pytorch实现cnn手写数字识别并计算查准率，查全率以及ALU的代码

以下是使用PyTorch实现CNN手写数字识别并计算查准率、查全率和ALU的示例代码：

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

# 设置超参数
num_epochs = 10
num_classes = 10
batch_size = 100
learning_rate = 0.001

# 加载数据集并进行预处理
train_dataset = datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor())

# 创建数据加载器
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)

# 定义CNN模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(7*7*32, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

# 实例化CNN模型
model = CNN()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        # 前向传播
        outputs = model(images)
        loss = criterion(outputs, labels)

        # 反向传播并优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 每训练100个batch就输出一次信息
        if (i+1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# 测试模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('准确率: {} %'.format(100 * correct / total))

# 计算查准率、查全率和ALU
with torch.no_grad():
    TP, TN, FP, FN = 0, 0, 0, 0
    for images, labels in test_loader:
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        for i in range(len(labels)):
            if labels[i] == predicted[i]:
                if labels[i] == 1:
                    TP += 1
                else:
                    TN += 1
            else:
                if labels[i] == 1:
                    FN += 1
                else:
                    FP += 1

    precision = TP / (TP + FP)
    recall = TP / (TP + FN)
    ALU = (TN + TP) / (TN + TP + FP + FN)
    print('查准率: {:.4f}, 查全率: {:.4f}, ALU: {:.4f}'.format(precision, recall, ALU))

在以上代码中，我们首先加载MNIST数据集并进行预处理。然后，我们定义了一个CNN模型，并且实例化了该模型。接着，我们定义了损失函数和优化器，并在训练过程中使用它们。最后，我们测试了模型的准确率，并计算了查准率、查全率和ALU。

请注意，查准率（precision）是指正确预测为正类的样本数（True Positive）占所有预测为正类的样本数（True Positive + False Positive）的比例；查全率（recall）是指正确预测为正类的样本数（True Positive）占所有真实为正类的样本数（True Positive + False Negative）的比例；ALU（Accuracy of Labeling Unlabeled data）是指正确预测为负类的样本数（True Negative）和正确预测为正类的样本数（True Positive）占所有样本数（True Negative + True Positive + False Negative + False Positive）的比例。