如何将CNN LSTM表单keras转换为pytorch

import torch
import torch.nn as nn
import torch.nn.functional as F

class CNNLSTM(nn.Module):
    def __init__(self):
        super(CNNLSTM, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.dropout = nn.Dropout(0.5)
        self.lstm = nn.LSTM(64, 128, batch_first=True)
        self.fc = nn.Linear(128, num_classes)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.relu(self.conv2(x))
        x = x.view(x.size(0), -1)
        x = self.dropout(x)
        x = x.unsqueeze(1)
        x, _ = self.lstm(x)
        x = x[:, -1, :]
        x = self.fc(x)
        return x

num_classes = 10
learning_rate = 0.001
criterion = nn.CrossEntropyLoss()

model = CNNLSTM()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 假设有训练数据集 train_dataset 和测试数据集 test_dataset

# 创建数据加载器
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)

# 训练模型
for epoch in range(num_epochs):
    for images, labels in train_loader:
        optimizer.zero_grad()
        outputs = model(images)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

    # 在测试集上评估模型
    with torch.no_grad():
        correct = 0
        total = 0
        for images, labels in test_loader:
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

        accuracy = 100 * correct / total
        print('Epoch [{}/{}], Accuracy: {:.2f}%'.format(epoch+1, num_epochs, accuracy))