ResNet

In [ ]:

# 这里实现的是18层ResNet
import torch
import torch.nn as nn
import torch
import torch.nn as nn

# 这里实现的是18层ResNet import torch import torch.nn as nn import torch import torch.nn as nn

In [ ]:

# 定义基本的残差块
class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channels, out_channels, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_channels != self.expansion * out_channels:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_channels, self.expansion * out_channels, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(self.expansion * out_channels)
            )

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        out += self.shortcut(residual)
        out = self.relu(out)

        return out

# 定义基本的残差块 class BasicBlock(nn.Module): expansion = 1 def __init__(self, in_channels, out_channels, stride=1): super(BasicBlock, self).__init__() self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(out_channels) self.relu = nn.ReLU() self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(out_channels) self.shortcut = nn.Sequential() if stride != 1 or in_channels != self.expansion * out_channels: self.shortcut = nn.Sequential( nn.Conv2d(in_channels, self.expansion * out_channels, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(self.expansion * out_channels) ) def forward(self, x): residual = x out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) out += self.shortcut(residual) out = self.relu(out) return out

In [ ]:

# 定义ResNet模型
class ResNet(nn.Module):
    def __init__(self, block=BasicBlock, layers=[2, 2, 2, 2], num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 64
        
        self.conv1 = nn.Conv2d(in_channels=1,out_channels=64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        
        self.res_layer = nn.Sequential(
            self.make_layer(block, 64, layers[0]),
            self.make_layer(block, 128, layers[1], stride=2),
            self.make_layer(block, 256, layers[2], stride=2),
            self.make_layer(block, 512, layers[3], stride=2)
        )

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Sequential(
            nn.Flatten(),
            nn.Linear(512 * block.expansion, num_classes)
        )
        
    def make_layer(self, block, out_channels, blocks, stride=1):
        layers = []
        layers.append(block(self.in_channels, out_channels, stride))
        self.in_channels = out_channels * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.in_channels, out_channels))
        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.res_layer(x)
        x = self.avgpool(x)
        x = self.fc(x)

        return x

# 定义ResNet模型 class ResNet(nn.Module): def __init__(self, block=BasicBlock, layers=[2, 2, 2, 2], num_classes=10): super(ResNet, self).__init__() self.in_channels = 64 self.conv1 = nn.Conv2d(in_channels=1,out_channels=64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(64) self.relu = nn.ReLU() self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.res_layer = nn.Sequential( self.make_layer(block, 64, layers[0]), self.make_layer(block, 128, layers[1], stride=2), self.make_layer(block, 256, layers[2], stride=2), self.make_layer(block, 512, layers[3], stride=2) ) self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) self.fc = nn.Sequential( nn.Flatten(), nn.Linear(512 * block.expansion, num_classes) ) def make_layer(self, block, out_channels, blocks, stride=1): layers = [] layers.append(block(self.in_channels, out_channels, stride)) self.in_channels = out_channels * block.expansion for _ in range(1, blocks): layers.append(block(self.in_channels, out_channels)) 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.res_layer(x) x = self.avgpool(x) x = self.fc(x) return x