评估-----评估算法的指标

评估算法的优劣一般会用到以下参数：
TN： 真反例 FN: 假反例
TP： 真正例 FP: 假正例

• **精确率/查准率（precision）：**预测正确的正样本个数与预测为正样本的个数的比值
  precision = TP/(TP+FP)

• 召回率/查全率/检出率(recall）：通常用来评估实验的完整性。预测正确的正样本个数与实际正样本个数的比值
  recall = TP/(TP+FN)

• 准确率(accuracy）：通常用来评估实验的质量。预测正确的样本个数与所有样本个数的比值；
  accuracy = (TP+TN)/(TP+TN+FP+FN)

• 误检率：预测错误的正样本个数与预测为正样本的个数的比值
  rate-wj = 1-precision = FP/(TP+FP)

• 漏检率：未预测到的正样本个数与实际正样本个数的比值
  rate-lj = 1-recall = FN/(TP+FN)

• 错误率：预测错误的样本个数与所有样本个数的比值
  rate-error = 1-accuracy=(FP+FN)/(TP+TN+FP+FN)

• 平准计算时间：预测样本总时间与待预测样本总数目的比值

• F值: 评估模型性能的综合指标
  F1 = （2precisionrecall)/(precision+recall）

• ap(Average Precision) ap就是平均精准度，对PR曲线上的Precision值求均值
  11-points 法
  
  mmdetection计算ap的 示例代码：

def eval_map(det_results,
             gt_bboxes,
             gt_labels,
             gt_ignore=None,
             scale_ranges=None,
             iou_thr=0.5,
             dataset=None,
             print_summary=True):
    """Evaluate mAP of a dataset.

    Args:
        det_results (list): a list of list, [[cls1_det, cls2_det, ...], ...]
        gt_bboxes (list): ground truth bboxes of each image, a list of K*4
            array.
        gt_labels (list): ground truth labels of each image, a list of K array
        gt_ignore (list): gt ignore indicators of each image, a list of K array
        scale_ranges (list, optional): [(min1, max1), (min2, max2), ...]
        iou_thr (float): IoU threshold
        dataset (None or str or list): dataset name or dataset classes, there
            are minor differences in metrics for different datsets, e.g.
            "voc07", "imagenet_det", etc.
        print_summary (bool): whether to print the mAP summary

    Returns:
        tuple: (mAP, [dict, dict, ...])
    """
    assert len(det_results) == len(gt_bboxes) == len(gt_labels)
    if gt_ignore is not None:
        assert len(gt_ignore) == len(gt_labels)
        for i in range(len(gt_ignore)):
            assert len(gt_labels[i]) == len(gt_ignore[i])
    area_ranges = ([(rg[0]**2, rg[1]**2) for rg in scale_ranges]
                   if scale_ranges is not None else None)
    num_scales = len(scale_ranges) if scale_ranges is not None else 1
    eval_results = []
    num_classes = len(det_results[0])  # positive class num
    gt_labels = [
        label if label.ndim == 1 else label[:, 0] for label in gt_labels
    ]
    for i in range(num_classes):
        # get gt and det bboxes of this class
        cls_dets, cls_gts, cls_gt_ignore = get_cls_results(
            det_results, gt_bboxes, gt_labels, gt_ignore, i)
        # calculate tp and fp for each image
        tpfp_func = (
            tpfp_imagenet if dataset in ['det', 'vid'] else tpfp_default)
        tpfp = [
            tpfp_func(cls_dets[j], cls_gts[j], cls_gt_ignore[j], iou_thr,
                      area_ranges) for j in range(len(cls_dets))
        ]
        tp, fp = tuple(zip(*tpfp))
        # calculate gt number of each scale, gts ignored or beyond scale
        # are not counted
        num_gts = np.zeros(num_scales, dtype=int)
        for j, bbox in enumerate(cls_gts):
            if area_ranges is None:
                num_gts[0] += np.sum(np.logical_not(cls_gt_ignore[j]))
            else:
                gt_areas = (bbox[:, 2] - bbox[:, 0] + 1) * (
                    bbox[:, 3] - bbox[:, 1] + 1)
                for k, (min_area, max_area) in enumerate(area_ranges):
                    num_gts[k] += np.sum(
                        np.logical_not(cls_gt_ignore[j]) &
                        (gt_areas >= min_area) & (gt_areas < max_area))
        # sort all det bboxes by score, also sort tp and fp
        cls_dets = np.vstack(cls_dets)
        num_dets = cls_dets.shape[0]
        sort_inds = np.argsort(-cls_dets[:, -1])
        tp = np.hstack(tp)[:, sort_inds]
        fp = np.hstack(fp)[:, sort_inds]
        # calculate recall and precision with tp and fp
        tp = np.cumsum(tp, axis=1)
        fp = np.cumsum(fp, axis=1)
        eps = np.finfo(np.float32).eps
        recalls = tp / np.maximum(num_gts[:, np.newaxis], eps)
        precisions = tp / np.maximum((tp + fp), eps)
        # calculate AP
        if scale_ranges is None:
            recalls = recalls[0, :]
            precisions = precisions[0, :]
            num_gts = num_gts.item()
        mode = 'area' if dataset != 'voc07' else '11points'
        ap = average_precision(recalls, precisions, mode)
        eval_results.append({
            'num_gts': num_gts,
            'num_dets': num_dets,
            'recall': recalls,
            'precision': precisions,
            'ap': ap
        })
    if scale_ranges is not None:
        # shape (num_classes, num_scales)
        all_ap = np.vstack([cls_result['ap'] for cls_result in eval_results])
        all_num_gts = np.vstack(
            [cls_result['num_gts'] for cls_result in eval_results])
        mean_ap = [
            all_ap[all_num_gts[:, i] > 0, i].mean()
            if np.any(all_num_gts[:, i] > 0) else 0.0
            for i in range(num_scales)
        ]
    else:
        aps = []
        for cls_result in eval_results:
            if cls_result['num_gts'] > 0:
                aps.append(cls_result['ap'])
        mean_ap = np.array(aps).mean().item() if aps else 0.0
    if print_summary:
        print_map_summary(mean_ap, eval_results, dataset)

    return mean_ap, eval_results

under area curve 法

• map map就是多类别平均精准度