def create_roidb_from_box_list(self, box_list, gt_roidb):
"""
given ground truth, prepare roidb
:param box_list: [image_index] ndarray of [box_index][x1, x2, y1, y2]
:param gt_roidb: [image_index]['boxes', 'gt_classes', 'gt_overlaps', 'flipped']
:return: roidb: [image_index]['boxes', 'gt_classes', 'gt_overlaps', 'flipped']
"""
assert len(
box_list
) == self.num_images, 'number of boxes matrix must match number of images'
roidb = []
for i in range(self.num_images):
roi_rec = dict()
roi_rec['image'] = gt_roidb[i]['image']
roi_rec['height'] = gt_roidb[i]['height']
roi_rec['width'] = gt_roidb[i]['width']
boxes = box_list[i]
if boxes.shape[1] == 5:
boxes = boxes[:, :4]
num_boxes = boxes.shape[0]
overlaps = np.zeros((num_boxes, self.num_classes),
dtype=np.float32)
if gt_roidb is not None and gt_roidb[i]['boxes'].size > 0:
gt_boxes = gt_roidb[i]['boxes']
gt_classes = gt_roidb[i]['gt_classes']
# n boxes and k gt_boxes => n * k overlap
gt_overlaps = bbox_overlaps(boxes.astype(np.float),
gt_boxes.astype(np.float))
# for each box in n boxes, select only maximum overlap (must be greater than zero)
argmaxes = gt_overlaps.argmax(axis=1)
maxes = gt_overlaps.max(axis=1)
I = np.where(maxes > 0)[0]
overlaps[I, gt_classes[argmaxes[I]]] = maxes[I]
roi_rec.update({
'boxes':
boxes,
'gt_classes':
np.zeros((num_boxes, ), dtype=np.int32),
'gt_overlaps':
overlaps,
'max_classes':
overlaps.argmax(axis=1),
'max_overlaps':
overlaps.max(axis=1),
'flipped':
False
})
# background roi => background class
zero_indexes = np.where(roi_rec['max_overlaps'] == 0)[0]
assert all(roi_rec['max_classes'][zero_indexes] == 0)
# foreground roi => foreground class
nonzero_indexes = np.where(roi_rec['max_overlaps'] > 0)[0]
assert all(roi_rec['max_classes'][nonzero_indexes] != 0)
roidb.append(roi_rec)
return roidb
def sample_rois(rois,
fg_rois_per_image,
rois_per_image,
num_classes,
cfg,
labels=None,
overlaps=None,
bbox_targets=None,
gt_boxes=None):
"""
generate random sample of ROIs comprising foreground and background examples
:param rois: all_rois [n, 4]; e2e: [n, 5] with batch_index
:param fg_rois_per_image: foreground roi number
:param rois_per_image: total roi number
:param num_classes: number of classes
:param labels: maybe precomputed
:param overlaps: maybe precomputed (max_overlaps)
:param bbox_targets: maybe precomputed
:param gt_boxes: optional for e2e [n, 5] (x1, y1, x2, y2, cls)
:return: (labels, rois, bbox_targets, bbox_weights)
"""
if labels is None:
overlaps = bbox_overlaps(rois[:, 1:].astype(np.float),
gt_boxes[:, :4].astype(np.float))
gt_assignment = overlaps.argmax(axis=1)
overlaps = overlaps.max(axis=1)
labels = gt_boxes[gt_assignment, 4]
# foreground RoI with FG_THRESH overlap
fg_indexes = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]
# guard against the case when an image has fewer than fg_rois_per_image foreground RoIs
fg_rois_per_this_image = np.minimum(fg_rois_per_image, fg_indexes.size)
# Sample foreground regions without replacement
if len(fg_indexes) > fg_rois_per_this_image:
fg_indexes = npr.choice(fg_indexes,
size=fg_rois_per_this_image,
replace=False)
# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
bg_indexes = np.where((overlaps < cfg.TRAIN.BG_THRESH_HI)
& (overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]
# Compute number of background RoIs to take from this image (guarding against there being fewer than desired)
bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image
bg_rois_per_this_image = np.minimum(bg_rois_per_this_image,
bg_indexes.size)
# Sample foreground regions without replacement
if len(bg_indexes) > bg_rois_per_this_image:
bg_indexes = npr.choice(bg_indexes,
size=bg_rois_per_this_image,
replace=False)
# indexes selected
keep_indexes = np.append(fg_indexes, bg_indexes)
# pad more to ensure a fixed minibatch size
while keep_indexes.shape[0] < rois_per_image:
gap = np.minimum(len(rois), rois_per_image - keep_indexes.shape[0])
gap_indexes = npr.choice(range(len(rois)), size=gap, replace=False)
keep_indexes = np.append(keep_indexes, gap_indexes)
# select labels
labels = labels[keep_indexes]
# set labels of bg_rois to be 0
labels[fg_rois_per_this_image:] = 0
rois = rois[keep_indexes]
# load or compute bbox_target
if bbox_targets is not None:
bbox_target_data = bbox_targets[keep_indexes, :]
else:
targets = bbox_transform(rois[:, 1:],
gt_boxes[gt_assignment[keep_indexes], :4])
if cfg.TRAIN.BBOX_NORMALIZATION_PRECOMPUTED:
targets = ((targets - np.array(cfg.TRAIN.BBOX_MEANS)) /
np.array(cfg.TRAIN.BBOX_STDS))
bbox_target_data = np.hstack((labels[:, np.newaxis], targets))
bbox_targets, bbox_weights = \
expand_bbox_regression_targets(bbox_target_data, num_classes, cfg)
return rois, labels, bbox_targets, bbox_weights
def assign_anchor(feat_shape, gt_boxes, im_info, cfg, feat_stride=16,
scales=(8, 16, 32), ratios=(0.5, 1, 2), allowed_border=0,
normalize_target=False, bbox_mean=(0.0, 0.0, 0.0, 0.0),
bbox_std=(0.1, 0.1, 0.4, 0.4)):
"""
assign ground truth boxes to anchor positions
:param feat_shape: infer output shape
:param gt_boxes: assign ground truth
:param im_info: filter out anchors overlapped with edges
:param feat_stride: anchor position step
:param scales: used to generate anchors, affects num_anchors (per location)
:param ratios: aspect ratios of generated anchors
:param allowed_border: filter out anchors with edge overlap > allowed_border
:param normalize_target: normalize rpn target
:param bbox_mean: anchor target mean
:param bbox_std: anchor target std
:return: dict of label
'label': of shape (batch_size, 1) <- (batch_size, num_anchors, feat_height, feat_width)
'bbox_target': of shape (batch_size, num_anchors * 4, feat_height, feat_width)
'bbox_inside_weight': *todo* mark the assigned anchors
'bbox_outside_weight': used to normalize the bbox_loss, all weights sums to RPN_POSITIVE_WEIGHT
"""
def _unmap(data, count, inds, fill=0):
"""" unmap a subset inds of data into original data of size count """
if len(data.shape) == 1:
ret = np.empty((count,), dtype=np.float32)
ret.fill(fill)
ret[inds] = data
else:
ret = np.empty((count,) + data.shape[1:], dtype=np.float32)
ret.fill(fill)
ret[inds, :] = data
return ret
DEBUG = False
im_info = im_info[0]
scales = np.array(scales, dtype=np.float32)
base_anchors = generate_anchors(base_size=feat_stride, ratios=list(ratios), scales=scales)
num_anchors = base_anchors.shape[0]
feat_height, feat_width = feat_shape[-2:]
if DEBUG:
print('anchors:')
print(base_anchors)
print('anchor shapes:')
print(np.hstack((base_anchors[:, 2::4] - base_anchors[:, 0::4],
base_anchors[:, 3::4] - base_anchors[:, 1::4])))
print('im_info', im_info)
print('height', feat_height, 'width', feat_width)
print('gt_boxes shape', gt_boxes.shape)
print('gt_boxes', gt_boxes)
# 1. generate proposals from bbox deltas and shifted anchors
shift_x = np.arange(0, feat_width) * feat_stride
shift_y = np.arange(0, feat_height) * feat_stride
shift_x, shift_y = np.meshgrid(shift_x, shift_y)
shifts = np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(), shift_y.ravel())).transpose()
# add A anchors (1, A, 4) to
# cell K shifts (K, 1, 4) to get
# shift anchors (K, A, 4)
# reshape to (K*A, 4) shifted anchors
A = num_anchors
K = shifts.shape[0]
all_anchors = base_anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2))
all_anchors = all_anchors.reshape((K * A, 4))
total_anchors = int(K * A)
# only keep anchors inside the image
inds_inside = np.where((all_anchors[:, 0] >= -allowed_border) &
(all_anchors[:, 1] >= -allowed_border) &
(all_anchors[:, 2] < im_info[1] + allowed_border) &
(all_anchors[:, 3] < im_info[0] + allowed_border))[0]
if DEBUG:
print('total_anchors', total_anchors)
print('inds_inside', len(inds_inside))
# keep only inside anchors
anchors = all_anchors[inds_inside, :]
if DEBUG:
print('anchors shape', anchors.shape)
# label: 1 is positive, 0 is negative, -1 is dont care
labels = np.empty((len(inds_inside),), dtype=np.float32)
labels.fill(-1)
if gt_boxes.size > 0:
# overlap between the anchors and the gt boxes
# overlaps (ex, gt)
overlaps = bbox_overlaps(anchors.astype(np.float), gt_boxes.astype(np.float))
argmax_overlaps = overlaps.argmax(axis=1)
max_overlaps = overlaps[np.arange(len(inds_inside)), argmax_overlaps]
gt_argmax_overlaps = overlaps.argmax(axis=0)
gt_max_overlaps = overlaps[gt_argmax_overlaps, np.arange(overlaps.shape[1])]
gt_argmax_overlaps = np.where(overlaps == gt_max_overlaps)[0]
if not cfg.TRAIN.RPN_CLOBBER_POSITIVES:
# assign bg labels first so that positive labels can clobber them
labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0
# fg label: for each gt, anchor with highest overlap
labels[gt_argmax_overlaps] = 1
# fg label: above threshold IoU
labels[max_overlaps >= cfg.TRAIN.RPN_POSITIVE_OVERLAP] = 1
if cfg.TRAIN.RPN_CLOBBER_POSITIVES:
# assign bg labels last so that negative labels can clobber positives
labels[max_overlaps < cfg.TRAIN.RPN_NEGATIVE_OVERLAP] = 0
else:
labels[:] = 0
# subsample positive labels if we have too many
num_fg = int(cfg.TRAIN.RPN_FG_FRACTION * cfg.TRAIN.RPN_BATCH_SIZE)
fg_inds = np.where(labels == 1)[0]
if len(fg_inds) > num_fg:
disable_inds = npr.choice(fg_inds, size=(len(fg_inds) - num_fg), replace=False)
if DEBUG:
disable_inds = fg_inds[:(len(fg_inds) - num_fg)]
labels[disable_inds] = -1
# subsample negative labels if we have too many
num_bg = cfg.TRAIN.RPN_BATCH_SIZE - np.sum(labels == 1)
bg_inds = np.where(labels == 0)[0]
if len(bg_inds) > num_bg:
disable_inds = npr.choice(bg_inds, size=(len(bg_inds) - num_bg), replace=False)
if DEBUG:
disable_inds = bg_inds[:(len(bg_inds) - num_bg)]
labels[disable_inds] = -1
bbox_targets = np.zeros((len(inds_inside), 4), dtype=np.float32)
if gt_boxes.size > 0:
bbox_targets[:] = bbox_transform(anchors, gt_boxes[argmax_overlaps, :4])
bbox_weights = np.zeros((len(inds_inside), 4), dtype=np.float32)
bbox_weights[labels == 1, :] = np.array(cfg.TRAIN.RPN_BBOX_WEIGHTS)
if DEBUG:
_sums = bbox_targets[labels == 1, :].sum(axis=0)
_squared_sums = (bbox_targets[labels == 1, :] ** 2).sum(axis=0)
_counts = np.sum(labels == 1)
means = _sums / (_counts + 1e-14)
stds = np.sqrt(_squared_sums / _counts - means ** 2)
print('means', means)
print('stdevs', stds)
if normalize_target:
bbox_targets = ((bbox_targets - np.array(bbox_mean))
/ np.array(bbox_std))
# map up to original set of anchors
labels = _unmap(labels, total_anchors, inds_inside, fill=-1)
bbox_targets = _unmap(bbox_targets, total_anchors, inds_inside, fill=0)
bbox_weights = _unmap(bbox_weights, total_anchors, inds_inside, fill=0)
if DEBUG:
print('rpn: max max_overlaps', np.max(max_overlaps))
print('rpn: num_positives', np.sum(labels == 1))
print('rpn: num_negatives', np.sum(labels == 0))
_fg_sum = np.sum(labels == 1)
_bg_sum = np.sum(labels == 0)
_count = 1
print('rpn: num_positive avg', _fg_sum / _count)
print('rpn: num_negative avg', _bg_sum / _count)
labels = labels.reshape((1, feat_height, feat_width, A)).transpose(0, 3, 1, 2)
labels = labels.reshape((1, A * feat_height * feat_width))
bbox_targets = bbox_targets.reshape((1, feat_height, feat_width, A * 4)).transpose(0, 3, 1, 2)
bbox_weights = bbox_weights.reshape((1, feat_height, feat_width, A * 4)).transpose((0, 3, 1, 2))
label = {'label': labels,
'bbox_target': bbox_targets,
'bbox_weight': bbox_weights}
return label
def evaluate_recall(self, roidb, candidate_boxes=None, thresholds=None):
"""
evaluate detection proposal recall metrics
record max overlap value for each gt box; return vector of overlap values
:param roidb: used to evaluate
:param candidate_boxes: if not given, use roidb's non-gt boxes
:param thresholds: array-like recall threshold
:return: None
ar: average recall, recalls: vector recalls at each IoU overlap threshold
thresholds: vector of IoU overlap threshold, gt_overlaps: vector of all ground-truth overlaps
"""
all_log_info = ''
area_names = ['all', '0-25', '25-50', '50-100',
'100-200', '200-300', '300-inf']
area_ranges = [[0**2, 1e5**2], [0**2, 25**2], [25**2, 50**2], [50**2, 100**2],
[100**2, 200**2], [200**2, 300**2], [300**2, 1e5**2]]
area_counts = []
for area_name, area_range in zip(area_names[1:], area_ranges[1:]):
area_count = 0
for i in range(self.num_images):
if candidate_boxes is None:
# default is use the non-gt boxes from roidb
non_gt_inds = np.where(roidb[i]['gt_classes'] == 0)[0]
boxes = roidb[i]['boxes'][non_gt_inds, :]
else:
boxes = candidate_boxes[i]
boxes_areas = (boxes[:, 2] - boxes[:, 0] + 1) * (boxes[:, 3] - boxes[:, 1] + 1)
valid_range_inds = np.where((boxes_areas >= area_range[0]) & (boxes_areas < area_range[1]))[0]
area_count += len(valid_range_inds)
area_counts.append(area_count)
total_counts = float(sum(area_counts))
for area_name, area_count in zip(area_names[1:], area_counts):
log_info = 'percentage of {} {}'.format(area_name, area_count / total_counts)
print(log_info)
all_log_info += log_info
log_info = 'average number of proposal {}'.format(total_counts / self.num_images)
print(log_info)
all_log_info += log_info
for area_name, area_range in zip(area_names, area_ranges):
gt_overlaps = np.zeros(0)
num_pos = 0
for i in range(self.num_images):
# check for max_overlaps == 1 avoids including crowd annotations
max_gt_overlaps = roidb[i]['gt_overlaps'].max(axis=1)
gt_inds = np.where((roidb[i]['gt_classes'] > 0) & (max_gt_overlaps == 1))[0]
gt_boxes = roidb[i]['boxes'][gt_inds, :]
gt_areas = (gt_boxes[:, 2] - gt_boxes[:, 0] + 1) * (gt_boxes[:, 3] - gt_boxes[:, 1] + 1)
valid_gt_inds = np.where((gt_areas >= area_range[0]) & (gt_areas < area_range[1]))[0]
gt_boxes = gt_boxes[valid_gt_inds, :]
num_pos += len(valid_gt_inds)
if candidate_boxes is None:
# default is use the non-gt boxes from roidb
non_gt_inds = np.where(roidb[i]['gt_classes'] == 0)[0]
boxes = roidb[i]['boxes'][non_gt_inds, :]
else:
boxes = candidate_boxes[i]
if boxes.shape[0] == 0:
continue
overlaps = bbox_overlaps(boxes.astype(np.float), gt_boxes.astype(np.float))
_gt_overlaps = np.zeros((gt_boxes.shape[0]))
# choose whatever is smaller to iterate
rounds = min(boxes.shape[0], gt_boxes.shape[0])
for j in range(rounds):
# find which proposal maximally covers each gt box
argmax_overlaps = overlaps.argmax(axis=0)
# get the IoU amount of coverage for each gt box
max_overlaps = overlaps.max(axis=0)
# find which gt box is covered by most IoU
gt_ind = max_overlaps.argmax()
gt_ovr = max_overlaps.max()
assert (gt_ovr >= 0), '%s\n%s\n%s' % (boxes, gt_boxes, overlaps)
# 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 = np.hstack((gt_overlaps, _gt_overlaps))
gt_overlaps = np.sort(gt_overlaps)
if thresholds is None:
step = 0.05
thresholds = np.arange(0.5, 0.95 + 1e-5, step)
recalls = np.zeros_like(thresholds)
# compute recall for each IoU threshold
for i, t in enumerate(thresholds):
recalls[i] = (gt_overlaps >= t).sum() / float(num_pos)
ar = recalls.mean()
# print results
log_info = 'average recall for {}: {:.3f}'.format(area_name, ar)
print(log_info)
all_log_info += log_info
for threshold, recall in zip(thresholds, recalls):
log_info = 'recall @{:.2f}: {:.3f}'.format(threshold, recall)
print(log_info)
all_log_info += log_info
return all_log_info