Spaces:
Runtime error
Runtime error
File size: 36,623 Bytes
b334e29 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 |
import torch
import torch.nn as nn
from mmcv.cnn import bias_init_with_prob, normal_init
from mmcv.ops import DeformConv2d, MaskedConv2d
from mmcv.runner import force_fp32
from mmdet.core import (anchor_inside_flags, build_anchor_generator,
build_assigner, build_bbox_coder, build_sampler,
calc_region, images_to_levels, multi_apply,
multiclass_nms, unmap)
from ..builder import HEADS, build_loss
from .anchor_head import AnchorHead
class FeatureAdaption(nn.Module):
"""Feature Adaption Module.
Feature Adaption Module is implemented based on DCN v1.
It uses anchor shape prediction rather than feature map to
predict offsets of deform conv layer.
Args:
in_channels (int): Number of channels in the input feature map.
out_channels (int): Number of channels in the output feature map.
kernel_size (int): Deformable conv kernel size.
deform_groups (int): Deformable conv group size.
"""
def __init__(self,
in_channels,
out_channels,
kernel_size=3,
deform_groups=4):
super(FeatureAdaption, self).__init__()
offset_channels = kernel_size * kernel_size * 2
self.conv_offset = nn.Conv2d(
2, deform_groups * offset_channels, 1, bias=False)
self.conv_adaption = DeformConv2d(
in_channels,
out_channels,
kernel_size=kernel_size,
padding=(kernel_size - 1) // 2,
deform_groups=deform_groups)
self.relu = nn.ReLU(inplace=True)
def init_weights(self):
normal_init(self.conv_offset, std=0.1)
normal_init(self.conv_adaption, std=0.01)
def forward(self, x, shape):
offset = self.conv_offset(shape.detach())
x = self.relu(self.conv_adaption(x, offset))
return x
@HEADS.register_module()
class GuidedAnchorHead(AnchorHead):
"""Guided-Anchor-based head (GA-RPN, GA-RetinaNet, etc.).
This GuidedAnchorHead will predict high-quality feature guided
anchors and locations where anchors will be kept in inference.
There are mainly 3 categories of bounding-boxes.
- Sampled 9 pairs for target assignment. (approxes)
- The square boxes where the predicted anchors are based on. (squares)
- Guided anchors.
Please refer to https://arxiv.org/abs/1901.03278 for more details.
Args:
num_classes (int): Number of classes.
in_channels (int): Number of channels in the input feature map.
feat_channels (int): Number of hidden channels.
approx_anchor_generator (dict): Config dict for approx generator
square_anchor_generator (dict): Config dict for square generator
anchor_coder (dict): Config dict for anchor coder
bbox_coder (dict): Config dict for bbox coder
reg_decoded_bbox (bool): If true, the regression loss would be
applied directly on decoded bounding boxes, converting both
the predicted boxes and regression targets to absolute
coordinates format. Default False. It should be `True` when
using `IoULoss`, `GIoULoss`, or `DIoULoss` in the bbox head.
deform_groups: (int): Group number of DCN in
FeatureAdaption module.
loc_filter_thr (float): Threshold to filter out unconcerned regions.
loss_loc (dict): Config of location loss.
loss_shape (dict): Config of anchor shape loss.
loss_cls (dict): Config of classification loss.
loss_bbox (dict): Config of bbox regression loss.
"""
def __init__(
self,
num_classes,
in_channels,
feat_channels=256,
approx_anchor_generator=dict(
type='AnchorGenerator',
octave_base_scale=8,
scales_per_octave=3,
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
square_anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
scales=[8],
strides=[4, 8, 16, 32, 64]),
anchor_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]
),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]
),
reg_decoded_bbox=False,
deform_groups=4,
loc_filter_thr=0.01,
train_cfg=None,
test_cfg=None,
loss_loc=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_shape=dict(type='BoundedIoULoss', beta=0.2, loss_weight=1.0),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)): # yapf: disable
super(AnchorHead, self).__init__()
self.in_channels = in_channels
self.num_classes = num_classes
self.feat_channels = feat_channels
self.deform_groups = deform_groups
self.loc_filter_thr = loc_filter_thr
# build approx_anchor_generator and square_anchor_generator
assert (approx_anchor_generator['octave_base_scale'] ==
square_anchor_generator['scales'][0])
assert (approx_anchor_generator['strides'] ==
square_anchor_generator['strides'])
self.approx_anchor_generator = build_anchor_generator(
approx_anchor_generator)
self.square_anchor_generator = build_anchor_generator(
square_anchor_generator)
self.approxs_per_octave = self.approx_anchor_generator \
.num_base_anchors[0]
self.reg_decoded_bbox = reg_decoded_bbox
# one anchor per location
self.num_anchors = 1
self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False)
self.loc_focal_loss = loss_loc['type'] in ['FocalLoss']
self.sampling = loss_cls['type'] not in ['FocalLoss']
self.ga_sampling = train_cfg is not None and hasattr(
train_cfg, 'ga_sampler')
if self.use_sigmoid_cls:
self.cls_out_channels = self.num_classes
else:
self.cls_out_channels = self.num_classes + 1
# build bbox_coder
self.anchor_coder = build_bbox_coder(anchor_coder)
self.bbox_coder = build_bbox_coder(bbox_coder)
# build losses
self.loss_loc = build_loss(loss_loc)
self.loss_shape = build_loss(loss_shape)
self.loss_cls = build_loss(loss_cls)
self.loss_bbox = build_loss(loss_bbox)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
if self.train_cfg:
self.assigner = build_assigner(self.train_cfg.assigner)
# use PseudoSampler when sampling is False
if self.sampling and hasattr(self.train_cfg, 'sampler'):
sampler_cfg = self.train_cfg.sampler
else:
sampler_cfg = dict(type='PseudoSampler')
self.sampler = build_sampler(sampler_cfg, context=self)
self.ga_assigner = build_assigner(self.train_cfg.ga_assigner)
if self.ga_sampling:
ga_sampler_cfg = self.train_cfg.ga_sampler
else:
ga_sampler_cfg = dict(type='PseudoSampler')
self.ga_sampler = build_sampler(ga_sampler_cfg, context=self)
self.fp16_enabled = False
self._init_layers()
def _init_layers(self):
self.relu = nn.ReLU(inplace=True)
self.conv_loc = nn.Conv2d(self.in_channels, 1, 1)
self.conv_shape = nn.Conv2d(self.in_channels, self.num_anchors * 2, 1)
self.feature_adaption = FeatureAdaption(
self.in_channels,
self.feat_channels,
kernel_size=3,
deform_groups=self.deform_groups)
self.conv_cls = MaskedConv2d(self.feat_channels,
self.num_anchors * self.cls_out_channels,
1)
self.conv_reg = MaskedConv2d(self.feat_channels, self.num_anchors * 4,
1)
def init_weights(self):
normal_init(self.conv_cls, std=0.01)
normal_init(self.conv_reg, std=0.01)
bias_cls = bias_init_with_prob(0.01)
normal_init(self.conv_loc, std=0.01, bias=bias_cls)
normal_init(self.conv_shape, std=0.01)
self.feature_adaption.init_weights()
def forward_single(self, x):
loc_pred = self.conv_loc(x)
shape_pred = self.conv_shape(x)
x = self.feature_adaption(x, shape_pred)
# masked conv is only used during inference for speed-up
if not self.training:
mask = loc_pred.sigmoid()[0] >= self.loc_filter_thr
else:
mask = None
cls_score = self.conv_cls(x, mask)
bbox_pred = self.conv_reg(x, mask)
return cls_score, bbox_pred, shape_pred, loc_pred
def forward(self, feats):
return multi_apply(self.forward_single, feats)
def get_sampled_approxs(self, featmap_sizes, img_metas, device='cuda'):
"""Get sampled approxs and inside flags according to feature map sizes.
Args:
featmap_sizes (list[tuple]): Multi-level feature map sizes.
img_metas (list[dict]): Image meta info.
device (torch.device | str): device for returned tensors
Returns:
tuple: approxes of each image, inside flags of each image
"""
num_imgs = len(img_metas)
# since feature map sizes of all images are the same, we only compute
# approxes for one time
multi_level_approxs = self.approx_anchor_generator.grid_anchors(
featmap_sizes, device=device)
approxs_list = [multi_level_approxs for _ in range(num_imgs)]
# for each image, we compute inside flags of multi level approxes
inside_flag_list = []
for img_id, img_meta in enumerate(img_metas):
multi_level_flags = []
multi_level_approxs = approxs_list[img_id]
# obtain valid flags for each approx first
multi_level_approx_flags = self.approx_anchor_generator \
.valid_flags(featmap_sizes,
img_meta['pad_shape'],
device=device)
for i, flags in enumerate(multi_level_approx_flags):
approxs = multi_level_approxs[i]
inside_flags_list = []
for i in range(self.approxs_per_octave):
split_valid_flags = flags[i::self.approxs_per_octave]
split_approxs = approxs[i::self.approxs_per_octave, :]
inside_flags = anchor_inside_flags(
split_approxs, split_valid_flags,
img_meta['img_shape'][:2],
self.train_cfg.allowed_border)
inside_flags_list.append(inside_flags)
# inside_flag for a position is true if any anchor in this
# position is true
inside_flags = (
torch.stack(inside_flags_list, 0).sum(dim=0) > 0)
multi_level_flags.append(inside_flags)
inside_flag_list.append(multi_level_flags)
return approxs_list, inside_flag_list
def get_anchors(self,
featmap_sizes,
shape_preds,
loc_preds,
img_metas,
use_loc_filter=False,
device='cuda'):
"""Get squares according to feature map sizes and guided anchors.
Args:
featmap_sizes (list[tuple]): Multi-level feature map sizes.
shape_preds (list[tensor]): Multi-level shape predictions.
loc_preds (list[tensor]): Multi-level location predictions.
img_metas (list[dict]): Image meta info.
use_loc_filter (bool): Use loc filter or not.
device (torch.device | str): device for returned tensors
Returns:
tuple: square approxs of each image, guided anchors of each image,
loc masks of each image
"""
num_imgs = len(img_metas)
num_levels = len(featmap_sizes)
# since feature map sizes of all images are the same, we only compute
# squares for one time
multi_level_squares = self.square_anchor_generator.grid_anchors(
featmap_sizes, device=device)
squares_list = [multi_level_squares for _ in range(num_imgs)]
# for each image, we compute multi level guided anchors
guided_anchors_list = []
loc_mask_list = []
for img_id, img_meta in enumerate(img_metas):
multi_level_guided_anchors = []
multi_level_loc_mask = []
for i in range(num_levels):
squares = squares_list[img_id][i]
shape_pred = shape_preds[i][img_id]
loc_pred = loc_preds[i][img_id]
guided_anchors, loc_mask = self._get_guided_anchors_single(
squares,
shape_pred,
loc_pred,
use_loc_filter=use_loc_filter)
multi_level_guided_anchors.append(guided_anchors)
multi_level_loc_mask.append(loc_mask)
guided_anchors_list.append(multi_level_guided_anchors)
loc_mask_list.append(multi_level_loc_mask)
return squares_list, guided_anchors_list, loc_mask_list
def _get_guided_anchors_single(self,
squares,
shape_pred,
loc_pred,
use_loc_filter=False):
"""Get guided anchors and loc masks for a single level.
Args:
square (tensor): Squares of a single level.
shape_pred (tensor): Shape predections of a single level.
loc_pred (tensor): Loc predections of a single level.
use_loc_filter (list[tensor]): Use loc filter or not.
Returns:
tuple: guided anchors, location masks
"""
# calculate location filtering mask
loc_pred = loc_pred.sigmoid().detach()
if use_loc_filter:
loc_mask = loc_pred >= self.loc_filter_thr
else:
loc_mask = loc_pred >= 0.0
mask = loc_mask.permute(1, 2, 0).expand(-1, -1, self.num_anchors)
mask = mask.contiguous().view(-1)
# calculate guided anchors
squares = squares[mask]
anchor_deltas = shape_pred.permute(1, 2, 0).contiguous().view(
-1, 2).detach()[mask]
bbox_deltas = anchor_deltas.new_full(squares.size(), 0)
bbox_deltas[:, 2:] = anchor_deltas
guided_anchors = self.anchor_coder.decode(
squares, bbox_deltas, wh_ratio_clip=1e-6)
return guided_anchors, mask
def ga_loc_targets(self, gt_bboxes_list, featmap_sizes):
"""Compute location targets for guided anchoring.
Each feature map is divided into positive, negative and ignore regions.
- positive regions: target 1, weight 1
- ignore regions: target 0, weight 0
- negative regions: target 0, weight 0.1
Args:
gt_bboxes_list (list[Tensor]): Gt bboxes of each image.
featmap_sizes (list[tuple]): Multi level sizes of each feature
maps.
Returns:
tuple
"""
anchor_scale = self.approx_anchor_generator.octave_base_scale
anchor_strides = self.approx_anchor_generator.strides
# Currently only supports same stride in x and y direction.
for stride in anchor_strides:
assert (stride[0] == stride[1])
anchor_strides = [stride[0] for stride in anchor_strides]
center_ratio = self.train_cfg.center_ratio
ignore_ratio = self.train_cfg.ignore_ratio
img_per_gpu = len(gt_bboxes_list)
num_lvls = len(featmap_sizes)
r1 = (1 - center_ratio) / 2
r2 = (1 - ignore_ratio) / 2
all_loc_targets = []
all_loc_weights = []
all_ignore_map = []
for lvl_id in range(num_lvls):
h, w = featmap_sizes[lvl_id]
loc_targets = torch.zeros(
img_per_gpu,
1,
h,
w,
device=gt_bboxes_list[0].device,
dtype=torch.float32)
loc_weights = torch.full_like(loc_targets, -1)
ignore_map = torch.zeros_like(loc_targets)
all_loc_targets.append(loc_targets)
all_loc_weights.append(loc_weights)
all_ignore_map.append(ignore_map)
for img_id in range(img_per_gpu):
gt_bboxes = gt_bboxes_list[img_id]
scale = torch.sqrt((gt_bboxes[:, 2] - gt_bboxes[:, 0]) *
(gt_bboxes[:, 3] - gt_bboxes[:, 1]))
min_anchor_size = scale.new_full(
(1, ), float(anchor_scale * anchor_strides[0]))
# assign gt bboxes to different feature levels w.r.t. their scales
target_lvls = torch.floor(
torch.log2(scale) - torch.log2(min_anchor_size) + 0.5)
target_lvls = target_lvls.clamp(min=0, max=num_lvls - 1).long()
for gt_id in range(gt_bboxes.size(0)):
lvl = target_lvls[gt_id].item()
# rescaled to corresponding feature map
gt_ = gt_bboxes[gt_id, :4] / anchor_strides[lvl]
# calculate ignore regions
ignore_x1, ignore_y1, ignore_x2, ignore_y2 = calc_region(
gt_, r2, featmap_sizes[lvl])
# calculate positive (center) regions
ctr_x1, ctr_y1, ctr_x2, ctr_y2 = calc_region(
gt_, r1, featmap_sizes[lvl])
all_loc_targets[lvl][img_id, 0, ctr_y1:ctr_y2 + 1,
ctr_x1:ctr_x2 + 1] = 1
all_loc_weights[lvl][img_id, 0, ignore_y1:ignore_y2 + 1,
ignore_x1:ignore_x2 + 1] = 0
all_loc_weights[lvl][img_id, 0, ctr_y1:ctr_y2 + 1,
ctr_x1:ctr_x2 + 1] = 1
# calculate ignore map on nearby low level feature
if lvl > 0:
d_lvl = lvl - 1
# rescaled to corresponding feature map
gt_ = gt_bboxes[gt_id, :4] / anchor_strides[d_lvl]
ignore_x1, ignore_y1, ignore_x2, ignore_y2 = calc_region(
gt_, r2, featmap_sizes[d_lvl])
all_ignore_map[d_lvl][img_id, 0, ignore_y1:ignore_y2 + 1,
ignore_x1:ignore_x2 + 1] = 1
# calculate ignore map on nearby high level feature
if lvl < num_lvls - 1:
u_lvl = lvl + 1
# rescaled to corresponding feature map
gt_ = gt_bboxes[gt_id, :4] / anchor_strides[u_lvl]
ignore_x1, ignore_y1, ignore_x2, ignore_y2 = calc_region(
gt_, r2, featmap_sizes[u_lvl])
all_ignore_map[u_lvl][img_id, 0, ignore_y1:ignore_y2 + 1,
ignore_x1:ignore_x2 + 1] = 1
for lvl_id in range(num_lvls):
# ignore negative regions w.r.t. ignore map
all_loc_weights[lvl_id][(all_loc_weights[lvl_id] < 0)
& (all_ignore_map[lvl_id] > 0)] = 0
# set negative regions with weight 0.1
all_loc_weights[lvl_id][all_loc_weights[lvl_id] < 0] = 0.1
# loc average factor to balance loss
loc_avg_factor = sum(
[t.size(0) * t.size(-1) * t.size(-2)
for t in all_loc_targets]) / 200
return all_loc_targets, all_loc_weights, loc_avg_factor
def _ga_shape_target_single(self,
flat_approxs,
inside_flags,
flat_squares,
gt_bboxes,
gt_bboxes_ignore,
img_meta,
unmap_outputs=True):
"""Compute guided anchoring targets.
This function returns sampled anchors and gt bboxes directly
rather than calculates regression targets.
Args:
flat_approxs (Tensor): flat approxs of a single image,
shape (n, 4)
inside_flags (Tensor): inside flags of a single image,
shape (n, ).
flat_squares (Tensor): flat squares of a single image,
shape (approxs_per_octave * n, 4)
gt_bboxes (Tensor): Ground truth bboxes of a single image.
img_meta (dict): Meta info of a single image.
approxs_per_octave (int): number of approxs per octave
cfg (dict): RPN train configs.
unmap_outputs (bool): unmap outputs or not.
Returns:
tuple
"""
if not inside_flags.any():
return (None, ) * 5
# assign gt and sample anchors
expand_inside_flags = inside_flags[:, None].expand(
-1, self.approxs_per_octave).reshape(-1)
approxs = flat_approxs[expand_inside_flags, :]
squares = flat_squares[inside_flags, :]
assign_result = self.ga_assigner.assign(approxs, squares,
self.approxs_per_octave,
gt_bboxes, gt_bboxes_ignore)
sampling_result = self.ga_sampler.sample(assign_result, squares,
gt_bboxes)
bbox_anchors = torch.zeros_like(squares)
bbox_gts = torch.zeros_like(squares)
bbox_weights = torch.zeros_like(squares)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
bbox_anchors[pos_inds, :] = sampling_result.pos_bboxes
bbox_gts[pos_inds, :] = sampling_result.pos_gt_bboxes
bbox_weights[pos_inds, :] = 1.0
# map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_squares.size(0)
bbox_anchors = unmap(bbox_anchors, num_total_anchors, inside_flags)
bbox_gts = unmap(bbox_gts, num_total_anchors, inside_flags)
bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags)
return (bbox_anchors, bbox_gts, bbox_weights, pos_inds, neg_inds)
def ga_shape_targets(self,
approx_list,
inside_flag_list,
square_list,
gt_bboxes_list,
img_metas,
gt_bboxes_ignore_list=None,
unmap_outputs=True):
"""Compute guided anchoring targets.
Args:
approx_list (list[list]): Multi level approxs of each image.
inside_flag_list (list[list]): Multi level inside flags of each
image.
square_list (list[list]): Multi level squares of each image.
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image.
img_metas (list[dict]): Meta info of each image.
gt_bboxes_ignore_list (list[Tensor]): ignore list of gt bboxes.
unmap_outputs (bool): unmap outputs or not.
Returns:
tuple
"""
num_imgs = len(img_metas)
assert len(approx_list) == len(inside_flag_list) == len(
square_list) == num_imgs
# anchor number of multi levels
num_level_squares = [squares.size(0) for squares in square_list[0]]
# concat all level anchors and flags to a single tensor
inside_flag_flat_list = []
approx_flat_list = []
square_flat_list = []
for i in range(num_imgs):
assert len(square_list[i]) == len(inside_flag_list[i])
inside_flag_flat_list.append(torch.cat(inside_flag_list[i]))
approx_flat_list.append(torch.cat(approx_list[i]))
square_flat_list.append(torch.cat(square_list[i]))
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
(all_bbox_anchors, all_bbox_gts, all_bbox_weights, pos_inds_list,
neg_inds_list) = multi_apply(
self._ga_shape_target_single,
approx_flat_list,
inside_flag_flat_list,
square_flat_list,
gt_bboxes_list,
gt_bboxes_ignore_list,
img_metas,
unmap_outputs=unmap_outputs)
# no valid anchors
if any([bbox_anchors is None for bbox_anchors in all_bbox_anchors]):
return None
# sampled anchors of all images
num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list])
num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list])
# split targets to a list w.r.t. multiple levels
bbox_anchors_list = images_to_levels(all_bbox_anchors,
num_level_squares)
bbox_gts_list = images_to_levels(all_bbox_gts, num_level_squares)
bbox_weights_list = images_to_levels(all_bbox_weights,
num_level_squares)
return (bbox_anchors_list, bbox_gts_list, bbox_weights_list,
num_total_pos, num_total_neg)
def loss_shape_single(self, shape_pred, bbox_anchors, bbox_gts,
anchor_weights, anchor_total_num):
shape_pred = shape_pred.permute(0, 2, 3, 1).contiguous().view(-1, 2)
bbox_anchors = bbox_anchors.contiguous().view(-1, 4)
bbox_gts = bbox_gts.contiguous().view(-1, 4)
anchor_weights = anchor_weights.contiguous().view(-1, 4)
bbox_deltas = bbox_anchors.new_full(bbox_anchors.size(), 0)
bbox_deltas[:, 2:] += shape_pred
# filter out negative samples to speed-up weighted_bounded_iou_loss
inds = torch.nonzero(
anchor_weights[:, 0] > 0, as_tuple=False).squeeze(1)
bbox_deltas_ = bbox_deltas[inds]
bbox_anchors_ = bbox_anchors[inds]
bbox_gts_ = bbox_gts[inds]
anchor_weights_ = anchor_weights[inds]
pred_anchors_ = self.anchor_coder.decode(
bbox_anchors_, bbox_deltas_, wh_ratio_clip=1e-6)
loss_shape = self.loss_shape(
pred_anchors_,
bbox_gts_,
anchor_weights_,
avg_factor=anchor_total_num)
return loss_shape
def loss_loc_single(self, loc_pred, loc_target, loc_weight,
loc_avg_factor):
loss_loc = self.loss_loc(
loc_pred.reshape(-1, 1),
loc_target.reshape(-1).long(),
loc_weight.reshape(-1),
avg_factor=loc_avg_factor)
return loss_loc
@force_fp32(
apply_to=('cls_scores', 'bbox_preds', 'shape_preds', 'loc_preds'))
def loss(self,
cls_scores,
bbox_preds,
shape_preds,
loc_preds,
gt_bboxes,
gt_labels,
img_metas,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == self.approx_anchor_generator.num_levels
device = cls_scores[0].device
# get loc targets
loc_targets, loc_weights, loc_avg_factor = self.ga_loc_targets(
gt_bboxes, featmap_sizes)
# get sampled approxes
approxs_list, inside_flag_list = self.get_sampled_approxs(
featmap_sizes, img_metas, device=device)
# get squares and guided anchors
squares_list, guided_anchors_list, _ = self.get_anchors(
featmap_sizes, shape_preds, loc_preds, img_metas, device=device)
# get shape targets
shape_targets = self.ga_shape_targets(approxs_list, inside_flag_list,
squares_list, gt_bboxes,
img_metas)
if shape_targets is None:
return None
(bbox_anchors_list, bbox_gts_list, anchor_weights_list, anchor_fg_num,
anchor_bg_num) = shape_targets
anchor_total_num = (
anchor_fg_num if not self.ga_sampling else anchor_fg_num +
anchor_bg_num)
# get anchor targets
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = self.get_targets(
guided_anchors_list,
inside_flag_list,
gt_bboxes,
img_metas,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels)
if cls_reg_targets is None:
return None
(labels_list, label_weights_list, bbox_targets_list, bbox_weights_list,
num_total_pos, num_total_neg) = cls_reg_targets
num_total_samples = (
num_total_pos + num_total_neg if self.sampling else num_total_pos)
# anchor number of multi levels
num_level_anchors = [
anchors.size(0) for anchors in guided_anchors_list[0]
]
# concat all level anchors to a single tensor
concat_anchor_list = []
for i in range(len(guided_anchors_list)):
concat_anchor_list.append(torch.cat(guided_anchors_list[i]))
all_anchor_list = images_to_levels(concat_anchor_list,
num_level_anchors)
# get classification and bbox regression losses
losses_cls, losses_bbox = multi_apply(
self.loss_single,
cls_scores,
bbox_preds,
all_anchor_list,
labels_list,
label_weights_list,
bbox_targets_list,
bbox_weights_list,
num_total_samples=num_total_samples)
# get anchor location loss
losses_loc = []
for i in range(len(loc_preds)):
loss_loc = self.loss_loc_single(
loc_preds[i],
loc_targets[i],
loc_weights[i],
loc_avg_factor=loc_avg_factor)
losses_loc.append(loss_loc)
# get anchor shape loss
losses_shape = []
for i in range(len(shape_preds)):
loss_shape = self.loss_shape_single(
shape_preds[i],
bbox_anchors_list[i],
bbox_gts_list[i],
anchor_weights_list[i],
anchor_total_num=anchor_total_num)
losses_shape.append(loss_shape)
return dict(
loss_cls=losses_cls,
loss_bbox=losses_bbox,
loss_shape=losses_shape,
loss_loc=losses_loc)
@force_fp32(
apply_to=('cls_scores', 'bbox_preds', 'shape_preds', 'loc_preds'))
def get_bboxes(self,
cls_scores,
bbox_preds,
shape_preds,
loc_preds,
img_metas,
cfg=None,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(shape_preds) == len(
loc_preds)
num_levels = len(cls_scores)
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
device = cls_scores[0].device
# get guided anchors
_, guided_anchors, loc_masks = self.get_anchors(
featmap_sizes,
shape_preds,
loc_preds,
img_metas,
use_loc_filter=not self.training,
device=device)
result_list = []
for img_id in range(len(img_metas)):
cls_score_list = [
cls_scores[i][img_id].detach() for i in range(num_levels)
]
bbox_pred_list = [
bbox_preds[i][img_id].detach() for i in range(num_levels)
]
guided_anchor_list = [
guided_anchors[img_id][i].detach() for i in range(num_levels)
]
loc_mask_list = [
loc_masks[img_id][i].detach() for i in range(num_levels)
]
img_shape = img_metas[img_id]['img_shape']
scale_factor = img_metas[img_id]['scale_factor']
proposals = self._get_bboxes_single(cls_score_list, bbox_pred_list,
guided_anchor_list,
loc_mask_list, img_shape,
scale_factor, cfg, rescale)
result_list.append(proposals)
return result_list
def _get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
mlvl_masks,
img_shape,
scale_factor,
cfg,
rescale=False):
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors, mask in zip(cls_scores, bbox_preds,
mlvl_anchors,
mlvl_masks):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
# if no location is kept, end.
if mask.sum() == 0:
continue
# reshape scores and bbox_pred
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
# filter scores, bbox_pred w.r.t. mask.
# anchors are filtered in get_anchors() beforehand.
scores = scores[mask, :]
bbox_pred = bbox_pred[mask, :]
if scores.dim() == 0:
anchors = anchors.unsqueeze(0)
scores = scores.unsqueeze(0)
bbox_pred = bbox_pred.unsqueeze(0)
# filter anchors, bbox_pred, scores w.r.t. scores
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
# remind that we set FG labels to [0, num_class-1]
# since mmdet v2.0
# BG cat_id: num_class
max_scores, _ = scores[:, :-1].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = self.bbox_coder.decode(
anchors, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
# multi class NMS
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
|