def match_targets_to_proposals(self, proposal, target):
match_quality_matrix = boxlist_iou(target, proposal)
matched_idxs = self.proposal_matcher(match_quality_matrix)
# Fast RCNN only need "labels" field for selecting the targets
target = target.copy_with_fields("labels")
# get the targets corresponding GT for each proposal
matched_targets = target[matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
return matched_targets
def __call__(self,
proposals,
source_score,
labels,
device,
return_targets=False):
gt_boxes = torch.zeros((0, 4), dtype=torch.float, device=device)
gt_classes = torch.zeros((0, 1), dtype=torch.long, device=device)
gt_scores = torch.zeros((0, 1), dtype=torch.float, device=device)
# not using the background class
_prob = source_score[:, 1:].clone()
_labels = labels[1:]
positive_classes = _labels.eq(1).nonzero(as_tuple=False)[:, 0]
for c in positive_classes:
cls_prob = _prob[:, c]
max_index = torch.argmax(cls_prob)
gt_boxes = torch.cat(
(gt_boxes, proposals.bbox[max_index].view(1, -1)), dim=0)
gt_classes = torch.cat((gt_classes, c.add(1).view(1, 1)), dim=0)
gt_scores = torch.cat((gt_scores, cls_prob[max_index].view(1, 1)),
dim=0)
_prob[max_index].fill_(0)
if return_targets == True:
gt_boxes = BoxList(gt_boxes, proposals.size, mode=proposals.mode)
gt_boxes.add_field('labels', gt_classes[:, 0].float())
# gt_boxes.add_field('difficult', bb)
return gt_boxes
if gt_boxes.shape[0] == 0:
num_rois = len(source_score)
pseudo_labels = torch.zeros(num_rois,
dtype=torch.long,
device=device)
loss_weights = torch.zeros(num_rois,
dtype=torch.float,
device=device)
else:
gt_boxes = BoxList(gt_boxes, proposals.size, mode=proposals.mode)
overlaps = boxlist_iou(proposals, gt_boxes)
max_overlaps, gt_assignment = overlaps.max(dim=1)
pseudo_labels = gt_classes[gt_assignment, 0]
loss_weights = gt_scores[gt_assignment, 0]
# Select background RoIs as those with <= FG_IOU_THRESHOLD
bg_inds = max_overlaps.le(
cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD).nonzero(
as_tuple=False)[:, 0]
pseudo_labels[bg_inds] = 0
# PCL_TRICK:
# ignore_thres = 0.1
# ignore_inds = max_overlaps.le(ignore_thres).nonzero(as_tuple=False)[:,0]
# loss_weights[ignore_inds] = 0
return pseudo_labels, loss_weights
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 calc_detection_voc_prec_rec(gt_boxlists, pred_boxlists, iou_thresh=0.5):
"""Calculate precision and recall based on evaluation code of PASCAL VOC.
This function calculates precision and recall of
predicted bounding boxes obtained from a dataset which has :math:`N`
images.
The code is based on the evaluation code used in PASCAL VOC Challenge.
"""
n_pos = defaultdict(int)
score = defaultdict(list)
match = defaultdict(list)
for gt_boxlist, pred_boxlist in zip(gt_boxlists, pred_boxlists):
pred_bbox = pred_boxlist.bbox.numpy()
pred_label = pred_boxlist.get_field("labels").numpy()
pred_score = pred_boxlist.get_field("scores").numpy()
gt_bbox = gt_boxlist.bbox.numpy()
gt_label = gt_boxlist.get_field("labels").numpy()
gt_difficult = gt_boxlist.get_field("difficult").numpy()
for l in np.unique(np.concatenate((pred_label, gt_label)).astype(int)):
pred_mask_l = pred_label == l
pred_bbox_l = pred_bbox[pred_mask_l]
pred_score_l = pred_score[pred_mask_l]
# sort by score
order = pred_score_l.argsort()[::-1]
pred_bbox_l = pred_bbox_l[order]
pred_score_l = pred_score_l[order]
gt_mask_l = gt_label == l
gt_bbox_l = gt_bbox[gt_mask_l]
gt_difficult_l = gt_difficult[gt_mask_l]
n_pos[l] += np.logical_not(gt_difficult_l).sum()
score[l].extend(pred_score_l)
if len(pred_bbox_l) == 0:
continue
if len(gt_bbox_l) == 0:
match[l].extend((0, ) * pred_bbox_l.shape[0])
continue
# VOC evaluation follows integer typed bounding boxes.
pred_bbox_l = pred_bbox_l.copy()
pred_bbox_l[:, 2:] += 1
gt_bbox_l = gt_bbox_l.copy()
gt_bbox_l[:, 2:] += 1
iou = boxlist_iou(
BoxList(pred_bbox_l, gt_boxlist.size),
BoxList(gt_bbox_l, gt_boxlist.size),
).numpy()
gt_index = iou.argmax(axis=1)
# set -1 if there is no matching ground truth
gt_index[iou.max(axis=1) < iou_thresh] = -1
del iou
selec = np.zeros(gt_bbox_l.shape[0], dtype=bool)
for gt_idx in gt_index:
if gt_idx >= 0:
if gt_difficult_l[gt_idx]:
match[l].append(-1)
else:
if not selec[gt_idx]:
match[l].append(1)
else:
match[l].append(0)
selec[gt_idx] = True
else:
match[l].append(0)
n_fg_class = max(n_pos.keys()) + 1
prec = [None] * n_fg_class
rec = [None] * n_fg_class
for l in n_pos.keys():
score_l = np.array(score[l])
match_l = np.array(match[l], dtype=np.int8)
order = score_l.argsort()[::-1]
match_l = match_l[order]
tp = np.cumsum(match_l == 1)
fp = np.cumsum(match_l == 0)
# If an element of fp + tp is 0,
# the corresponding element of prec[l] is nan.
prec[l] = tp / (fp + tp)
# If n_pos[l] is 0, rec[l] is None.
if n_pos[l] > 0:
rec[l] = tp / n_pos[l]
return prec, rec
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 __call__(self,
proposals,
source_score,
labels,
device,
return_targets=False):
num_rois = len(proposals)
k = int(num_rois * self.portion)
num_gt_cls = labels[1:].sum()
if num_gt_cls != 0 and num_rois != 0:
cls_prob = source_score[:, 1:]
gt_cls_inds = labels[1:].nonzero(as_tuple=False)[:, 0]
sorted_scores, max_inds = cls_prob[:, gt_cls_inds].sort(
dim=0, descending=True)
sorted_scores = sorted_scores[:k]
max_inds = max_inds[:k]
_boxes = proposals.bbox[max_inds.t().contiguous().view(-1)].view(
num_gt_cls.int(), -1, 4)
_boxes = BatchBoxList(_boxes, proposals.size, mode=proposals.mode)
ious = batch_boxlist_iou(_boxes, _boxes)
k_ind = torch.zeros(num_gt_cls.int(),
k,
dtype=torch.bool,
device=device)
k_ind[:, 0] = 1 # always take the one with max score
for ii in range(1, k):
max_iou, _ = torch.max(ious[:, ii:ii + 1, :ii], dim=2)
k_ind[:, ii] = (max_iou < self.iou_th).byte().squeeze(-1)
gt_boxes = _boxes.bbox[k_ind]
gt_cls_id = gt_cls_inds + 1
temp_cls = torch.ones(
(_boxes.bbox.shape[:2]), device=device) * gt_cls_id.view(
-1, 1).float()
gt_classes = temp_cls[k_ind].view(-1, 1).long()
gt_scores = sorted_scores.t().contiguous()[k_ind].view(-1, 1)
if gt_boxes.shape[0] != 0:
gt_boxes = BoxList(gt_boxes,
proposals.size,
mode=proposals.mode)
overlaps = boxlist_iou(proposals, gt_boxes)
# TODO: pytorch and numpy argmax perform differently
# max_overlaps, gt_assignment = overlaps.max(dim=1)
max_overlaps = torch.tensor(overlaps.cpu().numpy().max(axis=1),
device=device)
gt_assignment = torch.tensor(
overlaps.cpu().numpy().argmax(axis=1), device=device)
pseudo_labels = gt_classes[gt_assignment, 0]
loss_weights = gt_scores[gt_assignment, 0]
# fg_inds = max_overlaps.ge(cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD).nonzero(as_tuple=False)[:,0]
# Select background RoIs as those with <= FG_IOU_THRESHOLD
bg_inds = max_overlaps.lt(
cfg.MODEL.ROI_HEADS.FG_IOU_THRESHOLD).nonzero(
as_tuple=False)[:, 0]
pseudo_labels[bg_inds] = 0
# compute regression targets
if return_targets:
matched_targets = gt_boxes[gt_assignment]
regression_targets = self.box_coder.encode(
matched_targets.bbox, proposals.bbox)
return pseudo_labels, loss_weights, regression_targets
return pseudo_labels, loss_weights
# corner case
pseudo_labels = torch.zeros(num_rois, dtype=torch.long, device=device)
loss_weights = torch.zeros(num_rois, dtype=torch.float, device=device)
if return_targets:
regression_targets = torch.zeros(num_rois,
4,
dtype=torch.float,
device=device)
return pseudo_labels, loss_weights, regression_targets
return pseudo_labels, loss_weights
