def anchor_target_layer(rpn_cls_score, gt_boxes, gt_ishard, dontcare_areas, im_info, _feat_stride, anchor_scales):
"""
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 : (1, 1, HxA, W), for each anchor, 0 denotes bg, 1 fg, -1 dontcare
rpn_bbox_targets: (1, 4xA, H, W), distances of the anchors to the gt_boxes(may contains some transform)
that are the regression objectives
rpn_bbox_inside_weights: (1, 4xA, H, W) weights of each boxes, mainly accepts hyper param in cfg
rpn_bbox_outside_weights: (1, 4xA, H, W) used to balance the fg/bg,
beacuse the numbers of bgs and fgs mays significiantly different
"""
rpn_cls_score = rpn_cls_score.data.cpu().numpy()
rpn_labels, rpn_bbox_targets, rpn_bbox_inside_weights, rpn_bbox_outside_weights = \
anchor_target_layer_py(rpn_cls_score, gt_boxes, gt_ishard, dontcare_areas, im_info, _feat_stride, anchor_scales)
rpn_labels = network.np_to_variable(rpn_labels, is_cuda=True, dtype=torch.LongTensor)
rpn_bbox_targets = network.np_to_variable(rpn_bbox_targets, is_cuda=True)
rpn_bbox_inside_weights = network.np_to_variable(rpn_bbox_inside_weights, is_cuda=True)
rpn_bbox_outside_weights = network.np_to_variable(rpn_bbox_outside_weights, is_cuda=True)
return rpn_labels, rpn_bbox_targets, rpn_bbox_inside_weights, rpn_bbox_outside_weights
评论列表
文章目录
