), stride=1 nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(places * self.expansion), ) # torch.Size([1, 256, 56, 56]) # torch.Size([1, 512, 28, 28]) # torch.Size([1, 1024, 14, 14]) # torch.Size([1, 2048, 7, 7]) if self.downsampling: self.downsample = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places*self.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(places*self.expansion) ) self.relu = nn.ReLU(inplace=True) def forward(self, x): # 实线分支 residual = x out = self.bottleneck(x) # 虚线分支 if self.downsampling: residual = self.downsample(x) out += residual out = self.relu(out) return out # 定义ResNeXt残差结构 class ResNeXtBlock(nn.Module): def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 2, cardinality=32): super(ResNeXtBlock,self).__init__() self.expansion = expansion self.downsampling = downsampling # torch.Size([1, 256, 56, 56]) # torch.Size([1, 512, 28, 28]) # torch.Size([1, 1024, 14, 14]) # torch.Size([1, 2048, 7, 7]) self.bottleneck = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False, groups=cardinality), # 使用了组卷积 nn.BatchNorm2d(places), nn.ReLU(inplace=True), nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(places * self.expansion), ) if self.downsampling: self.downsample = nn.Sequential( nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(places * self.expansion) ) self.relu = nn.ReLU(inplace=True) def forward(self, x): # 实现分支 residual = x out = self.bottleneck(x) # 虚线分支 if self.downsampling: residual = self.downsample(x) out += residual out = self.relu(out) return out class ResNet(nn.Module): def __init__(self,blocks, blockkinds, num_classes=num_class): super(ResNet,self).__init__() self.blockkinds = blockkinds self.conv1 = Conv1(in_planes = 3, places= 64) # 对应浅层网络结构 if self.blockkinds == BasicBlock: self.expansion = 1 # 64 -> 64 self.layer1 = self.make_layer(in_places=64, places=64, block=blocks[0], stride=1) # 64 -> 128 self.layer2 = self.make_layer(in_places=64, places=128, block=blocks[1], stride=2) # 128 -> 256 self.layer3 = self.make_layer(in_places=128, places=256, block=blocks[2], stride=2) # 256 -> 512 self.layer4 = self.make_layer(in_places=256, places=512, block=blocks[3], stride=2) self.fc = nn.Linear(512, num_classes) print("blockkinds == BasicBlock") # 对应深层网络结构 if self.blockkinds == Bottleneck: self.expansion = 4 # 64 -> 64 self.layer1 = self.make_layer(in_places = 64, places= 64, block=blocks[0], stride=1) # 256 -> 128 self.layer2 = self.make_layer(in_places = 256,places=128, block=blocks[1], stride=2) # 512 -> 256 self.layer3 = self.make_layer(in_places=512,places=256, block=blocks[2], stride=2) # 1024 -> 512 self.layer4 = self.make_layer(in_places=1024,places=512, block=blocks[3], stride=2) self.fc = nn.Linear(2048, num_classes) print("blockkinds == Bottleneck") # 对应ResNeXt结构 if self.blockkinds == ResNeXtBlock: self.expansion = 2 # 64 -> 128 self.layer1 = self.make_layer(in_places=64, places=128, block=blocks[0], stride=1) # 256 -> 256 self.layer2 = self.make_layer(in_places=256, places=256, block=blocks[1], stride=2) # 512 -> 512 self.layer3 = self.make_layer(in_places=512, places=512, block=blocks[2], stride=2) # 1024 -> 1024 self.layer4 = self.make_layer(in_places=1024, places=1024, block=blocks[3], stride=2) self.fc = nn.Linear(2048, num_classes) print("blockkinds == ResNeXtBlock") self.avgpool = nn.AvgPool2d(7, stride=1) # 初始化网络结构 for m in self.modules(): if isinstance(m, nn.Conv2d): # 采用了何凯明的初始化方法 nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif isinstance(m, nn.BatchNorm2d): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) def make_layer(self, in_places, places, block, stride): layers = [] # torch.Size([1, 64, 56, 56]) -> torch.Size([1, 256, 56, 56]), stride=1 故w,h不变 # torch.Size([1, 256, 56, 56]) -> torch.Size([1, 512, 28, 28]), stride=2 故w,h变 # torch.Size([1, 512, 28, 28]) -> torch.Size([1, 1024, 14, 14]),stride=2 故w,h变 # torch.Size([1, 1024, 14, 14]) -> torch.Size([1, 2048, 7, 7]), stride=2 故w,h变 # 此步需要通过虚线分支,downsampling=True layers.append(self.blockkinds(in_places, places, stride, downsampling =True)) # torch.Size([1, 256, 56, 56]) -> torch.Size([1, 256, 56, 56]) # torch.Size([1, 512, 28, 28]) -> torch.Size([1, 512, 28, 28]) # torch.Size([1, 1024, 14, 14]) -> torch.Size([1, 1024, 14, 14]) # torch.Size([1, 2048, 7, 7]) -> torch.Size([1, 2048, 7, 7]) # print("places*self.expansion:", places*self.expansion) # print("block:", block) # 此步需要通过实线分支,downsampling=False, 每个大模块的第一个残差结构需要改变步长 for i in range(1, block): layers.append(self.blockkinds(places*self.expansion, places)) return nn.Sequential(*layers) def forward(self, x): # conv1层 x = self.conv1(x) # torch.Size([1, 64, 56, 56]) # conv2_x层 x = self.layer1(x) # torch.Size([1, 256, 56, 56]) # conv3_x层 x = self.layer2(x) # torch.Size([1, 512, 28, 28]) # conv4_x层 x = self.layer3(x) # torch.Size([1, 1024, 14, 14]) # conv5_x层 x = self.layer4(x) # torch.Size([1, 2048, 7, 7]) x = self.avgpool(x) # torch.Size([1, 2048, 1, 1]) / torch.Size([1, 512]) x = x.view(x.size(0), -1) # torch.Size([1, 2048]) / torch.Size([1, 512]) x = self.fc(x) # torch.Size([1, 5]) return x def ResNet18(): return ResNet(resnet18_params, BasicBlock) def ResNet34(): return ResNet(resnet34_params, BasicBlock) def ResNet50(): return ResNet(resnet50_params, Bottleneck) def ResNet101(): return ResNet(resnet101_params, Bottleneck) def ResNet152(): return ResNet(resnet152_params, Bottleneck) def ResNeXt50_32x4d(): return ResNet(resnext50_32x4d_params, ResNeXtBlock) def ResNeXt101_32x8d(): return ResNet(resnext101_32x8d_params, ResNeXtBlock) if __name__=='__main__': # model = torchvision.models.resnet50() # 模型测试 # model = ResNet18() # model = ResNet34() # model = ResNet50() # model = ResNet101() # model = ResNet152() # model = ResNeXt50_32x4d() model = ResNeXt101_32x8d() # print(model) input = torch.randn(1, 3, 224, 224) out = model(input) print(out.shape)
参考:
https://www.bilibili.com/video/BV1T7411T7wa