复现ResNeXt50和Reset50 pytorch代码

女爷i 2022-11-16 10:51 197阅读 0赞

# Reset50和ResNeXt50网络图 #

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2hoaGhoaGhoaGh3d3d3d3d3d3d3_size_16_color_FFFFFF_t_70][]

# Reset50 101 152 pytorch代码复现 #

import torch
    import torch.nn as nn
    import torchvision
    import numpy as np
    
    print("PyTorch Version: ",torch.__version__)
    print("Torchvision Version: ",torchvision.__version__)
    
    __all__ = ['ResNet50', 'ResNet101','ResNet152']
    
    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 Bottleneck(nn.Module):
        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(
                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),
                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, num_classes=1000, expansion = 4):
            super(ResNet,self).__init__()
            self.expansion = expansion
    
            self.conv1 = Conv1(in_planes = 3, places= 64)
    
            self.layer1 = self.make_layer(in_places = 64, places= 64, block=blocks[0], stride=1)
            self.layer2 = self.make_layer(in_places = 256,places=128, block=blocks[1], stride=2)
            self.layer3 = self.make_layer(in_places=512,places=256, block=blocks[2], stride=2)
            self.layer4 = self.make_layer(in_places=1024,places=512, block=blocks[3], stride=2)
    
            self.avgpool = nn.AvgPool2d(7, stride=1)
            self.fc = nn.Linear(2048,num_classes)
    
            for m in self.modules():
                if isinstance(m, nn.Conv2d):
                    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 = []
            layers.append(Bottleneck(in_places, places,stride, downsampling =True))
            for i in range(1, block):
                layers.append(Bottleneck(places*self.expansion, places))
    
            return nn.Sequential(*layers)
    
    
        def forward(self, x):
            x = self.conv1(x)
    
            x = self.layer1(x)
            x = self.layer2(x)
            x = self.layer3(x)
            x = self.layer4(x)
    
            x = self.avgpool(x)
            x = x.view(x.size(0), -1)
            x = self.fc(x)
            return x
    
    def ResNet50():
        return ResNet([3, 4, 6, 3])
    
    def ResNet101():
        return ResNet([3, 4, 23, 3])
    
    def ResNet152():
        return ResNet([3, 8, 36, 3])
    
    
    if __name__=='__main__':
        #model = torchvision.models.resnet50()
        model = ResNet50()
        print(model)
    
        input = torch.randn(1, 3, 224, 224)
        out = model(input)
        print(out.shape)

# ResNeXt50 pytorch代码  #

import torch
    import torch.nn as nn
    
    class Block(nn.Module):
        def __init__(self,in_channels, out_channels, stride=1, is_shortcut=False):
            super(Block,self).__init__()
            self.relu = nn.ReLU(inplace=True)
            self.is_shortcut = is_shortcut
            self.conv1 = nn.Sequential(
                nn.Conv2d(in_channels, out_channels // 2, kernel_size=1,stride=stride,bias=False),
                nn.BatchNorm2d(out_channels // 2),
                nn.ReLU()
            )
            self.conv2 = nn.Sequential(
                nn.Conv2d(out_channels // 2, out_channels // 2, kernel_size=3, stride=1, padding=1, groups=32,
                                       bias=False),
                nn.BatchNorm2d(out_channels // 2),
                nn.ReLU()
            )
            self.conv3 = nn.Sequential(
                nn.Conv2d(out_channels // 2, out_channels, kernel_size=1,stride=1,bias=False),
                nn.BatchNorm2d(out_channels),
            )
            if is_shortcut:
                self.shortcut = nn.Sequential(
                nn.Conv2d(in_channels,out_channels,kernel_size=1,stride=stride,bias=1),
                nn.BatchNorm2d(out_channels)
            )
        def forward(self, x):
            x_shortcut = x
            x = self.conv1(x)
            x = self.conv2(x)
            x = self.conv3(x)
            if self.is_shortcut:
                x_shortcut = self.shortcut(x_shortcut)
            x = x + x_shortcut
            x = self.relu(x)
            return x
    
    class Resnext(nn.Module):
        def __init__(self,num_classes,layer=[3,4,6,3]):
            super(Resnext,self).__init__()
            self.conv1 = nn.Sequential(
                nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False),
                nn.BatchNorm2d(64),
                nn.ReLU(),
                nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
            )
            self.conv2 = self._make_layer(64,256,1,num=layer[0])
            self.conv3 = self._make_layer(256,512,2,num=layer[1])
            self.conv4 = self._make_layer(512,1024,2,num=layer[2])
            self.conv5 = self._make_layer(1024,2048,2,num=layer[3])
            self.global_average_pool = nn.AvgPool2d(kernel_size=7, stride=1)
            self.fc = nn.Linear(2048,num_classes)
        def forward(self, x):
            x = self.conv1(x)
            x = self.conv2(x)
            x = self.conv3(x)
            x = self.conv4(x)
            x = self.conv5(x)
            x = self.global_average_pool(x)
            x = torch.flatten(x,1)
            x = self.fc(x)
            return x
        def _make_layer(self,in_channels,out_channels,stride,num):
            layers = []
            block_1=Block(in_channels, out_channels,stride=stride,is_shortcut=True)
            layers.append(block_1)
            for i in range(1, num):
                layers.append(Block(out_channels,out_channels,stride=1,is_shortcut=False))
            return nn.Sequential(*layers)
    
    
    net = Resnext(10)
    x = torch.rand((10, 3, 224, 224))
    for name,layer in net.named_children():
        if name != "fc":
            x = layer(x)
            print(name, 'output shaoe:', x.shape)
        else:
            x = x.view(x.size(0), -1)
            x = layer(x)
            print(name, 'output shaoe:', x.shape)

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2hoaGhoaGhoaGh3d3d3d3d3d3d3_size_16_color_FFFFFF_t_70]: /images/20221022/22de537b1d014617a07e33ff160329af.png