目标检测任务中mAP的计算

def voc_eval(detpath,
             annopath,
             imagesetfile,
             classname,
             cachedir,
             ovthresh=0.5,
             use_07_metric=False):

  # 首先获取GT路径
  if not os.path.isdir(cachedir):
    os.mkdir(cachedir)
  cachefile = os.path.join(cachedir, '%s_annots.pkl' % imagesetfile)
  # 读取图片的ID
  with open(imagesetfile, 'r') as f:
    lines = f.readlines()
  imagenames = [x.strip() for x in lines]

  # 载入GT的标注，如果cache已经存在，直接读取，否则读文件，写cache
  if not os.path.isfile(cachefile):
    # load annotations
    recs = {}
    for i, imagename in enumerate(imagenames):
      recs[imagename] = parse_rec(annopath.format(imagename))
      if i % 100 == 0:
        print('Reading annotation for {:d}/{:d}'.format(
          i + 1, len(imagenames)))
    # save
    print('Saving cached annotations to {:s}'.format(cachefile))
    with open(cachefile, 'wb') as f:
      pickle.dump(recs, f)
  else:
    # load
    with open(cachefile, 'rb') as f:
      try:
        recs = pickle.load(f)
      except:
        recs = pickle.load(f, encoding='bytes')

  # 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}

  # 加载模型预测框
  # 格式[img_id, x1, y1, x2, y2]共5维
  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])

  nd = len(image_ids) # 注意这里是预测框的总数量，而不是图片的数量
  tp = np.zeros(nd) # 初始化每个框的TP标志
  fp = np.zeros(nd) # 初始化每个框的FP标志

  if BB.shape[0] > 0:
    # sort by confidence
    sorted_ind = np.argsort(-confidence)
    sorted_scores = np.sort(-confidence)
    BB = BB[sorted_ind, :]
    image_ids = [image_ids[x] for x in sorted_ind]

    # go down dets and mark TPs and FPs
    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)  # 对FP和TP求cumsum
  tp = np.cumsum(tp)  # TP_cumsum + FP_cumsum其实就等于当前预测框的综述，也就是P
  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

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: # VOC07采用11点采样的方法计算线下面积
    # 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])  #估算当前recall的precision使用recall大于当前recall的precision最大值
      ap = ap + p / 11.
  else:  # VOC2012使用相邻两个recall点求矩形面积的方法求线下面积
    # 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