示例#1
0
    def assign(self, bboxes, gt_bboxes, gt_bboxes_ignore=None, gt_labels=None):
        """Assign gt to bboxes.

        This method assign a gt bbox to every bbox (proposal/anchor), each bbox
        will be assigned with -2, -1, or a positive number. -2 means don't care,
        -1 means negative sample, positive number is the index of
        assigned gt.
        The assignment is done in following steps, the order matters.

        1. assign every bbox to -2
        2. assign proposals whose iou with all gts < neg_iou_thr to -1
        3. for each bbox, if the iou with its nearest gt >= pos_iou_thr,
           assign it to that bbox
        4. for each gt bbox, assign its nearest proposals (may be more than
           one) to itself

        Args:
            bboxes (Tensor): Bounding boxes to be assigned, shape(n, 4).
            gt_bboxes (Tensor): Groundtruth boxes, shape (k, 4).
            gt_bboxes_ignore (Tensor, optional): Ground truth bboxes that are
                labelled as `ignored`, e.g., crowd boxes in COCO.
            gt_labels (Tensor, optional): Label of gt_bboxes, shape (k, ).

        Returns:
            :obj:`AssignResult`: The assign result.
        """
        if bboxes.shape[0] == 0 or gt_bboxes.shape[0] == 0:
            raise ValueError('No gt or bboxes')
        bboxes = bboxes[:, :4]
        overlaps = boxlist_iou(gt_bboxes, bboxes)

        if (self.ignore_iof_thr > 0) and (gt_bboxes_ignore is not None) and (
                gt_bboxes_ignore.numel() > 0):
            if self.ignore_wrt_candidates:
                ignore_overlaps = boxlist_iou(bboxes,
                                              gt_bboxes_ignore,
                                              mode='iof')
                ignore_max_overlaps, _ = ignore_overlaps.max(dim=1)
            else:
                ignore_overlaps = boxlist_iou(gt_bboxes_ignore,
                                              bboxes,
                                              mode='iof')
                ignore_max_overlaps, _ = ignore_overlaps.max(dim=0)
            overlaps[:, ignore_max_overlaps > self.ignore_iof_thr] = -1

        assign_result = self.assign_wrt_overlaps(overlaps, gt_labels)
        return assign_result
示例#2
0
 def match_targets_to_proposals(self, proposal, target):
     match_quality_matrix = boxlist_iou(target, proposal)
     matched_idxs = self.proposal_matcher(match_quality_matrix)
     # Keypoint RCNN needs "labels" and "keypoints "fields for creating the targets
     target = target.copy_with_fields(["labels", "keypoints"])
     # get the targets corresponding GT for each proposal
     # NB: need to clamp the indices because we can have a single
     # GT in the image, and matched_idxs can be -2, which goes
     # out of bounds
     matched_targets = target[matched_idxs.clamp(min=0)]
     matched_targets.add_field("matched_idxs", matched_idxs)
     return matched_targets
示例#3
0
    def match_targets_to_anchors(self, anchor, target, copied_fields=[]):
        match_quality_matrix = boxlist_iou(target, anchor)
        matched_idxs = self.proposal_matcher(match_quality_matrix)
        # RPN doesn't need any fields from target for creating the labels, so clear them all
        target = target.copy_with_fields(copied_fields)
        # get the targets corresponding GT for each anchor
        # NB: need to clamp the indices because we can have a single GT in the image,
        # and matched_idxs can be -2, which goes out of bounds

        # matched_targets = target[matched_idxs.clamp(min=0)]

        if self.use_negative_samples and len(target) == 0:
            matched_targets = target
        else:
            matched_targets = target[matched_idxs.clamp(min=0)]

        matched_targets.add_field("matched_idxs", matched_idxs)
        return matched_targets
示例#4
0
    def match_targets_to_proposals(self, proposal, target):
        match_quality_matrix = boxlist_iou(target, proposal)
        matched_idxs = self.proposal_matcher(match_quality_matrix)

        # target = target.copy_with_fields("labels")
        # matched_targets = target[matched_idxs.clamp(min=0)]

        if self.use_negative_samples and len(target) == 0:
            matched_targets = target
            matched_targets.add_field("labels", matched_idxs.clamp(min=1,
                                                                   max=1))
        else:
            # Fast RCNN only need "labels" field for selecting the targets
            target = target.copy_with_fields("labels")
            # get the targets corresponding GT for each proposal
            # NB: need to clamp the indices because we can have a single GT in the image,
            # and matched_idxs can be -2, which goes out of bounds
            matched_targets = target[matched_idxs.clamp(min=0)]

        matched_targets.add_field("matched_idxs", matched_idxs)
        return matched_targets
示例#5
0
def evaluate_box_proposals(
    predictions, dataset, thresholds=None, area="all", limit=None
):
    """Evaluate detection proposal recall metrics. This function is a much
    faster alternative to the official COCO API recall evaluation code. However,
    it produces slightly different results.
    """
    # Record max overlap value for each gt box
    # Return vector of overlap values
    areas = {
        "all": 0,
        "small": 1,
        "medium": 2,
        "large": 3,
        "96-128": 4,
        "128-256": 5,
        "256-512": 6,
        "512-inf": 7,
    }
    area_ranges = [
        [0 ** 2, 1e5 ** 2],  # all
        [0 ** 2, 32 ** 2],  # small
        [32 ** 2, 96 ** 2],  # medium
        [96 ** 2, 1e5 ** 2],  # large
        [96 ** 2, 128 ** 2],  # 96-128
        [128 ** 2, 256 ** 2],  # 128-256
        [256 ** 2, 512 ** 2],  # 256-512
        [512 ** 2, 1e5 ** 2],
    ]  # 512-inf
    assert area in areas, "Unknown area range: {}".format(area)
    area_range = area_ranges[areas[area]]
    gt_overlaps = []
    num_pos = 0

    for image_id, prediction in enumerate(predictions):
        original_id = dataset.id_to_img_map[image_id]

        # TODO replace with get_img_info?
        img_info = dataset.get_img_info(image_id)
        image_width = img_info["width"]
        image_height = img_info["height"]
        prediction = prediction.resize((image_width, image_height))

        # sort predictions in descending order
        # TODO maybe remove this and make it explicit in the documentation
        inds = prediction.get_field("scores").sort(descending=True)[1]
        prediction = prediction[inds]

        ann_ids = dataset.coco.getAnnIds(imgIds=original_id)
        anno = dataset.coco.loadAnns(ann_ids)
        gt_boxes = [obj["bbox"] for obj in anno if obj["iscrowd"] == 0]
        gt_boxes = torch.as_tensor(gt_boxes).reshape(-1, 4)  # guard against no boxes
        gt_boxes = BoxList(gt_boxes, (image_width, image_height), mode="xywh").convert(
            "xyxy"
        )
        gt_areas = torch.as_tensor([obj["area"] for obj in anno if obj["iscrowd"] == 0])

        if len(gt_boxes) == 0:
            continue

        valid_gt_inds = (gt_areas >= area_range[0]) & (gt_areas <= area_range[1])
        gt_boxes = gt_boxes[valid_gt_inds]

        num_pos += len(gt_boxes)

        if len(gt_boxes) == 0:
            continue

        if len(prediction) == 0:
            continue

        if limit is not None and len(prediction) > limit:
            prediction = prediction[:limit]

        overlaps = boxlist_iou(prediction, gt_boxes)

        _gt_overlaps = torch.zeros(len(gt_boxes))
        for j in range(min(len(prediction), len(gt_boxes))):
            # find which proposal box maximally covers each gt box
            # and get the iou amount of coverage for each gt box
            max_overlaps, argmax_overlaps = overlaps.max(dim=0)

            # find which gt box is 'best' covered (i.e. 'best' = most iou)
            gt_ovr, gt_ind = max_overlaps.max(dim=0)
            assert gt_ovr >= 0
            # find the proposal box that covers the best covered gt box
            box_ind = argmax_overlaps[gt_ind]
            # record the iou coverage of this gt box
            _gt_overlaps[j] = overlaps[box_ind, gt_ind]
            assert _gt_overlaps[j] == gt_ovr
            # mark the proposal box and the gt box as used
            overlaps[box_ind, :] = -1
            overlaps[:, gt_ind] = -1

        # append recorded iou coverage level
        gt_overlaps.append(_gt_overlaps)
    gt_overlaps = torch.cat(gt_overlaps, dim=0)
    gt_overlaps, _ = torch.sort(gt_overlaps)

    if thresholds is None:
        step = 0.05
        thresholds = torch.arange(0.5, 0.95 + 1e-5, step, dtype=torch.float32)
    recalls = torch.zeros_like(thresholds)
    # compute recall for each iou threshold
    for i, t in enumerate(thresholds):
        recalls[i] = (gt_overlaps >= t).float().sum() / float(num_pos)
    # ar = 2 * np.trapz(recalls, thresholds)
    ar = recalls.mean()
    return {
        "ar": ar,
        "recalls": recalls,
        "thresholds": thresholds,
        "gt_overlaps": gt_overlaps,
        "num_pos": num_pos,
    }
示例#6
0
def calc_detection_voc_prec_rec(gt_boxlists, pred_boxlists, iou_thresh=0.5):
    """Calculate precision and recall based on evaluation code of PASCAL VOC.
    This function calculates precision and recall of
    predicted bounding boxes obtained from a dataset which has :math:`N`
    images.
    The code is based on the evaluation code used in PASCAL VOC Challenge.
   """
    n_pos = defaultdict(int)
    score = defaultdict(list)
    match = defaultdict(list)
    for gt_boxlist, pred_boxlist in zip(gt_boxlists, pred_boxlists):
        pred_bbox = pred_boxlist.bbox.numpy()
        pred_label = pred_boxlist.get_field("labels").numpy()
        pred_score = pred_boxlist.get_field("scores").numpy()
        gt_bbox = gt_boxlist.bbox.numpy()
        gt_label = gt_boxlist.get_field("labels").numpy()
        gt_difficult = gt_boxlist.get_field("difficult").numpy()

        for l in np.unique(np.concatenate((pred_label, gt_label)).astype(int)):
            pred_mask_l = pred_label == l
            pred_bbox_l = pred_bbox[pred_mask_l]
            pred_score_l = pred_score[pred_mask_l]
            # sort by score
            order = pred_score_l.argsort()[::-1]
            pred_bbox_l = pred_bbox_l[order]
            pred_score_l = pred_score_l[order]

            gt_mask_l = gt_label == l
            gt_bbox_l = gt_bbox[gt_mask_l]
            gt_difficult_l = gt_difficult[gt_mask_l]

            n_pos[l] += np.logical_not(gt_difficult_l).sum()
            score[l].extend(pred_score_l)

            if len(pred_bbox_l) == 0:
                continue
            if len(gt_bbox_l) == 0:
                match[l].extend((0,) * pred_bbox_l.shape[0])
                continue

            # VOC evaluation follows integer typed bounding boxes.
            pred_bbox_l = pred_bbox_l.copy()
            pred_bbox_l[:, 2:] += 1
            gt_bbox_l = gt_bbox_l.copy()
            gt_bbox_l[:, 2:] += 1
            iou = boxlist_iou(
                BoxList(pred_bbox_l, gt_boxlist.size),
                BoxList(gt_bbox_l, gt_boxlist.size),
            ).numpy()
            gt_index = iou.argmax(axis=1)
            # set -1 if there is no matching ground truth
            gt_index[iou.max(axis=1) < iou_thresh] = -1
            del iou

            selec = np.zeros(gt_bbox_l.shape[0], dtype=bool)
            for gt_idx in gt_index:
                if gt_idx >= 0:
                    if gt_difficult_l[gt_idx]:
                        match[l].append(-1)
                    else:
                        if not selec[gt_idx]:
                            match[l].append(1)
                        else:
                            match[l].append(0)
                    selec[gt_idx] = True
                else:
                    match[l].append(0)

    n_fg_class = max(n_pos.keys()) + 1
    prec = [None] * n_fg_class
    rec = [None] * n_fg_class

    for l in n_pos.keys():
        score_l = np.array(score[l])
        match_l = np.array(match[l], dtype=np.int8)

        order = score_l.argsort()[::-1]
        match_l = match_l[order]

        tp = np.cumsum(match_l == 1)
        fp = np.cumsum(match_l == 0)

        # If an element of fp + tp is 0,
        # the corresponding element of prec[l] is nan.
        prec[l] = tp / (fp + tp)
        # If n_pos[l] is 0, rec[l] is None.
        if n_pos[l] > 0:
            rec[l] = tp / n_pos[l]

    return prec, rec
    def assign(self,
               approxs,
               squares,
               approxs_per_octave,
               gt_bboxes,
               gt_bboxes_ignore=None,
               gt_labels=None):
        """Assign gt to approxs.

        This method assign a gt bbox to each group of approxs (bboxes),
        each group of approxs is represent by a base approx (bbox) and
        will be assigned with -2, -1, or a positive number.
        -2 means don't care, -1 means negative sample,
        positive number is the index of assigned gt.
        The assignment is done in following steps, the order matters.

        1. assign every bbox to -2
        2. use the max IoU of each group of approxs to assign
        2. assign proposals whose iou with all gts < neg_iou_thr to -1
        3. for each bbox, if the iou with its nearest gt >= pos_iou_thr,
           assign it to that bbox
        4. for each gt bbox, assign its nearest proposals (may be more than
           one) to itself

        Args:
            approxs (Tensor): Bounding boxes to be assigned,
        shape(approxs_per_octave*n, 4).
            squares (Tensor): Base Bounding boxes to be assigned,
        shape(n, 4).
            approxs_per_octave (int): number of approxs per octave
            gt_bboxes (Tensor): Groundtruth boxes, shape (k, 4).
            gt_bboxes_ignore (Tensor, optional): Ground truth bboxes that are
                labelled as `ignored`, e.g., crowd boxes in COCO.
            gt_labels (Tensor, optional): Label of gt_bboxes, shape (k, ).

        Returns:
            :obj:`AssignResult`: The assign result.
        """

        if squares.shape[0] == 0 or gt_bboxes.shape[0] == 0:
            raise ValueError('No gt or approxs')
        num_squares = squares.size(0)
        num_gts = gt_bboxes.size(0)
        # re-organize anchors by approxs_per_octave x num_squares
        approxs = torch.transpose(
            approxs.view(num_squares, approxs_per_octave, 4), 0,
            1).contiguous().view(-1, 4)
        all_overlaps = boxlist_iou(approxs, gt_bboxes)

        overlaps, _ = all_overlaps.view(approxs_per_octave, num_squares,
                                        num_gts).max(dim=0)
        overlaps = torch.transpose(overlaps, 0, 1)

        bboxes = squares[:, :4]

        if (self.ignore_iof_thr > 0) and (gt_bboxes_ignore is not None) and (
                gt_bboxes_ignore.numel() > 0):
            if self.ignore_wrt_candidates:
                ignore_overlaps = boxlist_iou(bboxes,
                                              gt_bboxes_ignore,
                                              mode='iof')
                ignore_max_overlaps, _ = ignore_overlaps.max(dim=1)
            else:
                ignore_overlaps = bbox_overlaps(gt_bboxes_ignore,
                                                bboxes,
                                                mode='iof')
                ignore_max_overlaps, _ = ignore_overlaps.max(dim=0)
            overlaps[:, ignore_max_overlaps > self.ignore_iof_thr] = -1

        assign_result = self.assign_wrt_overlaps(overlaps, gt_labels)
        return assign_result