pytorch神经网络学习笔记07----一个使用pytorch对卷积神经网络做交叉验证的例子

下面是一个使用 PyTorch 对卷积神经网络进行交叉验证的示例。假设我们有一个模型类，名为 “CNN”。

import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.model_selection import KFold

# 定义模型类
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(32 * 8 * 8, 128)
        self.fc2 = nn.Linear(128, 10)
    
    def forward(self, x):
        x = self.pool(nn.functional.relu(self.conv1(x)))
        x = self.pool(nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 32 * 8 * 8)
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 定义交叉验证参数
k = 5
epochs = 10
batch_size = 64
lr = 0.001

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=lr, momentum=0.9)

# 加载数据集
train_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True)

# 初始化 k-fold
kf = KFold(n_splits=k, shuffle=True)

# 交叉验证训练
for fold, (train_indices, val_indices) in enumerate(kf.split(trainset)):
  # 数据分为训练集和验证集
  train_sampler = torch.utils.data.sampler.SubsetRandomSampler(train_indices)
  val_sampler = torch.utils.data.sampler.SubsetRandomSampler(val_indices)
  train_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, sampler=train_sampler)
  val_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, sampler=val_sampler)

  # 初始化模型
  net = CNN()

  # 训练模型
  for epoch in range(epochs):
    running_loss = 0.0
    for i, data in enumerate(train_loader):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()

    # 输出训练结果
    print("Fold [%d]/[%d] Epoch [%d]/[%d] Loss: %.3f" % (fold+1, k, epoch+1, epochs, running_loss/(i+1)))
    
    # 验证模型
    correct = 0
    total = 0
    with torch.no_grad():
        for data in val_loader:
            images, labels = data
            outputs = net(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

    accuracy = 100 * correct / total
    print('Validation Accuracy: %d %%' % (accuracy))

下面是一个使用 PyTorch 对卷积神经网络进行交叉验证的示例。假设我们有一个模型类，名为 “CNN”。

Copy code
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.model_selection import KFold

定义模型类

class CNN(nn.Module):
def init(self):
super(CNN, self).init()
self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1)
self.conv2 = nn.Conv2d(16, 32, kernel_size=3, padding=1)
self.pool = nn.MaxPool2d(2, 2)
self.fc1 = nn.Linear(32 * 8 * 8, 128)
self.fc2 = nn.Linear(128, 10)

def forward(self, x):
    x = self.pool(nn.functional.relu(self.conv1(x)))
    x = self.pool(nn.functional.relu(self.conv2(x)))
    x = x.view(-1, 32 * 8 * 8)
    x = nn.functional.relu(self.fc1(x))
    x = self.fc2(x)
    return x

定义交叉验证参数

k = 5
epochs = 10
batch_size = 64
lr = 0.001

定义损失函数和优化器

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

加载数据集

train_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True)

初始化 k-fold

kf = KFold(n_splits=k, shuffle=True)

交叉验证训练

for fold, (train_indices, val_indices) in enumerate(kf.split(trainset)):

数据分为训练集和验证集

train_sampler = torch.utils.data.sampler.SubsetRandomSampler(train_indices)
val_sampler = torch.utils.data.sampler.SubsetRandomSampler(val_indices)
train_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, sampler=train_sampler)
val_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, sampler=val_sampler)

初始化模型

net = CNN()

训练模型

for epoch in range(epochs):
running_loss = 0.0
for i, data in enumerate(train_loader):
inputs, labels = data
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()

# 输出训练结果
print("Fold [%d]/[%d] Epoch [%d]/[%d] Loss: %.3f" % (fold+1, k, epoch+1, epochs, running_loss/(i+1)))

# 验证模型
correct = 0
total = 0
with torch.no_grad():
    for data in val_loader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

accuracy = 100 * correct / total
print('Validation Accuracy: %d %%' % (accuracy))

这个示例代码中，我们首先定义了我们的 CNN 模型，并设置了一些超参数和优化器和损失函数。

然后我们使用 K-Fold 方法将数据拆分为训练和验证集，并利用 PyTorch 中的 DataLoader 将数据加载至模型中。

接着我们对每个 fold 进行训练和验证，跟踪损失并输出结果。最后计算交叉验证的准确率（accuracy）并打印出来。