def find_top_rpn_proposals(self, rpn_cls_score_list, rpn_bbox_offset_list,
anchors_list, im_info):
prev_nms_top_n = (self.cfg.train_prev_nms_top_n
if self.training else self.cfg.test_prev_nms_top_n)
post_nms_top_n = (self.cfg.train_post_nms_top_n
if self.training else self.cfg.test_post_nms_top_n)
return_rois = []
for bid in range(im_info.shape[0]):
batch_proposal_list = []
batch_score_list = []
batch_level_list = []
for l, (rpn_cls_score, rpn_bbox_offset, anchors) in enumerate(
zip(rpn_cls_score_list, rpn_bbox_offset_list,
anchors_list)):
# get proposals and scores
offsets = rpn_bbox_offset[bid].transpose(2, 3, 0,
1).reshape(-1, 4)
proposals = self.box_coder.decode(anchors, offsets)
scores = rpn_cls_score[bid].transpose(1, 2, 0).flatten()
scores.detach()
# prev nms top n
scores, order = F.topk(scores,
descending=True,
k=prev_nms_top_n)
proposals = proposals[order, :]
batch_proposal_list.append(proposals)
batch_score_list.append(scores)
batch_level_list.append(F.full_like(scores, l))
# gather proposals, scores, level
proposals = F.concat(batch_proposal_list, axis=0)
scores = F.concat(batch_score_list, axis=0)
levels = F.concat(batch_level_list, axis=0)
proposals = layers.get_clipped_boxes(proposals, im_info[bid])
# filter invalid proposals and apply total level nms
keep_mask = layers.filter_boxes(proposals)
_, keep_inds = F.cond_take(keep_mask == 1, keep_mask)
proposals = proposals[keep_inds, :]
scores = scores[keep_inds]
levels = levels[keep_inds]
nms_keep_inds = layers.batched_nms(proposals, scores, levels,
self.cfg.rpn_nms_threshold,
post_nms_top_n)
# generate rois to rcnn head, rois shape (N, 5), info [batch_id, x1, y1, x2, y2]
rois = F.concat([proposals, scores.reshape(-1, 1)], axis=1)
rois = rois[nms_keep_inds]
batch_inds = F.full((rois.shape[0], 1), bid)
batch_rois = F.concat([batch_inds, rois[:, :4]], axis=1)
return_rois.append(batch_rois)
return_rois = F.concat(return_rois, axis=0)
return return_rois.detach()
def __call__(self, matrix):
"""
matrix(tensor): A two dim tensor with shape of (N, M). N is number of GT-boxes,
while M is the number of anchors in detection.
"""
assert len(matrix.shape) == 2
max_scores = matrix.max(axis=0)
match_indices = F.argmax(matrix, axis=0)
# default ignore label: -1
labels = F.full_like(match_indices, -1)
for label, low, high in zip(self.labels, self.thresholds[:-1],
self.thresholds[1:]):
mask = (max_scores >= low) & (max_scores < high)
labels[mask] = label
if self.allow_low_quality_matches:
mask = (matrix == F.max(matrix, axis=1,
keepdims=True)).sum(axis=0) > 0
labels[mask] = 1
return match_indices, labels