读取训练集、验证集和测试集的三个csv文件每条数据集共43个特征前42位为特征值最后1位为类别标签标签共有10个类别分别是0129现使用CNN和BiGRU双模型并行分别做为特征提取器其中将原始数据从一维格式转换为二维格式输入CNN中输入BiGRU的数据为原始数据然后将两特征提取器的结果进行contact特征融合最后使用softmax对融合的结果进行10分类有训练过程验证测试结果使用pytorch写

以下是使用PyTorch编写的代码示例，实现了使用CNN和BiGRU双模型并行进行特征提取和融合的分类任务：

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split

# 读取数据集
train_data = pd.read_csv('train.csv')
val_data = pd.read_csv('val.csv')
test_data = pd.read_csv('test.csv')

# 划分特征和标签
train_features, train_labels = train_data.iloc[:, :42].values, train_data.iloc[:, 42].values
val_features, val_labels = val_data.iloc[:, :42].values, val_data.iloc[:, 42].values
test_features, test_labels = test_data.iloc[:, :42].values, test_data.iloc[:, 42].values

# 转换为PyTorch的Tensor
train_features = torch.Tensor(train_features)
train_labels = torch.Tensor(train_labels).long()
val_features = torch.Tensor(val_features)
val_labels = torch.Tensor(val_labels).long()
test_features = torch.Tensor(test_features)
test_labels = torch.Tensor(test_labels).long()

# 数据集类
class MyDataset(Dataset):
    def __init__(self, features, labels):
        self.features = features
        self.labels = labels
    
    def __len__(self):
        return len(self.features)
    
    def __getitem__(self, index):
        return self.features[index], self.labels[index]

# 定义CNN模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv1d(1, 16, 3)
        self.conv2 = nn.Conv1d(16, 32, 3)
        self.fc1 = nn.Linear(32 * 38, 128)
        self.fc2 = nn.Linear(128, 64)
    
    def forward(self, x):
        x = x.view(-1, 1, 42)
        x = F.relu(self.conv1(x))
        x = F.relu(self.conv2(x))
        x = x.view(-1, 32 * 38)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        return x

# 定义BiGRU模型
class BiGRU(nn.Module):
    def __init__(self):
        super(BiGRU, self).__init__()
        self.gru = nn.GRU(42, 64, bidirectional=True)
        self.fc = nn.Linear(128, 64)
    
    def forward(self, x):
        x = x.view(-1, 42, 1)
        x, _ = self.gru(x)
        x = x[:, -1, :]
        x = self.fc(x)
        return x

# 定义整体模型
class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.cnn = CNN()
        self.gru = BiGRU()
        self.fc = nn.Linear(128, 10)
    
    def forward(self, x1, x2):
        x1 = self.cnn(x1)
        x2 = self.gru(x2)
        x = torch.cat((x1, x2), dim=1)
        x = self.fc(x)
        return x

# 创建数据加载器
batch_size = 32
train_dataset = MyDataset(train_features, train_labels)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
val_dataset = MyDataset(val_features, val_labels)
val_loader = DataLoader(val_dataset, batch_size=batch_size)
test_dataset = MyDataset(test_features, test_labels)
test_loader = DataLoader(test_dataset, batch_size=batch_size)

# 定义训练函数
def train(model, device, train_loader, optimizer, epoch):
    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, data)
        loss = F.cross_entropy(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))

# 定义验证函数
def validate(model, device, val_loader):
    model.eval()
    val_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in val_loader:
            data, target = data.to(device), target.to(device)
            output = model(data, data)
            val_loss += F.cross_entropy(output, target, reduction='sum').item()
            pred = output.argmax(dim=1, keepdim=True)
            correct += pred.eq(target.view_as(pred)).sum().item()

    val_loss /= len(val_loader.dataset)
    val_accuracy = 100. * correct / len(val_loader.dataset)
    print('Validation set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)'.format(
        val_loss, correct, len(val_loader.dataset), val_accuracy))

# 初始化模型、设备和优化器
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = Model().to(device)
optimizer = optim.Adam(model.parameters(), lr=0.001)

# 训练模型
for epoch in range(1, 11):
    train(model, device, train_loader, optimizer, epoch)
    validate(model, device, val_loader)

# 测试模型
model.eval()
test_loss = 0
test_correct = 0
with torch.no_grad():
    for data, target in test_loader:
        data, target = data.to(device), target.to(device)
        output = model(data, data)
        test_loss += F.cross_entropy(output, target, reduction='sum').item()
        pred = output.argmax(dim=1, keepdim=True)
        test_correct += pred.eq(target.view_as(pred)).sum().item()

test_loss /= len(test_loader.dataset)
test_accuracy = 100. * test_correct / len(test_loader.dataset)
print('Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)'.format(
    test_loss, test_correct, len(test_loader.dataset), test_accuracy))

需要注意的是，以上代码仅为示例，模型结构和超参数可能需要根据具体任务进行调整和优化。另外，为了运行效率，可以考虑使用GPU进行加速，如果没有GPU，可以将device = torch.device("cuda" if torch.cuda.is_available() else "cpu")改为device = torch.device("cpu")。