目標檢測和分類論文中的生僻概念

目標檢測相關：

目標檢測中的相應評價指標：AP，mAP，top-1，top-5,p-r等等一覽
http://blog.sina.com.cn/s/blog_9db078090102whzw.html

mean average precision（MAP）在電腦視覺中是如何計算和應用的。
https://www.zhihu.com/question/41540197/answer/91698989

精確率與召回率，RoC曲線與PR曲線
http://www.ppvke.com/Blog/archives/45988

什麼是映像分類的Top-5錯誤率。
https://www.zhihu.com/question/36463511

映像分類Top-5 錯誤率
https://www.jianshu.com/p/355785bd77cb

Evaluation & Calculate Top-N Accuracy: Top 1 and Top 5
https://stackoverflow.com/questions/37668902/evaluation-calculate-top-n-accuracy-top-1-and-top-5

AP計算代碼：（https://github.com/facebookresearch/Detectron/blob/05d04d3a024f0991339de45872d02f2f50669b3d/lib/datasets/voc_eval.py#L54）

def voc_ap(rec, prec, use_07_metric=False):    """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 apdef voc_eval(detpath,             annopath,             imagesetfile,             classname,             cachedir,             ovthresh=0.5,             use_07_metric=False):    """rec, prec, ap = voc_eval(detpath,                                annopath,                                imagesetfile,                                classname,                                [ovthresh],                                [use_07_metric])    Top level function that does the PASCAL VOC evaluation.    detpath: Path to detections        detpath.format(classname) should produce the detection results file.    annopath: Path to annotations        annopath.format(imagename) should be the xml annotations file.    imagesetfile: Text file containing the list of images, one image per line.    classname: Category name (duh)    cachedir: Directory for caching the annotations    [ovthresh]: Overlap threshold (default = 0.5)    [use_07_metric]: Whether to use VOC07's 11 point AP computation        (default False)    """    # assumes detections are in detpath.format(classname)    # assumes annotations are in annopath.format(imagename)    # assumes imagesetfile is a text file with each line an image name    # cachedir caches the annotations in a pickle file    # first load gt    if not os.path.isdir(cachedir):        os.mkdir(cachedir)    imageset = os.path.splitext(os.path.basename(imagesetfile))[0]    cachefile = os.path.join(cachedir, imageset + '_annots.pkl')    # read list of images    with open(imagesetfile, 'r') as f:        lines = f.readlines()    imagenames = [x.strip() for x in lines]    if not os.path.isfile(cachefile):        # load annots        recs = {}        for i, imagename in enumerate(imagenames):            recs[imagename] = parse_rec(annopath.format(imagename))            if i % 100 == 0:                logger.info(                    'Reading annotation for {:d}/{:d}'.format(                        i + 1, len(imagenames)))        # save        logger.info('Saving cached annotations to {:s}'.format(cachefile))        with open(cachefile, 'w') as f:            cPickle.dump(recs, f)    else:        # load        with open(cachefile, 'r') as f:            recs = cPickle.load(f)    # extract gt objects for this class    class_recs = {}    npos = 0    for imagename in imagenames:        R = [obj for obj in recs[imagename] if obj['name'] == classname]        bbox = np.array([x['bbox'] for x in R])        difficult = np.array([x['difficult'] for x in R]).astype(np.bool)        det = [False] * len(R)        npos = npos + sum(~difficult)        class_recs[imagename] = {'bbox': bbox,                                 'difficult': difficult,                                 'det': det}    # read dets    detfile = detpath.format(classname)    with open(detfile, 'r') as f:        lines = f.readlines()    splitlines = [x.strip().split(' ') for x in lines]    image_ids = [x[0] for x in splitlines]    confidence = np.array([float(x[1]) for x in splitlines])    BB = np.array([[float(z) for z in x[2:]] for x in splitlines])    # sort by confidence    sorted_ind = np.argsort(-confidence)    BB = BB[sorted_ind, :]    image_ids = [image_ids[x] for x in sorted_ind]    # go down dets and mark TPs and FPs    nd = len(image_ids)    tp = np.zeros(nd)    fp = np.zeros(nd)    for d in range(nd):        R = class_recs[image_ids[d]]        bb = BB[d, :].astype(float)        ovmax = -np.inf        BBGT = R['bbox'].astype(float)        if BBGT.size > 0:            # compute overlaps            # intersection            ixmin = np.maximum(BBGT[:, 0], bb[0])            iymin = np.maximum(BBGT[:, 1], bb[1])            ixmax = np.minimum(BBGT[:, 2], bb[2])            iymax = np.minimum(BBGT[:, 3], bb[3])            iw = np.maximum(ixmax - ixmin + 1., 0.)            ih = np.maximum(iymax - iymin + 1., 0.)            inters = iw * ih            # union            uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +                   (BBGT[:, 2] - BBGT[:, 0] + 1.) *                   (BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)            overlaps = inters / uni            ovmax = np.max(overlaps)            jmax = np.argmax(overlaps)        if ovmax > ovthresh:            if not R['difficult'][jmax]:                if not R['det'][jmax]:                    tp[d] = 1.                    R['det'][jmax] = 1                else:                    fp[d] = 1.        else:            fp[d] = 1.    # compute precision recall    fp = np.cumsum(fp)    tp = np.cumsum(tp)    rec = tp / float(npos)    # avoid divide by zero in case the first detection matches a difficult    # ground truth    prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)    ap = voc_ap(rec, prec, use_07_metric)    return rec, prec, ap