Skip to content
TheChatArchiveThe Chat Archive
gpt-4-0314· openaiHugging Face Suzhen/CodeChat

用pytorch写出在图片分类模型训练中应用稀疏编码技巧,用CIFAR10数据集,然后进行训练,写出完整代码,中文注释,代码可直接运行

  1. User

    用pytorch写出在图片分类模型训练中应用稀疏编码技巧,用CIFAR10数据集,然后进行训练,写出完整代码,中文注释,代码可直接运行

  2. Assistant
    import torch
    import torch.nn as nn
    import torch.optim as optim
    import torchvision
    import torchvision.transforms as transforms
    
    # 定义网络模型
    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(3, 6, 5)
            self.pool = nn.MaxPool2d(2, 2)
            self.conv2 = nn.Conv2d(6, 16, 5)
            self.fc1 = nn.Linear(16 * 5 * 5, 120)
            self.fc2 = nn.Linear(120, 84)
            self.fc3 = nn.Linear(84, 10)
    
        def forward(self, x):
            x = self.pool(F.relu(self.conv1(x)))
            x = self.pool(F.relu(self.conv2(x)))
            x = x.view(-1, 16 * 5 * 5)
            x = F.relu(self.fc1(x))
            x = F.relu(self.fc2(x))
            x = self.fc3(x)
            return x
    
    net = Net()
    
    # 加载CIFAR10数据集
    transform = transforms.Compose(
        [transforms.RandomHorizontalFlip(),
         transforms.RandomCrop(32, padding=4),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    
    trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                            download=True, transform=transform)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=100,
                                              shuffle=True, num_workers=2)
    
    testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                           download=True, transform=transform)
    testloader = torch.utils.data.DataLoader(testset, batch_size=100,
                                             shuffle=False, num_workers=2)
    
    # 定义损失函数和优化器
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
    
    # 训练网络
    for epoch in range(10):
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data
    
            # 清零梯度
            optimizer.zero_grad()
    
            # 正向传播,反向传播和优化
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
    
            running_loss += loss.item()
    
        # 打印每个epoch的平均损失
        print(f'Epoch {epoch + 1}, Loss: {running_loss / (i + 1):.4f}')
    
    print('Finished Training')
    
    # 在测试数据集上的性能
    correct = 0
    total = 0
    
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            outputs = net(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    
    print(f'Accuracy of the network on the 10000 test images: {100 * correct / total}%')
    

    代码说明:

    1. 引入需要的库,定义卷积神经网络模型。
    2. 使用torchvision加载CIFAR10数据集,并进行数据增强。
    3. 定义损失函数与优化器。
    4. 训练网络,打印每个epoch的平均损失。
    5. 在训练完成后,评估网络在测试数据集上的性能。
  3. User

    以上代码没有用到数据集的稀疏编码的技巧,请用上稀疏编码的技巧,重新写出代码,代码可直接运行

  4. Assistant
    import torch
    import torch.nn as nn
    import torch.optim as optim
    import torchvision
    import torchvision.transforms as transforms
    
    # 定义网络模型
    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(3, 6, 5)
            self.pool = nn.MaxPool2d(2, 2)
            self.conv2 = nn.Conv2d(6, 16, 5)
            self.fc1 = nn.Linear(16 * 5 * 5, 120)
            self.fc2 = nn.Linear(120, 84)
            self.dropout = nn.Dropout2d(p=0.5)
            self.fc3 = nn.Linear(84, 10)
    
        def forward(self, x):
            x = self.pool(F.relu(self.conv1(x)))
            x = self.pool(F.relu(self.conv2(x)))
            x = x.view(-1, 16 * 5 * 5)
            x = F.relu(self.fc1(x))
            x = F.relu(self.fc2(x))
            x = self.dropout(x)
            x = self.fc3(x)
            return x
    
    net = Net()
    
    # 加载CIFAR10数据集
    transform = transforms.Compose(
        [transforms.RandomHorizontalFlip(),
         transforms.RandomCrop(32, padding=4),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    
    trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                            download=True, transform=transform)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=100,
                                              shuffle=True, num_workers=2)
    
    testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                           download=True, transform=transform)
    testloader = torch.utils.data.DataLoader(testset, batch_size=100,
                                             shuffle=False, num_workers=2)
    
    # 定义损失函数和优化器
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9, weight_decay=5e-4)
    
    # 训练网络
    for epoch in range(10):
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data
    
            # 清零梯度
            optimizer.zero_grad()
    
            # 正向传播,反向传播和优化
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
    
            running_loss += loss.item()
    
        # 打印每个epoch的平均损失
        print(f'Epoch {epoch + 1}, Loss: {running_loss / (i + 1):.4f}')
    
    print('Finished Training')
    
    # 在测试数据集上的性能
    correct = 0
    total = 0
    
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            outputs = net(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    
    print(f'Accuracy of the network on the 10000 test images: {100 * correct / total}%')
    

    代码说明:

    1. 引入需要的库,定义卷积神经网络模型,在全连接层之间加入dropout层,提高数据稀疏性。
    2. 使用torchvision加载CIFAR10数据集,并进行数据增强。
    3. 定义损失函数与优化器,并在优化器中添加L2正则化(weight_decay)来增强稀疏性。
    4. 训练网络,打印每个epoch的平均损失。
    5. 在训练完成后,评估网络在测试数据集上的性能。