k折交叉验证代码 pytorch
时间: 2023-11-20 19:14:19 浏览: 46
当然可以!以下是一个使用PyTorch进行k折交叉验证的示例代码:
```python
import torch
from torch.utils.data import DataLoader, SubsetRandomSampler
from torchvision.datasets import CIFAR10
from torchvision.transforms import ToTensor
from sklearn.model_selection import KFold
# 设置随机种子
torch.manual_seed(0)
# 加载数据集
dataset = CIFAR10(root='data/', train=True, download=True, transform=ToTensor())
# 定义模型
model = YourModel()
# 定义损失函数和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
# 设置k折交叉验证的折数
k = 5
# 初始化k折交叉验证器
kfold = KFold(n_splits=k, shuffle=True)
# 执行k折交叉验证
for fold, (train_ids, val_ids) in enumerate(kfold.split(dataset)):
print(f'Fold {fold + 1}/{k}')
print('-' * 10)
# 根据折数生成训练集和验证集的数据加载器
train_loader = DataLoader(dataset, batch_size=32, sampler=SubsetRandomSampler(train_ids))
val_loader = DataLoader(dataset, batch_size=32, sampler=SubsetRandomSampler(val_ids))
# 训练模型
for epoch in range(10):
model.train()
running_loss = 0.0
for inputs, labels in train_loader:
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
epoch_loss = running_loss / len(train_loader)
print(f'Train Loss: {epoch_loss}')
# 在验证集上评估模型
model.eval()
correct = 0
total = 0
with torch.no_grad():
for inputs, labels in val_loader:
outputs = model(inputs)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
accuracy = correct / total
print(f'Validation Accuracy: {accuracy}')
print()
```
请注意,以上代码仅为示例,您可能需要根据您的数据集和模型进行适当的修改。