def _get_target_single(self,
flat_anchors,
valid_flags,
num_level_anchors,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
img_meta,
label_channels=1,
unmap_outputs=True):
"""Compute regression, classification targets for anchors in a single
image.
Args:
flat_anchors (Tensor): Multi-level anchors of the image, which are
concatenated into a single tensor of shape (num_anchors ,4)
valid_flags (Tensor): Multi level valid flags of the image,
which are concatenated into a single tensor of
shape (num_anchors,).
num_level_anchors Tensor): Number of anchors of each scale level.
gt_bboxes (Tensor): Ground truth bboxes of the image,
shape (num_gts, 4).
gt_bboxes_ignore (Tensor): Ground truth bboxes to be
ignored, shape (num_ignored_gts, 4).
gt_labels (Tensor): Ground truth labels of each box,
shape (num_gts,).
img_meta (dict): Meta info of the image.
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple: N is the number of total anchors in the image.
labels (Tensor): Labels of all anchors in the image with shape
(N,).
label_weights (Tensor): Label weights of all anchor in the
image with shape (N,).
bbox_targets (Tensor): BBox targets of all anchors in the
image with shape (N, 4).
bbox_weights (Tensor): BBox weights of all anchors in the
image with shape (N, 4)
pos_inds (Tensor): Indices of postive anchor with shape
(num_pos,).
neg_inds (Tensor): Indices of negative anchor with shape
(num_neg,).
"""
# pad_shape属性是图片没有经过collate函数右下pad后的图片size,也就是datalayer吐出的图片shape
# inside_flags会改变总anchor数目
inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2],
self.train_cfg.allowed_border)
if not inside_flags.any():
return (None, ) * 7
# assign gt and sample anchors
# 要小心这个步骤，可能anchors变少了
anchors = flat_anchors[inside_flags, :]
# 调试anchor
# imgs = []
# count = 0
# 由于anchors可能变少了，故num_level_anchors参数遍历是不对的
# for num_level in num_level_anchors:
# an = flat_anchors[count:count + num_level]
# count += num_level
# img = show_pos_anchor(img_meta, an, gt_bboxes, is_show=False)
# imgs.append(img)
# cv_core.show_img(imgs)
num_level_anchors_inside = self.get_num_level_anchors_inside(
num_level_anchors, inside_flags)
assign_result = self.assigner.assign(anchors, num_level_anchors_inside,
gt_bboxes, gt_bboxes_ignore,
gt_labels)
sampling_result = self.sampler.sample(assign_result, anchors,
gt_bboxes)
# 正样本可视化
if self.debug:
gt_inds = assign_result.gt_inds # 0 1 -1 正负忽略样本标志
index = gt_inds > 0
gt_inds = gt_inds[index]
print('单张图片中正样本anchor个数', len(gt_inds))
imgs = []
count = 0
for num_level in num_level_anchors_inside: # 注意要用num_level_anchors_inside，而不是num_level_anchors
gt_inds = assign_result.gt_inds[count:count + num_level]
anchor = anchors[count:count + num_level]
count += num_level
index = gt_inds > 0
gt_anchor = anchor[index]
img = show_pos_anchor(img_meta,
gt_anchor,
gt_bboxes,
is_show=False)
imgs.append(img)
cv_core.show_img(imgs)
num_valid_anchors = anchors.shape[0]
bbox_targets = torch.zeros_like(anchors)
bbox_weights = torch.zeros_like(anchors)
labels = anchors.new_full((num_valid_anchors, ),
self.num_classes,
dtype=torch.long)
label_weights = anchors.new_zeros(num_valid_anchors, dtype=torch.float)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
pos_bbox_targets = self.bbox_coder.encode(
sampling_result.pos_bboxes, sampling_result.pos_gt_bboxes)
bbox_targets[pos_inds, :] = pos_bbox_targets
bbox_weights[pos_inds, :] = 1.0
if gt_labels is None:
# Only rpn gives gt_labels as None
# Foreground is the first class since v2.5.0
labels[pos_inds] = 0
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if self.train_cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = self.train_cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_anchors.size(0)
anchors = unmap(anchors, num_total_anchors, inside_flags)
labels = unmap(labels,
num_total_anchors,
inside_flags,
fill=self.num_classes)
label_weights = unmap(label_weights, num_total_anchors,
inside_flags)
bbox_targets = unmap(bbox_targets, num_total_anchors, inside_flags)
bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags)
return (anchors, labels, label_weights, bbox_targets, bbox_weights,
pos_inds, neg_inds)
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, :]
# 利用approxs和gt bbox，对shape分支进行重新正负样本分配
assign_result = self.ga_assigner.assign(approxs, squares,
self.approxs_per_octave,
gt_bboxes, gt_bboxes_ignore)
# 随机采用有两个目的：随机采样正样本，但是最大目的其实是将assign_result和squares绑定
# squares相当于anchor
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:
# 这里可以发现，shape分支的预测target其实是squares和gt bbox的编码后结果
bbox_anchors[
pos_inds, :] = sampling_result.pos_bboxes # 就是对应的squares
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 _point_target_single(self,
flat_proposals,
valid_flags,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
label_channels=1,
stage='init',
unmap_outputs=True):
inside_flags = valid_flags
if not inside_flags.any():
return (None, ) * 7
# assign gt and sample proposals
proposals = flat_proposals[inside_flags, :]
if stage == 'init': # 初始训练
assigner = self.init_assigner
pos_weight = self.train_cfg.init.pos_weight
else: # refine训练
assigner = self.refine_assigner
pos_weight = self.train_cfg.refine.pos_weight
# proposals实际上是point坐标，不是anchor坐标
# 得到特征图上面每个点应该负责哪个gt bbox
assign_result = assigner.assign(proposals, gt_bboxes, gt_bboxes_ignore,
None if self.sampling else gt_labels)
# 伪随机
sampling_result = self.sampler.sample(assign_result, proposals,
gt_bboxes)
num_valid_proposals = proposals.shape[0]
bbox_gt = proposals.new_zeros([num_valid_proposals, 4])
pos_proposals = torch.zeros_like(proposals)
proposals_weights = proposals.new_zeros([num_valid_proposals, 4])
labels = proposals.new_full((num_valid_proposals, ),
self.num_classes,
dtype=torch.long)
label_weights = proposals.new_zeros(num_valid_proposals,
dtype=torch.float)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
pos_gt_bboxes = sampling_result.pos_gt_bboxes
bbox_gt[pos_inds, :] = pos_gt_bboxes
pos_proposals[pos_inds, :] = proposals[pos_inds, :]
proposals_weights[pos_inds, :] = 1.0
if gt_labels is None:
# Only rpn gives gt_labels as None
# Foreground is the first class
labels[pos_inds] = 0
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of proposals
if unmap_outputs:
num_total_proposals = flat_proposals.size(0)
labels = unmap(labels, num_total_proposals, inside_flags)
label_weights = unmap(label_weights, num_total_proposals,
inside_flags)
bbox_gt = unmap(bbox_gt, num_total_proposals, inside_flags)
pos_proposals = unmap(pos_proposals, num_total_proposals,
inside_flags)
proposals_weights = unmap(proposals_weights, num_total_proposals,
inside_flags)
return (labels, label_weights, bbox_gt, pos_proposals,
proposals_weights, pos_inds, neg_inds)
def _get_targets_single(self,
flat_anchors,
valid_flags,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
img_meta,
label_channels=1,
unmap_outputs=True,
num_level_anchors=None):
"""Compute regression and classification targets for anchors in a
single image.
Args:
flat_anchors (Tensor): Multi-level anchors of the image, which are
concatenated into a single tensor of shape (num_anchors ,4)
valid_flags (Tensor): Multi level valid flags of the image,
which are concatenated into a single tensor of
shape (num_anchors,).
gt_bboxes (Tensor): Ground truth bboxes of the image,
shape (num_gts, 4).
img_meta (dict): Meta info of the image.
gt_bboxes_ignore (Tensor): Ground truth bboxes to be
ignored, shape (num_ignored_gts, 4).
img_meta (dict): Meta info of the image.
gt_labels (Tensor): Ground truth labels of each box,
shape (num_gts,).
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple:
labels_list (list[Tensor]): Labels of each level
label_weights_list (list[Tensor]): Label weights of each level
bbox_targets_list (list[Tensor]): BBox targets of each level
bbox_weights_list (list[Tensor]): BBox weights of each level
num_total_pos (int): Number of positive samples in all images
num_total_neg (int): Number of negative samples in all images
"""
# # 默认self.train_cfg.allowed_border=-1 也就是仅仅看valid_flags就可以,功能重复
inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2],
self.train_cfg.allowed_border)
if not inside_flags.any():
return (None,) * 7
# assign gt and sample anchors
anchors = flat_anchors[inside_flags, :]
# 核心类，基于anchor和gt bbox，进行正负样本anchor分配
assign_result = self.assigner.assign(
anchors, gt_bboxes, gt_bboxes_ignore,
None if self.sampling else gt_labels)
if self.debug:
# 统计下正样本个数
print('----anchor分配正负样本后，正样本anchor可视化，白色bbox是gt----')
gt_inds = assign_result.gt_inds # 0 1 -1 正负忽略样本标志
index = gt_inds > 0
gt_inds = gt_inds[index]
gt_anchors = anchors[index]
print('单张图片中正样本anchor个数', len(gt_inds))
if num_level_anchors is None: # 不分层显示
show_pos_anchor(img_meta, gt_anchors, gt_bboxes)
else:
imgs = []
count = 0
for num_level in num_level_anchors:
gt_inds = assign_result.gt_inds[count:count + num_level]
anchor = anchors[count:count + num_level]
count += num_level
index = gt_inds > 0
gt_anchor = anchor[index]
img = show_pos_anchor(img_meta, gt_anchor, gt_bboxes, is_show=False)
imgs.append(img)
print('从大特征图到小特征图顺序显示')
cv_core.show_img(imgs)
# 正负样本采样，默认是伪随机，也就是相当于没有
sampling_result = self.sampler.sample(assign_result, anchors,
gt_bboxes)
num_valid_anchors = anchors.shape[0] # 这里计算的仅仅是有效区域anchor
bbox_targets = torch.zeros_like(anchors)
bbox_weights = torch.zeros_like(anchors)
labels = anchors.new_full((num_valid_anchors,),
self.background_label,
dtype=torch.long)
# 正负样本区域权重为1，其余位置全部设置为0
label_weights = anchors.new_zeros(num_valid_anchors, dtype=torch.float)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
# 是否需要对gt进行编码，主要是区分l1 loss和iou类 loss
# l1 loss需要编解码，iou loss不需要
if not self.reg_decoded_bbox:
pos_bbox_targets = self.bbox_coder.encode(
sampling_result.pos_bboxes, sampling_result.pos_gt_bboxes)
else:
pos_bbox_targets = sampling_result.pos_gt_bboxes
bbox_targets[pos_inds, :] = pos_bbox_targets
bbox_weights[pos_inds, :] = 1.0
if gt_labels is None:
# only rpn gives gt_labels as None, this time FG is 1
labels[pos_inds] = 1
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds] # labels里面存储的，0-num_class表示正样本对应的class，num_class表示背景
if self.train_cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = self.train_cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# 为了方便计算，还原到最原始anchor个数，这个操作也非常关键，特别是label_weights和bbox_weights
# map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_anchors.size(0)
labels = unmap(
labels,
num_total_anchors,
inside_flags,
fill=self.background_label) # fill bg label
label_weights = unmap(label_weights, num_total_anchors,
inside_flags)
bbox_targets = unmap(bbox_targets, num_total_anchors, inside_flags)
bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags)
return (labels, label_weights, bbox_targets, bbox_weights, pos_inds,
neg_inds, sampling_result)
def _get_target_single(self,
flat_anchors,
valid_flags,
num_level_anchors,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
img_meta,
label_channels=1,
unmap_outputs=True):
"""Compute regression, classification targets for anchors in a single
image.
Args:
flat_anchors (Tensor): Multi-level anchors of the image, which are
concatenated into a single tensor of shape (num_anchors, 4)
valid_flags (Tensor): Multi level valid flags of the image,
which are concatenated into a single tensor of
shape (num_anchors,).
num_level_anchors Tensor): Number of anchors of each scale level.
gt_bboxes (Tensor): Ground truth bboxes of the image,
shape (num_gts, 4).
gt_bboxes_ignore (Tensor): Ground truth bboxes to be
ignored, shape (num_ignored_gts, 4).
gt_labels (Tensor): Ground truth labels of each box,
shape (num_gts,).
img_meta (dict): Meta info of the image.
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple: N is the number of total anchors in the image.
anchors (Tensor): All anchors in the image with shape (N, 4).
labels (Tensor): Labels of all anchors in the image with shape
(N,).
label_weights (Tensor): Label weights of all anchor in the
image with shape (N,).
bbox_targets (Tensor): BBox targets of all anchors in the
image with shape (N, 4).
bbox_weights (Tensor): BBox weights of all anchors in the
image with shape (N, 4).
pos_inds (Tensor): Indices of postive anchor with shape
(num_pos,).
neg_inds (Tensor): Indices of negative anchor with shape
(num_neg,).
"""
inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2],
self.train_cfg.allowed_border)
if not inside_flags.any():
return (None,) * 7
# assign gt and sample anchors
anchors = flat_anchors[inside_flags, :]
num_level_anchors_inside = self.get_num_level_anchors_inside(
num_level_anchors, inside_flags)
assign_result = self.assigner.assign(anchors, num_level_anchors_inside,
gt_bboxes, gt_bboxes_ignore,
gt_labels)
sampling_result = self.sampler.sample(assign_result, anchors,
gt_bboxes)
num_valid_anchors = anchors.shape[0]
bbox_targets = torch.zeros_like(anchors)
bbox_weights = torch.zeros_like(anchors)
labels = anchors.new_full((num_valid_anchors,),
self.num_classes,
dtype=torch.long)
label_weights = anchors.new_zeros(num_valid_anchors, dtype=torch.float)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
pos_bbox_targets = sampling_result.pos_gt_bboxes
bbox_targets[pos_inds, :] = pos_bbox_targets
bbox_weights[pos_inds, :] = 1.0
if gt_labels is None:
# Only rpn gives gt_labels as None
# Foreground is the first class
labels[pos_inds] = 0
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if self.train_cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = self.train_cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_anchors.size(0)
anchors = unmap(anchors, num_total_anchors, inside_flags)
labels = unmap(
labels, num_total_anchors, inside_flags, fill=self.num_classes)
label_weights = unmap(label_weights, num_total_anchors,
inside_flags)
bbox_targets = unmap(bbox_targets, num_total_anchors, inside_flags)
bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags)
return (anchors, labels, label_weights, bbox_targets, bbox_weights,
pos_inds, neg_inds)
def _get_target_single(self,
flat_approxs,
inside_flags,
flat_squares,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
img_meta,
label_channels=None,
sampling=True,
unmap_outputs=True):
"""Compute regression and classification targets for anchors in a
single image.
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, \
shape (num_gts, 4).
gt_bboxes_ignore (Tensor): Ground truth bboxes to be
ignored, shape (num_ignored_gts, 4).
gt_labels (Tensor): Ground truth labels of each box,
shape (num_gts,).
img_meta (dict): Meta info of the image.
label_channels (int): Channel of label.
sampling (bool): Sample Anchors or not.
unmap_outputs (bool): unmap outputs or not.
Returns:
tuple:
- labels_list (Tensor): Labels in a single image
- label_weights (Tensor): Label weights in a single image
- bbox_cls_targets (Tensor): BBox cls targets in a single image
- bbox_cls_weights (Tensor): BBox cls weights in a single image
- bbox_reg_targets (Tensor): BBox reg targets in a single image
- bbox_reg_weights (Tensor): BBox reg weights in a single image
- num_total_pos (int): Number of positive samples \
in a single image
- num_total_neg (int): Number of negative samples \
in a single image
"""
if not inside_flags.any():
return (None, ) * 8
# 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, :]
# 近似anchor正负样本分配策略
assign_result = self.assigner.assign(approxs, squares,
self.approxs_per_octave,
gt_bboxes, gt_bboxes_ignore)
# 伪随机，实际上就是将每个正样本分配位置和squares、gt_bboxes绑定
sampling_result = self.sampler.sample(assign_result, squares,
gt_bboxes)
num_valid_squares = squares.shape[0]
# 第一步桶分类targets
bbox_cls_targets = squares.new_zeros(
(num_valid_squares, self.side_num * 4))
bbox_cls_weights = squares.new_zeros(
(num_valid_squares, self.side_num * 4))
# 第二步精细回归targets
bbox_reg_targets = squares.new_zeros(
(num_valid_squares, self.side_num * 4))
bbox_reg_weights = squares.new_zeros(
(num_valid_squares, self.side_num * 4))
# 每个特征图位置所负责的gt bbox值
labels = squares.new_full((num_valid_squares, ),
self.num_classes,
dtype=torch.long)
label_weights = squares.new_zeros(num_valid_squares, dtype=torch.float)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
# pos_bboxes是squares，pos_gt_bboxes是gt bbox,本算法核心
(pos_bbox_reg_targets, pos_bbox_reg_weights, pos_bbox_cls_targets,
pos_bbox_cls_weights) = self.bbox_coder.encode(
sampling_result.pos_bboxes, sampling_result.pos_gt_bboxes)
# 注意pos_bbox_reg_targets，其输出是(n,28)
# 28表示4x7，假设任何一条gt bbox的边，其都可以算出相对每个桶的offset
# 对于任何一个anchor，由前面的近似anchor分配策略，可以知道哪些anchor是正样本，负责预测对应gt bbox
# 在确定了anchor和gt bbox的对应关系后，假设分成7个桶，那么这7个桶里面也有正负样本定义规则
# 对于pos_bbox_reg_targets，是gt bbox所落在的桶和邻居桶都算正样本，其余几个桶忽略掉即可
# 对于pos_bbox_reg_weights的7个位置有n个是0
# pos_bbox_reg_targets里面的任意7个数都表示7个桶中心坐标相对同一个gt bbox边的offset，也就是我们的学习值
bbox_cls_targets[pos_inds, :] = pos_bbox_cls_targets
bbox_reg_targets[pos_inds, :] = pos_bbox_reg_targets
bbox_cls_weights[pos_inds, :] = pos_bbox_cls_weights
bbox_reg_weights[pos_inds, :] = pos_bbox_reg_weights
if gt_labels is None:
# Only rpn gives gt_labels as None
# Foreground is the first class
labels[pos_inds] = 0
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if self.train_cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = self.train_cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_squares.size(0)
labels = unmap(labels,
num_total_anchors,
inside_flags,
fill=self.num_classes)
label_weights = unmap(label_weights, num_total_anchors,
inside_flags)
bbox_cls_targets = unmap(bbox_cls_targets, num_total_anchors,
inside_flags)
bbox_cls_weights = unmap(bbox_cls_weights, num_total_anchors,
inside_flags)
bbox_reg_targets = unmap(bbox_reg_targets, num_total_anchors,
inside_flags)
bbox_reg_weights = unmap(bbox_reg_weights, num_total_anchors,
inside_flags)
return (labels, label_weights, bbox_cls_targets, bbox_cls_weights,
bbox_reg_targets, bbox_reg_weights, pos_inds, neg_inds)
def _get_targets_single(self,
flat_anchors,
valid_flags,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
img_meta,
label_channels=1,
unmap_outputs=True):
"""Compute regression and classification targets for anchors in a
single image.
Args:
flat_anchors (Tensor): Multi-level anchors of the image, which are
concatenated into a single tensor of shape (num_anchors ,4)
valid_flags (Tensor): Multi level valid flags of the image,
which are concatenated into a single tensor of
shape (num_anchors,).
gt_bboxes (Tensor): Ground truth bboxes of the image,
shape (num_gts, 4).
img_meta (dict): Meta info of the image.
gt_bboxes_ignore (Tensor): Ground truth bboxes to be
ignored, shape (num_ignored_gts, 4).
img_meta (dict): Meta info of the image.
gt_labels (Tensor): Ground truth labels of each box,
shape (num_gts,).
label_channels (int): Channel of label.
unmap_outputs (bool): Whether to map outputs back to the original
set of anchors.
Returns:
tuple:
labels_list (list[Tensor]): Labels of each level
label_weights_list (list[Tensor]): Label weights of each level
bbox_targets_list (list[Tensor]): BBox targets of each level
bbox_weights_list (list[Tensor]): BBox weights of each level
num_total_pos (int): Number of positive samples in all images
num_total_neg (int): Number of negative samples in all images
"""
inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2],
self.train_cfg.allowed_border)
if not inside_flags.any():
return (None, ) * 7
# assign gt and sample anchors
anchors = flat_anchors[inside_flags, :]
assign_result = self.assigner.assign(
anchors, gt_bboxes, gt_bboxes_ignore,
None if self.sampling else gt_labels)
sampling_result = self.sampler.sample(assign_result, anchors,
gt_bboxes)
num_valid_anchors = anchors.shape[0]
bbox_targets = torch.zeros_like(anchors)
bbox_weights = torch.zeros_like(anchors)
labels = anchors.new_full((num_valid_anchors, ),
self.background_label,
dtype=torch.long)
label_weights = anchors.new_zeros(num_valid_anchors, dtype=torch.float)
pos_inds = sampling_result.pos_inds
neg_inds = sampling_result.neg_inds
if len(pos_inds) > 0:
if not self.reg_decoded_bbox:
pos_bbox_targets = self.bbox_coder.encode(
sampling_result.pos_bboxes, sampling_result.pos_gt_bboxes)
else:
pos_bbox_targets = sampling_result.pos_gt_bboxes
bbox_targets[pos_inds, :] = pos_bbox_targets
bbox_weights[pos_inds, :] = 1.0
if gt_labels is None:
# only rpn gives gt_labels as None, this time FG is 1
labels[pos_inds] = 1
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if self.train_cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = self.train_cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_anchors.size(0)
labels = unmap(labels,
num_total_anchors,
inside_flags,
fill=self.background_label) # fill bg label
label_weights = unmap(label_weights, num_total_anchors,
inside_flags)
bbox_targets = unmap(bbox_targets, num_total_anchors, inside_flags)
bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags)
return (labels, label_weights, bbox_targets, bbox_weights, pos_inds,
neg_inds, sampling_result)
