def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
img_metas,
cfg,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == len(self.anchor_generators)
anchor_list, valid_flag_list = self.get_anchors(
featmap_sizes, img_metas)
cls_reg_targets = anchor_target(anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
self.target_means,
self.target_stds,
cfg,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=1,
sampling=False,
unmap_outputs=False)
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_images = len(img_metas)
all_cls_scores = torch.cat([
s.permute(0, 2, 3, 1).reshape(
num_images, -1, self.cls_out_channels) for s in cls_scores
], 1)
all_labels = torch.cat(labels_list, -1).view(num_images, -1)
all_label_weights = torch.cat(label_weights_list,
-1).view(num_images, -1)
all_bbox_preds = torch.cat([
b.permute(0, 2, 3, 1).reshape(num_images, -1, 4)
for b in bbox_preds
], -2)
all_bbox_targets = torch.cat(bbox_targets_list,
-2).view(num_images, -1, 4)
all_bbox_weights = torch.cat(bbox_weights_list,
-2).view(num_images, -1, 4)
losses_cls, losses_bbox = multi_apply(self.loss_single,
all_cls_scores,
all_bbox_preds,
all_labels,
all_label_weights,
all_bbox_targets,
all_bbox_weights,
num_total_samples=num_total_pos,
cfg=cfg)
return dict(loss_cls=losses_cls, loss_bbox=losses_bbox)
def loss(self,
cls_scores,
bbox_preds,
gt_bboxes,
gt_labels,
img_metas,
cfg,
gt_bboxes_ignore=None):
featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores]
assert len(featmap_sizes) == len(self.anchor_generators)
anchor_list, valid_flag_list = self.get_anchors(
featmap_sizes, img_metas)
label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1
cls_reg_targets = anchor_target(anchor_list,
valid_flag_list,
gt_bboxes,
img_metas,
self.target_means,
self.target_stds,
cfg,
gt_bboxes_ignore_list=gt_bboxes_ignore,
gt_labels_list=gt_labels,
label_channels=label_channels,
sampling=self.sampling)
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)
losses_cls, losses_bbox = multi_apply(
self.loss_single,
cls_scores,
bbox_preds,
labels_list,
label_weights_list,
bbox_targets_list,
bbox_weights_list,
num_total_samples=num_total_samples,
cfg=cfg)
return dict(loss_cls=losses_cls, loss_bbox=losses_bbox)
def fcos_target(self, points, gt_bboxes_list, gt_labels_list):
assert len(points) == len(self.regress_ranges)
num_levels = len(points)
# expand regress ranges to align with points
expanded_regress_ranges = [
points[i].new_tensor(self.regress_ranges[i])[None].expand_as(
points[i]) for i in range(num_levels)
]
# concat all levels points and regress ranges
concat_regress_ranges = torch.cat(expanded_regress_ranges, dim=0)
concat_points = torch.cat(points, dim=0)
# get labels and bbox_targets of each image
labels_list, bbox_targets_list = multi_apply(
self.fcos_target_single,
gt_bboxes_list,
gt_labels_list,
points=concat_points,
regress_ranges=concat_regress_ranges)
# split to per img, per level
num_points = [center.size(0) for center in 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 per level image
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]))
concat_lvl_bbox_targets.append(
torch.cat(
[bbox_targets[i] for bbox_targets in bbox_targets_list]))
return concat_lvl_labels, concat_lvl_bbox_targets
def forward(self, feats):
return multi_apply(self.forward_single, feats)