经典卷积神经网络 - AlexNet

AlexNet是由Alex Krizhevsky、Ilya Sutskever和Geoffrey Hinton在2012年ImageNet图像分类竞赛中提出的一种经典的卷积神经网络。当时，AlexNet在 ImageNet 大规模视觉识别竞赛中取得了优异的成绩，把深度学习模型在比赛中的正确率提升到一个前所未有的高度。因此，它的出现对深度学习发展具有里程碑式的意义。

基本结构

AlexNet输入为RGB三通道的224 × 224 × 3大小的图像（也可填充为227 × 227 × 3 ）。AlexNet 共包含5 个卷积层（包含3个池化）和 3 个全连接层。其中，每个卷积层都包含卷积核、偏置项、ReLU激活函数和局部响应归一化（LRN）模块。第1、2、5个卷积层后面都跟着一个最大池化层，后三个层为全连接层。最终输出层为softmax，将网络输出转化为概率值，用于预测图像的类别。

由于ImageNet数据集太大，本文以MNIST数据集进行代替，修改网络参数，输入通道为1，输出结果为10个。

代码实现

model.py

import torch
from torch import nn

class AlexNet(nn.Module):
    def __init__(self, *args, **kwargs) -> None:
        super().__init__(*args, **kwargs)
        self.model = nn.Sequential(
            nn.Conv2d(1,96,kernel_size=11,stride=4,padding=1),nn.ReLU(),
            nn.MaxPool2d(kernel_size=3,stride=2),
            nn.Conv2d(96,256,kernel_size=5,padding=2),nn.ReLU(),
            nn.MaxPool2d(kernel_size=3,stride=2),
            nn.Conv2d(256,384,kernel_size=3,padding=1),nn.ReLU(),
            nn.Conv2d(384,384,kernel_size=3,padding=1),nn.ReLU(),
            nn.Conv2d(384,256,kernel_size=3,padding=1),nn.ReLU(),
            nn.MaxPool2d(kernel_size=3,stride=2),
            nn.Flatten(),
            nn.Linear(6400,4096),nn.ReLU(),
            nn.Dropout(p=0.5),
            nn.Linear(4096,4096),nn.ReLU(),
            nn.Dropout(p=0.5),
            nn.Linear(4096,10)
        )

    def forward(self,x):
        return self.model(x)

# 验证网络正确性
if __name__ == '__main__':
    net = AlexNet()
    my_input = torch.ones((64,1,28,28))
    my_output = net(my_input)
    print(my_output.shape)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

train.py

import torch
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from torchvision import datasets
from torchvision.transforms import transforms
from model import AlexNet

# 扫描数据次数
epochs = 10
# 分组大小
batch = 64
# 学习率
learning_rate = 0.01
# 训练次数
train_step = 0
# 测试次数
test_step = 0


# 定义图像转换
transform = transforms.Compose([
    transforms.Resize(224),
    transforms.ToTensor()
])
# 读取数据
train_dataset = datasets.MNIST(root="./dataset",train=True,transform=transform,download=True)
test_dataset = datasets.MNIST(root="./dataset",train=False,transform=transform,download=True)
# 加载数据
train_dataloader = DataLoader(train_dataset,batch_size=batch,shuffle=True,num_workers=0)
test_dataloader = DataLoader(test_dataset,batch_size=batch,shuffle=True,num_workers=0)
# 数据大小
train_size = len(train_dataset)
test_size = len(test_dataset)
print("训练集大小：{}".format(train_size))
print("验证集大小：{}".format(test_size))

# GPU
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")
print(device)
# 创建网络
net = AlexNet()
net = net.to(device)
# 定义损失函数
loss = nn.CrossEntropyLoss()
loss = loss.to(device)
# 定义优化器
optimizer = torch.optim.SGD(net.parameters(),lr=learning_rate)

writer = SummaryWriter("logs")
# 训练
for epoch in range(epochs):
    print("-------------------第 {} 轮训练开始-------------------".format(epoch))
    net.train()
    for data in train_dataloader:
        train_step = train_step + 1
        images,targets = data
        images = images.to(device)
        targets = targets.to(device)
        outputs = net(images)
        loss_out = loss(outputs,targets)
        optimizer.zero_grad()
        loss_out.backward()
        optimizer.step()

        if train_step%100==0:
            writer.add_scalar("Train Loss",scalar_value=loss_out.item(),global_step=train_step)
            print("训练次数：{}，Loss：{}".format(train_step,loss_out.item()))

    # 测试
    net.eval()
    total_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            test_step = test_step + 1
            images, targets = data
            images = images.to(device)
            targets = targets.to(device)
            outputs = net(images)
            loss_out = loss(outputs, targets)
            total_loss = total_loss + loss_out
            accuracy = (targets == torch.argmax(outputs,dim=1)).sum()
            total_accuracy = total_accuracy + accuracy
        # 计算精确率
        print(total_accuracy)
        accuracy_rate = total_accuracy / test_size

        print("第 {} 轮，验证集总损失为：{}".format(epoch+1,total_loss))
        print("第 {} 轮，精确率为：{}".format(epoch+1,accuracy_rate))
        writer.add_scalar("Test Total Loss",scalar_value=total_loss,global_step=epoch+1)
        writer.add_scalar("Accuracy Rate",scalar_value=accuracy_rate,global_step=epoch+1)
    torch.save(net,"./model/net_{}.pth".format(epoch+1))
    print("模型net_{}.pth已保存".format(epoch+1))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94