深度学习之基于卷积神经网络的手写数字识别（课后作业）

给出的代码如下：

import torch
from keras.src.metrics.accuracy_metrics import accuracy
from sympy.physics.units import momentum
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt

batch_size = 64
learning_rate = 0.01

#将图像转化为张量
transforms = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

#加载数据集
train_dataset = datasets.MNIST(root='../dataset',
                               train=True,
                               transform=transforms,
                               download=True)

train_loader = DataLoader(train_dataset,
                          batch_size=batch_size,
                          shuffle=True)

test_dataset = datasets.MNIST(root='../dataset',
                              train=False,
                              transform=transforms,
                              download=False)
test_loader = DataLoader(test_dataset,
                         batch_size=batch_size,
                         shuffle=False)

#定义带有卷积层的神经网络模型
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(in_channels=1,out_channels=10,kernel_size=5,bias=False)
        self.conv2 = torch.nn.Conv2d(in_channels=10,out_channels=20,kernel_size=5,bias=False)
        self.conv3 = torch.nn.Conv2d(in_channels=20,out_channels=30,kernel_size=3,bias=False)
        self.pooling = torch.nn.MaxPool2d(2)
        self.linear1 = torch.nn.Linear(in_features=30,out_features=256,bias=True)
        self.linear2 = torch.nn.Linear(in_features=256,out_features=64,bias=True)
        self.linear3 = torch.nn.Linear(in_features=64,out_features=10,bias=True)

    def forward(self, x):
        batch_size = x.size(0)
        x = self.pooling(F.relu(self.conv1(x)))
        x = self.pooling(F.relu(self.conv2(x)))
        x = self.pooling(F.relu(self.conv3(x)))
        x = x.view(batch_size,-1)
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.linear3(x)
        return x
#创建实例
model = Net()
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.to(device)

#定义损失函数及优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(),lr=learning_rate,momentum=0.5)

#训练过程
def train(epoch):
    model.train()
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs,target = inputs.to(device),target.to(device)
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print(f'[{epoch + 1}, {batch_idx + 1:5d}] loss: {running_loss / 300:.3f}')
            running_loss = 0.0

def test(epoch):
    model.eval()
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            input,labels = data
            input,labels = input.to(device),labels.to(device)
            output = model(input)
            _, predicted = torch.max(output.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
        accuracy = 100 * correct / total
        print(f'Accuracy on test set: {accuracy:.3f}')
        return accuracy

if  __name__ == '__main__':
    epochs = 10
    epoch_list = []
    accuracy_list = []
    loss_list = []

    for epoch in range(epochs):
        train(epoch)
        accuracy = test(epoch)
        epoch_list.append(epoch + 1)  # 记录epoch编号(1-10)
        accuracy_list.append(accuracy)  # 记录每个epoch的准确率

    # 绘制准确率曲线
    plt.figure(figsize=(12, 5))
    plt.subplot(1, 2, 1)
    plt.plot(epoch_list, accuracy_list, 'b-')
    plt.title('Test Accuracy vs. Epochs')
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy (%)')
    plt.grid(True)
    plt.tight_layout()
    plt.show()

训练训练着准确率都变成过山车了。。。