def setup_pair(self, object_rois, relationship_rois, scores_object, scores_relationship, graph_generation=False): # overlaps: (rois x gt_boxes) roi_num = min(cfg.TEST.MPN_BBOX_NUM, object_rois.size(0)) rois = object_rois[:roi_num, :] relationship_num = min(cfg.TEST.MPN_REGION_NUM, relationship_rois.size(0)) relationship_rois = relationship_rois[:relationship_num, :] subject_inds, object_inds, pair_rois = compare_rel_rois( rois, relationship_rois, scores_object[:roi_num], scores_relationship[:relationship_num], topN_obj=cfg.TEST.MPN_BBOX_NUM, topN_rel=cfg.TEST.MPN_REGION_NUM, obj_rel_thresh=cfg.TEST.MPN_OBJ_REL_THRESH, max_objects=cfg.TEST.MPN_MAX_OBJECTS, topN_covers=cfg.TEST.MPN_COVER_NUM, cover_thresh=cfg.TEST.MPN_MAKE_COVER_THRESH) subject_inds, object_inds, pair_rois = subject_inds.cpu().numpy(), object_inds.cpu().numpy(), pair_rois.data.cpu().numpy() subject_inds, object_inds = np.append(subject_inds, object_inds), np.append(object_inds, subject_inds) pair_rois = np.vstack((pair_rois, pair_rois)) mat_phrase = np.zeros((subject_inds.size, 2), dtype=np.int64) mat_phrase[:, 0] = subject_inds mat_phrase[:, 1] = object_inds mat_object = np.zeros((roi_num, 2, pair_rois.shape[0]), dtype=np.int64) for i in range(pair_rois.shape[0]): mat_object[subject_inds[i], 0, i] = 1 mat_object[object_inds[i], 1, i] = 1 overlaps_phrase = bbox_intersections( np.ascontiguousarray(relationship_rois.data.cpu().numpy()[:, 1:5], dtype=np.float), np.ascontiguousarray(pair_rois[:, 1:5], dtype=np.float)) max_overlaps_phrase = overlaps_phrase.max(axis=1) if graph_generation: keep_inds = np.where(max_overlaps_phrase >= cfg.TEST.MPN_PHRASE_REGION_OVERLAP_THRESH)[0] else: keep_inds = range(relationship_rois.size(0)) relationship_rois = relationship_rois[keep_inds, :] mat_region = (overlaps_phrase[keep_inds, :] > cfg.TEST.MPN_PHRASE_REGION_OVERLAP_THRESH).astype(np.int64) mat_phrase = np.concatenate((mat_phrase, mat_region.transpose()), 1) return rois, pair_rois, relationship_rois, mat_object, mat_phrase, mat_region
def forward(self, bottom, top): # Algorithm: # # for each (H, W) location i # generate 9 anchor boxes centered on cell i # apply predicted bbox deltas at cell i to each of the 9 anchors # filter out-of-image anchors # measure GT overlap assert bottom[0].data.shape[0] == 1, \ 'Only single item batches are supported' # map of shape (..., H, W) height, width = bottom[0].data.shape[-2:] # GT boxes (x1, y1, x2, y2, label) gt_boxes = bottom[1].data # im_info im_info = bottom[2].data[0, :] gt_ishard = bottom[4].data dontcare_areas = bottom[5].data if DEBUG: print('') print('im_size: ({}, {})'.format(im_info[0], im_info[1])) print('scale: {}'.format(im_info[2])) print('height, width: ({}, {})'.format(height, width)) print('rpn: gt_boxes.shape', gt_boxes.shape) print('rpn: gt_boxes', gt_boxes) # 1. Generate proposals from bbox deltas and shifted anchors shift_x = np.arange(0, width) * self._feat_stride shift_y = np.arange(0, height) * self._feat_stride shift_x, shift_y = np.meshgrid(shift_x, shift_y) shifts = np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(), shift_y.ravel())).transpose() # add A anchors (1, A, 4) to # cell K shifts (K, 1, 4) to get # shift anchors (K, A, 4) # reshape to (K*A, 4) shifted anchors A = self._num_anchors K = shifts.shape[0] all_anchors = (self._anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2))) all_anchors = all_anchors.reshape((K * A, 4)) total_anchors = int(K * A) # only keep anchors inside the image inds_inside = np.where( (all_anchors[:, 0] >= -self._allowed_border) & (all_anchors[:, 1] >= -self._allowed_border) & (all_anchors[:, 2] < im_info[1] + self._allowed_border) & # width (all_anchors[:, 3] < im_info[0] + self._allowed_border) # height )[0] if DEBUG: print('total_anchors', total_anchors) print('inds_inside', len(inds_inside)) # keep only inside anchors anchors = all_anchors[inds_inside, :] if DEBUG: print('anchors.shape', anchors.shape) # label: 1 is positive, 0 is negative, -1 is dont care labels = np.empty((len(inds_inside), ), dtype=np.float32) labels.fill(-1) # overlaps between the anchors and the gt boxes # overlaps (ex, gt) overlaps = bbox_overlaps( np.ascontiguousarray(anchors, dtype=np.float), np.ascontiguousarray(gt_boxes, dtype=np.float)) argmax_overlaps = overlaps.argmax(axis=1) max_overlaps = overlaps[np.arange(len(inds_inside)), argmax_overlaps] gt_argmax_overlaps = overlaps.argmax(axis=0) gt_max_overlaps = overlaps[gt_argmax_overlaps, np.arange(overlaps.shape[1])] gt_argmax_overlaps = np.where(overlaps == gt_max_overlaps)[0] if not cfg.TRAIN.RPN_CLOBBER_POSITIVES: # assign bg labels first so that positive labels can clobber them labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0 # fg label: for each gt, anchor with highest overlap labels[gt_argmax_overlaps] = 1 # fg label: above threshold IOU labels[max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1 if cfg.TRAIN.RPN_CLOBBER_POSITIVES: # assign bg labels last so that negative labels can clobber positives labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0 # preclude dontcare areas if dontcare_areas is not None and dontcare_areas.shape[0] > 0: # intersec shape is D x A intersecs = bbox_intersections( np.ascontiguousarray(dontcare_areas, dtype=np.float), # D x 4 np.ascontiguousarray(anchors, dtype=np.float) # A x 4 ) intersecs_ = intersecs.sum(axis=0) # A x 1 labels[intersecs_ > cfg.TRAIN.DONTCARE_AREA_INTERSECTION_HI] = -1 # preclude hard samples that are highly occlusioned, truncated or difficult to see if cfg.TRAIN.PRECLUDE_HARD_SAMPLES and gt_ishard is not None and gt_ishard.shape[0] > 0: assert gt_ishard.shape[0] == gt_boxes.shape[0] gt_ishard = gt_ishard.astype(int) gt_hardboxes = gt_boxes[gt_ishard == 1, :] if gt_hardboxes.shape[0] > 0: # H x A hard_overlaps = bbox_overlaps( np.ascontiguousarray(gt_hardboxes, dtype=np.float), # H x 4 np.ascontiguousarray(anchors, dtype=np.float)) # A x 4 hard_max_overlaps = hard_overlaps.max(axis=0) # (A) labels[hard_max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = -1 max_intersec_label_inds = hard_overlaps.argmax(axis=1) # H x 1 labels[max_intersec_label_inds] = -1 # # subsample positive labels if we have too many num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCHSIZE) fg_inds = np.where(labels == 1)[0] if len(fg_inds) > num_fg: disable_inds = npr.choice( fg_inds, size=(len(fg_inds) - num_fg), replace=False) labels[disable_inds] = -1 # subsample negative labels if we have too many num_bg = cfg.TRAIN.RPN_BATCHSIZE - np.sum(labels == 1) bg_inds = np.where(labels == 0)[0] if len(bg_inds) > num_bg: disable_inds = npr.choice( bg_inds, size=(len(bg_inds) - num_bg), replace=False) labels[disable_inds] = -1 #print "was %s inds, disabling %s, now %s inds" % ( #len(bg_inds), len(disable_inds), np.sum(labels == 0)) bbox_targets = np.zeros((len(inds_inside), 4), dtype=np.float32) bbox_targets = _compute_targets(anchors, gt_boxes[argmax_overlaps, :]) bbox_inside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32) bbox_inside_weights[labels == 1, :] = np.array(cfg.TRAIN.RPN_BBOX_INSIDE_WEIGHTS) bbox_outside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32) if cfg.TRAIN.RPN_POSITIVE_WEIGHT < 0: # uniform weighting of examples (given non-uniform sampling) num_examples = np.sum(labels >= 0) positive_weights = np.ones((1, 4)) * 1.0 / num_examples negative_weights = np.ones((1, 4)) * 1.0 / num_examples else: assert ((cfg.TRAIN.RPN_POSITIVE_WEIGHT > 0) & (cfg.TRAIN.RPN_POSITIVE_WEIGHT < 1)) positive_weights = (cfg.TRAIN.RPN_POSITIVE_WEIGHT / np.sum(labels == 1)) negative_weights = ((1.0 - cfg.TRAIN.RPN_POSITIVE_WEIGHT) / np.sum(labels == 0)) bbox_outside_weights[labels == 1, :] = positive_weights bbox_outside_weights[labels == 0, :] = negative_weights if DEBUG: self._sums += bbox_targets[labels == 1, :].sum(axis=0) self._squared_sums += (bbox_targets[labels == 1, :] ** 2).sum(axis=0) self._counts += np.sum(labels == 1) means = self._sums / self._counts stds = np.sqrt(self._squared_sums / self._counts - means ** 2) print('means:') print(means) print('stdevs:') print(stds) # map up to original set of anchors labels = _unmap(labels, total_anchors, inds_inside, fill=-1) bbox_targets = _unmap(bbox_targets, total_anchors, inds_inside, fill=0) bbox_inside_weights = _unmap(bbox_inside_weights, total_anchors, inds_inside, fill=0) bbox_outside_weights = _unmap(bbox_outside_weights, total_anchors, inds_inside, fill=0) if DEBUG: print('rpn: max max_overlap', np.max(max_overlaps)) print('rpn: num_positive', np.sum(labels == 1)) print('rpn: num_negative', np.sum(labels == 0)) self._fg_sum += np.sum(labels == 1) self._bg_sum += np.sum(labels == 0) self._count += 1 print('rpn: num_positive avg', self._fg_sum / self._count) print('rpn: num_negative avg', self._bg_sum / self._count) # labels labels = labels.reshape((1, height, width, A)).transpose(0, 3, 1, 2) labels = labels.reshape((1, 1, A * height, width)) top[0].reshape(*labels.shape) top[0].data[...] = labels # bbox_targets bbox_targets = bbox_targets \ .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2) top[1].reshape(*bbox_targets.shape) top[1].data[...] = bbox_targets # bbox_inside_weights bbox_inside_weights = bbox_inside_weights \ .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2) assert bbox_inside_weights.shape[2] == height assert bbox_inside_weights.shape[3] == width top[2].reshape(*bbox_inside_weights.shape) top[2].data[...] = bbox_inside_weights # bbox_outside_weights bbox_outside_weights = bbox_outside_weights \ .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2) assert bbox_outside_weights.shape[2] == height assert bbox_outside_weights.shape[3] == width top[3].reshape(*bbox_outside_weights.shape) top[3].data[...] = bbox_outside_weights
def _sample_rois(all_rois, gt_boxes, gt_ishard, dontcare_areas, fg_rois_per_image, rois_per_image, num_classes): """Generate a random sample of RoIs comprising foreground and background examples. """ # overlaps: (rois x gt_boxes) overlaps = bbox_overlaps( np.ascontiguousarray(all_rois[:, 1:5], dtype=np.float), np.ascontiguousarray(gt_boxes[:, :4], dtype=np.float)) gt_assignment = overlaps.argmax(axis=1) max_overlaps = overlaps.max(axis=1) labels = gt_boxes[gt_assignment, 4] # preclude hard samples ignore_inds = np.empty(shape=(0), dtype=int) if cfg.TRAIN.PRECLUDE_HARD_SAMPLES and gt_ishard is not None and gt_ishard.shape[ 0] > 0: gt_ishard = gt_ishard.astype(int) gt_hardboxes = gt_boxes[gt_ishard == 1, :] if gt_hardboxes.shape[0] > 0: # R x H hard_overlaps = bbox_overlaps( np.ascontiguousarray(all_rois[:, 1:5], dtype=np.float), np.ascontiguousarray(gt_hardboxes[:, :4], dtype=np.float)) hard_max_overlaps = hard_overlaps.max(axis=1) # R x 1 # hard_gt_assignment = hard_overlaps.argmax(axis=0) # H ignore_inds = np.append( ignore_inds, np.where(hard_max_overlaps >= cfg.TRAIN.FG_THRESH)[0]) # if DEBUG: # if ignore_inds.size > 1: # print 'num hard: {:d}:'.format(ignore_inds.size) # print 'hard box:', gt_hardboxes # print 'rois: ' # print all_rois[ignore_inds] # preclude dontcare areas if dontcare_areas is not None and dontcare_areas.shape[0] > 0: # intersec shape is D x R intersecs = bbox_intersections( np.ascontiguousarray(dontcare_areas, dtype=np.float), # D x 4 np.ascontiguousarray(all_rois[:, 1:5], dtype=np.float) # R x 4 ) intersecs_sum = intersecs.sum(axis=0) # R x 1 ignore_inds = np.append( ignore_inds, np.where( intersecs_sum > cfg.TRAIN.DONTCARE_AREA_INTERSECTION_HI)[0]) # if ignore_inds.size >= 1: # print 'num dontcare: {:d}:'.format(ignore_inds.size) # print 'dontcare box:', dontcare_areas.astype(int) # print 'rois: ' # print all_rois[ignore_inds].astype(int) # Select foreground RoIs as those with >= FG_THRESH overlap fg_inds = np.where(max_overlaps >= cfg.TRAIN.FG_THRESH)[0] fg_inds = np.setdiff1d(fg_inds, ignore_inds) # Guard against the case when an image has fewer than fg_rois_per_image # foreground RoIs fg_rois_per_this_image = min(fg_rois_per_image, fg_inds.size) # Sample foreground regions without replacement if fg_inds.size > 0: fg_inds = npr.choice(fg_inds, size=int(fg_rois_per_this_image), replace=False) # Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI) bg_inds = np.where((max_overlaps < cfg.TRAIN.BG_THRESH_HI) & (max_overlaps >= cfg.TRAIN.BG_THRESH_LO))[0] bg_inds = np.setdiff1d(bg_inds, ignore_inds) # Compute number of background RoIs to take from this image (guarding # against there being fewer than desired) bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image bg_rois_per_this_image = min(bg_rois_per_this_image, bg_inds.size) # Sample background regions without replacement if bg_inds.size > 0: bg_inds = npr.choice(bg_inds, size=int(bg_rois_per_this_image), replace=False) # The indices that we're selecting (both fg and bg) keep_inds = np.append(fg_inds, bg_inds) # Select sampled values from various arrays: labels = labels[keep_inds] # Clamp labels for the background RoIs to 0 labels[int(fg_rois_per_this_image):] = 0 rois = all_rois[keep_inds] bbox_target_data = _compute_targets(rois[:, 1:5], gt_boxes[gt_assignment[keep_inds], :4], labels) bbox_targets, bbox_inside_weights = \ _get_bbox_regression_labels(bbox_target_data, num_classes) return labels, rois, bbox_targets, bbox_inside_weights
def anchor_target_layer(rpn_cls_score, gt_boxes, gt_ishard, dontcare_areas, im_info, _feat_stride=[16, ], anchor_scales=[4, 8, 16, 32]): """ Assign anchors to ground-truth targets. Produces anchor classification labels and bounding-box regression targets. Parameters ---------- rpn_cls_score: for pytorch (1, Ax2, H, W) bg/fg scores of previous conv layer gt_boxes: (G, 5) vstack of [x1, y1, x2, y2, class] gt_ishard: (G, 1), 1 or 0 indicates difficult or not dontcare_areas: (D, 4), some areas may contains small objs but no labelling. D may be 0 im_info: a list of [image_height, image_width, scale_ratios] _feat_stride: the downsampling ratio of feature map to the original input image anchor_scales: the scales to the basic_anchor (basic anchor is [16, 16]) ---------- Returns ---------- rpn_labels : (HxWxA, 1), for each anchor, 0 denotes bg, 1 fg, -1 dontcare rpn_bbox_targets: (HxWxA, 4), distances of the anchors to the gt_boxes(may contains some transform) that are the regression objectives rpn_bbox_inside_weights: (HxWxA, 4) weights of each boxes, mainly accepts hyper param in cfg rpn_bbox_outside_weights: (HxWxA, 4) used to balance the fg/bg, beacuse the numbers of bgs and fgs mays significiantly different """ _anchors = generate_anchors(scales=np.array(anchor_scales)) _num_anchors = _anchors.shape[0] if DEBUG: print ('anchors:') print (_anchors) print ('anchor shapes:') print (np.hstack(( _anchors[:, 2::4] - _anchors[:, 0::4], _anchors[:, 3::4] - _anchors[:, 1::4], ))) _counts = cfg.EPS _sums = np.zeros((1, 4)) _squared_sums = np.zeros((1, 4)) _fg_sum = 0 _bg_sum = 0 _count = 0 # allow boxes to sit over the edge by a small amount _allowed_border = 0 # map of shape (..., H, W) # height, width = rpn_cls_score.shape[1:3] im_info = im_info[0] # Algorithm: # # for each (H, W) location i # generate 9 anchor boxes centered on cell i # apply predicted bbox deltas at cell i to each of the 9 anchors # filter out-of-image anchors # measure GT overlap assert rpn_cls_score.shape[0] == 1, \ 'Only single item batches are supported' # map of shape (..., H, W) # pytorch (bs, c, h, w) height, width = rpn_cls_score.shape[2:4] if DEBUG: print ('AnchorTargetLayer: height', height, 'width', width) print ('') print ('im_size: ({}, {})'.format(im_info[0], im_info[1])) print ('scale: {}'.format(im_info[2])) print ('height, width: ({}, {})'.format(height, width)) print ('rpn: gt_boxes.shape', gt_boxes.shape) print ('rpn: gt_boxes', gt_boxes) # 1. Generate proposals from bbox deltas and shifted anchors shift_x = np.arange(0, width) * _feat_stride shift_y = np.arange(0, height) * _feat_stride shift_x, shift_y = np.meshgrid(shift_x, shift_y) # in W H order # K is H x W shifts = np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(), shift_y.ravel())).transpose() # add A anchors (1, A, 4) to # cell K shifts (K, 1, 4) to get # shift anchors (K, A, 4) # reshape to (K*A, 4) shifted anchors A = _num_anchors K = shifts.shape[0] all_anchors = (_anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2))) all_anchors = all_anchors.reshape((K * A, 4)) total_anchors = int(K * A) # only keep anchors inside the image inds_inside = np.where( (all_anchors[:, 0] >= -_allowed_border) & (all_anchors[:, 1] >= -_allowed_border) & (all_anchors[:, 2] < im_info[1] + _allowed_border) & # width (all_anchors[:, 3] < im_info[0] + _allowed_border) # height )[0] if DEBUG: print ('total_anchors', total_anchors) print ('inds_inside', len(inds_inside)) # keep only inside anchors anchors = all_anchors[inds_inside, :] if DEBUG: print ('anchors.shape', anchors.shape) # label: 1 is positive, 0 is negative, -1 is dont care # (A) labels = np.empty((len(inds_inside),), dtype=np.float32) labels.fill(-1) # overlaps between the anchors and the gt boxes # overlaps (ex, gt), shape is A x G overlaps = bbox_overlaps( np.ascontiguousarray(anchors, dtype=np.float), np.ascontiguousarray(gt_boxes, dtype=np.float)) argmax_overlaps = overlaps.argmax(axis=1) # (A) max_overlaps = overlaps[np.arange(len(inds_inside)), argmax_overlaps] gt_argmax_overlaps = overlaps.argmax(axis=0) # G gt_max_overlaps = overlaps[gt_argmax_overlaps, np.arange(overlaps.shape[1])] gt_argmax_overlaps = np.where(overlaps == gt_max_overlaps)[0] if not cfg.TRAIN.RPN_CLOBBER_POSITIVES: # assign bg labels first so that positive labels can clobber them labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0 # fg label: for each gt, anchor with highest overlap labels[gt_argmax_overlaps] = 1 # fg label: above threshold IOU labels[max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1 if cfg.TRAIN.RPN_CLOBBER_POSITIVES: # assign bg labels last so that negative labels can clobber positives labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0 # preclude dontcare areas if dontcare_areas is not None and dontcare_areas.shape[0] > 0: # intersec shape is D x A intersecs = bbox_intersections( np.ascontiguousarray(dontcare_areas, dtype=np.float), # D x 4 np.ascontiguousarray(anchors, dtype=np.float) # A x 4 ) intersecs_ = intersecs.sum(axis=0) # A x 1 labels[intersecs_ > cfg.TRAIN.DONTCARE_AREA_INTERSECTION_HI] = -1 # preclude hard samples that are highly occlusioned, truncated or difficult to see if cfg.TRAIN.PRECLUDE_HARD_SAMPLES and gt_ishard is not None and gt_ishard.shape[0] > 0: assert gt_ishard.shape[0] == gt_boxes.shape[0] gt_ishard = gt_ishard.astype(int) gt_hardboxes = gt_boxes[gt_ishard == 1, :] if gt_hardboxes.shape[0] > 0: # H x A hard_overlaps = bbox_overlaps( np.ascontiguousarray(gt_hardboxes, dtype=np.float), # H x 4 np.ascontiguousarray(anchors, dtype=np.float)) # A x 4 hard_max_overlaps = hard_overlaps.max(axis=0) # (A) labels[hard_max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = -1 max_intersec_label_inds = hard_overlaps.argmax(axis=1) # H x 1 labels[max_intersec_label_inds] = -1 # # subsample positive labels if we have too many num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCHSIZE) fg_inds = np.where(labels == 1)[0] if len(fg_inds) > num_fg: disable_inds = npr.choice( fg_inds, size=(len(fg_inds) - num_fg), replace=False) labels[disable_inds] = -1 # subsample negative labels if we have too many num_bg = cfg.TRAIN.RPN_BATCHSIZE - np.sum(labels == 1) bg_inds = np.where(labels == 0)[0] if len(bg_inds) > num_bg: disable_inds = npr.choice( bg_inds, size=(len(bg_inds) - num_bg), replace=False) labels[disable_inds] = -1 # print "was %s inds, disabling %s, now %s inds" % ( # len(bg_inds), len(disable_inds), np.sum(labels == 0)) # bbox_targets = np.zeros((len(inds_inside), 4), dtype=np.float32) bbox_targets = _compute_targets(anchors, gt_boxes[argmax_overlaps, :]) bbox_inside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32) bbox_inside_weights[labels == 1, :] = np.array(cfg.TRAIN.RPN_BBOX_INSIDE_WEIGHTS) bbox_outside_weights = np.zeros((len(inds_inside), 4), dtype=np.float32) if cfg.TRAIN.RPN_POSITIVE_WEIGHT < 0: # uniform weighting of examples (given non-uniform sampling) # num_examples = np.sum(labels >= 0) + 1 # positive_weights = np.ones((1, 4)) * 1.0 / num_examples # negative_weights = np.ones((1, 4)) * 1.0 / num_examples positive_weights = np.ones((1, 4)) negative_weights = np.zeros((1, 4)) else: assert ((cfg.TRAIN.RPN_POSITIVE_WEIGHT > 0) & (cfg.TRAIN.RPN_POSITIVE_WEIGHT < 1)) positive_weights = (cfg.TRAIN.RPN_POSITIVE_WEIGHT / (np.sum(labels == 1)) + 1) negative_weights = ((1.0 - cfg.TRAIN.RPN_POSITIVE_WEIGHT) / (np.sum(labels == 0)) + 1) bbox_outside_weights[labels == 1, :] = positive_weights bbox_outside_weights[labels == 0, :] = negative_weights if DEBUG: _sums += bbox_targets[labels == 1, :].sum(axis=0) _squared_sums += (bbox_targets[labels == 1, :] ** 2).sum(axis=0) _counts += np.sum(labels == 1) means = _sums / _counts stds = np.sqrt(_squared_sums / _counts - means ** 2) print ('means:') print (means) print ('stdevs:') print (stds) # map up to original set of anchors labels = _unmap(labels, total_anchors, inds_inside, fill=-1) bbox_targets = _unmap(bbox_targets, total_anchors, inds_inside, fill=0) bbox_inside_weights = _unmap(bbox_inside_weights, total_anchors, inds_inside, fill=0) bbox_outside_weights = _unmap(bbox_outside_weights, total_anchors, inds_inside, fill=0) if DEBUG: print ('rpn: max max_overlap', np.max(max_overlaps)) print ('rpn: num_positive', np.sum(labels == 1)) print ('rpn: num_negative', np.sum(labels == 0)) _fg_sum += np.sum(labels == 1) _bg_sum += np.sum(labels == 0) _count += 1 print ('rpn: num_positive avg', _fg_sum / _count) print ('rpn: num_negative avg', _bg_sum / _count) # labels # pdb.set_trace() labels = labels.reshape((1, height, width, A)) labels = labels.transpose(0, 3, 1, 2) rpn_labels = labels.reshape((1, 1, A * height, width)).transpose(0, 2, 3, 1) # bbox_targets bbox_targets = bbox_targets \ .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2) rpn_bbox_targets = bbox_targets # bbox_inside_weights bbox_inside_weights = bbox_inside_weights \ .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2) # assert bbox_inside_weights.shape[2] == height # assert bbox_inside_weights.shape[3] == width rpn_bbox_inside_weights = bbox_inside_weights # bbox_outside_weights bbox_outside_weights = bbox_outside_weights \ .reshape((1, height, width, A * 4)).transpose(0, 3, 1, 2) # assert bbox_outside_weights.shape[2] == height # assert bbox_outside_weights.shape[3] == width rpn_bbox_outside_weights = bbox_outside_weights return rpn_labels, rpn_bbox_targets, rpn_bbox_inside_weights, rpn_bbox_outside_weights