博客

https://blog.csdn.net/a1154761720/article/details/50864994



https://blog.csdn.net/hysteric314/article/details/54093734



https://www.cnblogs.com/shixiangwan/p/7215926.html?utm_source=itdadao&utm_medium=referral

请参考以上链接，你的疑惑就消除了。

P=检测正确/（检测正确+检测误以为正确）   R=检测正确/（检测正确+检测误以为错误）

下面我主要说一下faster rcnn关于ap的计算：

根目录lib/dataset 下voc_eval.py有这样的代码

def voc_ap(rec, prec, use_07_metric=False):
    """ ap = voc_ap(rec, prec, [use_07_metric])
    Compute VOC AP given precision and recall.
    If use_07_metric is true, uses the
    VOC 07 11 point method (default:False).
    """
    if use_07_metric:
        # 11 point metric
        ap = 0.
        for t in np.arange(0., 1.1, 0.1):
            if np.sum(rec >= t) == 0:
                p = 0
            else:
                p = np.max(prec[rec >= t])
            ap = ap + p / 11.
    else:
        # correct AP calculation
        # first append sentinel values at the end
        mrec = np.concatenate(([0.], rec, [1.]))
        mpre = np.concatenate(([0.], prec, [0.]))

        # compute the precision envelope
        for i in range(mpre.size - 1, 0, -1):
            mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])

        # to calculate area under PR curve, look for points
        # where X axis (recall) changes value
        i = np.where(mrec[1:] != mrec[:-1])[0]

        # and sum (\Delta recall) * prec
        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
    return ap

什么意思呢？如果你的数据集是voc2007，ap就取最大的精确率，11点取平均循环加起来。否则，比如数据集voc2012那么就使用precision和recall积分求面积得到ap。你可以把此法用到voc2007上也没有关系，我就是这样做的。

感谢三个链接作者对我的启发帮助！