Merge branch 'hepj_work' into 'main'

增加conformer代码

See merge request dcutoolkit/deeplearing/dlexamples_new!7

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/assigners/hungarian_assigner.py

+import torch
+
+from ..builder import BBOX_ASSIGNERS
+from ..match_costs import build_match_cost
+from ..transforms import bbox_cxcywh_to_xyxy
+from .assign_result import AssignResult
+from .base_assigner import BaseAssigner
+
+try:
+    from scipy.optimize import linear_sum_assignment
+except ImportError:
+    linear_sum_assignment = None
+
+
+@BBOX_ASSIGNERS.register_module()
+class HungarianAssigner(BaseAssigner):
+    """Computes one-to-one matching between predictions and ground truth.
+
+    This class computes an assignment between the targets and the predictions
+    based on the costs. The costs are weighted sum of three components:
+    classfication cost, regression L1 cost and regression iou cost. The
+    targets don't include the no_object, so generally there are more
+    predictions than targets. After the one-to-one matching, the un-matched
+    are treated as backgrounds. Thus each query prediction will be assigned
+    with `0` or a positive integer indicating the ground truth index:
+
+    - 0: negative sample, no assigned gt
+    - positive integer: positive sample, index (1-based) of assigned gt
+
+    Args:
+        cls_weight (int | float, optional): The scale factor for classification
+            cost. Default 1.0.
+        bbox_weight (int | float, optional): The scale factor for regression
+            L1 cost. Default 1.0.
+        iou_weight (int | float, optional): The scale factor for regression
+            iou cost. Default 1.0.
+        iou_calculator (dict | optional): The config for the iou calculation.
+            Default type `BboxOverlaps2D`.
+        iou_mode (str | optional): "iou" (intersection over union), "iof"
+                (intersection over foreground), or "giou" (generalized
+                intersection over union). Default "giou".
+    """
+
+    def __init__(self,
+                 cls_cost=dict(type='ClassificationCost', weight=1.),
+                 reg_cost=dict(type='BBoxL1Cost', weight=1.0),
+                 iou_cost=dict(type='IoUCost', iou_mode='giou', weight=1.0)):
+        self.cls_cost = build_match_cost(cls_cost)
+        self.reg_cost = build_match_cost(reg_cost)
+        self.iou_cost = build_match_cost(iou_cost)
+
+    def assign(self,
+               bbox_pred,
+               cls_pred,
+               gt_bboxes,
+               gt_labels,
+               img_meta,
+               gt_bboxes_ignore=None,
+               eps=1e-7):
+        """Computes one-to-one matching based on the weighted costs.
+
+        This method assign each query prediction to a ground truth or
+        background. The `assigned_gt_inds` with -1 means don't care,
+        0 means negative sample, and positive number is the index (1-based)
+        of assigned gt.
+        The assignment is done in the following steps, the order matters.
+
+        1. assign every prediction to -1
+        2. compute the weighted costs
+        3. do Hungarian matching on CPU based on the costs
+        4. assign all to 0 (background) first, then for each matched pair
+           between predictions and gts, treat this prediction as foreground
+           and assign the corresponding gt index (plus 1) to it.
+
+        Args:
+            bbox_pred (Tensor): Predicted boxes with normalized coordinates
+                (cx, cy, w, h), which are all in range [0, 1]. Shape
+                [num_query, 4].
+            cls_pred (Tensor): Predicted classification logits, shape
+                [num_query, num_class].
+            gt_bboxes (Tensor): Ground truth boxes with unnormalized
+                coordinates (x1, y1, x2, y2). Shape [num_gt, 4].
+            gt_labels (Tensor): Label of `gt_bboxes`, shape (num_gt,).
+            img_meta (dict): Meta information for current image.
+            gt_bboxes_ignore (Tensor, optional): Ground truth bboxes that are
+                labelled as `ignored`. Default None.
+            eps (int | float, optional): A value added to the denominator for
+                numerical stability. Default 1e-7.
+
+        Returns:
+            :obj:`AssignResult`: The assigned result.
+        """
+        assert gt_bboxes_ignore is None, \
+            'Only case when gt_bboxes_ignore is None is supported.'
+        num_gts, num_bboxes = gt_bboxes.size(0), bbox_pred.size(0)
+
+        # 1. assign -1 by default
+        assigned_gt_inds = bbox_pred.new_full((num_bboxes, ),
+                                              -1,
+                                              dtype=torch.long)
+        assigned_labels = bbox_pred.new_full((num_bboxes, ),
+                                             -1,
+                                             dtype=torch.long)
+        if num_gts == 0 or num_bboxes == 0:
+            # No ground truth or boxes, return empty assignment
+            if num_gts == 0:
+                # No ground truth, assign all to background
+                assigned_gt_inds[:] = 0
+            return AssignResult(
+                num_gts, assigned_gt_inds, None, labels=assigned_labels)
+        img_h, img_w, _ = img_meta['img_shape']
+        factor = gt_bboxes.new_tensor([img_w, img_h, img_w,
+                                       img_h]).unsqueeze(0)
+
+        # 2. compute the weighted costs
+        # classification and bboxcost.
+        cls_cost = self.cls_cost(cls_pred, gt_labels)
+        # regression L1 cost
+        normalize_gt_bboxes = gt_bboxes / factor
+        reg_cost = self.reg_cost(bbox_pred, normalize_gt_bboxes)
+        # regression iou cost, defaultly giou is used in official DETR.
+        bboxes = bbox_cxcywh_to_xyxy(bbox_pred) * factor
+        iou_cost = self.iou_cost(bboxes, gt_bboxes)
+        # weighted sum of above three costs
+        cost = cls_cost + reg_cost + iou_cost
+
+        # 3. do Hungarian matching on CPU using linear_sum_assignment
+        cost = cost.detach().cpu()
+        if linear_sum_assignment is None:
+            raise ImportError('Please run "pip install scipy" '
+                              'to install scipy first.')
+        matched_row_inds, matched_col_inds = linear_sum_assignment(cost)
+        matched_row_inds = torch.from_numpy(matched_row_inds).to(
+            bbox_pred.device)
+        matched_col_inds = torch.from_numpy(matched_col_inds).to(
+            bbox_pred.device)
+
+        # 4. assign backgrounds and foregrounds
+        # assign all indices to backgrounds first
+        assigned_gt_inds[:] = 0
+        # assign foregrounds based on matching results
+        assigned_gt_inds[matched_row_inds] = matched_col_inds + 1
+        assigned_labels[matched_row_inds] = gt_labels[matched_col_inds]
+        return AssignResult(
+            num_gts, assigned_gt_inds, None, labels=assigned_labels)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/assigners/max_iou_assigner.py

+import torch
+
+from ..builder import BBOX_ASSIGNERS
+from ..iou_calculators import build_iou_calculator
+from .assign_result import AssignResult
+from .base_assigner import BaseAssigner
+
+
+@BBOX_ASSIGNERS.register_module()
+class MaxIoUAssigner(BaseAssigner):
+    """Assign a corresponding gt bbox or background to each bbox.
+
+    Each proposals will be assigned with `-1`, or a semi-positive integer
+    indicating the ground truth index.
+
+    - -1: negative sample, no assigned gt
+    - semi-positive integer: positive sample, index (0-based) of assigned gt
+
+    Args:
+        pos_iou_thr (float): IoU threshold for positive bboxes.
+        neg_iou_thr (float or tuple): IoU threshold for negative bboxes.
+        min_pos_iou (float): Minimum iou for a bbox to be considered as a
+            positive bbox. Positive samples can have smaller IoU than
+            pos_iou_thr due to the 4th step (assign max IoU sample to each gt).
+        gt_max_assign_all (bool): Whether to assign all bboxes with the same
+            highest overlap with some gt to that gt.
+        ignore_iof_thr (float): IoF threshold for ignoring bboxes (if
+            `gt_bboxes_ignore` is specified). Negative values mean not
+            ignoring any bboxes.
+        ignore_wrt_candidates (bool): Whether to compute the iof between
+            `bboxes` and `gt_bboxes_ignore`, or the contrary.
+        match_low_quality (bool): Whether to allow low quality matches. This is
+            usually allowed for RPN and single stage detectors, but not allowed
+            in the second stage. Details are demonstrated in Step 4.
+        gpu_assign_thr (int): The upper bound of the number of GT for GPU
+            assign. When the number of gt is above this threshold, will assign
+            on CPU device. Negative values mean not assign on CPU.
+    """
+
+    def __init__(self,
+                 pos_iou_thr,
+                 neg_iou_thr,
+                 min_pos_iou=.0,
+                 gt_max_assign_all=True,
+                 ignore_iof_thr=-1,
+                 ignore_wrt_candidates=True,
+                 match_low_quality=True,
+                 gpu_assign_thr=-1,
+                 iou_calculator=dict(type='BboxOverlaps2D')):
+        self.pos_iou_thr = pos_iou_thr
+        self.neg_iou_thr = neg_iou_thr
+        self.min_pos_iou = min_pos_iou
+        self.gt_max_assign_all = gt_max_assign_all
+        self.ignore_iof_thr = ignore_iof_thr
+        self.ignore_wrt_candidates = ignore_wrt_candidates
+        self.gpu_assign_thr = gpu_assign_thr
+        self.match_low_quality = match_low_quality
+        self.iou_calculator = build_iou_calculator(iou_calculator)
+
+    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 -1, or a semi-positive number. -1 means negative
+        sample, semi-positive number is the index (0-based) of assigned gt.
+        The assignment is done in following steps, the order matters.
+
+        1. assign every bbox to the background
+        2. assign proposals whose iou with all gts < neg_iou_thr to 0
+        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.
+
+        Example:
+            >>> self = MaxIoUAssigner(0.5, 0.5)
+            >>> bboxes = torch.Tensor([[0, 0, 10, 10], [10, 10, 20, 20]])
+            >>> gt_bboxes = torch.Tensor([[0, 0, 10, 9]])
+            >>> assign_result = self.assign(bboxes, gt_bboxes)
+            >>> expected_gt_inds = torch.LongTensor([1, 0])
+            >>> assert torch.all(assign_result.gt_inds == expected_gt_inds)
+        """
+        assign_on_cpu = True if (self.gpu_assign_thr > 0) and (
+            gt_bboxes.shape[0] > self.gpu_assign_thr) else False
+        # compute overlap and assign gt on CPU when number of GT is large
+        if assign_on_cpu:
+            device = bboxes.device
+            bboxes = bboxes.cpu()
+            gt_bboxes = gt_bboxes.cpu()
+            if gt_bboxes_ignore is not None:
+                gt_bboxes_ignore = gt_bboxes_ignore.cpu()
+            if gt_labels is not None:
+                gt_labels = gt_labels.cpu()
+
+        overlaps = self.iou_calculator(gt_bboxes, bboxes)
+
+        if (self.ignore_iof_thr > 0 and gt_bboxes_ignore is not None
+                and gt_bboxes_ignore.numel() > 0 and bboxes.numel() > 0):
+            if self.ignore_wrt_candidates:
+                ignore_overlaps = self.iou_calculator(
+                    bboxes, gt_bboxes_ignore, mode='iof')
+                ignore_max_overlaps, _ = ignore_overlaps.max(dim=1)
+            else:
+                ignore_overlaps = self.iou_calculator(
+                    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)
+        if assign_on_cpu:
+            assign_result.gt_inds = assign_result.gt_inds.to(device)
+            assign_result.max_overlaps = assign_result.max_overlaps.to(device)
+            if assign_result.labels is not None:
+                assign_result.labels = assign_result.labels.to(device)
+        return assign_result
+
+    def assign_wrt_overlaps(self, overlaps, gt_labels=None):
+        """Assign w.r.t. the overlaps of bboxes with gts.
+
+        Args:
+            overlaps (Tensor): Overlaps between k gt_bboxes and n bboxes,
+                shape(k, n).
+            gt_labels (Tensor, optional): Labels of k gt_bboxes, shape (k, ).
+
+        Returns:
+            :obj:`AssignResult`: The assign result.
+        """
+        num_gts, num_bboxes = overlaps.size(0), overlaps.size(1)
+
+        # 1. assign -1 by default
+        assigned_gt_inds = overlaps.new_full((num_bboxes, ),
+                                             -1,
+                                             dtype=torch.long)
+
+        if num_gts == 0 or num_bboxes == 0:
+            # No ground truth or boxes, return empty assignment
+            max_overlaps = overlaps.new_zeros((num_bboxes, ))
+            if num_gts == 0:
+                # No truth, assign everything to background
+                assigned_gt_inds[:] = 0
+            if gt_labels is None:
+                assigned_labels = None
+            else:
+                assigned_labels = overlaps.new_full((num_bboxes, ),
+                                                    -1,
+                                                    dtype=torch.long)
+            return AssignResult(
+                num_gts,
+                assigned_gt_inds,
+                max_overlaps,
+                labels=assigned_labels)
+
+        # for each anchor, which gt best overlaps with it
+        # for each anchor, the max iou of all gts
+        max_overlaps, argmax_overlaps = overlaps.max(dim=0)
+        # for each gt, which anchor best overlaps with it
+        # for each gt, the max iou of all proposals
+        gt_max_overlaps, gt_argmax_overlaps = overlaps.max(dim=1)
+
+        # 2. assign negative: below
+        # the negative inds are set to be 0
+        if isinstance(self.neg_iou_thr, float):
+            assigned_gt_inds[(max_overlaps >= 0)
+                             & (max_overlaps < self.neg_iou_thr)] = 0
+        elif isinstance(self.neg_iou_thr, tuple):
+            assert len(self.neg_iou_thr) == 2
+            assigned_gt_inds[(max_overlaps >= self.neg_iou_thr[0])
+                             & (max_overlaps < self.neg_iou_thr[1])] = 0
+
+        # 3. assign positive: above positive IoU threshold
+        pos_inds = max_overlaps >= self.pos_iou_thr
+        assigned_gt_inds[pos_inds] = argmax_overlaps[pos_inds] + 1
+
+        if self.match_low_quality:
+            # Low-quality matching will overwirte the assigned_gt_inds assigned
+            # in Step 3. Thus, the assigned gt might not be the best one for
+            # prediction.
+            # For example, if bbox A has 0.9 and 0.8 iou with GT bbox 1 & 2,
+            # bbox 1 will be assigned as the best target for bbox A in step 3.
+            # However, if GT bbox 2's gt_argmax_overlaps = A, bbox A's
+            # assigned_gt_inds will be overwritten to be bbox B.
+            # This might be the reason that it is not used in ROI Heads.
+            for i in range(num_gts):
+                if gt_max_overlaps[i] >= self.min_pos_iou:
+                    if self.gt_max_assign_all:
+                        max_iou_inds = overlaps[i, :] == gt_max_overlaps[i]
+                        assigned_gt_inds[max_iou_inds] = i + 1
+                    else:
+                        assigned_gt_inds[gt_argmax_overlaps[i]] = i + 1
+
+        if gt_labels is not None:
+            assigned_labels = assigned_gt_inds.new_full((num_bboxes, ), -1)
+            pos_inds = torch.nonzero(
+                assigned_gt_inds > 0, as_tuple=False).squeeze()
+            if pos_inds.numel() > 0:
+                assigned_labels[pos_inds] = gt_labels[
+                    assigned_gt_inds[pos_inds] - 1]
+        else:
+            assigned_labels = None
+
+        return AssignResult(
+            num_gts, assigned_gt_inds, max_overlaps, labels=assigned_labels)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/assigners/point_assigner.py

+import torch
+
+from ..builder import BBOX_ASSIGNERS
+from .assign_result import AssignResult
+from .base_assigner import BaseAssigner
+
+
+@BBOX_ASSIGNERS.register_module()
+class PointAssigner(BaseAssigner):
+    """Assign a corresponding gt bbox or background to each point.
+
+    Each proposals will be assigned with `0`, or a positive integer
+    indicating the ground truth index.
+
+    - 0: negative sample, no assigned gt
+    - positive integer: positive sample, index (1-based) of assigned gt
+    """
+
+    def __init__(self, scale=4, pos_num=3):
+        self.scale = scale
+        self.pos_num = pos_num
+
+    def assign(self, points, gt_bboxes, gt_bboxes_ignore=None, gt_labels=None):
+        """Assign gt to points.
+
+        This method assign a gt bbox to every points set, each points set
+        will be assigned with  the background_label (-1), or a label number.
+        -1 is background, and semi-positive number is the index (0-based) of
+        assigned gt.
+        The assignment is done in following steps, the order matters.
+
+        1. assign every points to the background_label (-1)
+        2. A point is assigned to some gt bbox if
+            (i) the point is within the k closest points to the gt bbox
+            (ii) the distance between this point and the gt is smaller than
+                other gt bboxes
+
+        Args:
+            points (Tensor): points to be assigned, shape(n, 3) while last
+                dimension stands for (x, y, stride).
+            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.
+                NOTE: currently unused.
+            gt_labels (Tensor, optional): Label of gt_bboxes, shape (k, ).
+
+        Returns:
+            :obj:`AssignResult`: The assign result.
+        """
+        num_points = points.shape[0]
+        num_gts = gt_bboxes.shape[0]
+
+        if num_gts == 0 or num_points == 0:
+            # If no truth assign everything to the background
+            assigned_gt_inds = points.new_full((num_points, ),
+                                               0,
+                                               dtype=torch.long)
+            if gt_labels is None:
+                assigned_labels = None
+            else:
+                assigned_labels = points.new_full((num_points, ),
+                                                  -1,
+                                                  dtype=torch.long)
+            return AssignResult(
+                num_gts, assigned_gt_inds, None, labels=assigned_labels)
+
+        points_xy = points[:, :2]
+        points_stride = points[:, 2]
+        points_lvl = torch.log2(
+            points_stride).int()  # [3...,4...,5...,6...,7...]
+        lvl_min, lvl_max = points_lvl.min(), points_lvl.max()
+
+        # assign gt box
+        gt_bboxes_xy = (gt_bboxes[:, :2] + gt_bboxes[:, 2:]) / 2
+        gt_bboxes_wh = (gt_bboxes[:, 2:] - gt_bboxes[:, :2]).clamp(min=1e-6)
+        scale = self.scale
+        gt_bboxes_lvl = ((torch.log2(gt_bboxes_wh[:, 0] / scale) +
+                          torch.log2(gt_bboxes_wh[:, 1] / scale)) / 2).int()
+        gt_bboxes_lvl = torch.clamp(gt_bboxes_lvl, min=lvl_min, max=lvl_max)
+
+        # stores the assigned gt index of each point
+        assigned_gt_inds = points.new_zeros((num_points, ), dtype=torch.long)
+        # stores the assigned gt dist (to this point) of each point
+        assigned_gt_dist = points.new_full((num_points, ), float('inf'))
+        points_range = torch.arange(points.shape[0])
+
+        for idx in range(num_gts):
+            gt_lvl = gt_bboxes_lvl[idx]
+            # get the index of points in this level
+            lvl_idx = gt_lvl == points_lvl
+            points_index = points_range[lvl_idx]
+            # get the points in this level
+            lvl_points = points_xy[lvl_idx, :]
+            # get the center point of gt
+            gt_point = gt_bboxes_xy[[idx], :]
+            # get width and height of gt
+            gt_wh = gt_bboxes_wh[[idx], :]
+            # compute the distance between gt center and
+            #   all points in this level
+            points_gt_dist = ((lvl_points - gt_point) / gt_wh).norm(dim=1)
+            # find the nearest k points to gt center in this level
+            min_dist, min_dist_index = torch.topk(
+                points_gt_dist, self.pos_num, largest=False)
+            # the index of nearest k points to gt center in this level
+            min_dist_points_index = points_index[min_dist_index]
+            # The less_than_recorded_index stores the index
+            #   of min_dist that is less then the assigned_gt_dist. Where
+            #   assigned_gt_dist stores the dist from previous assigned gt
+            #   (if exist) to each point.
+            less_than_recorded_index = min_dist < assigned_gt_dist[
+                min_dist_points_index]
+            # The min_dist_points_index stores the index of points satisfy:
+            #   (1) it is k nearest to current gt center in this level.
+            #   (2) it is closer to current gt center than other gt center.
+            min_dist_points_index = min_dist_points_index[
+                less_than_recorded_index]
+            # assign the result
+            assigned_gt_inds[min_dist_points_index] = idx + 1
+            assigned_gt_dist[min_dist_points_index] = min_dist[
+                less_than_recorded_index]
+
+        if gt_labels is not None:
+            assigned_labels = assigned_gt_inds.new_full((num_points, ), -1)
+            pos_inds = torch.nonzero(
+                assigned_gt_inds > 0, as_tuple=False).squeeze()
+            if pos_inds.numel() > 0:
+                assigned_labels[pos_inds] = gt_labels[
+                    assigned_gt_inds[pos_inds] - 1]
+        else:
+            assigned_labels = None
+
+        return AssignResult(
+            num_gts, assigned_gt_inds, None, labels=assigned_labels)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/assigners/region_assigner.py

+import torch
+
+from mmdet.core import anchor_inside_flags
+from ..builder import BBOX_ASSIGNERS
+from .assign_result import AssignResult
+from .base_assigner import BaseAssigner
+
+
+def calc_region(bbox, ratio, stride, featmap_size=None):
+    """Calculate region of the box defined by the ratio, the ratio is from the
+    center of the box to every edge."""
+    # project bbox on the feature
+    f_bbox = bbox / stride
+    x1 = torch.round((1 - ratio) * f_bbox[0] + ratio * f_bbox[2])
+    y1 = torch.round((1 - ratio) * f_bbox[1] + ratio * f_bbox[3])
+    x2 = torch.round(ratio * f_bbox[0] + (1 - ratio) * f_bbox[2])
+    y2 = torch.round(ratio * f_bbox[1] + (1 - ratio) * f_bbox[3])
+    if featmap_size is not None:
+        x1 = x1.clamp(min=0, max=featmap_size[1])
+        y1 = y1.clamp(min=0, max=featmap_size[0])
+        x2 = x2.clamp(min=0, max=featmap_size[1])
+        y2 = y2.clamp(min=0, max=featmap_size[0])
+    return (x1, y1, x2, y2)
+
+
+def anchor_ctr_inside_region_flags(anchors, stride, region):
+    """Get the flag indicate whether anchor centers are inside regions."""
+    x1, y1, x2, y2 = region
+    f_anchors = anchors / stride
+    x = (f_anchors[:, 0] + f_anchors[:, 2]) * 0.5
+    y = (f_anchors[:, 1] + f_anchors[:, 3]) * 0.5
+    flags = (x >= x1) & (x <= x2) & (y >= y1) & (y <= y2)
+    return flags
+
+
+@BBOX_ASSIGNERS.register_module()
+class RegionAssigner(BaseAssigner):
+    """Assign a corresponding gt bbox or background to each bbox.
+
+    Each proposals will be assigned with `-1`, `0`, or a positive integer
+    indicating the ground truth index.
+
+    - -1: don't care
+    - 0: negative sample, no assigned gt
+    - positive integer: positive sample, index (1-based) of assigned gt
+
+    Args:
+        center_ratio: ratio of the region in the center of the bbox to
+            define positive sample.
+        ignore_ratio: ratio of the region to define ignore samples.
+    """
+
+    def __init__(self, center_ratio=0.2, ignore_ratio=0.5):
+        self.center_ratio = center_ratio
+        self.ignore_ratio = ignore_ratio
+
+    def assign(self,
+               mlvl_anchors,
+               mlvl_valid_flags,
+               gt_bboxes,
+               img_meta,
+               featmap_sizes,
+               anchor_scale,
+               anchor_strides,
+               gt_bboxes_ignore=None,
+               gt_labels=None,
+               allowed_border=0):
+        """Assign gt to anchors.
+
+        This method assign a gt bbox to every bbox (proposal/anchor), each bbox
+        will be assigned with -1, 0, or a positive number. -1 means don't care,
+        0 means negative sample, positive number is the index (1-based) of
+        assigned gt.
+        The assignment is done in following steps, the order matters.
+
+        1. Assign every anchor to 0 (negative)
+        For each gt_bboxes:
+            2. Compute ignore flags based on ignore_region then
+                assign -1 to anchors w.r.t. ignore flags
+            3. Compute pos flags based on center_region then
+               assign gt_bboxes to anchors w.r.t. pos flags
+            4. Compute ignore flags based on adjacent anchor lvl then
+               assign -1 to anchors w.r.t. ignore flags
+            5. Assign anchor outside of image to -1
+
+        Args:
+            mlvl_anchors (list[Tensor]): Multi level anchors.
+            mlvl_valid_flags (list[Tensor]): Multi level valid flags.
+            gt_bboxes (Tensor): Ground truth bboxes of image
+            img_meta (dict): Meta info of image.
+            featmap_sizes (list[Tensor]): Feature mapsize each level
+            anchor_scale (int): Scale of the anchor.
+            anchor_strides (list[int]): Stride of the anchor.
+            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, ).
+            allowed_border (int, optional): The border to allow the valid
+                anchor. Defaults to 0.
+
+        Returns:
+            :obj:`AssignResult`: The assign result.
+        """
+        # TODO support gt_bboxes_ignore
+        if gt_bboxes_ignore is not None:
+            raise NotImplementedError
+        if gt_bboxes.shape[0] == 0:
+            raise ValueError('No gt bboxes')
+        num_gts = gt_bboxes.shape[0]
+        num_lvls = len(mlvl_anchors)
+        r1 = (1 - self.center_ratio) / 2
+        r2 = (1 - self.ignore_ratio) / 2
+
+        scale = torch.sqrt((gt_bboxes[:, 2] - gt_bboxes[:, 0]) *
+                           (gt_bboxes[:, 3] - gt_bboxes[:, 1]))
+        min_anchor_size = scale.new_full(
+            (1, ), float(anchor_scale * anchor_strides[0]))
+        target_lvls = torch.floor(
+            torch.log2(scale) - torch.log2(min_anchor_size) + 0.5)
+        target_lvls = target_lvls.clamp(min=0, max=num_lvls - 1).long()
+
+        # 1. assign 0 (negative) by default
+        mlvl_assigned_gt_inds = []
+        mlvl_ignore_flags = []
+        for lvl in range(num_lvls):
+            h, w = featmap_sizes[lvl]
+            assert h * w == mlvl_anchors[lvl].shape[0]
+            assigned_gt_inds = gt_bboxes.new_full((h * w, ),
+                                                  0,
+                                                  dtype=torch.long)
+            ignore_flags = torch.zeros_like(assigned_gt_inds)
+            mlvl_assigned_gt_inds.append(assigned_gt_inds)
+            mlvl_ignore_flags.append(ignore_flags)
+
+        for gt_id in range(num_gts):
+            lvl = target_lvls[gt_id].item()
+            featmap_size = featmap_sizes[lvl]
+            stride = anchor_strides[lvl]
+            anchors = mlvl_anchors[lvl]
+            gt_bbox = gt_bboxes[gt_id, :4]
+
+            # Compute regions
+            ignore_region = calc_region(gt_bbox, r2, stride, featmap_size)
+            ctr_region = calc_region(gt_bbox, r1, stride, featmap_size)
+
+            # 2. Assign -1 to ignore flags
+            ignore_flags = anchor_ctr_inside_region_flags(
+                anchors, stride, ignore_region)
+            mlvl_assigned_gt_inds[lvl][ignore_flags] = -1
+
+            # 3. Assign gt_bboxes to pos flags
+            pos_flags = anchor_ctr_inside_region_flags(anchors, stride,
+                                                       ctr_region)
+            mlvl_assigned_gt_inds[lvl][pos_flags] = gt_id + 1
+
+            # 4. Assign -1 to ignore adjacent lvl
+            if lvl > 0:
+                d_lvl = lvl - 1
+                d_anchors = mlvl_anchors[d_lvl]
+                d_featmap_size = featmap_sizes[d_lvl]
+                d_stride = anchor_strides[d_lvl]
+                d_ignore_region = calc_region(gt_bbox, r2, d_stride,
+                                              d_featmap_size)
+                ignore_flags = anchor_ctr_inside_region_flags(
+                    d_anchors, d_stride, d_ignore_region)
+                mlvl_ignore_flags[d_lvl][ignore_flags] = 1
+            if lvl < num_lvls - 1:
+                u_lvl = lvl + 1
+                u_anchors = mlvl_anchors[u_lvl]
+                u_featmap_size = featmap_sizes[u_lvl]
+                u_stride = anchor_strides[u_lvl]
+                u_ignore_region = calc_region(gt_bbox, r2, u_stride,
+                                              u_featmap_size)
+                ignore_flags = anchor_ctr_inside_region_flags(
+                    u_anchors, u_stride, u_ignore_region)
+                mlvl_ignore_flags[u_lvl][ignore_flags] = 1
+
+        # 4. (cont.) Assign -1 to ignore adjacent lvl
+        for lvl in range(num_lvls):
+            ignore_flags = mlvl_ignore_flags[lvl]
+            mlvl_assigned_gt_inds[lvl][ignore_flags] = -1
+
+        # 5. Assign -1 to anchor outside of image
+        flat_assigned_gt_inds = torch.cat(mlvl_assigned_gt_inds)
+        flat_anchors = torch.cat(mlvl_anchors)
+        flat_valid_flags = torch.cat(mlvl_valid_flags)
+        assert (flat_assigned_gt_inds.shape[0] == flat_anchors.shape[0] ==
+                flat_valid_flags.shape[0])
+        inside_flags = anchor_inside_flags(flat_anchors, flat_valid_flags,
+                                           img_meta['img_shape'],
+                                           allowed_border)
+        outside_flags = ~inside_flags
+        flat_assigned_gt_inds[outside_flags] = -1
+
+        if gt_labels is not None:
+            assigned_labels = torch.zeros_like(flat_assigned_gt_inds)
+            pos_flags = assigned_gt_inds > 0
+            assigned_labels[pos_flags] = gt_labels[
+                flat_assigned_gt_inds[pos_flags] - 1]
+        else:
+            assigned_labels = None
+
+        return AssignResult(
+            num_gts, flat_assigned_gt_inds, None, labels=assigned_labels)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/builder.py

+from mmcv.utils import Registry, build_from_cfg
+
+BBOX_ASSIGNERS = Registry('bbox_assigner')
+BBOX_SAMPLERS = Registry('bbox_sampler')
+BBOX_CODERS = Registry('bbox_coder')
+
+
+def build_assigner(cfg, **default_args):
+    """Builder of box assigner."""
+    return build_from_cfg(cfg, BBOX_ASSIGNERS, default_args)
+
+
+def build_sampler(cfg, **default_args):
+    """Builder of box sampler."""
+    return build_from_cfg(cfg, BBOX_SAMPLERS, default_args)
+
+
+def build_bbox_coder(cfg, **default_args):
+    """Builder of box coder."""
+    return build_from_cfg(cfg, BBOX_CODERS, default_args)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/__init__.py

+from .base_bbox_coder import BaseBBoxCoder
+from .bucketing_bbox_coder import BucketingBBoxCoder
+from .delta_xywh_bbox_coder import DeltaXYWHBBoxCoder
+from .legacy_delta_xywh_bbox_coder import LegacyDeltaXYWHBBoxCoder
+from .pseudo_bbox_coder import PseudoBBoxCoder
+from .tblr_bbox_coder import TBLRBBoxCoder
+from .yolo_bbox_coder import YOLOBBoxCoder
+
+__all__ = [
+    'BaseBBoxCoder', 'PseudoBBoxCoder', 'DeltaXYWHBBoxCoder',
+    'LegacyDeltaXYWHBBoxCoder', 'TBLRBBoxCoder', 'YOLOBBoxCoder',
+    'BucketingBBoxCoder'
+]

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/base_bbox_coder.py

+from abc import ABCMeta, abstractmethod
+
+
+class BaseBBoxCoder(metaclass=ABCMeta):
+    """Base bounding box coder."""
+
+    def __init__(self, **kwargs):
+        pass
+
+    @abstractmethod
+    def encode(self, bboxes, gt_bboxes):
+        """Encode deltas between bboxes and ground truth boxes."""
+        pass
+
+    @abstractmethod
+    def decode(self, bboxes, bboxes_pred):
+        """Decode the predicted bboxes according to prediction and base
+        boxes."""
+        pass

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/bucketing_bbox_coder.py

+import numpy as np
+import torch
+import torch.nn.functional as F
+
+from ..builder import BBOX_CODERS
+from ..transforms import bbox_rescale
+from .base_bbox_coder import BaseBBoxCoder
+
+
+@BBOX_CODERS.register_module()
+class BucketingBBoxCoder(BaseBBoxCoder):
+    """Bucketing BBox Coder for Side-Aware Bounday Localization (SABL).
+
+    Boundary Localization with Bucketing and Bucketing Guided Rescoring
+    are implemented here.
+
+    Please refer to https://arxiv.org/abs/1912.04260 for more details.
+
+    Args:
+        num_buckets (int): Number of buckets.
+        scale_factor (int): Scale factor of proposals to generate buckets.
+        offset_topk (int): Topk buckets are used to generate
+             bucket fine regression targets. Defaults to 2.
+        offset_upperbound (float): Offset upperbound to generate
+             bucket fine regression targets.
+             To avoid too large offset displacements. Defaults to 1.0.
+        cls_ignore_neighbor (bool): Ignore second nearest bucket or Not.
+             Defaults to True.
+        clip_border (bool, optional): Whether clip the objects outside the
+            border of the image. Defaults to True.
+    """
+
+    def __init__(self,
+                 num_buckets,
+                 scale_factor,
+                 offset_topk=2,
+                 offset_upperbound=1.0,
+                 cls_ignore_neighbor=True,
+                 clip_border=True):
+        super(BucketingBBoxCoder, self).__init__()
+        self.num_buckets = num_buckets
+        self.scale_factor = scale_factor
+        self.offset_topk = offset_topk
+        self.offset_upperbound = offset_upperbound
+        self.cls_ignore_neighbor = cls_ignore_neighbor
+        self.clip_border = clip_border
+
+    def encode(self, bboxes, gt_bboxes):
+        """Get bucketing estimation and fine regression targets during
+        training.
+
+        Args:
+            bboxes (torch.Tensor): source boxes, e.g., object proposals.
+            gt_bboxes (torch.Tensor): target of the transformation, e.g.,
+                ground truth boxes.
+
+        Returns:
+           encoded_bboxes(tuple[Tensor]): bucketing estimation
+            and fine regression targets and weights
+        """
+
+        assert bboxes.size(0) == gt_bboxes.size(0)
+        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
+        encoded_bboxes = bbox2bucket(bboxes, gt_bboxes, self.num_buckets,
+                                     self.scale_factor, self.offset_topk,
+                                     self.offset_upperbound,
+                                     self.cls_ignore_neighbor)
+        return encoded_bboxes
+
+    def decode(self, bboxes, pred_bboxes, max_shape=None):
+        """Apply transformation `pred_bboxes` to `boxes`.
+        Args:
+            boxes (torch.Tensor): Basic boxes.
+            pred_bboxes (torch.Tensor): Predictions for bucketing estimation
+                and fine regression
+            max_shape (tuple[int], optional): Maximum shape of boxes.
+                Defaults to None.
+
+        Returns:
+            torch.Tensor: Decoded boxes.
+        """
+        assert len(pred_bboxes) == 2
+        cls_preds, offset_preds = pred_bboxes
+        assert cls_preds.size(0) == bboxes.size(0) and offset_preds.size(
+            0) == bboxes.size(0)
+        decoded_bboxes = bucket2bbox(bboxes, cls_preds, offset_preds,
+                                     self.num_buckets, self.scale_factor,
+                                     max_shape, self.clip_border)
+
+        return decoded_bboxes
+
+
+def generat_buckets(proposals, num_buckets, scale_factor=1.0):
+    """Generate buckets w.r.t bucket number and scale factor of proposals.
+
+    Args:
+        proposals (Tensor): Shape (n, 4)
+        num_buckets (int): Number of buckets.
+        scale_factor (float): Scale factor to rescale proposals.
+
+    Returns:
+        tuple[Tensor]: (bucket_w, bucket_h, l_buckets, r_buckets,
+         t_buckets, d_buckets)
+
+            - bucket_w: Width of buckets on x-axis. Shape (n, ).
+            - bucket_h: Height of buckets on y-axis. Shape (n, ).
+            - l_buckets: Left buckets. Shape (n, ceil(side_num/2)).
+            - r_buckets: Right buckets. Shape (n, ceil(side_num/2)).
+            - t_buckets: Top buckets. Shape (n, ceil(side_num/2)).
+            - d_buckets: Down buckets. Shape (n, ceil(side_num/2)).
+    """
+    proposals = bbox_rescale(proposals, scale_factor)
+
+    # number of buckets in each side
+    side_num = int(np.ceil(num_buckets / 2.0))
+    pw = proposals[..., 2] - proposals[..., 0]
+    ph = proposals[..., 3] - proposals[..., 1]
+    px1 = proposals[..., 0]
+    py1 = proposals[..., 1]
+    px2 = proposals[..., 2]
+    py2 = proposals[..., 3]
+
+    bucket_w = pw / num_buckets
+    bucket_h = ph / num_buckets
+
+    # left buckets
+    l_buckets = px1[:, None] + (0.5 + torch.arange(
+        0, side_num).to(proposals).float())[None, :] * bucket_w[:, None]
+    # right buckets
+    r_buckets = px2[:, None] - (0.5 + torch.arange(
+        0, side_num).to(proposals).float())[None, :] * bucket_w[:, None]
+    # top buckets
+    t_buckets = py1[:, None] + (0.5 + torch.arange(
+        0, side_num).to(proposals).float())[None, :] * bucket_h[:, None]
+    # down buckets
+    d_buckets = py2[:, None] - (0.5 + torch.arange(
+        0, side_num).to(proposals).float())[None, :] * bucket_h[:, None]
+    return bucket_w, bucket_h, l_buckets, r_buckets, t_buckets, d_buckets
+
+
+def bbox2bucket(proposals,
+                gt,
+                num_buckets,
+                scale_factor,
+                offset_topk=2,
+                offset_upperbound=1.0,
+                cls_ignore_neighbor=True):
+    """Generate buckets estimation and fine regression targets.
+
+    Args:
+        proposals (Tensor): Shape (n, 4)
+        gt (Tensor): Shape (n, 4)
+        num_buckets (int): Number of buckets.
+        scale_factor (float): Scale factor to rescale proposals.
+        offset_topk (int): Topk buckets are used to generate
+             bucket fine regression targets. Defaults to 2.
+        offset_upperbound (float): Offset allowance to generate
+             bucket fine regression targets.
+             To avoid too large offset displacements. Defaults to 1.0.
+        cls_ignore_neighbor (bool): Ignore second nearest bucket or Not.
+             Defaults to True.
+
+    Returns:
+        tuple[Tensor]: (offsets, offsets_weights, bucket_labels, cls_weights).
+
+            - offsets: Fine regression targets. \
+                Shape (n, num_buckets*2).
+            - offsets_weights: Fine regression weights. \
+                Shape (n, num_buckets*2).
+            - bucket_labels: Bucketing estimation labels. \
+                Shape (n, num_buckets*2).
+            - cls_weights: Bucketing estimation weights. \
+                Shape (n, num_buckets*2).
+    """
+    assert proposals.size() == gt.size()
+
+    # generate buckets
+    proposals = proposals.float()
+    gt = gt.float()
+    (bucket_w, bucket_h, l_buckets, r_buckets, t_buckets,
+     d_buckets) = generat_buckets(proposals, num_buckets, scale_factor)
+
+    gx1 = gt[..., 0]
+    gy1 = gt[..., 1]
+    gx2 = gt[..., 2]
+    gy2 = gt[..., 3]
+
+    # generate offset targets and weights
+    # offsets from buckets to gts
+    l_offsets = (l_buckets - gx1[:, None]) / bucket_w[:, None]
+    r_offsets = (r_buckets - gx2[:, None]) / bucket_w[:, None]
+    t_offsets = (t_buckets - gy1[:, None]) / bucket_h[:, None]
+    d_offsets = (d_buckets - gy2[:, None]) / bucket_h[:, None]
+
+    # select top-k nearset buckets
+    l_topk, l_label = l_offsets.abs().topk(
+        offset_topk, dim=1, largest=False, sorted=True)
+    r_topk, r_label = r_offsets.abs().topk(
+        offset_topk, dim=1, largest=False, sorted=True)
+    t_topk, t_label = t_offsets.abs().topk(
+        offset_topk, dim=1, largest=False, sorted=True)
+    d_topk, d_label = d_offsets.abs().topk(
+        offset_topk, dim=1, largest=False, sorted=True)
+
+    offset_l_weights = l_offsets.new_zeros(l_offsets.size())
+    offset_r_weights = r_offsets.new_zeros(r_offsets.size())
+    offset_t_weights = t_offsets.new_zeros(t_offsets.size())
+    offset_d_weights = d_offsets.new_zeros(d_offsets.size())
+    inds = torch.arange(0, proposals.size(0)).to(proposals).long()
+
+    # generate offset weights of top-k nearset buckets
+    for k in range(offset_topk):
+        if k >= 1:
+            offset_l_weights[inds, l_label[:,
+                                           k]] = (l_topk[:, k] <
+                                                  offset_upperbound).float()
+            offset_r_weights[inds, r_label[:,
+                                           k]] = (r_topk[:, k] <
+                                                  offset_upperbound).float()
+            offset_t_weights[inds, t_label[:,
+                                           k]] = (t_topk[:, k] <
+                                                  offset_upperbound).float()
+            offset_d_weights[inds, d_label[:,
+                                           k]] = (d_topk[:, k] <
+                                                  offset_upperbound).float()
+        else:
+            offset_l_weights[inds, l_label[:, k]] = 1.0
+            offset_r_weights[inds, r_label[:, k]] = 1.0
+            offset_t_weights[inds, t_label[:, k]] = 1.0
+            offset_d_weights[inds, d_label[:, k]] = 1.0
+
+    offsets = torch.cat([l_offsets, r_offsets, t_offsets, d_offsets], dim=-1)
+    offsets_weights = torch.cat([
+        offset_l_weights, offset_r_weights, offset_t_weights, offset_d_weights
+    ],
+                                dim=-1)
+
+    # generate bucket labels and weight
+    side_num = int(np.ceil(num_buckets / 2.0))
+    labels = torch.stack(
+        [l_label[:, 0], r_label[:, 0], t_label[:, 0], d_label[:, 0]], dim=-1)
+
+    batch_size = labels.size(0)
+    bucket_labels = F.one_hot(labels.view(-1), side_num).view(batch_size,
+                                                              -1).float()
+    bucket_cls_l_weights = (l_offsets.abs() < 1).float()
+    bucket_cls_r_weights = (r_offsets.abs() < 1).float()
+    bucket_cls_t_weights = (t_offsets.abs() < 1).float()
+    bucket_cls_d_weights = (d_offsets.abs() < 1).float()
+    bucket_cls_weights = torch.cat([
+        bucket_cls_l_weights, bucket_cls_r_weights, bucket_cls_t_weights,
+        bucket_cls_d_weights
+    ],
+                                   dim=-1)
+    # ignore second nearest buckets for cls if necessay
+    if cls_ignore_neighbor:
+        bucket_cls_weights = (~((bucket_cls_weights == 1) &
+                                (bucket_labels == 0))).float()
+    else:
+        bucket_cls_weights[:] = 1.0
+    return offsets, offsets_weights, bucket_labels, bucket_cls_weights
+
+
+def bucket2bbox(proposals,
+                cls_preds,
+                offset_preds,
+                num_buckets,
+                scale_factor=1.0,
+                max_shape=None,
+                clip_border=True):
+    """Apply bucketing estimation (cls preds) and fine regression (offset
+    preds) to generate det bboxes.
+
+    Args:
+        proposals (Tensor): Boxes to be transformed. Shape (n, 4)
+        cls_preds (Tensor): bucketing estimation. Shape (n, num_buckets*2).
+        offset_preds (Tensor): fine regression. Shape (n, num_buckets*2).
+        num_buckets (int): Number of buckets.
+        scale_factor (float): Scale factor to rescale proposals.
+        max_shape (tuple[int, int]): Maximum bounds for boxes. specifies (H, W)
+        clip_border (bool, optional): Whether clip the objects outside the
+            border of the image. Defaults to True.
+
+    Returns:
+        tuple[Tensor]: (bboxes, loc_confidence).
+
+            - bboxes: predicted bboxes. Shape (n, 4)
+            - loc_confidence: localization confidence of predicted bboxes.
+                Shape (n,).
+    """
+
+    side_num = int(np.ceil(num_buckets / 2.0))
+    cls_preds = cls_preds.view(-1, side_num)
+    offset_preds = offset_preds.view(-1, side_num)
+
+    scores = F.softmax(cls_preds, dim=1)
+    score_topk, score_label = scores.topk(2, dim=1, largest=True, sorted=True)
+
+    rescaled_proposals = bbox_rescale(proposals, scale_factor)
+
+    pw = rescaled_proposals[..., 2] - rescaled_proposals[..., 0]
+    ph = rescaled_proposals[..., 3] - rescaled_proposals[..., 1]
+    px1 = rescaled_proposals[..., 0]
+    py1 = rescaled_proposals[..., 1]
+    px2 = rescaled_proposals[..., 2]
+    py2 = rescaled_proposals[..., 3]
+
+    bucket_w = pw / num_buckets
+    bucket_h = ph / num_buckets
+
+    score_inds_l = score_label[0::4, 0]
+    score_inds_r = score_label[1::4, 0]
+    score_inds_t = score_label[2::4, 0]
+    score_inds_d = score_label[3::4, 0]
+    l_buckets = px1 + (0.5 + score_inds_l.float()) * bucket_w
+    r_buckets = px2 - (0.5 + score_inds_r.float()) * bucket_w
+    t_buckets = py1 + (0.5 + score_inds_t.float()) * bucket_h
+    d_buckets = py2 - (0.5 + score_inds_d.float()) * bucket_h
+
+    offsets = offset_preds.view(-1, 4, side_num)
+    inds = torch.arange(proposals.size(0)).to(proposals).long()
+    l_offsets = offsets[:, 0, :][inds, score_inds_l]
+    r_offsets = offsets[:, 1, :][inds, score_inds_r]
+    t_offsets = offsets[:, 2, :][inds, score_inds_t]
+    d_offsets = offsets[:, 3, :][inds, score_inds_d]
+
+    x1 = l_buckets - l_offsets * bucket_w
+    x2 = r_buckets - r_offsets * bucket_w
+    y1 = t_buckets - t_offsets * bucket_h
+    y2 = d_buckets - d_offsets * bucket_h
+
+    if clip_border and max_shape is not None:
+        x1 = x1.clamp(min=0, max=max_shape[1] - 1)
+        y1 = y1.clamp(min=0, max=max_shape[0] - 1)
+        x2 = x2.clamp(min=0, max=max_shape[1] - 1)
+        y2 = y2.clamp(min=0, max=max_shape[0] - 1)
+    bboxes = torch.cat([x1[:, None], y1[:, None], x2[:, None], y2[:, None]],
+                       dim=-1)
+
+    # bucketing guided rescoring
+    loc_confidence = score_topk[:, 0]
+    top2_neighbor_inds = (score_label[:, 0] - score_label[:, 1]).abs() == 1
+    loc_confidence += score_topk[:, 1] * top2_neighbor_inds.float()
+    loc_confidence = loc_confidence.view(-1, 4).mean(dim=1)
+
+    return bboxes, loc_confidence

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/delta_xywh_bbox_coder.py

+import numpy as np
+import torch
+
+from ..builder import BBOX_CODERS
+from .base_bbox_coder import BaseBBoxCoder
+
+
+@BBOX_CODERS.register_module()
+class DeltaXYWHBBoxCoder(BaseBBoxCoder):
+    """Delta XYWH BBox coder.
+
+    Following the practice in `R-CNN <https://arxiv.org/abs/1311.2524>`_,
+    this coder encodes bbox (x1, y1, x2, y2) into delta (dx, dy, dw, dh) and
+    decodes delta (dx, dy, dw, dh) back to original bbox (x1, y1, x2, y2).
+
+    Args:
+        target_means (Sequence[float]): Denormalizing means of target for
+            delta coordinates
+        target_stds (Sequence[float]): Denormalizing standard deviation of
+            target for delta coordinates
+        clip_border (bool, optional): Whether clip the objects outside the
+            border of the image. Defaults to True.
+    """
+
+    def __init__(self,
+                 target_means=(0., 0., 0., 0.),
+                 target_stds=(1., 1., 1., 1.),
+                 clip_border=True):
+        super(BaseBBoxCoder, self).__init__()
+        self.means = target_means
+        self.stds = target_stds
+        self.clip_border = clip_border
+
+    def encode(self, bboxes, gt_bboxes):
+        """Get box regression transformation deltas that can be used to
+        transform the ``bboxes`` into the ``gt_bboxes``.
+
+        Args:
+            bboxes (torch.Tensor): Source boxes, e.g., object proposals.
+            gt_bboxes (torch.Tensor): Target of the transformation, e.g.,
+                ground-truth boxes.
+
+        Returns:
+            torch.Tensor: Box transformation deltas
+        """
+
+        assert bboxes.size(0) == gt_bboxes.size(0)
+        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
+        encoded_bboxes = bbox2delta(bboxes, gt_bboxes, self.means, self.stds)
+        return encoded_bboxes
+
+    def decode(self,
+               bboxes,
+               pred_bboxes,
+               max_shape=None,
+               wh_ratio_clip=16 / 1000):
+        """Apply transformation `pred_bboxes` to `boxes`.
+
+        Args:
+            boxes (torch.Tensor): Basic boxes.
+            pred_bboxes (torch.Tensor): Encoded boxes with shape
+            max_shape (tuple[int], optional): Maximum shape of boxes.
+                Defaults to None.
+            wh_ratio_clip (float, optional): The allowed ratio between
+                width and height.
+
+        Returns:
+            torch.Tensor: Decoded boxes.
+        """
+
+        assert pred_bboxes.size(0) == bboxes.size(0)
+        decoded_bboxes = delta2bbox(bboxes, pred_bboxes, self.means, self.stds,
+                                    max_shape, wh_ratio_clip, self.clip_border)
+
+        return decoded_bboxes
+
+
+def bbox2delta(proposals, gt, means=(0., 0., 0., 0.), stds=(1., 1., 1., 1.)):
+    """Compute deltas of proposals w.r.t. gt.
+
+    We usually compute the deltas of x, y, w, h of proposals w.r.t ground
+    truth bboxes to get regression target.
+    This is the inverse function of :func:`delta2bbox`.
+
+    Args:
+        proposals (Tensor): Boxes to be transformed, shape (N, ..., 4)
+        gt (Tensor): Gt bboxes to be used as base, shape (N, ..., 4)
+        means (Sequence[float]): Denormalizing means for delta coordinates
+        stds (Sequence[float]): Denormalizing standard deviation for delta
+            coordinates
+
+    Returns:
+        Tensor: deltas with shape (N, 4), where columns represent dx, dy,
+            dw, dh.
+    """
+    assert proposals.size() == gt.size()
+
+    proposals = proposals.float()
+    gt = gt.float()
+    px = (proposals[..., 0] + proposals[..., 2]) * 0.5
+    py = (proposals[..., 1] + proposals[..., 3]) * 0.5
+    pw = proposals[..., 2] - proposals[..., 0]
+    ph = proposals[..., 3] - proposals[..., 1]
+
+    gx = (gt[..., 0] + gt[..., 2]) * 0.5
+    gy = (gt[..., 1] + gt[..., 3]) * 0.5
+    gw = gt[..., 2] - gt[..., 0]
+    gh = gt[..., 3] - gt[..., 1]
+
+    dx = (gx - px) / pw
+    dy = (gy - py) / ph
+    dw = torch.log(gw / pw)
+    dh = torch.log(gh / ph)
+    deltas = torch.stack([dx, dy, dw, dh], dim=-1)
+
+    means = deltas.new_tensor(means).unsqueeze(0)
+    stds = deltas.new_tensor(stds).unsqueeze(0)
+    deltas = deltas.sub_(means).div_(stds)
+
+    return deltas
+
+
+def delta2bbox(rois,
+               deltas,
+               means=(0., 0., 0., 0.),
+               stds=(1., 1., 1., 1.),
+               max_shape=None,
+               wh_ratio_clip=16 / 1000,
+               clip_border=True):
+    """Apply deltas to shift/scale base boxes.
+
+    Typically the rois are anchor or proposed bounding boxes and the deltas are
+    network outputs used to shift/scale those boxes.
+    This is the inverse function of :func:`bbox2delta`.
+
+    Args:
+        rois (Tensor): Boxes to be transformed. Has shape (N, 4)
+        deltas (Tensor): Encoded offsets with respect to each roi.
+            Has shape (N, 4 * num_classes). Note N = num_anchors * W * H when
+            rois is a grid of anchors. Offset encoding follows [1]_.
+        means (Sequence[float]): Denormalizing means for delta coordinates
+        stds (Sequence[float]): Denormalizing standard deviation for delta
+            coordinates
+        max_shape (tuple[int, int]): Maximum bounds for boxes. specifies (H, W)
+        wh_ratio_clip (float): Maximum aspect ratio for boxes.
+        clip_border (bool, optional): Whether clip the objects outside the
+            border of the image. Defaults to True.
+
+    Returns:
+        Tensor: Boxes with shape (N, 4), where columns represent
+            tl_x, tl_y, br_x, br_y.
+
+    References:
+        .. [1] https://arxiv.org/abs/1311.2524
+
+    Example:
+        >>> rois = torch.Tensor([[ 0.,  0.,  1.,  1.],
+        >>>                      [ 0.,  0.,  1.,  1.],
+        >>>                      [ 0.,  0.,  1.,  1.],
+        >>>                      [ 5.,  5.,  5.,  5.]])
+        >>> deltas = torch.Tensor([[  0.,   0.,   0.,   0.],
+        >>>                        [  1.,   1.,   1.,   1.],
+        >>>                        [  0.,   0.,   2.,  -1.],
+        >>>                        [ 0.7, -1.9, -0.5,  0.3]])
+        >>> delta2bbox(rois, deltas, max_shape=(32, 32))
+        tensor([[0.0000, 0.0000, 1.0000, 1.0000],
+                [0.1409, 0.1409, 2.8591, 2.8591],
+                [0.0000, 0.3161, 4.1945, 0.6839],
+                [5.0000, 5.0000, 5.0000, 5.0000]])
+    """
+    means = deltas.new_tensor(means).view(1, -1).repeat(1, deltas.size(1) // 4)
+    stds = deltas.new_tensor(stds).view(1, -1).repeat(1, deltas.size(1) // 4)
+    denorm_deltas = deltas * stds + means
+    dx = denorm_deltas[:, 0::4]
+    dy = denorm_deltas[:, 1::4]
+    dw = denorm_deltas[:, 2::4]
+    dh = denorm_deltas[:, 3::4]
+    max_ratio = np.abs(np.log(wh_ratio_clip))
+    dw = dw.clamp(min=-max_ratio, max=max_ratio)
+    dh = dh.clamp(min=-max_ratio, max=max_ratio)
+    # Compute center of each roi
+    px = ((rois[:, 0] + rois[:, 2]) * 0.5).unsqueeze(1).expand_as(dx)
+    py = ((rois[:, 1] + rois[:, 3]) * 0.5).unsqueeze(1).expand_as(dy)
+    # Compute width/height of each roi
+    pw = (rois[:, 2] - rois[:, 0]).unsqueeze(1).expand_as(dw)
+    ph = (rois[:, 3] - rois[:, 1]).unsqueeze(1).expand_as(dh)
+    # Use exp(network energy) to enlarge/shrink each roi
+    gw = pw * dw.exp()
+    gh = ph * dh.exp()
+    # Use network energy to shift the center of each roi
+    gx = px + pw * dx
+    gy = py + ph * dy
+    # Convert center-xy/width/height to top-left, bottom-right
+    x1 = gx - gw * 0.5
+    y1 = gy - gh * 0.5
+    x2 = gx + gw * 0.5
+    y2 = gy + gh * 0.5
+    if clip_border and max_shape is not None:
+        x1 = x1.clamp(min=0, max=max_shape[1])
+        y1 = y1.clamp(min=0, max=max_shape[0])
+        x2 = x2.clamp(min=0, max=max_shape[1])
+        y2 = y2.clamp(min=0, max=max_shape[0])
+    bboxes = torch.stack([x1, y1, x2, y2], dim=-1).view(deltas.size())
+    return bboxes

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/legacy_delta_xywh_bbox_coder.py

+import numpy as np
+import torch
+
+from ..builder import BBOX_CODERS
+from .base_bbox_coder import BaseBBoxCoder
+
+
+@BBOX_CODERS.register_module()
+class LegacyDeltaXYWHBBoxCoder(BaseBBoxCoder):
+    """Legacy Delta XYWH BBox coder used in MMDet V1.x.
+
+    Following the practice in R-CNN [1]_, this coder encodes bbox (x1, y1, x2,
+    y2) into delta (dx, dy, dw, dh) and decodes delta (dx, dy, dw, dh)
+    back to original bbox (x1, y1, x2, y2).
+
+    Note:
+        The main difference between :class`LegacyDeltaXYWHBBoxCoder` and
+        :class:`DeltaXYWHBBoxCoder` is whether ``+ 1`` is used during width and
+        height calculation. We suggest to only use this coder when testing with
+        MMDet V1.x models.
+
+    References:
+        .. [1] https://arxiv.org/abs/1311.2524
+
+    Args:
+        target_means (Sequence[float]): denormalizing means of target for
+            delta coordinates
+        target_stds (Sequence[float]): denormalizing standard deviation of
+            target for delta coordinates
+    """
+
+    def __init__(self,
+                 target_means=(0., 0., 0., 0.),
+                 target_stds=(1., 1., 1., 1.)):
+        super(BaseBBoxCoder, self).__init__()
+        self.means = target_means
+        self.stds = target_stds
+
+    def encode(self, bboxes, gt_bboxes):
+        """Get box regression transformation deltas that can be used to
+        transform the ``bboxes`` into the ``gt_bboxes``.
+
+        Args:
+            bboxes (torch.Tensor): source boxes, e.g., object proposals.
+            gt_bboxes (torch.Tensor): target of the transformation, e.g.,
+                ground-truth boxes.
+
+        Returns:
+            torch.Tensor: Box transformation deltas
+        """
+        assert bboxes.size(0) == gt_bboxes.size(0)
+        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
+        encoded_bboxes = legacy_bbox2delta(bboxes, gt_bboxes, self.means,
+                                           self.stds)
+        return encoded_bboxes
+
+    def decode(self,
+               bboxes,
+               pred_bboxes,
+               max_shape=None,
+               wh_ratio_clip=16 / 1000):
+        """Apply transformation `pred_bboxes` to `boxes`.
+
+        Args:
+            boxes (torch.Tensor): Basic boxes.
+            pred_bboxes (torch.Tensor): Encoded boxes with shape
+            max_shape (tuple[int], optional): Maximum shape of boxes.
+                Defaults to None.
+            wh_ratio_clip (float, optional): The allowed ratio between
+                width and height.
+
+        Returns:
+            torch.Tensor: Decoded boxes.
+        """
+        assert pred_bboxes.size(0) == bboxes.size(0)
+        decoded_bboxes = legacy_delta2bbox(bboxes, pred_bboxes, self.means,
+                                           self.stds, max_shape, wh_ratio_clip)
+
+        return decoded_bboxes
+
+
+def legacy_bbox2delta(proposals,
+                      gt,
+                      means=(0., 0., 0., 0.),
+                      stds=(1., 1., 1., 1.)):
+    """Compute deltas of proposals w.r.t. gt in the MMDet V1.x manner.
+
+    We usually compute the deltas of x, y, w, h of proposals w.r.t ground
+    truth bboxes to get regression target.
+    This is the inverse function of `delta2bbox()`
+
+    Args:
+        proposals (Tensor): Boxes to be transformed, shape (N, ..., 4)
+        gt (Tensor): Gt bboxes to be used as base, shape (N, ..., 4)
+        means (Sequence[float]): Denormalizing means for delta coordinates
+        stds (Sequence[float]): Denormalizing standard deviation for delta
+            coordinates
+
+    Returns:
+        Tensor: deltas with shape (N, 4), where columns represent dx, dy,
+            dw, dh.
+    """
+    assert proposals.size() == gt.size()
+
+    proposals = proposals.float()
+    gt = gt.float()
+    px = (proposals[..., 0] + proposals[..., 2]) * 0.5
+    py = (proposals[..., 1] + proposals[..., 3]) * 0.5
+    pw = proposals[..., 2] - proposals[..., 0] + 1.0
+    ph = proposals[..., 3] - proposals[..., 1] + 1.0
+
+    gx = (gt[..., 0] + gt[..., 2]) * 0.5
+    gy = (gt[..., 1] + gt[..., 3]) * 0.5
+    gw = gt[..., 2] - gt[..., 0] + 1.0
+    gh = gt[..., 3] - gt[..., 1] + 1.0
+
+    dx = (gx - px) / pw
+    dy = (gy - py) / ph
+    dw = torch.log(gw / pw)
+    dh = torch.log(gh / ph)
+    deltas = torch.stack([dx, dy, dw, dh], dim=-1)
+
+    means = deltas.new_tensor(means).unsqueeze(0)
+    stds = deltas.new_tensor(stds).unsqueeze(0)
+    deltas = deltas.sub_(means).div_(stds)
+
+    return deltas
+
+
+def legacy_delta2bbox(rois,
+                      deltas,
+                      means=(0., 0., 0., 0.),
+                      stds=(1., 1., 1., 1.),
+                      max_shape=None,
+                      wh_ratio_clip=16 / 1000):
+    """Apply deltas to shift/scale base boxes in the MMDet V1.x manner.
+
+    Typically the rois are anchor or proposed bounding boxes and the deltas are
+    network outputs used to shift/scale those boxes.
+    This is the inverse function of `bbox2delta()`
+
+    Args:
+        rois (Tensor): Boxes to be transformed. Has shape (N, 4)
+        deltas (Tensor): Encoded offsets with respect to each roi.
+            Has shape (N, 4 * num_classes). Note N = num_anchors * W * H when
+            rois is a grid of anchors. Offset encoding follows [1]_.
+        means (Sequence[float]): Denormalizing means for delta coordinates
+        stds (Sequence[float]): Denormalizing standard deviation for delta
+            coordinates
+        max_shape (tuple[int, int]): Maximum bounds for boxes. specifies (H, W)
+        wh_ratio_clip (float): Maximum aspect ratio for boxes.
+
+    Returns:
+        Tensor: Boxes with shape (N, 4), where columns represent
+            tl_x, tl_y, br_x, br_y.
+
+    References:
+        .. [1] https://arxiv.org/abs/1311.2524
+
+    Example:
+        >>> rois = torch.Tensor([[ 0.,  0.,  1.,  1.],
+        >>>                      [ 0.,  0.,  1.,  1.],
+        >>>                      [ 0.,  0.,  1.,  1.],
+        >>>                      [ 5.,  5.,  5.,  5.]])
+        >>> deltas = torch.Tensor([[  0.,   0.,   0.,   0.],
+        >>>                        [  1.,   1.,   1.,   1.],
+        >>>                        [  0.,   0.,   2.,  -1.],
+        >>>                        [ 0.7, -1.9, -0.5,  0.3]])
+        >>> legacy_delta2bbox(rois, deltas, max_shape=(32, 32))
+        tensor([[0.0000, 0.0000, 1.5000, 1.5000],
+                [0.0000, 0.0000, 5.2183, 5.2183],
+                [0.0000, 0.1321, 7.8891, 0.8679],
+                [5.3967, 2.4251, 6.0033, 3.7749]])
+    """
+    means = deltas.new_tensor(means).repeat(1, deltas.size(1) // 4)
+    stds = deltas.new_tensor(stds).repeat(1, deltas.size(1) // 4)
+    denorm_deltas = deltas * stds + means
+    dx = denorm_deltas[:, 0::4]
+    dy = denorm_deltas[:, 1::4]
+    dw = denorm_deltas[:, 2::4]
+    dh = denorm_deltas[:, 3::4]
+    max_ratio = np.abs(np.log(wh_ratio_clip))
+    dw = dw.clamp(min=-max_ratio, max=max_ratio)
+    dh = dh.clamp(min=-max_ratio, max=max_ratio)
+    # Compute center of each roi
+    px = ((rois[:, 0] + rois[:, 2]) * 0.5).unsqueeze(1).expand_as(dx)
+    py = ((rois[:, 1] + rois[:, 3]) * 0.5).unsqueeze(1).expand_as(dy)
+    # Compute width/height of each roi
+    pw = (rois[:, 2] - rois[:, 0] + 1.0).unsqueeze(1).expand_as(dw)
+    ph = (rois[:, 3] - rois[:, 1] + 1.0).unsqueeze(1).expand_as(dh)
+    # Use exp(network energy) to enlarge/shrink each roi
+    gw = pw * dw.exp()
+    gh = ph * dh.exp()
+    # Use network energy to shift the center of each roi
+    gx = px + pw * dx
+    gy = py + ph * dy
+    # Convert center-xy/width/height to top-left, bottom-right
+
+    # The true legacy box coder should +- 0.5 here.
+    # However, current implementation improves the performance when testing
+    # the models trained in MMDetection 1.X (~0.5 bbox AP, 0.2 mask AP)
+    x1 = gx - gw * 0.5
+    y1 = gy - gh * 0.5
+    x2 = gx + gw * 0.5
+    y2 = gy + gh * 0.5
+    if max_shape is not None:
+        x1 = x1.clamp(min=0, max=max_shape[1] - 1)
+        y1 = y1.clamp(min=0, max=max_shape[0] - 1)
+        x2 = x2.clamp(min=0, max=max_shape[1] - 1)
+        y2 = y2.clamp(min=0, max=max_shape[0] - 1)
+    bboxes = torch.stack([x1, y1, x2, y2], dim=-1).view_as(deltas)
+    return bboxes

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/pseudo_bbox_coder.py

+from ..builder import BBOX_CODERS
+from .base_bbox_coder import BaseBBoxCoder
+
+
+@BBOX_CODERS.register_module()
+class PseudoBBoxCoder(BaseBBoxCoder):
+    """Pseudo bounding box coder."""
+
+    def __init__(self, **kwargs):
+        super(BaseBBoxCoder, self).__init__(**kwargs)
+
+    def encode(self, bboxes, gt_bboxes):
+        """torch.Tensor: return the given ``bboxes``"""
+        return gt_bboxes
+
+    def decode(self, bboxes, pred_bboxes):
+        """torch.Tensor: return the given ``pred_bboxes``"""
+        return pred_bboxes

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/tblr_bbox_coder.py

+import torch
+
+from ..builder import BBOX_CODERS
+from .base_bbox_coder import BaseBBoxCoder
+
+
+@BBOX_CODERS.register_module()
+class TBLRBBoxCoder(BaseBBoxCoder):
+    """TBLR BBox coder.
+
+    Following the practice in `FSAF <https://arxiv.org/abs/1903.00621>`_,
+    this coder encodes gt bboxes (x1, y1, x2, y2) into (top, bottom, left,
+    right) and decode it back to the original.
+
+    Args:
+        normalizer (list | float): Normalization factor to be
+          divided with when coding the coordinates. If it is a list, it should
+          have length of 4 indicating normalization factor in tblr dims.
+          Otherwise it is a unified float factor for all dims. Default: 4.0
+        clip_border (bool, optional): Whether clip the objects outside the
+            border of the image. Defaults to True.
+    """
+
+    def __init__(self, normalizer=4.0, clip_border=True):
+        super(BaseBBoxCoder, self).__init__()
+        self.normalizer = normalizer
+        self.clip_border = clip_border
+
+    def encode(self, bboxes, gt_bboxes):
+        """Get box regression transformation deltas that can be used to
+        transform the ``bboxes`` into the ``gt_bboxes`` in the (top, left,
+        bottom, right) order.
+
+        Args:
+            bboxes (torch.Tensor): source boxes, e.g., object proposals.
+            gt_bboxes (torch.Tensor): target of the transformation, e.g.,
+                ground truth boxes.
+
+        Returns:
+            torch.Tensor: Box transformation deltas
+        """
+        assert bboxes.size(0) == gt_bboxes.size(0)
+        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
+        encoded_bboxes = bboxes2tblr(
+            bboxes, gt_bboxes, normalizer=self.normalizer)
+        return encoded_bboxes
+
+    def decode(self, bboxes, pred_bboxes, max_shape=None):
+        """Apply transformation `pred_bboxes` to `boxes`.
+
+        Args:
+            boxes (torch.Tensor): Basic boxes.
+            pred_bboxes (torch.Tensor): Encoded boxes with shape
+            max_shape (tuple[int], optional): Maximum shape of boxes.
+                Defaults to None.
+
+        Returns:
+            torch.Tensor: Decoded boxes.
+        """
+        assert pred_bboxes.size(0) == bboxes.size(0)
+        decoded_bboxes = tblr2bboxes(
+            bboxes,
+            pred_bboxes,
+            normalizer=self.normalizer,
+            max_shape=max_shape,
+            clip_border=self.clip_border)
+
+        return decoded_bboxes
+
+
+def bboxes2tblr(priors, gts, normalizer=4.0, normalize_by_wh=True):
+    """Encode ground truth boxes to tblr coordinate.
+
+    It first convert the gt coordinate to tblr format,
+     (top, bottom, left, right), relative to prior box centers.
+     The tblr coordinate may be normalized by the side length of prior bboxes
+     if `normalize_by_wh` is specified as True, and it is then normalized by
+     the `normalizer` factor.
+
+    Args:
+        priors (Tensor): Prior boxes in point form
+            Shape: (num_proposals,4).
+        gts (Tensor): Coords of ground truth for each prior in point-form
+            Shape: (num_proposals, 4).
+        normalizer (Sequence[float] | float): normalization parameter of
+            encoded boxes. If it is a list, it has to have length = 4.
+            Default: 4.0
+        normalize_by_wh (bool): Whether to normalize tblr coordinate by the
+            side length (wh) of prior bboxes.
+
+    Return:
+        encoded boxes (Tensor), Shape: (num_proposals, 4)
+    """
+
+    # dist b/t match center and prior's center
+    if not isinstance(normalizer, float):
+        normalizer = torch.tensor(normalizer, device=priors.device)
+        assert len(normalizer) == 4, 'Normalizer must have length = 4'
+    assert priors.size(0) == gts.size(0)
+    prior_centers = (priors[:, 0:2] + priors[:, 2:4]) / 2
+    xmin, ymin, xmax, ymax = gts.split(1, dim=1)
+    top = prior_centers[:, 1].unsqueeze(1) - ymin
+    bottom = ymax - prior_centers[:, 1].unsqueeze(1)
+    left = prior_centers[:, 0].unsqueeze(1) - xmin
+    right = xmax - prior_centers[:, 0].unsqueeze(1)
+    loc = torch.cat((top, bottom, left, right), dim=1)
+    if normalize_by_wh:
+        # Normalize tblr by anchor width and height
+        wh = priors[:, 2:4] - priors[:, 0:2]
+        w, h = torch.split(wh, 1, dim=1)
+        loc[:, :2] /= h  # tb is normalized by h
+        loc[:, 2:] /= w  # lr is normalized by w
+    # Normalize tblr by the given normalization factor
+    return loc / normalizer
+
+
+def tblr2bboxes(priors,
+                tblr,
+                normalizer=4.0,
+                normalize_by_wh=True,
+                max_shape=None,
+                clip_border=True):
+    """Decode tblr outputs to prediction boxes.
+
+    The process includes 3 steps: 1) De-normalize tblr coordinates by
+    multiplying it with `normalizer`; 2) De-normalize tblr coordinates by the
+    prior bbox width and height if `normalize_by_wh` is `True`; 3) Convert
+    tblr (top, bottom, left, right) pair relative to the center of priors back
+    to (xmin, ymin, xmax, ymax) coordinate.
+
+    Args:
+        priors (Tensor): Prior boxes in point form (x0, y0, x1, y1)
+          Shape: (n,4).
+        tblr (Tensor): Coords of network output in tblr form
+          Shape: (n, 4).
+        normalizer (Sequence[float] | float): Normalization parameter of
+          encoded boxes. By list, it represents the normalization factors at
+          tblr dims. By float, it is the unified normalization factor at all
+          dims. Default: 4.0
+        normalize_by_wh (bool): Whether the tblr coordinates have been
+          normalized by the side length (wh) of prior bboxes.
+        max_shape (tuple, optional): Shape of the image. Decoded bboxes
+          exceeding which will be clamped.
+        clip_border (bool, optional): Whether clip the objects outside the
+            border of the image. Defaults to True.
+
+    Return:
+        encoded boxes (Tensor), Shape: (n, 4)
+    """
+    if not isinstance(normalizer, float):
+        normalizer = torch.tensor(normalizer, device=priors.device)
+        assert len(normalizer) == 4, 'Normalizer must have length = 4'
+    assert priors.size(0) == tblr.size(0)
+    loc_decode = tblr * normalizer
+    prior_centers = (priors[:, 0:2] + priors[:, 2:4]) / 2
+    if normalize_by_wh:
+        wh = priors[:, 2:4] - priors[:, 0:2]
+        w, h = torch.split(wh, 1, dim=1)
+        loc_decode[:, :2] *= h  # tb
+        loc_decode[:, 2:] *= w  # lr
+    top, bottom, left, right = loc_decode.split((1, 1, 1, 1), dim=1)
+    xmin = prior_centers[:, 0].unsqueeze(1) - left
+    xmax = prior_centers[:, 0].unsqueeze(1) + right
+    ymin = prior_centers[:, 1].unsqueeze(1) - top
+    ymax = prior_centers[:, 1].unsqueeze(1) + bottom
+    boxes = torch.cat((xmin, ymin, xmax, ymax), dim=1)
+    if clip_border and max_shape is not None:
+        boxes[:, 0].clamp_(min=0, max=max_shape[1])
+        boxes[:, 1].clamp_(min=0, max=max_shape[0])
+        boxes[:, 2].clamp_(min=0, max=max_shape[1])
+        boxes[:, 3].clamp_(min=0, max=max_shape[0])
+    return boxes

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/coder/yolo_bbox_coder.py

+import torch
+
+from ..builder import BBOX_CODERS
+from .base_bbox_coder import BaseBBoxCoder
+
+
+@BBOX_CODERS.register_module()
+class YOLOBBoxCoder(BaseBBoxCoder):
+    """YOLO BBox coder.
+
+    Following `YOLO <https://arxiv.org/abs/1506.02640>`_, this coder divide
+    image into grids, and encode bbox (x1, y1, x2, y2) into (cx, cy, dw, dh).
+    cx, cy in [0., 1.], denotes relative center position w.r.t the center of
+    bboxes. dw, dh are the same as :obj:`DeltaXYWHBBoxCoder`.
+
+    Args:
+        eps (float): Min value of cx, cy when encoding.
+    """
+
+    def __init__(self, eps=1e-6):
+        super(BaseBBoxCoder, self).__init__()
+        self.eps = eps
+
+    def encode(self, bboxes, gt_bboxes, stride):
+        """Get box regression transformation deltas that can be used to
+        transform the ``bboxes`` into the ``gt_bboxes``.
+
+        Args:
+            bboxes (torch.Tensor): Source boxes, e.g., anchors.
+            gt_bboxes (torch.Tensor): Target of the transformation, e.g.,
+                ground-truth boxes.
+            stride (torch.Tensor | int): Stride of bboxes.
+
+        Returns:
+            torch.Tensor: Box transformation deltas
+        """
+
+        assert bboxes.size(0) == gt_bboxes.size(0)
+        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
+        x_center_gt = (gt_bboxes[..., 0] + gt_bboxes[..., 2]) * 0.5
+        y_center_gt = (gt_bboxes[..., 1] + gt_bboxes[..., 3]) * 0.5
+        w_gt = gt_bboxes[..., 2] - gt_bboxes[..., 0]
+        h_gt = gt_bboxes[..., 3] - gt_bboxes[..., 1]
+        x_center = (bboxes[..., 0] + bboxes[..., 2]) * 0.5
+        y_center = (bboxes[..., 1] + bboxes[..., 3]) * 0.5
+        w = bboxes[..., 2] - bboxes[..., 0]
+        h = bboxes[..., 3] - bboxes[..., 1]
+        w_target = torch.log((w_gt / w).clamp(min=self.eps))
+        h_target = torch.log((h_gt / h).clamp(min=self.eps))
+        x_center_target = ((x_center_gt - x_center) / stride + 0.5).clamp(
+            self.eps, 1 - self.eps)
+        y_center_target = ((y_center_gt - y_center) / stride + 0.5).clamp(
+            self.eps, 1 - self.eps)
+        encoded_bboxes = torch.stack(
+            [x_center_target, y_center_target, w_target, h_target], dim=-1)
+        return encoded_bboxes
+
+    def decode(self, bboxes, pred_bboxes, stride):
+        """Apply transformation `pred_bboxes` to `boxes`.
+
+        Args:
+            boxes (torch.Tensor): Basic boxes, e.g. anchors.
+            pred_bboxes (torch.Tensor): Encoded boxes with shape
+            stride (torch.Tensor | int): Strides of bboxes.
+
+        Returns:
+            torch.Tensor: Decoded boxes.
+        """
+        assert pred_bboxes.size(0) == bboxes.size(0)
+        assert pred_bboxes.size(-1) == bboxes.size(-1) == 4
+        x_center = (bboxes[..., 0] + bboxes[..., 2]) * 0.5
+        y_center = (bboxes[..., 1] + bboxes[..., 3]) * 0.5
+        w = bboxes[..., 2] - bboxes[..., 0]
+        h = bboxes[..., 3] - bboxes[..., 1]
+        # Get outputs x, y
+        x_center_pred = (pred_bboxes[..., 0] - 0.5) * stride + x_center
+        y_center_pred = (pred_bboxes[..., 1] - 0.5) * stride + y_center
+        w_pred = torch.exp(pred_bboxes[..., 2]) * w
+        h_pred = torch.exp(pred_bboxes[..., 3]) * h
+
+        decoded_bboxes = torch.stack(
+            (x_center_pred - w_pred / 2, y_center_pred - h_pred / 2,
+             x_center_pred + w_pred / 2, y_center_pred + h_pred / 2),
+            dim=-1)
+
+        return decoded_bboxes

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/demodata.py

+import numpy as np
+import torch
+
+
+def ensure_rng(rng=None):
+    """Simple version of the ``kwarray.ensure_rng``
+
+    Args:
+        rng (int | numpy.random.RandomState | None):
+            if None, then defaults to the global rng. Otherwise this can be an
+            integer or a RandomState class
+    Returns:
+        (numpy.random.RandomState) : rng -
+            a numpy random number generator
+
+    References:
+        https://gitlab.kitware.com/computer-vision/kwarray/blob/master/kwarray/util_random.py#L270
+    """
+
+    if rng is None:
+        rng = np.random.mtrand._rand
+    elif isinstance(rng, int):
+        rng = np.random.RandomState(rng)
+    else:
+        rng = rng
+    return rng
+
+
+def random_boxes(num=1, scale=1, rng=None):
+    """Simple version of ``kwimage.Boxes.random``
+
+    Returns:
+        Tensor: shape (n, 4) in x1, y1, x2, y2 format.
+
+    References:
+        https://gitlab.kitware.com/computer-vision/kwimage/blob/master/kwimage/structs/boxes.py#L1390
+
+    Example:
+        >>> num = 3
+        >>> scale = 512
+        >>> rng = 0
+        >>> boxes = random_boxes(num, scale, rng)
+        >>> print(boxes)
+        tensor([[280.9925, 278.9802, 308.6148, 366.1769],
+                [216.9113, 330.6978, 224.0446, 456.5878],
+                [405.3632, 196.3221, 493.3953, 270.7942]])
+    """
+    rng = ensure_rng(rng)
+
+    tlbr = rng.rand(num, 4).astype(np.float32)
+
+    tl_x = np.minimum(tlbr[:, 0], tlbr[:, 2])
+    tl_y = np.minimum(tlbr[:, 1], tlbr[:, 3])
+    br_x = np.maximum(tlbr[:, 0], tlbr[:, 2])
+    br_y = np.maximum(tlbr[:, 1], tlbr[:, 3])
+
+    tlbr[:, 0] = tl_x * scale
+    tlbr[:, 1] = tl_y * scale
+    tlbr[:, 2] = br_x * scale
+    tlbr[:, 3] = br_y * scale
+
+    boxes = torch.from_numpy(tlbr)
+    return boxes

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/iou_calculators/__init__.py

+from .builder import build_iou_calculator
+from .iou2d_calculator import BboxOverlaps2D, bbox_overlaps
+
+__all__ = ['build_iou_calculator', 'BboxOverlaps2D', 'bbox_overlaps']

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/iou_calculators/builder.py

+from mmcv.utils import Registry, build_from_cfg
+
+IOU_CALCULATORS = Registry('IoU calculator')
+
+
+def build_iou_calculator(cfg, default_args=None):
+    """Builder of IoU calculator."""
+    return build_from_cfg(cfg, IOU_CALCULATORS, default_args)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/iou_calculators/iou2d_calculator.py

+import torch
+
+from .builder import IOU_CALCULATORS
+
+
+@IOU_CALCULATORS.register_module()
+class BboxOverlaps2D(object):
+    """2D Overlaps (e.g. IoUs, GIoUs) Calculator."""
+
+    def __call__(self, bboxes1, bboxes2, mode='iou', is_aligned=False):
+        """Calculate IoU between 2D bboxes.
+
+        Args:
+            bboxes1 (Tensor): bboxes have shape (m, 4) in <x1, y1, x2, y2>
+                format, or shape (m, 5) in <x1, y1, x2, y2, score> format.
+            bboxes2 (Tensor): bboxes have shape (m, 4) in <x1, y1, x2, y2>
+                format, shape (m, 5) in <x1, y1, x2, y2, score> format, or be
+                empty. If ``is_aligned `` is ``True``, then m and n must be
+                equal.
+            mode (str): "iou" (intersection over union), "iof" (intersection
+                over foreground), or "giou" (generalized intersection over
+                union).
+            is_aligned (bool, optional): If True, then m and n must be equal.
+                Default False.
+
+        Returns:
+            Tensor: shape (m, n) if ``is_aligned `` is False else shape (m,)
+        """
+        assert bboxes1.size(-1) in [0, 4, 5]
+        assert bboxes2.size(-1) in [0, 4, 5]
+        if bboxes2.size(-1) == 5:
+            bboxes2 = bboxes2[..., :4]
+        if bboxes1.size(-1) == 5:
+            bboxes1 = bboxes1[..., :4]
+        return bbox_overlaps(bboxes1, bboxes2, mode, is_aligned)
+
+    def __repr__(self):
+        """str: a string describing the module"""
+        repr_str = self.__class__.__name__ + '()'
+        return repr_str
+
+
+def bbox_overlaps(bboxes1, bboxes2, mode='iou', is_aligned=False, eps=1e-6):
+    """Calculate overlap between two set of bboxes.
+
+    If ``is_aligned `` is ``False``, then calculate the overlaps between each
+    bbox of bboxes1 and bboxes2, otherwise the overlaps between each aligned
+    pair of bboxes1 and bboxes2.
+
+    Args:
+        bboxes1 (Tensor): shape (B, m, 4) in <x1, y1, x2, y2> format or empty.
+        bboxes2 (Tensor): shape (B, n, 4) in <x1, y1, x2, y2> format or empty.
+            B indicates the batch dim, in shape (B1, B2, ..., Bn).
+            If ``is_aligned `` is ``True``, then m and n must be equal.
+        mode (str): "iou" (intersection over union), "iof" (intersection over
+            foreground) or "giou" (generalized intersection over union).
+            Default "iou".
+        is_aligned (bool, optional): If True, then m and n must be equal.
+            Default False.
+        eps (float, optional): A value added to the denominator for numerical
+            stability. Default 1e-6.
+
+    Returns:
+        Tensor: shape (m, n) if ``is_aligned `` is False else shape (m,)
+
+    Example:
+        >>> bboxes1 = torch.FloatTensor([
+        >>>     [0, 0, 10, 10],
+        >>>     [10, 10, 20, 20],
+        >>>     [32, 32, 38, 42],
+        >>> ])
+        >>> bboxes2 = torch.FloatTensor([
+        >>>     [0, 0, 10, 20],
+        >>>     [0, 10, 10, 19],
+        >>>     [10, 10, 20, 20],
+        >>> ])
+        >>> overlaps = bbox_overlaps(bboxes1, bboxes2)
+        >>> assert overlaps.shape == (3, 3)
+        >>> overlaps = bbox_overlaps(bboxes1, bboxes2, is_aligned=True)
+        >>> assert overlaps.shape == (3, )
+
+    Example:
+        >>> empty = torch.empty(0, 4)
+        >>> nonempty = torch.FloatTensor([[0, 0, 10, 9]])
+        >>> assert tuple(bbox_overlaps(empty, nonempty).shape) == (0, 1)
+        >>> assert tuple(bbox_overlaps(nonempty, empty).shape) == (1, 0)
+        >>> assert tuple(bbox_overlaps(empty, empty).shape) == (0, 0)
+    """
+
+    assert mode in ['iou', 'iof', 'giou'], f'Unsupported mode {mode}'
+    # Either the boxes are empty or the length of boxes's last dimenstion is 4
+    assert (bboxes1.size(-1) == 4 or bboxes1.size(0) == 0)
+    assert (bboxes2.size(-1) == 4 or bboxes2.size(0) == 0)
+
+    # Batch dim must be the same
+    # Batch dim: (B1, B2, ... Bn)
+    assert bboxes1.shape[:-2] == bboxes2.shape[:-2]
+    batch_shape = bboxes1.shape[:-2]
+
+    rows = bboxes1.size(-2)
+    cols = bboxes2.size(-2)
+    if is_aligned:
+        assert rows == cols
+
+    if rows * cols == 0:
+        if is_aligned:
+            return bboxes1.new(batch_shape + (rows, ))
+        else:
+            return bboxes1.new(batch_shape + (rows, cols))
+
+    area1 = (bboxes1[..., 2] - bboxes1[..., 0]) * (
+        bboxes1[..., 3] - bboxes1[..., 1])
+    area2 = (bboxes2[..., 2] - bboxes2[..., 0]) * (
+        bboxes2[..., 3] - bboxes2[..., 1])
+
+    if is_aligned:
+        lt = torch.max(bboxes1[..., :2], bboxes2[..., :2])  # [B, rows, 2]
+        rb = torch.min(bboxes1[..., 2:], bboxes2[..., 2:])  # [B, rows, 2]
+
+        wh = (rb - lt).clamp(min=0)  # [B, rows, 2]
+        overlap = wh[..., 0] * wh[..., 1]
+
+        if mode in ['iou', 'giou']:
+            union = area1 + area2 - overlap
+        else:
+            union = area1
+        if mode == 'giou':
+            enclosed_lt = torch.min(bboxes1[..., :2], bboxes2[..., :2])
+            enclosed_rb = torch.max(bboxes1[..., 2:], bboxes2[..., 2:])
+    else:
+        lt = torch.max(bboxes1[..., :, None, :2],
+                       bboxes2[..., None, :, :2])  # [B, rows, cols, 2]
+        rb = torch.min(bboxes1[..., :, None, 2:],
+                       bboxes2[..., None, :, 2:])  # [B, rows, cols, 2]
+
+        wh = (rb - lt).clamp(min=0)  # [B, rows, cols, 2]
+        overlap = wh[..., 0] * wh[..., 1]
+
+        if mode in ['iou', 'giou']:
+            union = area1[..., None] + area2[..., None, :] - overlap
+        else:
+            union = area1[..., None]
+        if mode == 'giou':
+            enclosed_lt = torch.min(bboxes1[..., :, None, :2],
+                                    bboxes2[..., None, :, :2])
+            enclosed_rb = torch.max(bboxes1[..., :, None, 2:],
+                                    bboxes2[..., None, :, 2:])
+
+    eps = union.new_tensor([eps])
+    union = torch.max(union, eps)
+    ious = overlap / union
+    if mode in ['iou', 'iof']:
+        return ious
+    # calculate gious
+    enclose_wh = (enclosed_rb - enclosed_lt).clamp(min=0)
+    enclose_area = enclose_wh[..., 0] * enclose_wh[..., 1]
+    enclose_area = torch.max(enclose_area, eps)
+    gious = ious - (enclose_area - union) / enclose_area
+    return gious

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/match_costs/__init__.py

+from .builder import build_match_cost
+from .match_cost import BBoxL1Cost, ClassificationCost, FocalLossCost, IoUCost
+
+__all__ = [
+    'build_match_cost', 'ClassificationCost', 'BBoxL1Cost', 'IoUCost',
+    'FocalLossCost'
+]

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/match_costs/builder.py

+from mmcv.utils import Registry, build_from_cfg
+
+MATCH_COST = Registry('Match Cost')
+
+
+def build_match_cost(cfg, default_args=None):
+    """Builder of IoU calculator."""
+    return build_from_cfg(cfg, MATCH_COST, default_args)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/bbox/match_costs/match_cost.py

+import torch
+
+from mmdet.core.bbox.iou_calculators import bbox_overlaps
+from mmdet.core.bbox.transforms import bbox_cxcywh_to_xyxy, bbox_xyxy_to_cxcywh
+from .builder import MATCH_COST
+
+
+@MATCH_COST.register_module()
+class BBoxL1Cost(object):
+    """BBoxL1Cost.
+
+     Args:
+         weight (int | float, optional): loss_weight
+         box_format (str, optional): 'xyxy' for DETR, 'xywh' for Sparse_RCNN
+
+     Examples:
+         >>> from mmdet.core.bbox.match_costs.match_cost import BBoxL1Cost
+         >>> import torch
+         >>> self = BBoxL1Cost()
+         >>> bbox_pred = torch.rand(1, 4)
+         >>> gt_bboxes= torch.FloatTensor([[0, 0, 2, 4], [1, 2, 3, 4]])
+         >>> factor = torch.tensor([10, 8, 10, 8])
+         >>> self(bbox_pred, gt_bboxes, factor)
+         tensor([[1.6172, 1.6422]])
+    """
+
+    def __init__(self, weight=1., box_format='xyxy'):
+        self.weight = weight
+        assert box_format in ['xyxy', 'xywh']
+        self.box_format = box_format
+
+    def __call__(self, bbox_pred, gt_bboxes):
+        """
+        Args:
+            bbox_pred (Tensor): Predicted boxes with normalized coordinates
+                (cx, cy, w, h), which are all in range [0, 1]. Shape
+                [num_query, 4].
+            gt_bboxes (Tensor): Ground truth boxes with normalized
+                coordinates (x1, y1, x2, y2). Shape [num_gt, 4].
+
+        Returns:
+            torch.Tensor: bbox_cost value with weight
+        """
+        if self.box_format == 'xywh':
+            gt_bboxes = bbox_xyxy_to_cxcywh(gt_bboxes)
+        elif self.box_format == 'xyxy':
+            bbox_pred = bbox_cxcywh_to_xyxy(bbox_pred)
+        bbox_cost = torch.cdist(bbox_pred, gt_bboxes, p=1)
+        return bbox_cost * self.weight
+
+
+@MATCH_COST.register_module()
+class FocalLossCost(object):
+    """FocalLossCost.
+
+     Args:
+         weight (int | float, optional): loss_weight
+         alpha (int | float, optional): focal_loss alpha
+         gamma (int | float, optional): focal_loss gamma
+         eps (float, optional): default 1e-12
+
+     Examples:
+         >>> from mmdet.core.bbox.match_costs.match_cost import FocalLossCost
+         >>> import torch
+         >>> self = FocalLossCost()
+         >>> cls_pred = torch.rand(4, 3)
+         >>> gt_labels = torch.tensor([0, 1, 2])
+         >>> factor = torch.tensor([10, 8, 10, 8])
+         >>> self(cls_pred, gt_labels)
+         tensor([[-0.3236, -0.3364, -0.2699],
+                [-0.3439, -0.3209, -0.4807],
+                [-0.4099, -0.3795, -0.2929],
+                [-0.1950, -0.1207, -0.2626]])
+    """
+
+    def __init__(self, weight=1., alpha=0.25, gamma=2, eps=1e-12):
+        self.weight = weight
+        self.alpha = alpha
+        self.gamma = gamma
+        self.eps = eps
+
+    def __call__(self, cls_pred, gt_labels):
+        """
+        Args:
+            cls_pred (Tensor): Predicted classification logits, shape
+                [num_query, num_class].
+            gt_labels (Tensor): Label of `gt_bboxes`, shape (num_gt,).
+
+        Returns:
+            torch.Tensor: cls_cost value with weight
+        """
+        cls_pred = cls_pred.sigmoid()
+        neg_cost = -(1 - cls_pred + self.eps).log() * (
+            1 - self.alpha) * cls_pred.pow(self.gamma)
+        pos_cost = -(cls_pred + self.eps).log() * self.alpha * (
+            1 - cls_pred).pow(self.gamma)
+        cls_cost = pos_cost[:, gt_labels] - neg_cost[:, gt_labels]
+        return cls_cost * self.weight
+
+
+@MATCH_COST.register_module()
+class ClassificationCost(object):
+    """ClsSoftmaxCost.
+
+     Args:
+         weight (int | float, optional): loss_weight
+
+     Examples:
+         >>> from mmdet.core.bbox.match_costs.match_cost import \
+         ... ClassificationCost
+         >>> import torch
+         >>> self = ClassificationCost()
+         >>> cls_pred = torch.rand(4, 3)
+         >>> gt_labels = torch.tensor([0, 1, 2])
+         >>> factor = torch.tensor([10, 8, 10, 8])
+         >>> self(cls_pred, gt_labels)
+         tensor([[-0.3430, -0.3525, -0.3045],
+                [-0.3077, -0.2931, -0.3992],
+                [-0.3664, -0.3455, -0.2881],
+                [-0.3343, -0.2701, -0.3956]])
+    """
+
+    def __init__(self, weight=1.):
+        self.weight = weight
+
+    def __call__(self, cls_pred, gt_labels):
+        """
+        Args:
+            cls_pred (Tensor): Predicted classification logits, shape
+                [num_query, num_class].
+            gt_labels (Tensor): Label of `gt_bboxes`, shape (num_gt,).
+
+        Returns:
+            torch.Tensor: cls_cost value with weight
+        """
+        # Following the official DETR repo, contrary to the loss that
+        # NLL is used, we approximate it in 1 - cls_score[gt_label].
+        # The 1 is a constant that doesn't change the matching,
+        # so it can be ommitted.
+        cls_score = cls_pred.softmax(-1)
+        cls_cost = -cls_score[:, gt_labels]
+        return cls_cost * self.weight
+
+
+@MATCH_COST.register_module()
+class IoUCost(object):
+    """IoUCost.
+
+     Args:
+         iou_mode (str, optional): iou mode such as 'iou' | 'giou'
+         weight (int | float, optional): loss weight
+
+     Examples:
+         >>> from mmdet.core.bbox.match_costs.match_cost import IoUCost
+         >>> import torch
+         >>> self = IoUCost()
+         >>> bboxes = torch.FloatTensor([[1,1, 2, 2], [2, 2, 3, 4]])
+         >>> gt_bboxes = torch.FloatTensor([[0, 0, 2, 4], [1, 2, 3, 4]])
+         >>> self(bboxes, gt_bboxes)
+         tensor([[-0.1250,  0.1667],
+                [ 0.1667, -0.5000]])
+    """
+
+    def __init__(self, iou_mode='giou', weight=1.):
+        self.weight = weight
+        self.iou_mode = iou_mode
+
+    def __call__(self, bboxes, gt_bboxes):
+        """
+        Args:
+            bboxes (Tensor): Predicted boxes with unnormalized coordinates
+                (x1, y1, x2, y2). Shape [num_query, 4].
+            gt_bboxes (Tensor): Ground truth boxes with unnormalized
+                coordinates (x1, y1, x2, y2). Shape [num_gt, 4].
+
+        Returns:
+            torch.Tensor: iou_cost value with weight
+        """
+        # overlaps: [num_bboxes, num_gt]
+        overlaps = bbox_overlaps(
+            bboxes, gt_bboxes, mode=self.iou_mode, is_aligned=False)
+        # The 1 is a constant that doesn't change the matching, so ommitted.
+        iou_cost = -overlaps
+        return iou_cost * self.weight