Calculation of evaluation indicators for each class

def validation(epoch_iterator_val, model, args):
# 设置模型为验证模式
model.eval()

# 初始化度量指标
dice_metric = DiceMetric(include_background=False, reduction="mean", get_not_nans=False)
dice_metric_batch = DiceMetric(include_background=False, reduction="mean_batch", get_not_nans=False)
hd_metric = HausdorffDistanceMetric(include_background=False, reduction="mean", percentile=95)
hd_metric_batch = HausdorffDistanceMetric(include_background=False, reduction="mean_batch", percentile=95)

# 后处理函数
post_label = AsDiscrete(to_onehot=args.num_classes)
post_pred = AsDiscrete(argmax=True, to_onehot=args.num_classes)

# 初始化度量值列表
metric_values_dice = []
metric_values_hd = []
metric_values_dice_per_class = [[] for _ in range(args.num_classes-1)]
metric_values_hd_per_class = [[] for _ in range(args.num_classes-1)]

with torch.no_grad():
    for step, batch in enumerate(epoch_iterator_val):
        val_inputs, val_labels = batch["image"].cuda(), batch["label"].cuda()

        # 使用滑动窗口推理
        val_outputs = sliding_window_inference(val_inputs, (96, 96, 96), 2, model)

        # 解码并转换标签和预测
        val_outputs = [post_pred(i) for i in decollate_batch(val_outputs)]
        val_labels = [post_label(i) for i in decollate_batch(val_labels)]

        # 计算每个类别的Dice和HD
        dice_metric(y_pred=val_outputs, y=val_labels)
        dice_metric_batch(y_pred=val_outputs, y=val_labels)

        hd_metric(y_pred=val_outputs, y=val_labels)
        hd_metric_batch(y_pred=val_outputs, y=val_labels)

        # 获取总体 Dice 和 HD 度量
        metric_dice = dice_metric.aggregate().item()
        metric_values_dice.append(metric_dice)
        metric_hd = hd_metric.aggregate().item()
        metric_values_hd.append(metric_hd)

        # 获取每个类别的度量结果
        dice_metric_per_class = dice_metric_batch.aggregate()
        hd_metric_per_class = hd_metric_batch.aggregate()

        # 提取每个类别的 Dice 和 HD
        for i in range(0, args.num_classes - 1):
            metric_dice_i = dice_metric_per_class[i].item()  # 修正索引
            metric_values_dice_per_class[i].append(metric_dice_i)

            metric_hd_i = hd_metric_per_class[i].item()  # 修正索引
            metric_values_hd_per_class[i].append(metric_hd_i)

        # 重置度量器以避免累计误差
        dice_metric.reset()
        dice_metric_batch.reset()
        hd_metric.reset()
        hd_metric_batch.reset()

    # 计算总体平均 Dice 和 HD
    avg_dice = np.mean(metric_values_dice)
    avg_hd = np.mean(metric_values_hd)

    print("\n" + "--" * 40 + "\n")

    # 输出总体平均 Dice 和 HD
    print(f"Overall Average - Dice: {avg_dice:.4f}, HD: {avg_hd:.4f}")

    # 输出每个类别的 Dice 和 HD 度量
    for i in range(1, args.num_classes):  # 从 1 开始跳过背景类
        avg_dice_per_class = np.mean(metric_values_dice_per_class[i - 1])
        avg_hd_per_class = np.mean(metric_values_hd_per_class[i - 1])
        print(f"Class {i} - Dice: {avg_dice_per_class:.4f}, HD: {avg_hd_per_class:.4f}")

    print("\n" + "--" * 40 + "\n")

    # 返回总的平均和每个类别的平均度量值
    return {
        "overall_dice": avg_dice,
        "overall_hd": avg_hd,
        "dice_per_class": [np.mean(metric_values_dice_per_class[i]) for i in range(args.num_classes - 1)],
        "hd_per_class": [np.mean(metric_values_hd_per_class[i]) for i in range(args.num_classes - 1)]
    }

I am using MONAI for research. My task is multi-category medical image segmentation. Now I need to obtain the evaluation index of each category. Is my code correct?

Review the supplied validation function, starting with the MONAI DiceMetric and HausdorffDistanceMetric calls and their aggregate and reset behavior. Compare the overall and per-class outputs against the intended foreground classes, and confirm that the returned lists and printed values contain one valid Dice and HD result for each category.