您好，登录后才能下订单哦！
密码登录
登录注册
点击 登录注册 即表示同意《亿速云用户服务条款》
卷积神经网络（Convolutional Neural Networks, CNNs）是深度学习领域中最重要和广泛应用的模型之一。它们在计算机视觉、自然语言处理、语音识别等领域取得了显著的成果。本文将介绍9大主题的卷积神经网络，并通过PyTorch实现这些模型。我们将从基础的LeNet开始，逐步深入到更复杂的模型，如ResNet、Inception、DenseNet等。
LeNet是由Yann LeCun等人在1998年提出的，是最早的卷积神经网络之一。它主要用于手写数字识别任务。
LeNet的结构相对简单，包含两个卷积层和三个全连接层。具体结构如下：
import torch
import torch.nn as nn
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(1, 6, kernel_size=5)
self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv2 = nn.Conv2d(6, 16, kernel_size=5)
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.fc1 = nn.Linear(16 * 4 * 4, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool1(torch.relu(self.conv1(x)))
x = self.pool2(torch.relu(self.conv2(x)))
x = x.view(-1, 16 * 4 * 4)
x = torch.relu(self.fc1(x))
x = torch.relu(self.fc2(x))
x = self.fc3(x)
return x
# 实例化模型
model = LeNet()
print(model)
AlexNet是由Alex Krizhevsky等人在2012年提出的，它在ImageNet竞赛中取得了显著的成绩，标志着深度学习在计算机视觉领域的崛起。
AlexNet的结构比LeNet复杂，包含五个卷积层和三个全连接层。具体结构如下：
import torch
import torch.nn as nn
class AlexNet(nn.Module):
def __init__(self, num_classes=1000):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 96, kernel_size=11, stride=4),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(96, 256, kernel_size=5, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(256, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
)
self.classifier = nn.Sequential(
nn.Linear(256 * 6 * 6, 4096),
nn.ReLU(inplace=True),
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
# 实例化模型
model = AlexNet()
print(model)
VGG是由牛津大学视觉几何组（Visual Geometry Group）提出的，它在2014年ImageNet竞赛中取得了优异的成绩。VGG的主要特点是使用了更小的卷积核（3x3）和更深的网络结构。
VGG有多种变体，如VGG16和VGG19。以VGG16为例，其结构如下：
import torch
import torch.nn as nn
class VGG16(nn.Module):
def __init__(self, num_classes=1000):
super(VGG16, self).__init__()
self.features = nn.Sequential(
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),
nn.Conv2d(64, 128, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(128, 128, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(128, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(256, 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=2, stride=2),
nn.Conv2d(256, 512, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(512, 512, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(512, 512, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(512, 512, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(512, 512, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(512, 512, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2),
)
self.classifier = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(inplace=True),
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), 512 * 7 * 7)
x = self.classifier(x)
return x
# 实例化模型
model = VGG16()
print(model)
GoogLeNet是由Google团队在2014年提出的，它在ImageNet竞赛中取得了优异的成绩。GoogLeNet的主要特点是引入了Inception模块，通过多尺度的卷积操作来提取特征。
GoogLeNet的结构较为复杂，主要包含多个Inception模块。以Inception v1为例，其结构如下：
import torch
import torch.nn as nn
import torch.nn.functional as F
class Inception(nn.Module):
def __init__(self, in_channels, out1x1, out3x3_reduce, out3x3, out5x5_reduce, out5x5, out_pool):
super(Inception, self).__init__()
self.branch1 = nn.Sequential(
nn.Conv2d(in_channels, out1x1, kernel_size=1),
nn.ReLU(inplace=True),
)
self.branch2 = nn.Sequential(
nn.Conv2d(in_channels, out3x3_reduce, kernel_size=1),
nn.ReLU(inplace=True),
nn.Conv2d(out3x3_reduce, out3x3, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
)
self.branch3 = nn.Sequential(
nn.Conv2d(in_channels, out5x5_reduce, kernel_size=1),
nn.ReLU(inplace=True),
nn.Conv2d(out5x5_reduce, out5x5, kernel_size=5, padding=2),
nn.ReLU(inplace=True),
)
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
nn.Conv2d(in_channels, out_pool, kernel_size=1),
nn.ReLU(inplace=True),
)
def forward(self, x):
branch1 = self.branch1(x)
branch2 = self.branch2(x)
branch3 = self.branch3(x)
branch4 = self.branch4(x)
return torch.cat([branch1, branch2, branch3, branch4], 1)
class GoogLeNet(nn.Module):
def __init__(self, num_classes=1000):
super(GoogLeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.conv2 = nn.Conv2d(64, 64, kernel_size=1)
self.conv3 = nn.Conv2d(64, 192, kernel_size=3, padding=1)
self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(0.4)
self.fc = nn.Linear(1024, num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.conv3(x)
x = self.maxpool2(x)
x = self.inception3a(x)
x = self.inception3b(x)
x = self.maxpool3(x)
x = self.inception4a(x)
x = self.inception4b(x)
x = self.inception4c(x)
x = self.inception4d(x)
x = self.inception4e(x)
x = self.maxpool4(x)
x = self.inception5a(x)
x = self.inception5b(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.dropout(x)
x = self.fc(x)
return x
# 实例化模型
model = GoogLeNet()
print(model)
ResNet是由微软研究院的Kaiming He等人在2015年提出的，它在ImageNet竞赛中取得了优异的成绩。ResNet的主要特点是引入了残差连接（Residual Connection），通过跳跃连接来解决深层网络中的梯度消失问题。
ResNet有多种变体，如ResNet18、ResNet34、ResNet50等。以ResNet18为例，其结构如下：
免责声明：本站发布的内容（图片、视频和文字）以原创、转载和分享为主，文章观点不代表本网站立场，如果涉及侵权请联系站长邮箱：is@yisu.com进行举报，并提供相关证据，一经查实，将立刻删除涉嫌侵权内容。