pytorch构建神经网络进行贝叶斯超参数优化的代码

下面是使用PyTorch构建神经网络进行贝叶斯超参数优化的代码示例。使用了贝叶斯优化库 `BayesianOptimization`。

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms

from bayes_opt import BayesianOptimization


class Net(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x


def train(model, device, train_loader, optimizer, criterion):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()


def test(model, device, test_loader, criterion):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += criterion(output, target).item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    accuracy = 100.0 * correct / len(test_loader.dataset)
    return test_loss, accuracy


def train_and_evaluate(hidden_size, learning_rate):
    # Set up device
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

    # Set up data loaders
    batch_size = 64
    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
    train_data = datasets.MNIST("data", train=True, download=True, transform=transform)
    test_data = datasets.MNIST("data", train=False, download=True, transform=transform)
    train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True)
    test_loader = DataLoader(test_data, batch_size=batch_size, shuffle=False)

    # Set up model
    input_size = 784
    output_size = 10
    model = Net(input_size, int(hidden_size), output_size).to(device)

    # Set up optimizer and loss function
    optimizer = optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9)
    criterion = nn.CrossEntropyLoss()

    # Train and test the model
    for epoch in range(10):
        train(model, device, train_loader, optimizer, criterion)
        test_loss, accuracy = test(model, device, test_loader, criterion)
        print(f"Epoch {epoch + 1} - Test Loss: {test_loss:.4f}, Accuracy: {accuracy:.2f}%")

    return accuracy


if __name__ == "__main__":
    # Define hyperparameter search space
    pbounds = {"hidden_size": (50, 500), "learning_rate": (1e-5, 1e-1)}

    # Set up optimizer
    optimizer = BayesianOptimization(f=train_and_evaluate, pbounds=pbounds)

    # Run optimizer
    optimizer.maximize(init_points=5, n_iter=20)
    
    # Print best hyperparameters
    print(optimizer.max)

在这个例子中，我们使用 MNIST 数据集作为我们的训练数据，并构建了一个简单的两层全连接神经网络作为我们的模型。然后，我们使用 `BayesianOptimization` 来搜索隐藏层大小和学习率的最佳值。在每次迭代中，我们使用 `train_and_evaluate` 函数来训练和测试模型，并返回测试准确率作为优化目标。最后，我们打印出找到的最佳超参数组合。