def select_over_all_levels(self, boxlists):
num_images = len(boxlists)
results = []
for i in range(num_images):
# multiclass nms
result = boxlist_ml_nms(boxlists[i], self.nms_thresh)
number_of_detections = len(result)
# Limit to max_per_image detections **over all classes**
if number_of_detections > self.fpn_post_nms_top_n > 0:
cls_scores = result.get_field("scores")
image_thresh, _ = torch.kthvalue(
cls_scores.cpu(),
number_of_detections - self.fpn_post_nms_top_n + 1)
keep = cls_scores >= image_thresh.item()
keep = torch.nonzero(keep).squeeze(1)
result = result[keep]
if self.score_voting:
boxes_al = boxlists[i].bbox
boxlist = boxlists[i]
labels = boxlists[i].get_field("labels")
scores = boxlists[i].get_field("scores")
sigma = 0.025
result_labels = result.get_field("labels")
for j in range(1, self.num_classes):
inds = (labels == j).nonzero().view(-1)
scores_j = scores[inds]
boxes_j = boxes_al[inds, :].view(-1, 4)
boxlist_for_class = BoxList(boxes_j,
boxlist.size,
mode="xyxy")
result_inds = (result_labels == j).nonzero().view(-1)
boxlist_for_class_nmsed = result[result_inds]
ious = boxlist_iou(boxlist_for_class_nmsed,
boxlist_for_class)
voted_boxes = []
for bi in range(len(boxlist_for_class_nmsed)):
cur_ious = ious[bi]
pos_inds = (cur_ious > 0.01).nonzero().squeeze(1)
pos_ious = cur_ious[pos_inds]
pos_boxes = boxlist_for_class.bbox[pos_inds]
pos_scores = scores_j[pos_inds]
pis = (torch.exp(-(1 - pos_ious)**2 / sigma) *
pos_scores).unsqueeze(1)
voted_box = torch.sum(pos_boxes * pis,
dim=0) / torch.sum(pis, dim=0)
voted_boxes.append(voted_box.unsqueeze(0))
if voted_boxes:
voted_boxes = torch.cat(voted_boxes, dim=0)
boxlist_for_class_nmsed_ = BoxList(
voted_boxes,
boxlist_for_class_nmsed.size,
mode="xyxy")
boxlist_for_class_nmsed_.add_field(
"scores",
boxlist_for_class_nmsed.get_field('scores'))
result.bbox[
result_inds] = boxlist_for_class_nmsed_.bbox
results.append(result)
return results
def match_targets_to_anchors(self, anchor, target, copied_fields=[]):
match_quality_matrix = boxlist_iou(target, anchor)
matched_idxs, _ = self.proposal_matcher(match_quality_matrix)
target = target.copy_with_fields(copied_fields)
matched_targets = target[matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
return matched_targets
def prepare_iou_based_targets(self, targets, anchors):
"""Compute IoU-based targets"""
cls_labels = []
reg_targets = []
matched_idx_all = []
for im_i in range(len(targets)):
targets_per_im = targets[im_i]
assert targets_per_im.mode == "xyxy"
anchors_per_im = cat_boxlist(anchors[im_i])
match_quality_matrix = boxlist_iou(targets_per_im, anchors_per_im)
matched_idxs, _ = self.matcher(match_quality_matrix)
targets_per_im = targets_per_im.copy_with_fields(['labels'])
matched_targets = targets_per_im[matched_idxs.clamp(min=0)]
cls_labels_per_im = matched_targets.get_field("labels")
cls_labels_per_im = cls_labels_per_im.to(dtype=torch.float32)
# Background (negative examples)
bg_indices = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
cls_labels_per_im[bg_indices] = 0
# discard indices that are between thresholds
inds_to_discard = matched_idxs == Matcher.BETWEEN_THRESHOLDS
cls_labels_per_im[inds_to_discard] = -1
matched_gts = matched_targets.bbox
matched_idx_all.append(matched_idxs.view(1, -1))
reg_targets_per_im = self.box_coder.encode(matched_gts, anchors_per_im.bbox)
cls_labels.append(cls_labels_per_im)
reg_targets.append(reg_targets_per_im)
return cls_labels, reg_targets, matched_idx_all
def match_targets_to_proposals(self, proposal, target):
match_quality_matrix = boxlist_iou(target, proposal)
matched_idxs, _ = self.proposal_matcher(match_quality_matrix)
# Mask RCNN needs "labels" and "masks "fields for creating the targets
target = target.copy_with_fields(["labels", "masks"])
# get the targets corresponding GT for each proposal
# NB: need to clamp the indices because we can have a single
# GT in the image, and matched_idxs can be -2, which goes
# out of bounds
matched_targets = target[matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
return matched_targets
def match_targets_to_anchors(self, anchor, target, copied_fields=[]):
match_quality_matrix = boxlist_iou(target, anchor)
matched_idxs, _ = self.proposal_matcher(match_quality_matrix)
# RPN doesn't need any fields from target
# for creating the labels, so clear them all
target = target.copy_with_fields(copied_fields)
# get the targets corresponding GT for each anchor
# NB: need to clamp the indices because we can have a single
# GT in the image, and matched_idxs can be -2, which goes
# out of bounds
matched_targets = target[matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
return matched_targets
def evaluate_box_proposals(predictions,
dataset,
thresholds=None,
area="all",
limit=None):
"""Evaluate detection proposal recall metrics. This function is a much
faster alternative to the official COCO API recall evaluation code. However,
it produces slightly different results.
"""
# Record max overlap value for each gt box
# Return vector of overlap values
areas = {
"all": 0,
"small": 1,
"medium": 2,
"large": 3,
"96-128": 4,
"128-256": 5,
"256-512": 6,
"512-inf": 7,
}
area_ranges = [
[0**2, 1e5**2], # all
[0**2, 32**2], # small
[32**2, 96**2], # medium
[96**2, 1e5**2], # large
[96**2, 128**2], # 96-128
[128**2, 256**2], # 128-256
[256**2, 512**2], # 256-512
[512**2, 1e5**2],
] # 512-inf
assert area in areas, "Unknown area range: {}".format(area)
area_range = area_ranges[areas[area]]
gt_overlaps = []
num_pos = 0
for image_id, prediction in enumerate(predictions):
original_id = dataset.id_to_img_map[image_id]
img_info = dataset.get_img_info(image_id)
image_width = img_info["width"]
image_height = img_info["height"]
prediction = prediction.resize((image_width, image_height))
# sort predictions in descending order
# TODO maybe remove this and make it explicit in the documentation
inds = prediction.get_field("objectness").sort(descending=True)[1]
prediction = prediction[inds]
ann_ids = dataset.coco.getAnnIds(imgIds=original_id)
anno = dataset.coco.loadAnns(ann_ids)
gt_boxes = [obj["bbox"] for obj in anno if obj["iscrowd"] == 0]
gt_boxes = torch.as_tensor(gt_boxes).reshape(
-1, 4) # guard against no boxes
gt_boxes = BoxList(gt_boxes, (image_width, image_height),
mode="xywh").convert("xyxy")
gt_areas = torch.as_tensor(
[obj["area"] for obj in anno if obj["iscrowd"] == 0])
if len(gt_boxes) == 0:
continue
valid_gt_inds = (gt_areas >= area_range[0]) & (gt_areas <=
area_range[1])
gt_boxes = gt_boxes[valid_gt_inds]
num_pos += len(gt_boxes)
if len(gt_boxes) == 0:
continue
if len(prediction) == 0:
continue
if limit is not None and len(prediction) > limit:
prediction = prediction[:limit]
overlaps = boxlist_iou(prediction, gt_boxes)
_gt_overlaps = torch.zeros(len(gt_boxes))
for j in range(min(len(prediction), len(gt_boxes))):
# find which proposal box maximally covers each gt box
# and get the iou amount of coverage for each gt box
max_overlaps, argmax_overlaps = overlaps.max(dim=0)
# find which gt box is 'best' covered (i.e. 'best' = most iou)
gt_ovr, gt_ind = max_overlaps.max(dim=0)
assert gt_ovr >= 0
# find the proposal box that covers the best covered gt box
box_ind = argmax_overlaps[gt_ind]
# record the iou coverage of this gt box
_gt_overlaps[j] = overlaps[box_ind, gt_ind]
assert _gt_overlaps[j] == gt_ovr
# mark the proposal box and the gt box as used
overlaps[box_ind, :] = -1
overlaps[:, gt_ind] = -1
# append recorded iou coverage level
gt_overlaps.append(_gt_overlaps)
gt_overlaps = torch.cat(gt_overlaps, dim=0)
gt_overlaps, _ = torch.sort(gt_overlaps)
if thresholds is None:
step = 0.05
thresholds = torch.arange(0.5, 0.95 + 1e-5, step, dtype=torch.float32)
recalls = torch.zeros_like(thresholds)
# compute recall for each iou threshold
for i, t in enumerate(thresholds):
recalls[i] = (gt_overlaps >= t).float().sum() / float(num_pos)
# ar = 2 * np.trapz(recalls, thresholds)
ar = recalls.mean()
return {
"ar": ar,
"recalls": recalls,
"thresholds": thresholds,
"gt_overlaps": gt_overlaps,
"num_pos": num_pos,
}
def prepare_targets(self, targets, anchors):
cls_labels = []
reg_targets = []
for im_i in range(len(targets)):
targets_per_im = targets[im_i]
assert targets_per_im.mode == "xyxy"
bboxes_per_im = targets_per_im.bbox
labels_per_im = targets_per_im.get_field("labels")
anchors_per_im = cat_boxlist(anchors[im_i])
num_gt = bboxes_per_im.shape[0]
if self.positive_type == 'SSC':
object_sizes_of_interest = [[-1, 64], [64, 128], [128, 256],
[256, 512], [512, INF]]
area_per_im = targets_per_im.area()
expanded_object_sizes_of_interest = []
points = []
for l, anchors_per_level in enumerate(anchors[im_i]):
anchors_per_level = anchors_per_level.bbox
anchors_cx_per_level = (anchors_per_level[:, 2] +
anchors_per_level[:, 0]) / 2.0
anchors_cy_per_level = (anchors_per_level[:, 3] +
anchors_per_level[:, 1]) / 2.0
points_per_level = torch.stack(
(anchors_cx_per_level, anchors_cy_per_level), dim=1)
points.append(points_per_level)
object_sizes_of_interest_per_level = \
points_per_level.new_tensor(object_sizes_of_interest[l])
expanded_object_sizes_of_interest.append(
object_sizes_of_interest_per_level[None].expand(
len(points_per_level), -1))
expanded_object_sizes_of_interest = torch.cat(
expanded_object_sizes_of_interest, dim=0)
points = torch.cat(points, dim=0)
xs, ys = points[:, 0], points[:, 1]
l = xs[:, None] - bboxes_per_im[:, 0][None]
t = ys[:, None] - bboxes_per_im[:, 1][None]
r = bboxes_per_im[:, 2][None] - xs[:, None]
b = bboxes_per_im[:, 3][None] - ys[:, None]
reg_targets_per_im = torch.stack([l, t, r, b], dim=2)
is_in_boxes = reg_targets_per_im.min(dim=2)[0] > 0.01
max_reg_targets_per_im = reg_targets_per_im.max(dim=2)[0]
is_cared_in_the_level = \
(max_reg_targets_per_im >= expanded_object_sizes_of_interest[:, [0]]) & \
(max_reg_targets_per_im <= expanded_object_sizes_of_interest[:, [1]])
locations_to_gt_area = area_per_im[None].repeat(len(points), 1)
locations_to_gt_area[is_in_boxes == 0] = INF
locations_to_gt_area[is_cared_in_the_level == 0] = INF
locations_to_min_area, locations_to_gt_inds = locations_to_gt_area.min(
dim=1)
cls_labels_per_im = labels_per_im[locations_to_gt_inds]
cls_labels_per_im[locations_to_min_area == INF] = 0
matched_gts = bboxes_per_im[locations_to_gt_inds]
elif self.positive_type == 'ATSS':
num_anchors_per_level = [
len(anchors_per_level.bbox)
for anchors_per_level in anchors[im_i]
]
ious = boxlist_iou(anchors_per_im, targets_per_im)
gt_cx = (bboxes_per_im[:, 2] + bboxes_per_im[:, 0]) / 2.0
gt_cy = (bboxes_per_im[:, 3] + bboxes_per_im[:, 1]) / 2.0
gt_points = torch.stack((gt_cx, gt_cy), dim=1)
anchors_cx_per_im = (anchors_per_im.bbox[:, 2] +
anchors_per_im.bbox[:, 0]) / 2.0
anchors_cy_per_im = (anchors_per_im.bbox[:, 3] +
anchors_per_im.bbox[:, 1]) / 2.0
anchor_points = torch.stack(
(anchors_cx_per_im, anchors_cy_per_im), dim=1)
distances = (anchor_points[:, None, :] -
gt_points[None, :, :]).pow(2).sum(-1).sqrt()
# Selecting candidates based on the center distance between anchor box and object
candidate_idxs = []
star_idx = 0
for level, anchors_per_level in enumerate(anchors[im_i]):
end_idx = star_idx + num_anchors_per_level[level]
distances_per_level = distances[star_idx:end_idx, :]
_, topk_idxs_per_level = distances_per_level.topk(
self.topk, dim=0, largest=False)
candidate_idxs.append(topk_idxs_per_level + star_idx)
star_idx = end_idx
candidate_idxs = torch.cat(candidate_idxs, dim=0)
# Using the sum of mean and standard deviation as the IoU threshold to select final positive samples
candidate_ious = ious[candidate_idxs, torch.arange(num_gt)]
iou_mean_per_gt = candidate_ious.mean(0)
iou_std_per_gt = candidate_ious.std(0)
iou_thresh_per_gt = iou_mean_per_gt + iou_std_per_gt
is_pos = candidate_ious >= iou_thresh_per_gt[None, :]
# Limiting the final positive samples’ center to object
anchor_num = anchors_cx_per_im.shape[0]
for ng in range(num_gt):
candidate_idxs[:, ng] += ng * anchor_num
e_anchors_cx = anchors_cx_per_im.view(1, -1).expand(
num_gt, anchor_num).contiguous().view(-1)
e_anchors_cy = anchors_cy_per_im.view(1, -1).expand(
num_gt, anchor_num).contiguous().view(-1)
candidate_idxs = candidate_idxs.view(-1)
l = e_anchors_cx[candidate_idxs].view(
-1, num_gt) - bboxes_per_im[:, 0]
t = e_anchors_cy[candidate_idxs].view(
-1, num_gt) - bboxes_per_im[:, 1]
r = bboxes_per_im[:, 2] - e_anchors_cx[candidate_idxs].view(
-1, num_gt)
b = bboxes_per_im[:, 3] - e_anchors_cy[candidate_idxs].view(
-1, num_gt)
is_in_gts = torch.stack([l, t, r, b],
dim=1).min(dim=1)[0] > 0.01
is_pos = is_pos & is_in_gts
# if an anchor box is assigned to multiple gts, the one with the highest IoU will be selected.
ious_inf = torch.full_like(ious,
-INF).t().contiguous().view(-1)
index = candidate_idxs.view(-1)[is_pos.view(-1)]
ious_inf[index] = ious.t().contiguous().view(-1)[index]
ious_inf = ious_inf.view(num_gt, -1).t()
anchors_to_gt_values, anchors_to_gt_indexs = ious_inf.max(
dim=1)
cls_labels_per_im = labels_per_im[anchors_to_gt_indexs]
cls_labels_per_im[anchors_to_gt_values == -INF] = 0
matched_gts = bboxes_per_im[anchors_to_gt_indexs]
elif self.positive_type == 'IoU':
match_quality_matrix = boxlist_iou(targets_per_im,
anchors_per_im)
matched_idxs = self.matcher(match_quality_matrix)
targets_per_im = targets_per_im.copy_with_fields(['labels'])
matched_targets = targets_per_im[matched_idxs.clamp(min=0)]
cls_labels_per_im = matched_targets.get_field("labels")
cls_labels_per_im = cls_labels_per_im.to(dtype=torch.float32)
# Background (negative examples)
bg_indices = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
cls_labels_per_im[bg_indices] = 0
# discard indices that are between thresholds
inds_to_discard = matched_idxs == Matcher.BETWEEN_THRESHOLDS
cls_labels_per_im[inds_to_discard] = -1
matched_gts = matched_targets.bbox
# Limiting positive samples’ center to object
# in order to filter out poor positives and use the centerness branch
pos_idxs = torch.nonzero(cls_labels_per_im > 0).squeeze(1)
pos_anchors_cx = (anchors_per_im.bbox[pos_idxs, 2] +
anchors_per_im.bbox[pos_idxs, 0]) / 2.0
pos_anchors_cy = (anchors_per_im.bbox[pos_idxs, 3] +
anchors_per_im.bbox[pos_idxs, 1]) / 2.0
l = pos_anchors_cx - matched_gts[pos_idxs, 0]
t = pos_anchors_cy - matched_gts[pos_idxs, 1]
r = matched_gts[pos_idxs, 2] - pos_anchors_cx
b = matched_gts[pos_idxs, 3] - pos_anchors_cy
is_in_gts = torch.stack([l, t, r, b],
dim=1).min(dim=1)[0] > 0.01
cls_labels_per_im[pos_idxs[is_in_gts == 0]] = -1
else:
raise NotImplementedError
reg_targets_per_im = self.box_coder.encode(matched_gts,
anchors_per_im.bbox)
cls_labels.append(cls_labels_per_im)
reg_targets.append(reg_targets_per_im)
return cls_labels, reg_targets