pytorch 使用AlexNet实现Mnist手写数字识别

AlexNet网络框架如下：AlexNet的原始输入图片大小为224*224，Mnist数据集中图片大小为28*28，所以需要对网络参数进行修改。

先调用train函数进行训练，训练好的参数会保存在params.pth文件中，训练好使用本地图片（画图软件生成）进行测试。

完整程序如下：

import torch
import torchvision as tv
import torchvision.transforms as transforms
import torch.nn as nn
import torch.optim as optim

import cv2
# 定义是否使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


# 定义AlexNet网络结构
class AlexNet(nn.Module):
    def __init__(self, width_mult=1):
        super(AlexNet, self).__init__()
        self.layer1 = nn.Sequential( # 输入1*28*28
            nn.Conv2d(1, 32, kernel_size=3, padding=1), # 32*28*28
            nn.MaxPool2d(kernel_size=2, stride=2), # 32*14*14
            nn.ReLU(inplace=True),
            )
        self.layer2 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=3, padding=1), # 64*14*14
            nn.MaxPool2d(kernel_size=2, stride=2), # 64*7*7
            nn.ReLU(inplace=True),
            )
        self.layer3 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, padding=1), # 128*7*7
            )
        self.layer4 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3, padding=1), # 256*7*7
            )

        self.layer5 = nn.Sequential(
            nn.Conv2d(256, 256, kernel_size=3, padding=1), # 256*7*7
            nn.MaxPool2d(kernel_size=3, stride=2), # 256*3*3
            nn.ReLU(inplace=True),
            )
        self.fc1 = nn.Linear(256*3*3, 1024)
        self.fc2 = nn.Linear(1024, 512)
        self.fc3 = nn.Linear(512, 10)

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.layer5(x)
        x = x.view(-1, 256*3*3)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x


# 超参数设置
EPOCH = 10 # 遍历数据集次数
BATCH_SIZE = 64  # 批处理尺寸(batch_size)
LR = 0.01  # 学习率

# 定义数据预处理方式
transform = transforms.ToTensor()

# 定义训练数据集
trainset = tv.datasets.MNIST(
    root='./data/',
    train=True,
    download=False,
    transform=transform)

# 定义训练批处理数据
trainloader = torch.utils.data.DataLoader(
    trainset,
    batch_size=BATCH_SIZE,
    shuffle=True,
)

# 定义测试数据集
testset = tv.datasets.MNIST(
    root='./data/',
    train=False,
    download=False,
    transform=transform)

# 定义测试批处理数据
testloader = torch.utils.data.DataLoader(
    testset,
    batch_size=BATCH_SIZE,
    shuffle=False,
)

# 定义损失函数loss function 和优化方式（采用SGD）
net = AlexNet().to(device)
a = torch.load('./params.pth')
net.load_state_dict(torch.load('./params.pth'))
criterion = nn.CrossEntropyLoss()  # 交叉熵损失函数，通常用于多分类问题上
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)

# 训练并保存模型参数
def train():

    for epoch in range(EPOCH):
        sum_loss = 0.0
        # 数据读取
        for i, data in enumerate(trainloader):
            inputs, labels = data
            inputs, labels = inputs.to(device), labels.to(device)

            # 梯度清零
            optimizer.zero_grad()

            # forward + backward
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

            # 每训练100个batch打印一次平均loss
            sum_loss += loss.item()
            if i % 100 == 99:
                print('[%d, %d] loss: %.03f'
                      % (epoch + 1, i + 1, sum_loss / 100))
                sum_loss = 0.0
        # 每跑完一次epoch测试一下准确率
        with torch.no_grad():
            correct = 0
            total = 0
            for data in testloader:
                images, labels = data
                images, labels = images.to(device), labels.to(device)
                outputs = net(images)
                # 取得分最高的那个类
                _, predicted = torch.max(outputs.data, 1)
                total += labels.size(0)
                correct += (predicted == labels).sum()
            print('第%d个epoch的识别准确率为：%d%%' % (epoch + 1, (100 * correct / total)))
        # 保存模型参数
        torch.save(net.state_dict(), './params.pth')

if __name__ == "__main__":
    # train()

    img = cv2.imread('./2.png', cv2.IMREAD_GRAYSCALE)
    img = cv2.resize(img,(28, 28))
    img = torch.from_numpy(img).float()
    img = img.view(1, 1, 28, 28)
    img = img.to(device)
    outputs = net(img)
    _, predicted = torch.max(outputs.data, 1)
    print(predicted.to('cpu').numpy().squeeze())

    # cv2.imshow('', img)
    # cv2.waitKey(0)