def mask_target_opr(proposals, targets, high_threshold, low_threshold,
discretization_size):
"""
Generate proposal targets for computing loss.
Args:
proposals: (list[BoxList])
targets: (list[BoxList])
high_threshold: (float)
low_threshold: (float)
discretization_size: (int)
"""
matcher = Matcher(high_threshold,
low_threshold,
allow_low_quality_matches=False)
# prepare targets
labels = []
masks = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
# match targets to proposals
match_quality_matrix = boxlist_iou(targets_per_image,
proposals_per_image)
matched_idxs = matcher(match_quality_matrix)
# Mask RCNN needs "labels" and "masks "fields for creating the targets
target = targets_per_image.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)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# this can probably be removed, but is left here for clarity
# and completeness
neg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[neg_inds] = 0
# mask scores are only computed on positive samples
positive_inds = torch.nonzero(labels_per_image > 0).squeeze(1)
segmentation_masks = matched_targets.get_field("masks")
segmentation_masks = segmentation_masks[positive_inds]
positive_proposals = proposals_per_image[positive_inds]
masks_per_image = project_masks_on_boxes(segmentation_masks,
positive_proposals,
discretization_size)
labels.append(labels_per_image)
masks.append(masks_per_image)
return labels, masks
def anchor_target_opr(
anchors, targets, box_coder, high_threshold, low_threshold,
allow_low_quality_matches=True):
"""
Generate anchor targets for computing retinanet loss.
Args:
anchors: (list[BoxList])
targets: (list[BoxList])
box_coder: (BoxCoder)
high_threshold: (float)
low_threshold: (float)
"""
matcher = Matcher(high_threshold, low_threshold,
allow_low_quality_matches=allow_low_quality_matches)
# prepare targets
labels = []
regression_targets = []
for anchors_per_image, targets_per_image in zip(anchors, targets):
# match targets to anchors
match_quality_matrix = boxlist_iou(targets_per_image, anchors_per_image)
matched_idxs = matcher(match_quality_matrix)
targets_per_image = targets_per_image.copy_with_fields(['labels'])
matched_targets = targets_per_image[matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
matched_idxs = matched_targets.get_field("matched_idxs")
# generate rpn labels
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.float32)
# Background (negative examples)
bg_indices = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[bg_indices] = 0
# discard indices that are between thresholds
inds_to_discard = matched_idxs == Matcher.BETWEEN_THRESHOLDS
labels_per_image[inds_to_discard] = -1
# compute regression targets
regression_targets_per_image = box_coder.encode(
matched_targets.bbox, anchors_per_image.bbox
)
labels.append(labels_per_image)
regression_targets.append(regression_targets_per_image)
return labels, regression_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 proposal_target_opr(
proposals, targets, box_coder, high_threshold, low_threshold,
batch_size_per_image, positive_fraction, return_ious=False,
return_sample_id=False, return_raw_proposals=False):
"""
Generate proposal targets for computing loss.
Args:
proposals: (list[BoxList])
targets: (list[BoxList])
box_coder: (BoxCoder)
high_threshold: (float)
low_threshold: (float)
batch_size_per_image: (int)
positive_fraction: (float)
return_ious: (bool)
"""
matcher = Matcher(high_threshold, low_threshold,
allow_low_quality_matches=False)
fg_bg_sampler = BalancedPositiveNegativeSampler(
batch_size_per_image, positive_fraction)
# prepare targets
labels = []
regression_targets = []
ious = []
for proposals_per_image, targets_per_image in zip(proposals, targets):
# match targets to proposals
match_quality_matrix = boxlist_iou(
targets_per_image, proposals_per_image)
matched_idxs = matcher(match_quality_matrix)
# Fast RCNN only need "labels" field for selecting the targets
target = targets_per_image.copy_with_fields("labels")
# 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_ious = match_quality_matrix.t()[
range(proposals_per_image.bbox.shape[0]), matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
matched_idxs = matched_targets.get_field("matched_idxs")
labels_per_image = matched_targets.get_field("labels")
labels_per_image = labels_per_image.to(dtype=torch.int64)
# Label background (below the low threshold)
bg_inds = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[bg_inds] = 0
# Label ignore proposals (between low and high thresholds)
ignore_inds = matched_idxs == Matcher.BETWEEN_THRESHOLDS
labels_per_image[ignore_inds] = -1 # -1 is ignored by sampler
# compute regression targets
regression_targets_per_image = box_coder.encode(
matched_targets.bbox, proposals_per_image.bbox
)
labels.append(labels_per_image)
regression_targets.append(regression_targets_per_image)
ious.append(matched_ious)
sampled_pos_inds, sampled_neg_inds = fg_bg_sampler(labels)
proposals = list(proposals)
# add corresponding label and regression_targets information to the bounding boxes
for labels_per_image, regression_targets_per_image, ious_per_image, \
proposals_per_image in zip(labels, regression_targets, ious, proposals):
proposals_per_image.add_field("labels", labels_per_image)
proposals_per_image.add_field(
"regression_targets", regression_targets_per_image
)
if return_ious:
proposals_per_image.add_field("ious", ious_per_image)
if return_sample_id:
sample_id = []
if return_raw_proposals:
raw_proposals = proposals.copy()
# distributed sampled proposals, that were obtained on all feature maps
# concatenated via the fg_bg_sampler, into individual feature map levels
for img_idx, (pos_inds_img, neg_inds_img) in enumerate(
zip(sampled_pos_inds, sampled_neg_inds)
):
img_sampled_inds = torch.nonzero(pos_inds_img | neg_inds_img).squeeze(1)
proposals_per_image = proposals[img_idx][img_sampled_inds]
proposals[img_idx] = proposals_per_image
if return_sample_id:
sample_id.append(img_sampled_inds)
if return_sample_id:
if return_raw_proposals:
return proposals, sample_id, raw_proposals
else:
return proposals, sample_id
else:
if return_raw_proposals:
return proposals, raw_proposals
else:
return proposals
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 anchor_target_opr(
anchors, targets, box_coder, high_threshold, low_threshold,
batch_size_per_image, positive_fraction):
"""
Generate anchor targets for computing loss.
Args:
anchors: (list[BoxList])
targets: (list[BoxList])
box_coder: (BoxCoder)
high_threshold: (float)
low_threshold: (float)
batch_size_per_image: (int)
positive_fraction: (float)
"""
matcher = Matcher(
high_threshold, low_threshold, allow_low_quality_matches=True)
fg_bg_sampler = BalancedPositiveNegativeSampler(
batch_size_per_image, positive_fraction)
anchors = [cat_boxlist(anchors_per_image) for anchors_per_image in anchors]
# prepare targets
labels = []
regression_targets = []
for anchors_per_image, targets_per_image in zip(anchors, targets):
# match targets to anchors
match_quality_matrix = boxlist_iou(targets_per_image, anchors_per_image)
matched_idxs = matcher(match_quality_matrix)
targets_per_image = targets_per_image.copy_with_fields([])
matched_targets = targets_per_image[matched_idxs.clamp(min=0)]
matched_targets.add_field("matched_idxs", matched_idxs)
matched_idxs = matched_targets.get_field("matched_idxs")
# generate rpn labels
labels_per_image = matched_idxs >= 0
labels_per_image = labels_per_image.to(dtype=torch.float32)
# Background (negative examples)
bg_indices = matched_idxs == Matcher.BELOW_LOW_THRESHOLD
labels_per_image[bg_indices] = 0
# discard anchors that go out of the boundaries of the image
labels_per_image[~anchors_per_image.get_field("visibility")] = -1
# discard indices that are between thresholds
inds_to_discard = matched_idxs == Matcher.BETWEEN_THRESHOLDS
labels_per_image[inds_to_discard] = -1
# compute regression targets
regression_targets_per_image = box_coder.encode(
matched_targets.bbox, anchors_per_image.bbox
)
labels.append(labels_per_image)
regression_targets.append(regression_targets_per_image)
sampled_pos_inds, sampled_neg_inds = fg_bg_sampler(labels)
sampled_pos_inds = torch.nonzero(
torch.cat(sampled_pos_inds, dim=0)).squeeze(1)
sampled_neg_inds = torch.nonzero(
torch.cat(sampled_neg_inds, dim=0)).squeeze(1)
sampled_inds = torch.cat([sampled_pos_inds, sampled_neg_inds], dim=0)
labels = torch.cat(labels, dim=0)
regression_targets = torch.cat(regression_targets, dim=0)
return labels, regression_targets, sampled_inds, sampled_pos_inds