两个段上联合的交集

Question

假设我有这两个数据框： Groundtruth和Prediction 。

每个 Dataframe 有 3 列； 行动，开始和结束。

**Prediction :**

Action  |   Start   | End
-------------------------
 3      |   0       | 10
 2      |   10      | 70
 3      |   80      | 120
 0      |  120      | 350
 7      |  400      | 610
...

**Groundtruth :**

Action  |   Start   | End
-------------------------
 2      |   20      | 140
 0      |  150      | 340
 6      |  420      | 600
...

我想使用所有列在这两个数据帧上计算交集比联合（IoU），这意味着首先操作以查看它是否是正确的预测，再加上每个操作的开始和结束段以查看是否正确开始和结束.

这是我的代码：

def compute_iou(y_pred, y_true):
    y_pred = y_pred.flatten()
    y_true = y_true.flatten()
    cm = confusion_matrix(y_true, y_pred)
    intersection = np.diag(cm)
    ground_truth_set = cm.sum(axis=1)
    predicted_set = cm.sum(axis=0)
    union = ground_truth_set + predicted_set - intersection
    IoU = intersection / union
    for i in range(len(IoU)):
        if (IoU[i]>0.5):
            IoU[i] = 1
    return round(np.mean(IoU)*100, 3)

当我想在操作列上计算 IoU 时，这很有效。

现在我该如何调整它，以便我可以让 IoU 在开始列和结束列上获得重叠段？

PS：Groundtruth 和 Prediction 数据帧的行数不同。

Answer 1

（后期编辑）

计算分为三种情况：

• 重叠：活动匹配的地方，并且在地面实况区间和预测区间之间存在重叠。
• 没有重叠：活动匹配，但没有这样的重叠。
• 没有命中：根本没有预测到活动，或者有错误的活动。

这是代码：

df = pd.merge(pred, groundtruth, on = "Action", how = "outer",  suffixes = ["_pred", "_gt"])

overlap = df[(df.Start_pred < df.End_gt) & (df.Start_gt < df.End_pred)]

intersection = (overlap[["End_pred", "End_gt"]].min(axis=1) - overlap[["Start_pred", "Start_gt"]].max(axis=1)).sum()

union_where_overlap = (overlap[["End_pred", "End_gt"]].max(axis=1) - overlap[["Start_pred", "Start_gt"]].\
                    min(axis=1)).sum()

no_hit = df[df.isna().sum(axis=1) > 0]
union_no_hit = (no_hit[["End_pred", "End_gt"]].max(axis=1) - no_hit[["Start_pred", "Start_gt"]].min(axis=1)).sum()

no_overlap = df[~((df.Start_pred < df.End_gt) & (df.Start_gt < df.End_pred))].dropna()
union_no_overlap = ((no_overlap.End_pred - no_overlap.Start_pred) + (no_overlap.End_gt - no_overlap.Start_gt)).sum()

IoU = intersection / (union_no_hit + union_where_overlap + union_no_overlap)