|
import torch |
|
import torch.nn as nn |
|
import torch.nn.functional as F |
|
from mmcv.cnn import Scale, normal_init |
|
from mmcv.runner import force_fp32 |
|
|
|
from mmdet.core import distance2bbox, multi_apply, multiclass_nms, reduce_mean |
|
from ..builder import HEADS, build_loss |
|
from .anchor_free_head import AnchorFreeHead |
|
|
|
INF = 1e8 |
|
|
|
|
|
@HEADS.register_module() |
|
class FCOSHead(AnchorFreeHead): |
|
"""Anchor-free head used in `FCOS <https://arxiv.org/abs/1904.01355>`_. |
|
|
|
The FCOS head does not use anchor boxes. Instead bounding boxes are |
|
predicted at each pixel and a centerness measure is used to suppress |
|
low-quality predictions. |
|
Here norm_on_bbox, centerness_on_reg, dcn_on_last_conv are training |
|
tricks used in official repo, which will bring remarkable mAP gains |
|
of up to 4.9. Please see https://github.com/tianzhi0549/FCOS for |
|
more detail. |
|
|
|
Args: |
|
num_classes (int): Number of categories excluding the background |
|
category. |
|
in_channels (int): Number of channels in the input feature map. |
|
strides (list[int] | list[tuple[int, int]]): Strides of points |
|
in multiple feature levels. Default: (4, 8, 16, 32, 64). |
|
regress_ranges (tuple[tuple[int, int]]): Regress range of multiple |
|
level points. |
|
center_sampling (bool): If true, use center sampling. Default: False. |
|
center_sample_radius (float): Radius of center sampling. Default: 1.5. |
|
norm_on_bbox (bool): If true, normalize the regression targets |
|
with FPN strides. Default: False. |
|
centerness_on_reg (bool): If true, position centerness on the |
|
regress branch. Please refer to https://github.com/tianzhi0549/FCOS/issues/89#issuecomment-516877042. |
|
Default: False. |
|
conv_bias (bool | str): If specified as `auto`, it will be decided by the |
|
norm_cfg. Bias of conv will be set as True if `norm_cfg` is None, otherwise |
|
False. Default: "auto". |
|
loss_cls (dict): Config of classification loss. |
|
loss_bbox (dict): Config of localization loss. |
|
loss_centerness (dict): Config of centerness loss. |
|
norm_cfg (dict): dictionary to construct and config norm layer. |
|
Default: norm_cfg=dict(type='GN', num_groups=32, requires_grad=True). |
|
|
|
Example: |
|
>>> self = FCOSHead(11, 7) |
|
>>> feats = [torch.rand(1, 7, s, s) for s in [4, 8, 16, 32, 64]] |
|
>>> cls_score, bbox_pred, centerness = self.forward(feats) |
|
>>> assert len(cls_score) == len(self.scales) |
|
""" |
|
|
|
def __init__(self, |
|
num_classes, |
|
in_channels, |
|
regress_ranges=((-1, 64), (64, 128), (128, 256), (256, 512), |
|
(512, INF)), |
|
center_sampling=False, |
|
center_sample_radius=1.5, |
|
norm_on_bbox=False, |
|
centerness_on_reg=False, |
|
loss_cls=dict( |
|
type='FocalLoss', |
|
use_sigmoid=True, |
|
gamma=2.0, |
|
alpha=0.25, |
|
loss_weight=1.0), |
|
loss_bbox=dict(type='IoULoss', loss_weight=1.0), |
|
loss_centerness=dict( |
|
type='CrossEntropyLoss', |
|
use_sigmoid=True, |
|
loss_weight=1.0), |
|
norm_cfg=dict(type='GN', num_groups=32, requires_grad=True), |
|
**kwargs): |
|
self.regress_ranges = regress_ranges |
|
self.center_sampling = center_sampling |
|
self.center_sample_radius = center_sample_radius |
|
self.norm_on_bbox = norm_on_bbox |
|
self.centerness_on_reg = centerness_on_reg |
|
super().__init__( |
|
num_classes, |
|
in_channels, |
|
loss_cls=loss_cls, |
|
loss_bbox=loss_bbox, |
|
norm_cfg=norm_cfg, |
|
**kwargs) |
|
self.loss_centerness = build_loss(loss_centerness) |
|
|
|
def _init_layers(self): |
|
"""Initialize layers of the head.""" |
|
super()._init_layers() |
|
self.conv_centerness = nn.Conv2d(self.feat_channels, 1, 3, padding=1) |
|
self.scales = nn.ModuleList([Scale(1.0) for _ in self.strides]) |
|
|
|
def init_weights(self): |
|
"""Initialize weights of the head.""" |
|
super().init_weights() |
|
normal_init(self.conv_centerness, std=0.01) |
|
|
|
def forward(self, feats): |
|
"""Forward features from the upstream network. |
|
|
|
Args: |
|
feats (tuple[Tensor]): Features from the upstream network, each is |
|
a 4D-tensor. |
|
|
|
Returns: |
|
tuple: |
|
cls_scores (list[Tensor]): Box scores for each scale level, \ |
|
each is a 4D-tensor, the channel number is \ |
|
num_points * num_classes. |
|
bbox_preds (list[Tensor]): Box energies / deltas for each \ |
|
scale level, each is a 4D-tensor, the channel number is \ |
|
num_points * 4. |
|
centernesses (list[Tensor]): centerness for each scale level, \ |
|
each is a 4D-tensor, the channel number is num_points * 1. |
|
""" |
|
return multi_apply(self.forward_single, feats, self.scales, |
|
self.strides) |
|
|
|
def forward_single(self, x, scale, stride): |
|
"""Forward features of a single scale level. |
|
|
|
Args: |
|
x (Tensor): FPN feature maps of the specified stride. |
|
scale (:obj: `mmcv.cnn.Scale`): Learnable scale module to resize |
|
the bbox prediction. |
|
stride (int): The corresponding stride for feature maps, only |
|
used to normalize the bbox prediction when self.norm_on_bbox |
|
is True. |
|
|
|
Returns: |
|
tuple: scores for each class, bbox predictions and centerness \ |
|
predictions of input feature maps. |
|
""" |
|
cls_score, bbox_pred, cls_feat, reg_feat = super().forward_single(x) |
|
if self.centerness_on_reg: |
|
centerness = self.conv_centerness(reg_feat) |
|
else: |
|
centerness = self.conv_centerness(cls_feat) |
|
|
|
|
|
bbox_pred = scale(bbox_pred).float() |
|
if self.norm_on_bbox: |
|
bbox_pred = F.relu(bbox_pred) |
|
if not self.training: |
|
bbox_pred *= stride |
|
else: |
|
bbox_pred = bbox_pred.exp() |
|
return cls_score, bbox_pred, centerness |
|
|
|
@force_fp32(apply_to=('cls_scores', 'bbox_preds', 'centernesses')) |
|
def loss(self, |
|
cls_scores, |
|
bbox_preds, |
|
centernesses, |
|
gt_bboxes, |
|
gt_labels, |
|
img_metas, |
|
gt_bboxes_ignore=None): |
|
"""Compute loss of the head. |
|
|
|
Args: |
|
cls_scores (list[Tensor]): Box scores for each scale level, |
|
each is a 4D-tensor, the channel number is |
|
num_points * num_classes. |
|
bbox_preds (list[Tensor]): Box energies / deltas for each scale |
|
level, each is a 4D-tensor, the channel number is |
|
num_points * 4. |
|
centernesses (list[Tensor]): centerness for each scale level, each |
|
is a 4D-tensor, the channel number is num_points * 1. |
|
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with |
|
shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format. |
|
gt_labels (list[Tensor]): class indices corresponding to each box |
|
img_metas (list[dict]): Meta information of each image, e.g., |
|
image size, scaling factor, etc. |
|
gt_bboxes_ignore (None | list[Tensor]): specify which bounding |
|
boxes can be ignored when computing the loss. |
|
|
|
Returns: |
|
dict[str, Tensor]: A dictionary of loss components. |
|
""" |
|
assert len(cls_scores) == len(bbox_preds) == len(centernesses) |
|
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores] |
|
all_level_points = self.get_points(featmap_sizes, bbox_preds[0].dtype, |
|
bbox_preds[0].device) |
|
labels, bbox_targets = self.get_targets(all_level_points, gt_bboxes, |
|
gt_labels) |
|
|
|
num_imgs = cls_scores[0].size(0) |
|
|
|
flatten_cls_scores = [ |
|
cls_score.permute(0, 2, 3, 1).reshape(-1, self.cls_out_channels) |
|
for cls_score in cls_scores |
|
] |
|
flatten_bbox_preds = [ |
|
bbox_pred.permute(0, 2, 3, 1).reshape(-1, 4) |
|
for bbox_pred in bbox_preds |
|
] |
|
flatten_centerness = [ |
|
centerness.permute(0, 2, 3, 1).reshape(-1) |
|
for centerness in centernesses |
|
] |
|
flatten_cls_scores = torch.cat(flatten_cls_scores) |
|
flatten_bbox_preds = torch.cat(flatten_bbox_preds) |
|
flatten_centerness = torch.cat(flatten_centerness) |
|
flatten_labels = torch.cat(labels) |
|
flatten_bbox_targets = torch.cat(bbox_targets) |
|
|
|
flatten_points = torch.cat( |
|
[points.repeat(num_imgs, 1) for points in all_level_points]) |
|
|
|
|
|
bg_class_ind = self.num_classes |
|
pos_inds = ((flatten_labels >= 0) |
|
& (flatten_labels < bg_class_ind)).nonzero().reshape(-1) |
|
num_pos = torch.tensor( |
|
len(pos_inds), dtype=torch.float, device=bbox_preds[0].device) |
|
num_pos = max(reduce_mean(num_pos), 1.0) |
|
loss_cls = self.loss_cls( |
|
flatten_cls_scores, flatten_labels, avg_factor=num_pos) |
|
|
|
pos_bbox_preds = flatten_bbox_preds[pos_inds] |
|
pos_centerness = flatten_centerness[pos_inds] |
|
|
|
if len(pos_inds) > 0: |
|
pos_bbox_targets = flatten_bbox_targets[pos_inds] |
|
pos_centerness_targets = self.centerness_target(pos_bbox_targets) |
|
pos_points = flatten_points[pos_inds] |
|
pos_decoded_bbox_preds = distance2bbox(pos_points, pos_bbox_preds) |
|
pos_decoded_target_preds = distance2bbox(pos_points, |
|
pos_bbox_targets) |
|
|
|
centerness_denorm = max( |
|
reduce_mean(pos_centerness_targets.sum().detach()), 1e-6) |
|
loss_bbox = self.loss_bbox( |
|
pos_decoded_bbox_preds, |
|
pos_decoded_target_preds, |
|
weight=pos_centerness_targets, |
|
avg_factor=centerness_denorm) |
|
loss_centerness = self.loss_centerness( |
|
pos_centerness, pos_centerness_targets, avg_factor=num_pos) |
|
else: |
|
loss_bbox = pos_bbox_preds.sum() |
|
loss_centerness = pos_centerness.sum() |
|
|
|
return dict( |
|
loss_cls=loss_cls, |
|
loss_bbox=loss_bbox, |
|
loss_centerness=loss_centerness) |
|
|
|
@force_fp32(apply_to=('cls_scores', 'bbox_preds', 'centernesses')) |
|
def get_bboxes(self, |
|
cls_scores, |
|
bbox_preds, |
|
centernesses, |
|
img_metas, |
|
cfg=None, |
|
rescale=False, |
|
with_nms=True): |
|
"""Transform network output for a batch into bbox predictions. |
|
|
|
Args: |
|
cls_scores (list[Tensor]): Box scores for each scale level |
|
with shape (N, num_points * num_classes, H, W). |
|
bbox_preds (list[Tensor]): Box energies / deltas for each scale |
|
level with shape (N, num_points * 4, H, W). |
|
centernesses (list[Tensor]): Centerness for each scale level with |
|
shape (N, num_points * 1, H, W). |
|
img_metas (list[dict]): Meta information of each image, e.g., |
|
image size, scaling factor, etc. |
|
cfg (mmcv.Config | None): Test / postprocessing configuration, |
|
if None, test_cfg would be used. Default: None. |
|
rescale (bool): If True, return boxes in original image space. |
|
Default: False. |
|
with_nms (bool): If True, do nms before return boxes. |
|
Default: True. |
|
|
|
Returns: |
|
list[tuple[Tensor, Tensor]]: Each item in result_list is 2-tuple. |
|
The first item is an (n, 5) tensor, where 5 represent |
|
(tl_x, tl_y, br_x, br_y, score) and the score between 0 and 1. |
|
The shape of the second tensor in the tuple is (n,), and |
|
each element represents the class label of the corresponding |
|
box. |
|
""" |
|
assert len(cls_scores) == len(bbox_preds) |
|
num_levels = len(cls_scores) |
|
|
|
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores] |
|
mlvl_points = self.get_points(featmap_sizes, bbox_preds[0].dtype, |
|
bbox_preds[0].device) |
|
|
|
cls_score_list = [cls_scores[i].detach() for i in range(num_levels)] |
|
bbox_pred_list = [bbox_preds[i].detach() for i in range(num_levels)] |
|
centerness_pred_list = [ |
|
centernesses[i].detach() for i in range(num_levels) |
|
] |
|
if torch.onnx.is_in_onnx_export(): |
|
assert len( |
|
img_metas |
|
) == 1, 'Only support one input image while in exporting to ONNX' |
|
img_shapes = img_metas[0]['img_shape_for_onnx'] |
|
else: |
|
img_shapes = [ |
|
img_metas[i]['img_shape'] |
|
for i in range(cls_scores[0].shape[0]) |
|
] |
|
scale_factors = [ |
|
img_metas[i]['scale_factor'] for i in range(cls_scores[0].shape[0]) |
|
] |
|
result_list = self._get_bboxes(cls_score_list, bbox_pred_list, |
|
centerness_pred_list, mlvl_points, |
|
img_shapes, scale_factors, cfg, rescale, |
|
with_nms) |
|
return result_list |
|
|
|
def _get_bboxes(self, |
|
cls_scores, |
|
bbox_preds, |
|
centernesses, |
|
mlvl_points, |
|
img_shapes, |
|
scale_factors, |
|
cfg, |
|
rescale=False, |
|
with_nms=True): |
|
"""Transform outputs for a single batch item into bbox predictions. |
|
|
|
Args: |
|
cls_scores (list[Tensor]): Box scores for a single scale level |
|
with shape (N, num_points * num_classes, H, W). |
|
bbox_preds (list[Tensor]): Box energies / deltas for a single scale |
|
level with shape (N, num_points * 4, H, W). |
|
centernesses (list[Tensor]): Centerness for a single scale level |
|
with shape (N, num_points * 4, H, W). |
|
mlvl_points (list[Tensor]): Box reference for a single scale level |
|
with shape (num_total_points, 4). |
|
img_shapes (list[tuple[int]]): Shape of the input image, |
|
list[(height, width, 3)]. |
|
scale_factors (list[ndarray]): Scale factor of the image arrange as |
|
(w_scale, h_scale, w_scale, h_scale). |
|
cfg (mmcv.Config | None): Test / postprocessing configuration, |
|
if None, test_cfg would be used. |
|
rescale (bool): If True, return boxes in original image space. |
|
Default: False. |
|
with_nms (bool): If True, do nms before return boxes. |
|
Default: True. |
|
|
|
Returns: |
|
tuple(Tensor): |
|
det_bboxes (Tensor): BBox predictions in shape (n, 5), where |
|
the first 4 columns are bounding box positions |
|
(tl_x, tl_y, br_x, br_y) and the 5-th column is a score |
|
between 0 and 1. |
|
det_labels (Tensor): A (n,) tensor where each item is the |
|
predicted class label of the corresponding box. |
|
""" |
|
cfg = self.test_cfg if cfg is None else cfg |
|
assert len(cls_scores) == len(bbox_preds) == len(mlvl_points) |
|
device = cls_scores[0].device |
|
batch_size = cls_scores[0].shape[0] |
|
|
|
nms_pre_tensor = torch.tensor( |
|
cfg.get('nms_pre', -1), device=device, dtype=torch.long) |
|
mlvl_bboxes = [] |
|
mlvl_scores = [] |
|
mlvl_centerness = [] |
|
for cls_score, bbox_pred, centerness, points in zip( |
|
cls_scores, bbox_preds, centernesses, mlvl_points): |
|
assert cls_score.size()[-2:] == bbox_pred.size()[-2:] |
|
scores = cls_score.permute(0, 2, 3, 1).reshape( |
|
batch_size, -1, self.cls_out_channels).sigmoid() |
|
centerness = centerness.permute(0, 2, 3, |
|
1).reshape(batch_size, |
|
-1).sigmoid() |
|
|
|
bbox_pred = bbox_pred.permute(0, 2, 3, |
|
1).reshape(batch_size, -1, 4) |
|
|
|
if nms_pre_tensor > 0 and (torch.onnx.is_in_onnx_export() |
|
or scores.shape[-2] > nms_pre_tensor): |
|
from torch import _shape_as_tensor |
|
|
|
num_anchor = _shape_as_tensor(scores)[-2].to(device) |
|
nms_pre = torch.where(nms_pre_tensor < num_anchor, |
|
nms_pre_tensor, num_anchor) |
|
|
|
max_scores, _ = (scores * centerness[..., None]).max(-1) |
|
_, topk_inds = max_scores.topk(nms_pre) |
|
points = points[topk_inds, :] |
|
batch_inds = torch.arange(batch_size).view( |
|
-1, 1).expand_as(topk_inds).long() |
|
bbox_pred = bbox_pred[batch_inds, topk_inds, :] |
|
scores = scores[batch_inds, topk_inds, :] |
|
centerness = centerness[batch_inds, topk_inds] |
|
|
|
bboxes = distance2bbox(points, bbox_pred, max_shape=img_shapes) |
|
mlvl_bboxes.append(bboxes) |
|
mlvl_scores.append(scores) |
|
mlvl_centerness.append(centerness) |
|
|
|
batch_mlvl_bboxes = torch.cat(mlvl_bboxes, dim=1) |
|
if rescale: |
|
batch_mlvl_bboxes /= batch_mlvl_bboxes.new_tensor( |
|
scale_factors).unsqueeze(1) |
|
batch_mlvl_scores = torch.cat(mlvl_scores, dim=1) |
|
batch_mlvl_centerness = torch.cat(mlvl_centerness, dim=1) |
|
|
|
|
|
deploy_nms_pre = cfg.get('deploy_nms_pre', -1) |
|
if deploy_nms_pre > 0 and torch.onnx.is_in_onnx_export(): |
|
batch_mlvl_scores, _ = ( |
|
batch_mlvl_scores * |
|
batch_mlvl_centerness.unsqueeze(2).expand_as(batch_mlvl_scores) |
|
).max(-1) |
|
_, topk_inds = batch_mlvl_scores.topk(deploy_nms_pre) |
|
batch_inds = torch.arange(batch_mlvl_scores.shape[0]).view( |
|
-1, 1).expand_as(topk_inds) |
|
batch_mlvl_scores = batch_mlvl_scores[batch_inds, topk_inds, :] |
|
batch_mlvl_bboxes = batch_mlvl_bboxes[batch_inds, topk_inds, :] |
|
batch_mlvl_centerness = batch_mlvl_centerness[batch_inds, |
|
topk_inds] |
|
|
|
|
|
|
|
padding = batch_mlvl_scores.new_zeros(batch_size, |
|
batch_mlvl_scores.shape[1], 1) |
|
batch_mlvl_scores = torch.cat([batch_mlvl_scores, padding], dim=-1) |
|
|
|
if with_nms: |
|
det_results = [] |
|
for (mlvl_bboxes, mlvl_scores, |
|
mlvl_centerness) in zip(batch_mlvl_bboxes, batch_mlvl_scores, |
|
batch_mlvl_centerness): |
|
det_bbox, det_label = multiclass_nms( |
|
mlvl_bboxes, |
|
mlvl_scores, |
|
cfg.score_thr, |
|
cfg.nms, |
|
cfg.max_per_img, |
|
score_factors=mlvl_centerness) |
|
det_results.append(tuple([det_bbox, det_label])) |
|
else: |
|
det_results = [ |
|
tuple(mlvl_bs) |
|
for mlvl_bs in zip(batch_mlvl_bboxes, batch_mlvl_scores, |
|
batch_mlvl_centerness) |
|
] |
|
return det_results |
|
|
|
def _get_points_single(self, |
|
featmap_size, |
|
stride, |
|
dtype, |
|
device, |
|
flatten=False): |
|
"""Get points according to feature map sizes.""" |
|
y, x = super()._get_points_single(featmap_size, stride, dtype, device) |
|
points = torch.stack((x.reshape(-1) * stride, y.reshape(-1) * stride), |
|
dim=-1) + stride // 2 |
|
return points |
|
|
|
def get_targets(self, points, gt_bboxes_list, gt_labels_list): |
|
"""Compute regression, classification and centerness targets for points |
|
in multiple images. |
|
|
|
Args: |
|
points (list[Tensor]): Points of each fpn level, each has shape |
|
(num_points, 2). |
|
gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image, |
|
each has shape (num_gt, 4). |
|
gt_labels_list (list[Tensor]): Ground truth labels of each box, |
|
each has shape (num_gt,). |
|
|
|
Returns: |
|
tuple: |
|
concat_lvl_labels (list[Tensor]): Labels of each level. \ |
|
concat_lvl_bbox_targets (list[Tensor]): BBox targets of each \ |
|
level. |
|
""" |
|
assert len(points) == len(self.regress_ranges) |
|
num_levels = len(points) |
|
|
|
expanded_regress_ranges = [ |
|
points[i].new_tensor(self.regress_ranges[i])[None].expand_as( |
|
points[i]) for i in range(num_levels) |
|
] |
|
|
|
concat_regress_ranges = torch.cat(expanded_regress_ranges, dim=0) |
|
concat_points = torch.cat(points, dim=0) |
|
|
|
|
|
num_points = [center.size(0) for center in points] |
|
|
|
|
|
labels_list, bbox_targets_list = multi_apply( |
|
self._get_target_single, |
|
gt_bboxes_list, |
|
gt_labels_list, |
|
points=concat_points, |
|
regress_ranges=concat_regress_ranges, |
|
num_points_per_lvl=num_points) |
|
|
|
|
|
labels_list = [labels.split(num_points, 0) for labels in labels_list] |
|
bbox_targets_list = [ |
|
bbox_targets.split(num_points, 0) |
|
for bbox_targets in bbox_targets_list |
|
] |
|
|
|
|
|
concat_lvl_labels = [] |
|
concat_lvl_bbox_targets = [] |
|
for i in range(num_levels): |
|
concat_lvl_labels.append( |
|
torch.cat([labels[i] for labels in labels_list])) |
|
bbox_targets = torch.cat( |
|
[bbox_targets[i] for bbox_targets in bbox_targets_list]) |
|
if self.norm_on_bbox: |
|
bbox_targets = bbox_targets / self.strides[i] |
|
concat_lvl_bbox_targets.append(bbox_targets) |
|
return concat_lvl_labels, concat_lvl_bbox_targets |
|
|
|
def _get_target_single(self, gt_bboxes, gt_labels, points, regress_ranges, |
|
num_points_per_lvl): |
|
"""Compute regression and classification targets for a single image.""" |
|
num_points = points.size(0) |
|
num_gts = gt_labels.size(0) |
|
if num_gts == 0: |
|
return gt_labels.new_full((num_points,), self.num_classes), \ |
|
gt_bboxes.new_zeros((num_points, 4)) |
|
|
|
areas = (gt_bboxes[:, 2] - gt_bboxes[:, 0]) * ( |
|
gt_bboxes[:, 3] - gt_bboxes[:, 1]) |
|
|
|
|
|
areas = areas[None].repeat(num_points, 1) |
|
regress_ranges = regress_ranges[:, None, :].expand( |
|
num_points, num_gts, 2) |
|
gt_bboxes = gt_bboxes[None].expand(num_points, num_gts, 4) |
|
xs, ys = points[:, 0], points[:, 1] |
|
xs = xs[:, None].expand(num_points, num_gts) |
|
ys = ys[:, None].expand(num_points, num_gts) |
|
|
|
left = xs - gt_bboxes[..., 0] |
|
right = gt_bboxes[..., 2] - xs |
|
top = ys - gt_bboxes[..., 1] |
|
bottom = gt_bboxes[..., 3] - ys |
|
bbox_targets = torch.stack((left, top, right, bottom), -1) |
|
|
|
if self.center_sampling: |
|
|
|
radius = self.center_sample_radius |
|
center_xs = (gt_bboxes[..., 0] + gt_bboxes[..., 2]) / 2 |
|
center_ys = (gt_bboxes[..., 1] + gt_bboxes[..., 3]) / 2 |
|
center_gts = torch.zeros_like(gt_bboxes) |
|
stride = center_xs.new_zeros(center_xs.shape) |
|
|
|
|
|
lvl_begin = 0 |
|
for lvl_idx, num_points_lvl in enumerate(num_points_per_lvl): |
|
lvl_end = lvl_begin + num_points_lvl |
|
stride[lvl_begin:lvl_end] = self.strides[lvl_idx] * radius |
|
lvl_begin = lvl_end |
|
|
|
x_mins = center_xs - stride |
|
y_mins = center_ys - stride |
|
x_maxs = center_xs + stride |
|
y_maxs = center_ys + stride |
|
center_gts[..., 0] = torch.where(x_mins > gt_bboxes[..., 0], |
|
x_mins, gt_bboxes[..., 0]) |
|
center_gts[..., 1] = torch.where(y_mins > gt_bboxes[..., 1], |
|
y_mins, gt_bboxes[..., 1]) |
|
center_gts[..., 2] = torch.where(x_maxs > gt_bboxes[..., 2], |
|
gt_bboxes[..., 2], x_maxs) |
|
center_gts[..., 3] = torch.where(y_maxs > gt_bboxes[..., 3], |
|
gt_bboxes[..., 3], y_maxs) |
|
|
|
cb_dist_left = xs - center_gts[..., 0] |
|
cb_dist_right = center_gts[..., 2] - xs |
|
cb_dist_top = ys - center_gts[..., 1] |
|
cb_dist_bottom = center_gts[..., 3] - ys |
|
center_bbox = torch.stack( |
|
(cb_dist_left, cb_dist_top, cb_dist_right, cb_dist_bottom), -1) |
|
inside_gt_bbox_mask = center_bbox.min(-1)[0] > 0 |
|
else: |
|
|
|
inside_gt_bbox_mask = bbox_targets.min(-1)[0] > 0 |
|
|
|
|
|
max_regress_distance = bbox_targets.max(-1)[0] |
|
inside_regress_range = ( |
|
(max_regress_distance >= regress_ranges[..., 0]) |
|
& (max_regress_distance <= regress_ranges[..., 1])) |
|
|
|
|
|
|
|
areas[inside_gt_bbox_mask == 0] = INF |
|
areas[inside_regress_range == 0] = INF |
|
min_area, min_area_inds = areas.min(dim=1) |
|
|
|
labels = gt_labels[min_area_inds] |
|
labels[min_area == INF] = self.num_classes |
|
bbox_targets = bbox_targets[range(num_points), min_area_inds] |
|
|
|
return labels, bbox_targets |
|
|
|
def centerness_target(self, pos_bbox_targets): |
|
"""Compute centerness targets. |
|
|
|
Args: |
|
pos_bbox_targets (Tensor): BBox targets of positive bboxes in shape |
|
(num_pos, 4) |
|
|
|
Returns: |
|
Tensor: Centerness target. |
|
""" |
|
|
|
left_right = pos_bbox_targets[:, [0, 2]] |
|
top_bottom = pos_bbox_targets[:, [1, 3]] |
|
centerness_targets = ( |
|
left_right.min(dim=-1)[0] / left_right.max(dim=-1)[0]) * ( |
|
top_bottom.min(dim=-1)[0] / top_bottom.max(dim=-1)[0]) |
|
return torch.sqrt(centerness_targets) |
|
|