def fpn_anchor_target_opr_core_impl(gt_boxes,
im_info,
anchors,
allow_low_quality_matches=True):
ignore_label = config.ignore_label
# get the gt boxes
gtboxes = gt_boxes[:im_info[5].astype(np.int32)]
ignore_mask = F.equal(gtboxes[:, 4], config.ignore_label)
# find the valid gtboxes
_, index = F.cond_take(1 - ignore_mask > 0, ignore_mask)
valid_gt_boxes = gtboxes[index.astype(np.int32)]
# compute the iou matrix
overlaps = box_overlap_opr(anchors, valid_gt_boxes[:, :4])
# match the dtboxes
a_shp0 = anchors.shape[0]
argmax_overlaps = F.argmax(overlaps, axis=1)
max_overlaps = F.nn.indexing_one_hot(overlaps,
argmax_overlaps.astype(np.int32), 1)
labels = F.ones(a_shp0).astype(np.int32) * ignore_label
# set negative ones
labels = labels * (max_overlaps >= config.rpn_negative_overlap).astype(
np.float32)
# set positive ones
fg_mask = (max_overlaps >= config.rpn_positive_overlap)
const_one = mge.tensor(1.0)
if allow_low_quality_matches:
# match the max gt
gt_max_overlaps = F.max(overlaps, axis=0)
gt_argmax_overlaps = F.argmax(overlaps, axis=0)
gt_argmax_overlaps = gt_argmax_overlaps.astype(np.int32)
max_overlaps[gt_argmax_overlaps] = 1.
m = gt_max_overlaps.shape[0]
argmax_overlaps[gt_argmax_overlaps] = F.linspace(0, m - 1,
m).astype(np.int32)
fg_mask = (max_overlaps >= config.rpn_positive_overlap)
labels[fg_mask] = 1
# compute the bbox targets
bbox_targets = bbox_transform_opr(anchors,
valid_gt_boxes[argmax_overlaps, :4])
if config.rpn_bbox_normalize_targets:
std_opr = mge.tensor(config.bbox_normalize_stds[None, :]).to(
anchors.device)
mean_opr = mge.tensor(config.bbox_normalize_means[None, :]).to(
anchors.device)
minus_opr = mean_opr / std_opr
bbox_targets = bbox_targets / std_opr - minus_opr
return labels, bbox_targets
def fpn_anchor_target_opr_core_impl(gt_boxes,
im_info,
anchors,
allow_low_quality_matches=True):
ignore_label = config.ignore_label
# get the gt boxes
valid_gt_boxes = gt_boxes[:im_info[5], :]
non_ignore_mask = valid_gt_boxes[:, -1] > 0
non_ignore_inds = mask_to_inds(non_ignore_mask)
valid_gt_boxes = valid_gt_boxes.ai[non_ignore_inds]
# compute the iou matrix
overlaps = box_overlap_opr(anchors, valid_gt_boxes[:, :4])
# match the dtboxes
a_shp0 = anchors.shape[0]
max_overlaps = F.max(overlaps, axis=1)
argmax_overlaps = F.argmax(overlaps, axis=1)
# all ignore
labels = mge.ones(a_shp0).astype(np.int32) * ignore_label
# set negative ones
labels = labels * (max_overlaps >= config.rpn_negative_overlap)
# set positive ones
fg_mask = (max_overlaps >= config.rpn_positive_overlap)
const_one = mge.tensor(1.0)
if allow_low_quality_matches:
# match the max gt
gt_max_overlaps = F.max(overlaps, axis=0)
gt_argmax_overlaps = F.argmax(overlaps, axis=0)
g_shp0 = valid_gt_boxes.shapeof()[0]
gt_id = F.linspace(0, g_shp0 - 1, g_shp0).astype(np.int32)
argmax_overlaps = argmax_overlaps.set_ai(gt_id)[gt_argmax_overlaps]
max_overlaps = max_overlaps.set_ai(
const_one.broadcast(g_shp0))[gt_argmax_overlaps]
fg_mask = (max_overlaps >= config.rpn_positive_overlap)
# set positive ones
fg_mask_ind = mask_to_inds(fg_mask)
labels = labels.set_ai(const_one.broadcast(
fg_mask_ind.shapeof()))[fg_mask_ind]
# compute the targets
bbox_targets = bbox_transform_opr(anchors,
valid_gt_boxes.ai[argmax_overlaps, :4])
if config.rpn_bbox_normalize_targets:
std_opr = mge.tensor(config.bbox_normalize_stds[None, :])
mean_opr = mge.tensor(config.bbox_normalize_means[None, :])
minus_opr = mean_opr / std_opr
bbox_targets = bbox_targets / std_opr - minus_opr
return labels, bbox_targets
def cascade_roi_target(rpn_rois, im_info, gt_boxes, pos_threshold=0.5, top_k=1):
return_rois = []
return_labels = []
return_bbox_targets = []
# get per image proposals and gt_boxes
for bid in range(config.batch_per_gpu):
gt_boxes_perimg = gt_boxes[bid, :im_info[bid, 5], :]
batch_inds = mge.ones((gt_boxes_perimg.shapeof()[0], 1)) * bid
#if config.proposal_append_gt:
gt_rois = F.concat([batch_inds, gt_boxes_perimg[:, :4]], axis=1)
batch_roi_mask = rpn_rois[:, 0] == bid
batch_roi_inds = mask_to_inds(batch_roi_mask)
all_rois = F.concat([rpn_rois.ai[batch_roi_inds], gt_rois], axis=0)
overlaps_normal, overlaps_ignore = box_overlap_ignore_opr(
all_rois[:, 1:5], gt_boxes_perimg)
overlaps_normal, overlaps_normal_indices = F.argsort(overlaps_normal, descending=True)
overlaps_ignore, overlaps_ignore_indices = F.argsort(overlaps_ignore, descending=True)
# gt max and indices, ignore max and indices
max_overlaps_normal = overlaps_normal[:, :top_k].reshape(-1)
gt_assignment_normal = overlaps_normal_indices[:, :top_k].reshape(-1)
max_overlaps_ignore = overlaps_ignore[:, :top_k].reshape(-1)
gt_assignment_ignore = overlaps_ignore_indices[:, :top_k].reshape(-1)
# cons masks
ignore_assign_mask = (max_overlaps_normal < config.fg_threshold) * (
max_overlaps_ignore > max_overlaps_normal)
max_overlaps = max_overlaps_normal * (1 - ignore_assign_mask) + \
max_overlaps_ignore * ignore_assign_mask
gt_assignment = gt_assignment_normal * (1- ignore_assign_mask) + \
gt_assignment_ignore * ignore_assign_mask
gt_assignment = gt_assignment.astype(np.int32)
labels = gt_boxes_perimg.ai[gt_assignment, 4]
fg_mask = (max_overlaps >= config.fg_threshold) * (1 - F.equal(labels, config.ignore_label))
bg_mask = (max_overlaps < config.bg_threshold_high) * (
max_overlaps >= config.bg_threshold_low)
fg_mask = fg_mask.reshape(-1, top_k)
bg_mask = bg_mask.reshape(-1, top_k)
#pos_max = config.num_rois * config.fg_ratio
#fg_inds_mask = _bernoulli_sample_masks(fg_mask[:, 0], pos_max, 1)
#neg_max = config.num_rois - fg_inds_mask.sum()
#bg_inds_mask = _bernoulli_sample_masks(bg_mask[:, 0], neg_max, 1)
labels = labels * fg_mask.reshape(-1)
#keep_mask = fg_inds_mask + bg_inds_mask
#keep_inds = mask_to_inds(keep_mask)
#keep_inds = keep_inds[:F.minimum(config.num_rois, keep_inds.shapeof()[0])]
# labels
labels = labels.reshape(-1, top_k)
gt_assignment = gt_assignment.reshape(-1, top_k).reshape(-1)
target_boxes = gt_boxes_perimg.ai[gt_assignment, :4]
#rois = all_rois.ai[keep_inds]
target_shape = (all_rois.shapeof()[0], top_k, all_rois.shapeof()[-1])
target_rois = F.add_axis(all_rois, 1).broadcast(target_shape).reshape(-1, all_rois.shapeof()[-1])
bbox_targets = bbox_transform_opr(target_rois[:, 1:5], target_boxes)
if config.rcnn_bbox_normalize_targets:
std_opr = mge.tensor(config.bbox_normalize_stds[None, :])
mean_opr = mge.tensor(config.bbox_normalize_means[None, :])
minus_opr = mean_opr / std_opr
bbox_targets = bbox_targets / std_opr - minus_opr
bbox_targets = bbox_targets.reshape(-1, top_k * 4)
return_rois.append(all_rois)
return_labels.append(labels)
return_bbox_targets.append(bbox_targets)
if config.batch_per_gpu == 1:
return F.zero_grad(all_rois), F.zero_grad(labels), F.zero_grad(bbox_targets)
else:
return_rois = F.concat(return_rois, axis=0)
return_labels = F.concat(return_labels, axis=0)
return_bbox_targets = F.concat(return_bbox_targets, axis=0)
return F.zero_grad(return_rois), F.zero_grad(return_labels), F.zero_grad(return_bbox_targets)
def fpn_roi_target(rpn_rois,
im_info,
gt_boxes,
fg_threshold=config.fg_threshold,
top_k=1):
return_rois, return_labels = [], []
return_bbox_targets = []
# get per image proposals and gt_boxes
batch_per_gpu = im_info.shape[0]
sampling = True
# is_sample = True if top_k < 2 else False
for bid in range(batch_per_gpu):
gt_boxes_perimg = gt_boxes[bid, :im_info[bid, 5].astype(np.int32), :]
dummy_gt = F.ones([1, gt_boxes_perimg.shape[1]])
batch_inds = F.ones((gt_boxes_perimg.shape[0], 1)) * bid
#if config.proposal_append_gt:
gt_rois = F.concat([batch_inds, gt_boxes_perimg[:, :4]], axis=1)
batch_rois_mask = F.equal(rpn_rois[:, 0], bid) > 0
_, batch_rois_index = F.cond_take(batch_rois_mask, batch_rois_mask)
# batch_roi_mask = rpn_rois[:, 0] == bid
# batch_roi_inds = mask_to_inds(batch_roi_mask)
all_rois= F.concat([rpn_rois[batch_rois_index], gt_rois], axis=0) if sampling \
else rpn_rois[batch_rois_index]
# all_rois = F.concat([rpn_rois.ai[batch_roi_inds], gt_rois], axis=0)
gt_boxes_perimg = F.concat([gt_boxes_perimg, dummy_gt], axis=0)
overlaps_normal, overlaps_ignore = box_overlap_ignore_opr(
all_rois[:, 1:5], gt_boxes_perimg)
# overlaps_normal, overlaps_normal_indices = F.argsort(overlaps_normal, descending=True)
# overlaps_ignore, overlaps_ignore_indices = F.argsort(overlaps_ignore, descending=True)
overlaps_normal_indices = F.argsort(overlaps_normal, descending=True)
overlaps_normal = F.gather(overlaps_normal, 1, overlaps_normal_indices)
# overlaps_normal = F.nn.indexing_one_hot(overlaps_normal, overlaps_normal_indices, 1)
overlaps_ignore_indices = F.argsort(overlaps_ignore, descending=True)
overlaps_ignore = F.gather(overlaps_ignore, 1, overlaps_ignore_indices)
# overlaps_ignore = F.nn.indexing_one_hot(overlaps_ignore, overlaps_ignore_indices, 1)
# gt max and indices, ignore max and indices
max_overlaps_normal = overlaps_normal[:, :top_k].flatten()
gt_assignment_normal = overlaps_normal_indices[:, :top_k].flatten()
max_overlaps_ignore = overlaps_ignore[:, :top_k].flatten()
gt_assignment_ignore = overlaps_ignore_indices[:, :top_k].flatten()
# cons masks
ignore_assign_mask = (max_overlaps_normal < fg_threshold).astype(
np.float32) * (max_overlaps_ignore > max_overlaps_normal).astype(
np.float32)
max_overlaps = max_overlaps_normal * (1 - ignore_assign_mask).astype(np.float32) + \
max_overlaps_ignore * ignore_assign_mask
gt_assignment = gt_assignment_normal * (1- ignore_assign_mask) + \
gt_assignment_ignore * ignore_assign_mask
gt_assignment = gt_assignment.astype(np.int32)
labels = gt_boxes_perimg[gt_assignment, 4]
fg_mask = (max_overlaps >= fg_threshold).astype(
np.float32) * (1 - F.equal(labels, config.ignore_label))
bg_mask = (max_overlaps < config.bg_threshold_high).astype(
np.float32) * (max_overlaps >= config.bg_threshold_low).astype(
np.float32)
fg_mask = fg_mask.reshape(-1, top_k)
bg_mask = bg_mask.reshape(-1, top_k)
pos_max = config.num_rois * config.fg_ratio
fg_inds_mask = _bernoulli_sample_masks(
fg_mask[:,
0], pos_max, 1) if sampling else F.equal(fg_mask[:, 0], 0)
neg_max = config.num_rois - fg_inds_mask.sum()
bg_inds_mask = _bernoulli_sample_masks(
bg_mask[:,
0], neg_max, 1) if sampling else F.equal(bg_mask[:, 0], 0)
labels = labels * fg_mask.reshape(-1)
keep_mask = fg_inds_mask + bg_inds_mask
keep_mask = keep_mask + F.equal(keep_mask.sum(), 0)
# keep_inds = mask_to_inds(keep_mask)
_, keep_inds = F.cond_take(keep_mask > 0, keep_mask)
#keep_inds = keep_inds[:F.minimum(config.num_rois, keep_inds.shapeof()[0])]
# labels
labels = labels.reshape(-1, top_k)[keep_inds]
gt_assignment = gt_assignment.reshape(
-1, top_k)[keep_inds].reshape(-1).astype(np.int32)
target_boxes = gt_boxes_perimg[gt_assignment, :4]
# rois = all_rois.ai[keep_inds]
rois = all_rois[keep_inds]
# target_shape = (rois.shapeof()[0], top_k, rois.shapeof()[-1])
n, c = rois.shape[0], rois.shape[1]
target_rois = F.broadcast_to(F.expand_dims(rois, 1),
(n, top_k, c)).reshape(-1, c)
# target_rois = F.add_axis(rois, 1).broadcast(target_shape).reshape(-1, rois.shapeof()[-1])
bbox_targets = bbox_transform_opr(target_rois[:, 1:5],
target_boxes[:, :4])
if config.rcnn_bbox_normalize_targets:
std_opr = mge.tensor(config.bbox_normalize_stds[None, :]).to(
rois.device)
mean_opr = mge.tensor(config.bbox_normalize_means[None, :]).to(
rois.device)
minus_opr = mean_opr / std_opr
bbox_targets = bbox_targets / std_opr - minus_opr
bbox_targets = bbox_targets.reshape(-1, top_k * 4)
return_rois.append(rois)
return_labels.append(labels)
return_bbox_targets.append(bbox_targets)
if config.batch_per_gpu == 1:
rois, labels, bbox_targets = rois.detach(), labels.detach(
), bbox_targets.detach()
return rois, labels, bbox_targets
# return F.zero_grad(rois), F.zero_grad(labels), F.zero_grad(bbox_targets)
else:
return_rois = F.concat(return_rois, axis=0)
return_labels = F.concat(return_labels, axis=0)
return_bbox_targets = F.concat(return_bbox_targets, axis=0)
return_rois = return_rois.detach()
return_labels = return_labels.detach()
return_bbox_targets = return_bbox_targets.detach()
return return_rois, return_labels, return_bbox_targets
def fpn_roi_target(rpn_rois,
rpn_rois_inds,
im_info,
gt_boxes,
top_k_default=1):
return_rois = []
return_labels = []
return_bbox_targets = []
# get per image proposals and gt_boxes
for bid in range(config.train_batch_per_gpu):
gt_boxes_perimg = gt_boxes[bid, :int(im_info[bid, 5]), :] #1,5
top_k = top_k_default if int(im_info[bid, 5]) > 1 else 1
batch_inds = torch.ones(
(gt_boxes_perimg.shape[0], 1)).type_as(gt_boxes_perimg) * bid #1,1
#if config.proposal_append_gt:
gt_rois = torch.cat([batch_inds, gt_boxes_perimg[:, :4]],
axis=1) #1,1 cat 1,4 = 1,5
if bid == 0:
all_rois = torch.cat([rpn_rois[:rpn_rois_inds[0]], gt_rois],
axis=0)
else:
all_rois = torch.cat(
[rpn_rois[rpn_rois_inds[bid - 1]:rpn_rois_inds[bid]], gt_rois],
axis=0)
overlaps_normal, overlaps_ignore = box_overlap_ignore_opr(
all_rois[:, 1:5], gt_boxes_perimg)
overlaps_normal, overlaps_normal_indices = overlaps_normal.sort(
descending=True, dim=1) #2001,1 2039,39
overlaps_ignore, overlaps_ignore_indices = overlaps_ignore.sort(
descending=True, dim=1)
# gt max and indices, ignore max and indices
max_overlaps_normal = overlaps_normal[:, :top_k].flatten(
) #2001(???) 4078(2039*2)
gt_assignment_normal = overlaps_normal_indices[:, :top_k].flatten()
max_overlaps_ignore = overlaps_ignore[:, :top_k].flatten()
gt_assignment_ignore = overlaps_ignore_indices[:, :top_k].flatten()
# cons masks
ignore_assign_mask = (max_overlaps_normal < config.fg_threshold) * (
max_overlaps_ignore > max_overlaps_normal)
max_overlaps = max_overlaps_normal * ~ignore_assign_mask + \
max_overlaps_ignore * ignore_assign_mask
gt_assignment = gt_assignment_normal * ~ignore_assign_mask + \
gt_assignment_ignore * ignore_assign_mask
labels = gt_boxes_perimg[gt_assignment, 4]
fg_mask = (max_overlaps >= config.fg_threshold) * (labels !=
config.ignore_label)
bg_mask = (max_overlaps < config.bg_threshold_high) * (
max_overlaps >= config.bg_threshold_low)
labels[~fg_mask] = 0
fg_mask = fg_mask.reshape(-1, top_k)
bg_mask = bg_mask.reshape(-1, top_k)
pos_max = config.num_rois * config.fg_ratio
fg_inds_mask = _bernoulli_sample_masks(fg_mask[:, 0], pos_max, True)
neg_max = config.num_rois - fg_inds_mask.sum()
bg_inds_mask = _bernoulli_sample_masks(bg_mask[:, 0], neg_max, True)
keep_mask = fg_inds_mask + bg_inds_mask
# labels
labels = labels.reshape(-1, top_k)[keep_mask]
gt_assignment = gt_assignment.reshape(-1, top_k)[keep_mask].flatten()
target_boxes = gt_boxes_perimg[gt_assignment, :4]
rois = all_rois[keep_mask]
target_rois = rois.repeat(1, top_k).reshape(-1, all_rois.shape[-1])
bbox_targets = bbox_transform_opr(target_rois[:, 1:5], target_boxes)
if config.rcnn_bbox_normalize_targets:
std_opr = torch.tensor(
config.bbox_normalize_stds[None, :]).type_as(bbox_targets)
mean_opr = torch.tensor(
config.bbox_normalize_means[None, :]).type_as(bbox_targets)
minus_opr = mean_opr / std_opr
bbox_targets = bbox_targets / std_opr - minus_opr
bbox_targets = bbox_targets.reshape(-1, top_k * 4)
return_rois.append(rois)
return_labels.append(labels)
return_bbox_targets.append(bbox_targets)
if config.train_batch_per_gpu == 1:
return rois, labels, bbox_targets
else:
return_rois = torch.cat(return_rois, axis=0)
return_labels = torch.cat(return_labels, axis=0)
return_bbox_targets = torch.cat(return_bbox_targets, axis=0)
return return_rois, return_labels, return_bbox_targets
def _anchor_double_target(gt_boxes, im_info, all_anchors):
gt_boxes, im_info = gt_boxes.detach(), im_info.detach()
all_anchors = all_anchors.detach()
gt_boxes = gt_boxes[:im_info[5].astype(np.int32), :]
dummy = -F.ones([1, gt_boxes.shape[1]]).to(gt_boxes.device)
gt_boxes = F.concat([gt_boxes, dummy], axis=0)
valid_mask = 1 - (gt_boxes[:, 4] < 0).astype(np.float32)
anchor_centers = _compute_center(all_anchors)
gtboxes_centers = _compute_center(gt_boxes)
# gtboxes_centers = gtboxes_centers * valid_mask.unsqueeze(1)
gtboxes_centers = gtboxes_centers * F.expand_dims(valid_mask, axis=1)
N, K = all_anchors.shape[0], gt_boxes.shape[0]
an_centers = F.expand_dims(anchor_centers, axis=1)
gt_centers = F.expand_dims(gtboxes_centers, axis=0)
# an_centers = anchor_centers.unsqueeze(1).repeat(1, K, 1)
# gt_centers = gtboxes_centers.unsqueeze(0).repeat(N, 1, 1)
distance = F.abs(an_centers - gt_centers)
distance = F.sqrt(F.pow(distance, 2).sum(axis=2))
start = 0
end = 5
overlaps = box_overlap_opr(all_anchors[:, :4], gt_boxes[:, :4])
overlaps *= F.expand_dims(valid_mask, axis=0)
default_num = 16
ious_list = []
for l in range(start, end):
_, index = F.cond_take(all_anchors[:, 4] == l, all_anchors[:, 4])
level_dist = distance[index, :].transpose(1, 0)
ious = overlaps[index, :].transpose(1, 0)
sorted_index = F.argsort(level_dist, descending=False)
n = min(sorted_index.shape[1], default_num)
ious = F.gather(ious, 1, sorted_index[:, :n]).transpose(1, 0)
ious_list.append(ious)
ious = F.concat(ious_list, axis=0)
mean_var = F.mean(ious, axis=0)
std_var = F.std(ious, 0)
iou_thresh_per_gt = mean_var + std_var
iou_thresh_per_gt = F.maximum(iou_thresh_per_gt, 0.2)
# limits the anchor centers in the gtboxes
N, K = all_anchors.shape[0], gt_boxes.shape[0]
anchor_points = an_centers
pos_area = _compute_pos_area(gt_boxes, 0.3)
# pos_area = pos_area.unsqueeze(0).repeat(N, 1, 1)
pos_area = F.broadcast_to(F.expand_dims(pos_area, axis=0),
(N, K, pos_area.shape[-1]))
l = anchor_points[:, :, 0] - pos_area[:, :, 0]
r = pos_area[:, :, 2] - anchor_points[:, :, 0]
t = anchor_points[:, :, 1] - pos_area[:, :, 1]
b = pos_area[:, :, 3] - anchor_points[:, :, 1]
is_in_gt = F.stack([l, r, t, b], axis=2)
is_in_gt = is_in_gt.min(axis=2) > 0.1
valid_mask = (overlaps >= F.expand_dims(
iou_thresh_per_gt, axis=0)) * is_in_gt.astype(np.float32)
ious = overlaps * valid_mask
sorted_index = F.argsort(ious, 1)
sorted_overlaps = F.gather(ious, 1, sorted_index)
max_overlaps = sorted_overlaps[:, :2].flatten()
argmax_overlaps = sorted_index[:, :2].flatten()
n, c = all_anchors.shape
device = all_anchors.device
labels = -F.ones(2 * n).to(device)
positive_mask = (max_overlaps >= 0.2).to(device).astype(np.float32)
negative_mask = (max_overlaps < 0.2).to(device).astype(np.float32)
labels = positive_mask + labels * (1 - positive_mask) * (1 - negative_mask)
bbox_targets = gt_boxes[argmax_overlaps, :4]
all_anchors = F.broadcast_to(F.expand_dims(all_anchors, axis=1),
(n, 2, c)).reshape(-1, c)
bbox_targets = bbox_transform_opr(all_anchors[:, :4], bbox_targets)
labels_cat = gt_boxes[argmax_overlaps, 4]
labels_cat = labels_cat * (1 - F.equal(labels, -1).astype(
np.float32)) - F.equal(labels, -1).astype(np.float32)
return labels, bbox_targets, labels_cat
def rpn_anchor_target_opr_impl(gt_boxes,
im_info,
anchors,
clobber_positives=True,
ignore_label=-1,
background_label=0):
gt_boxes, im_info = gt_boxes.detach(), im_info.detach()
anchors = anchors.detach()
# NOTE: For multi-gpu version, this function should be re-written
a_shp0 = anchors.shape[0]
valid_gt_boxes = gt_boxes[:im_info[5], :]
valid_mask = (gt_boxes[:im_info[5], 4] > 0).astype(np.float32)
overlaps = box_overlap_opr(anchors[:, :4], valid_gt_boxes[:, :4])
overlaps = overlaps * valid_mask.unsqueeze(0)
argmax_overlaps = torch.argmax(overlaps, axis=1)
max_overlaps = torch.gather(overlaps, 1, argmax_overlaps.unsqueeze(1))
gt_argmax_overlaps = torch.argmax(overlaps, axis=0)
gt_argmax_overlaps = torch.gather(overlaps, 1,
gt_argmax_overlaps.unsqueeze(0))
cond_max_overlaps = overlaps.eq(gt_argmax_overlaps).astype(np.float32)
cmo_shape1 = cond_max_overlaps.shape[1]
gt_argmax_overlaps = torch.nonzero(cond_max_overlaps.flatten(),
as_tuple=False)
gt_argmax_overlaps = gt_argmax_overlaps // cmo_shape1
labels = ignore_label * F.ones(a_shp0)
fg_mask = (max_overlaps >= config.rpn_positive_overlap).astype(np.float32)
fg_mask[gt_argmax_overlaps] = 1
index = torch.nonzero(fg_mask, as_tuple=False).reshape(-1).long()
labels[index] = 1
bbox_targets = bbox_transform_opr(anchors, valid_gt_boxes[index, :4])
# fg_mask[gt_argmax_overlaps]
# --- megbrain fashion code ---
# argmax_overlaps = O.Argmax(overlaps, axis=1)
# max_overlaps = O.IndexingOneHot(overlaps, 1, argmax_overlaps)
# gt_argmax_overlaps = O.Argmax(overlaps, axis=0)
# gt_max_overlaps = O.IndexingOneHot(overlaps, 0, gt_argmax_overlaps)
# cond_max_overlaps = overlaps.eq(gt_max_overlaps.add_axis(0))
# cmo_shape1 = cond_max_overlaps.shape[1]
# gt_argmax_overlaps = \
# O.CondTake(cond_max_overlaps.flatten(), cond_max_overlaps.flatten(),
# 'EQ',1).outputs[1]
# # why should be divided by the cmo_shape1
# gt_argmax_overlaps = gt_argmax_overlaps // cmo_shape1
# labels = O.ones(a_shp0) * ignore_label
# const_one = O.ConstProvider(1.0)
# if not clobber_positives:
# labels = labels * (max_overlaps >= config.rpn_negative_overlap)
# fg_mask = (max_overlaps >= config.rpn_positive_overlap)
# fg_mask = fg_mask.set_ai[gt_argmax_overlaps](
# const_one.broadcast(gt_argmax_overlaps.shape))
# fg_mask_ind = O.CondTake(fg_mask, fg_mask, 'EQ', 1).outputs[1]
# labels = labels.set_ai[fg_mask_ind](const_one.broadcast(fg_mask_ind.shape))
# if clobber_positives:
# labels = labels * (max_overlaps >= config.rpn_negative_overlap)
# Here, we compute the targets for each anchors
# bbox_targets = bbox_transform_opr(
# anchors, valid_gt_boxes.ai[argmax_overlaps, :4])
return labels, bbox_targets
def _anchor_target(gt_boxes, im_info, all_anchors):
gt_boxes, im_info = gt_boxes.detach(), im_info.detach()
all_anchors = all_anchors.detach()
gt_boxes = gt_boxes[:im_info[5], :]
valid_mask = 1 - (gt_boxes[:, 4] < 0).astype(np.float32)
anchor_centers = _compute_center(all_anchors)
gtboxes_centers = _compute_center(gt_boxes) * F.expand_dims(valid_mask,
axis=0)
N, K = all_anchors.shape[0], gt_boxes.shape[0]
# an_centers = anchor_centers.unsqueeze(1).repeat(1, K, 1)
an_centers = F.expand_dims(anchor_centers, axis=1)
gt_centers = F.expand_dims(gtboxes_centers, axis=0)
# gt_centers = gtboxes_centers.unsqueeze(0).repeat(N, 1, 1)
distance = F.abs(an_centers - gt_centers)
distance = F.sqrt(F.pow(distance, 2).sum(axis=2))
start = 0
end = 5
overlaps = box_overlap_opr(all_anchors[:, :4], gt_boxes[:, :4])
overlaps = overlaps * valid_mask.unsqueeze(0)
default_num = 9
ious_list = []
for l in range(start, end):
index = torch.nonzero(all_anchors[:, 4].eq(l), as_tuple=False)[:, 0]
level_dist = level_dist[index, :].transpose(1, 0)
ious = distance[index, :].transpose(1, 0)
sorted_index = torch.argsort(ious, 1, descending=False)
n = min(default_num, sorted_index.shape[1])
ious = torch.gather(ious, 1, sorted_index[:, :n]).transpose(1, 0)
ious_list.append(ious)
ious = F.concat(ious_list, axis=0)
mean_var = ious.mean(0)
std_var = ious.std(0)
iou_thresh_per_gt = mean_var + std_var
iou_thresh_per_gt = torch.clamp(iou_thresh_per_gt, 0.35)
n = iou_thresh_per_gt.shape[0]
# limits the anchor centers in the gtboxes
N, K = all_anchors.shape[0], gt_boxes.shape[0]
anchor_points = an_centers
proxies = gt_boxes.unsqueeze(0).repeat(N, 1, 1)
l = anchor_points[:, :, 0] - proxies[:, :, 0]
r = proxies[:, :, 2] - anchor_points[:, :, 0]
t = anchor_points[:, :, 1] - proxies[:, :, 1]
b = proxies[:, :, 3] - anchor_points[:, :, 1]
is_in_gt = F.stack([l, r, t, b], axis=2)
is_in_gt = is_in_gt.min(axis=2) > 0.1
valid_mask = (overlaps >= iou_thresh_per_gt.unsqueeze(0)) * is_in_gt
ious = overlaps * valid_mask
argmax_overlaps = torch.argmax(ious, axis=1)
max_overlaps = torch.gather(ious, 1, argmax_overlaps.unsqueeze(1))
n = all_anchors.shape[0]
labels = -F.ones(n)
positive_mask = max_overlaps > 0
negative_mask = max_overlaps < config.rpn_negative_overlap
labels = positive_mask + labels * (1 - positive_mask) * (1 - negative_mask)
bbox_targets = gt_boxes[argmax_overlaps, :4]
bbox_targets = bbox_transform_opr(all_anchors[:, :4], bbox_targets)
labels_cat = gt_boxes[argmax_overlaps, 4]
labels_cat = labels_cat * (1 - labels.eq(0).astype(np.float32))
labels_cat = labels_cat * (1 - labels.eq(-1).astype(
np.float32)) - labels.eq(-1).astype(np.float32)
return labels, bbox_targets, labels_cat
