当前位置：首页 > news >正文

常用的卷积神经网络及Pytorch示例实现

news 来源：原创 2025/5/30 0:05:47

以下是几种常用的卷积神经网络（CNN）架构及其 PyTorch 实现示例，涵盖经典模型和现代变体。这些模型在图像分类、目标检测等任务中表现卓越。

1. LeNet-5（1998）

特点
首个成功应用于手写数字识别的CNN。
结构：卷积层 + 池化层 + 全连接层。
适用场景：小尺寸图像分类（如MNIST）。

PyTorch实现：

import torch.nn as nn

class LeNet(nn.Module):
    def __init__(self, num_classes=10):
        super(LeNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(1, 6, kernel_size=5),  # 输入1通道（灰度）
            nn.ReLU(),
            nn.AvgPool2d(kernel_size=2),
            nn.Conv2d(6, 16, kernel_size=5),
            nn.ReLU(),
            nn.AvgPool2d(kernel_size=2)
        )
        self.classifier = nn.Sequential(
            nn.Linear(16*4*4, 120),  # 根据输入尺寸调整
            nn.ReLU(),
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84, num_classes)
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), -1)
        x = self.classifier(x)
        return x

# 示例：MNIST分类
model = LeNet(num_classes=10)

2. AlexNet（2012）

特点
引入ReLU激活函数和Dropout，大幅提升性能。
使用GPU加速训练。
适用场景：中等尺寸图像分类（如ImageNet）。

PyTorch实现：

class AlexNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256*6*6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), 256*6*6)
        x = self.classifier(x)
        return x

# 示例：ImageNet分类
model = AlexNet(num_classes=1000)

3. VGG（2014）

特点
使用重复的3x3卷积块，加深网络。
常见变体：VGG16、VGG19。
适用场景：高精度图像分类。

PyTorch实现：

class VGG16(nn.Module):
    def __init__(self, num_classes=1000):
        super(VGG16, self).__init__()
        self.features = nn.Sequential(
            # Block 1
            nn.Conv2d(3, 64, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(64, 64, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            # Block 2-5（类似结构，此处省略）
            # ...
        )
        self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
        self.classifier = nn.Sequential(
            nn.Linear(512*7*7, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.classifier(x)
        return x

# 使用PyTorch内置VGG（推荐）
import torchvision.models as models
vgg16 = models.vgg16(pretrained=True)  # 加载预训练权重

4. ResNet（2015）

特点
引入残差连接（Residual Block），解决梯度消失问题。
支持极深网络（如ResNet-152）。
适用场景：通用视觉任务。

PyTorch实现（简化版）：

class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.shortcut = nn.Sequential()
        if stride != 1 or in_channels != out_channels:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride),
                nn.BatchNorm2d(out_channels)
        )

    def forward(self, x):
        residual = x
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x += self.shortcut(residual)
        x = self.relu(x)
        return x

class ResNet18(nn.Module):
    def __init__(self, num_classes=10):
        super(ResNet18, self).__init__()
        self.in_channels = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        # 添加残差块
        self.layer1 = self._make_layer(64, 64, 2, stride=1)
        self.layer2 = self._make_layer(64, 128, 2, stride=2)
        self.layer3 = self._make_layer(128, 256, 2, stride=2)
        self.layer4 = self._make_layer(256, 512, 2, stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, num_classes)

    def _make_layer(self, in_channels, out_channels, blocks, stride):
        layers = []
        layers.append(ResidualBlock(in_channels, out_channels, stride))
        for _ in range(1, blocks):
            layers.append(ResidualBlock(out_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.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

# 示例：CIFAR-10分类
model = ResNet18(num_classes=10)

5. MobileNet（2017）

特点
使用深度可分离卷积（Depthwise Separable Convolution），降低计算量。
适合移动端和嵌入式设备。

PyTorch实现：

class DepthwiseSeparableConv(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1):
        super().__init__()
        self.depthwise = nn.Conv2d(in_channels, in_channels, kernel_size=3, 
                                  stride=stride, padding=1, groups=in_channels)
        self.pointwise = nn.Conv2d(in_channels, out_channels, kernel_size=1)

    def forward(self, x):
        x = self.depthwise(x)
        x = self.pointwise(x)
        return x

class MobileNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(MobileNet, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, kernel_size=3, stride=2, padding=1),
            nn.ReLU(inplace=True),
            DepthwiseSeparableConv(32, 64, stride=1),
            DepthwiseSeparableConv(64, 128, stride=2),
            DepthwiseSeparableConv(128, 128, stride=1),
            DepthwiseSeparableConv(128, 256, stride=2),
            # 更多层...
            nn.AdaptiveAvgPool2d(1)
        )
        self.fc = nn.Linear(256, num_classes)

    def forward(self, x):
        x = self.model(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

# 示例：轻量化模型
model = MobileNet(num_classes=1000)

6. 使用预训练模型（PyTorch内置）

PyTorch提供多种预训练模型，可直接加载：

import torchvision.models as models

# 加载预训练模型
resnet50 = models.resnet50(pretrained=True)
inception_v3 = models.inception_v3(pretrained=True)
mobilenet_v2 = models.mobilenet_v2(pretrained=True)

# 微调（修改最后一层）
resnet50.fc = nn.Linear(resnet50.fc.in_features, num_classes=10)

训练示例（以CIFAR-10为例）

import torch.optim as optim

# 定义模型、损失函数、优化器
model = ResNet18(num_classes=10)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)

# 训练循环
for epoch in range(10):
    for inputs, labels in train_loader:
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    print(f'Epoch {epoch+1}, Loss: {loss.item():.4f}')

总结：模型选择指南

模型	参数量	适用场景	优势
LeNet	~60k	简单分类（MNIST）	结构简单，计算量小
AlexNet	~60M	中等图像分类	经典基准模型
VGG	~138M	高精度分类	结构规则，易于扩展
ResNet	~25M (18层)	通用视觉任务	解决梯度消失，支持极深网络
MobileNet	~3.5M	移动端/嵌入式设备	计算高效，参数量少