def draw_proposal_recall(img, proposals, proposal_scores, gt_boxes):
"""
Draw top3 proposals for each gt.
Args:
proposals: NPx4
proposal_scores: NP
gt_boxes: NG
"""
bbox_iou_float = get_iou_callable()
box_ious = bbox_iou_float(gt_boxes, proposals) # ng x np
box_ious_argsort = np.argsort(-box_ious, axis=1)
good_proposals_ind = box_ious_argsort[:, :3] # for each gt, find 3 best proposals
good_proposals_ind = np.unique(good_proposals_ind.ravel())
proposals = proposals[good_proposals_ind, :]
tags = list(map(str, proposal_scores[good_proposals_ind]))
img = viz.draw_boxes(img, proposals, tags)
return img, good_proposals_ind
def get_anchor_labels(anchors, gt_boxes, crowd_boxes):
"""
Label each anchor as fg/bg/ignore.
Args:
anchors: Ax4 float
gt_boxes: Bx4 float
crowd_boxes: Cx4 float
Returns:
anchor_labels: (A,) int. Each element is {-1, 0, 1}
anchor_boxes: Ax4. Contains the target gt_box for each anchor when the anchor is fg.
"""
# This function will modify labels and return the filtered inds
def filter_box_label(labels, value, max_num):
curr_inds = np.where(labels == value)[0]
if len(curr_inds) > max_num:
disable_inds = np.random.choice(
curr_inds, size=(len(curr_inds) - max_num),
replace=False)
labels[disable_inds] = -1 # ignore them
curr_inds = np.where(labels == value)[0]
return curr_inds
bbox_iou_float = get_iou_callable()
NA, NB = len(anchors), len(gt_boxes)
assert NB > 0 # empty images should have been filtered already
box_ious = bbox_iou_float(anchors, gt_boxes) # NA x NB
ious_argmax_per_anchor = box_ious.argmax(axis=1) # NA,
ious_max_per_anchor = box_ious.max(axis=1)
ious_max_per_gt = np.amax(box_ious, axis=0, keepdims=True) # 1xNB
# for each gt, find all those anchors (including ties) that has the max ious with it
anchors_with_max_iou_per_gt = np.where(box_ious == ious_max_per_gt)[0]
# Setting NA labels: 1--fg 0--bg -1--ignore
anchor_labels = -np.ones((NA,), dtype='int32') # NA,
# the order of setting neg/pos labels matter
anchor_labels[anchors_with_max_iou_per_gt] = 1
anchor_labels[ious_max_per_anchor >= config.POSITIVE_ANCHOR_THRES] = 1
anchor_labels[ious_max_per_anchor < config.NEGATIVE_ANCHOR_THRES] = 0
# First label all non-ignore candidate boxes which overlap crowd as ignore
if crowd_boxes.size > 0:
cand_inds = np.where(anchor_labels >= 0)[0]
cand_anchors = anchors[cand_inds]
ious = bbox_iou_float(cand_anchors, crowd_boxes)
overlap_with_crowd = cand_inds[ious.max(axis=1) > config.CROWD_OVERLAP_THRES]
anchor_labels[overlap_with_crowd] = -1
# Filter fg labels: ignore some fg if fg is too many
old_num_fg = np.sum(anchor_labels == 1)
target_num_fg = int(config.RPN_BATCH_PER_IM * config.RPN_FG_RATIO)
fg_inds = filter_box_label(anchor_labels, 1, target_num_fg)
# Note that fg could be fewer than the target ratio
# filter bg labels. num_bg is not allowed to be too many
old_num_bg = np.sum(anchor_labels == 0)
if old_num_bg == 0 or len(fg_inds) == 0:
# No valid bg/fg in this image, skip.
# This can happen if, e.g. the image has large crowd.
raise MalformedData("No valid foreground/background for RPN!")
target_num_bg = config.RPN_BATCH_PER_IM - len(fg_inds)
bg_inds = filter_box_label(anchor_labels, 0, target_num_bg)
# Set anchor boxes: the best gt_box for each fg anchor
anchor_boxes = np.zeros((NA, 4), dtype='float32')
fg_boxes = gt_boxes[ious_argmax_per_anchor[fg_inds], :]
anchor_boxes[fg_inds, :] = fg_boxes
return anchor_labels, anchor_boxes