用pytorch实现卷积神经网络Lenet5的CIFAR10分类问题

  LeNet-5中主要有2个卷积层、2个下采样层（池化层）、3个全连接层3种连接方式。依次分别为C1层(卷积层)，S2层(下采样层)C3层(卷积层)S4层(下采样层)F5层(全连接层)F6层(全连接层)F7层(全连接层)。具体形式本文不再赘述。

import torch
from torchvision import datasets
from torchvision import transforms
from torch.utils.data import DataLoader
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = datasets.CIFAR10('data', train=True,download=True, transform=transform)
trainloader = DataLoader(trainset, batch_size=4,shuffle=True, num_workers=0)

testset = datasets.CIFAR10('data', train=False,download=True, transform=transform)
testloader = DataLoader(testset, batch_size=4,shuffle=False, num_workers=0)

classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')

以上为引入cifar10训练集合和测试集合

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


class CNNNet(nn.Module):
    def __init__(self):
        super(CNNNet,self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3,out_channels=16,kernel_size=5,stride=1)
        self.pool1 = nn.MaxPool2d(kernel_size=2,stride=2)
        self.conv2 = nn.Conv2d(in_channels=16,out_channels=36,kernel_size=3,stride=1)
        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.fc1 = nn.Linear(1296,120)
        self.fc2 = nn.Linear(120,84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self,x):
        x=self.pool1(F.relu(self.conv1(x)))
        x=self.pool2(F.relu(self.conv2(x)))
        #print(x.shape)
        x=x.view(-1,36*6*6)
        x=F.relu(self.fc3(F.relu(self.fc2(F.relu(self.fc1(x))))))
        return x

net = CNNNet()
net=net.to(device)
print(net)
LR=0.001

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

定义网络：如上可以看到定义的两个池化层，两个卷积层和三个全连接层。

if __name__ == '__main__':
    for epoch in range(10):
        net.train()
        running_loss = 0.0
     
        for i, (inputs, labels) in enumerate(trainloader):
            # 获取训练数据

            #inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)

            # 权重参数梯度清零
            optimizer.zero_grad()

            # 正向及反向传播
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

            # 显示损失值
            running_loss += loss.item()
            if i % 2000 == 1999:    # print every 2000 mini-batches
                print('[%d, %5d] loss: %.3f' %(epoch + 1, i + 1, running_loss / 2000))
                running_loss = 0.0

    print('Finished Training')

如上 训练网络，最终loss如下图

net.eval()
    correct = 0
    total = 0
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = net(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

    print('Accuracy of the network on the 10000 test images: %d %%' % (
            100 * correct / total))
    class_correct = list(0. for i in range(10))
    class_total = list(0. for i in range(10))
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = net(images)
            _, predicted = torch.max(outputs, 1)
            c = (predicted == labels).squeeze()
            for i in range(4):
                label = labels[i]
                class_correct[label] += c[i].item()
                class_total[label] += 1

    for i in range(10):
        print('Accuracy of %5s : %2d %%' % (
            classes[i], 100 * class_correct[i] / class_total[i]))

如上测试网络，精度为

Accuracy of the network on the 10000 test images: 68 %

各分类精度为

Accuracy of plane : 71 %
Accuracy of   car : 75 %
Accuracy of  bird : 63 %
Accuracy of   cat : 47 %
Accuracy of  deer : 58 %
Accuracy of   dog : 63 %
Accuracy of  frog : 81 %
Accuracy of horse : 66 %
Accuracy of  ship : 84 %
Accuracy of truck : 71 %