将下面这段代码进行完善并加入当每隔50个epoch最佳准确率不改变时候更新学习率的部分import torchimport torchvisionmodels as modelsfrom torchutils import datafrom torch import nnfrom torch import optimimport numpy as npimport argparsefrom dat

下面是完善并加入学习率更新部分的代码：

from torch.optim.lr_scheduler import ReduceLROnPlateau

# 设置ReduceLROnPlateau学习率调度器
scheduler = ReduceLROnPlateau(optimizer, mode='max', factor=0.5, patience=10, verbose=True)

best_accuracy = 0.0  # 保存最佳模型的准确率
best_epoch = 0
no_improve_count = 0  # 记录连续没有提升的epoch次数

for epoch in range(args.epochs):
    model.train()
    # 遍历训练集数据
    for imgs, labels in my_datalodaer:
        steps += 1
        labels = torch.tensor(labels, dtype=torch.long)
        imgs, labels = imgs.to(DEVICE), labels.to(DEVICE)
        optimizer.zero_grad()  # 梯度归零
        outputs = model(imgs)
        loss = loss_fn(outputs, labels)
        loss.backward()  # 反向传播计算梯度
        optimizer.step()  # 梯度优化
        running_loss += loss.item()

        if steps % count == 0:
            test_loss = 0
            accuracy = 0
            model.eval()
            with torch.no_grad():
                # 遍历测试集数据
                for imgs, labels in test_dl:
                    labels = torch.tensor(labels, dtype=torch.long)
                    imgs, labels = imgs.to(DEVICE), labels.to(DEVICE)
                    outputs = model(imgs)
                    loss = loss_fn(outputs, labels)
                    test_loss += loss.item()
                    ps = torch.exp(outputs)
                    top_p, top_class = ps.topk(1, dim=1)
                    equals = top_class == labels.view(*top_class.shape)
                    accuracy += torch.mean(equals.type(torch.FloatTensor)).item()
            train_losses.append(running_loss / len(train_dl))
            test_losses.append(test_loss / len(test_dl))
            if steps % (int(50)) == 0:
                print(
                    f"Epoch {epoch + 1}/{args.epochs}.. "
                    f"Train loss: {running_loss / count:.3f}.. "
                    f"Test loss: {test_loss / len(test_dl):.3f}.. "
                    f"Test accuracy: {accuracy / len(test_dl):.3f}")
            running_loss = 0
            model.train()
            if accuracy > best_accuracy:
                best_accuracy = accuracy
                best_epoch = epoch
                torch.save(model, "Direction_model.pth")
                no_improve_count = 0
            else:
                no_improve_count += 1
                if no_improve_count >= 50:
                    # 更新学习率
                    scheduler.step(best_accuracy)
                    if optimizer.param_groups[0]['lr'] < 1e-6:
                        # 学习率过小，停止训练
                        print("Learning rate too small, training stopped.")
                        break
                    no_improve_count = 0

print("Training completed.")

在上述代码中，首先引入了ReduceLROnPlateau学习率调度器，它会在每隔一定的epoch中检查模型的准确率是否有提升，如果没有提升，则会将学习率降低一定的倍数（通过factor参数指定）。在代码中使用mode='max'表示要寻找准确率的最大值，patience参数表示连续多少个epoch没有提升时才进行学习率更新。当学习率更新后，会重置no_improve_count计数器为0。

在代码中添加了best_epoch变量来记录最佳准确率对应的epoch，以便在保存最佳模型时使用。

最后，在每个epoch结束后，增加了判断no_improve_count是否达到50的条件，如果达到，则调用scheduler.step(best_accuracy)来更新学习率，并重置no_improve_count为0。如果学习率小于1e-6，则认为学习率过小，停止训练