帮我写一段使用三层MLP神经网络模型的代码,分为训练及预测两个部分,使用ACC评估函数,nn.CrossEntropyLoss()损失

当然可以，这里是一个简单的例子，使用PyTorch库来构建一个三层全连接（Multilayer Perceptron，MLP）神经网络模型，包括训练和预测功能，并采用交叉熵损失函数（nn.CrossEntropyLoss）以及准确率（Accuracy）作为评估指标。首先，确保已经安装了torch库。

import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.metrics import accuracy_score

# 定义三层MLP模型
class MLP(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super(MLP, self).__init__()
        self.fc1 = nn.Linear(input_dim, hidden_dim)
        self.fc2 = nn.Linear(hidden_dim, hidden_dim)
        self.fc3 = nn.Linear(hidden_dim, output_dim)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 示例数据设置
input_dim = 784  # 假设输入特征维度为28x28
hidden_dim = 512
output_dim = 10  # 假设是10分类任务
num_epochs = 10
batch_size = 64
learning_rate = 0.001

# 创建模型、损失函数和优化器
model = MLP(input_dim, hidden_dim, output_dim)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 模拟数据集
# train_loader, test_loader = ...  # 这里假设你已经有了数据加载器
# 实际上你需要从torch.utils.data中加载数据

def train(model, data_loader, criterion, optimizer):
    model.train()
    running_loss = 0.0
    total_correct = 0
    for inputs, labels in data_loader:
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        _, predicted = torch.max(outputs.data, 1)
        total_correct += (predicted == labels).sum().item()
        running_loss += loss.item() * inputs.size(0)
    avg_loss = running_loss / len(data_loader.dataset)
    accuracy = total_correct / len(data_loader.dataset)
    return avg_loss, accuracy

def predict(model, data_loader):
    model.eval()
    predictions = []
    true_labels = []
    with torch.no_grad():
        for inputs, labels in data_loader:
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, 1)
            predictions.extend(predicted.tolist())
            true_labels.extend(labels.tolist())

    return predictions, true_labels

# 训练过程
for epoch in range(num_epochs):
    train_loss, train_acc = train(model, train_loader, criterion, optimizer)
    print(f"Epoch {epoch+1}/{num_epochs}, Loss: {train_loss:.4f}, Accuracy: {train_acc*100:.2f}%")

# 预测阶段
test_predictions, test_true_labels = predict(model, test_loader)
test_accuracy = accuracy_score(test_true_labels, test_predictions)
print(f"Test Accuracy: {test_accuracy*100:.2f}%")