def get_sampled_approxs(self,
featmap_sizes,
img_metas,
cfg,
device='cuda'):
"""Get sampled approxs and inside flags according to feature map sizes.
用于生成所有的anchor，而且还有anchor是否有效
Args:
featmap_sizes (list[tuple]): Multi-level feature map sizes.特征图大小
img_metas (list[dict]): Image meta info.图片标签
device (torch.device | str): device for returned tensors
Returns:
tuple: approxes of each image, inside flags of each image
"""
num_imgs = len(img_metas) #有多少个标签
num_levels = len(featmap_sizes) #有多少个特征图
# since feature map sizes of all images are the same, we only compute
# approxes for one time
multi_level_approxs = []
for i in range(num_levels): #对所有的特征图生成anchor
approxs = self.approx_generators[i].grid_anchors(
featmap_sizes[i], self.anchor_strides[i],
device=device) #生成一个特征图上的anchor，是（N,4）
multi_level_approxs.append(approxs)
approxs_list = [multi_level_approxs for _ in range(num_imgs)
] #每个图片都要有所有anchor，但是每个图片的ANCHOR都是一样的，所以直接复制
# for each image, we compute inside flags of multi level approxes计算出所有的anchor在每个图上对应的有效标识
inside_flag_list = []
for img_id, img_meta in enumerate(img_metas): #对每张图片的标签
multi_level_flags = []
multi_level_approxs = approxs_list[img_id] #选中他对应的anchor
for i in range(num_levels): #对每个尺度的特征图
approxs = multi_level_approxs[i] #选中他对应的anchor
anchor_stride = self.anchor_strides[i]
feat_h, feat_w = featmap_sizes[i] #计算特征图的大小
h, w, _ = img_meta['pad_shape'] #标签形状
valid_feat_h = min(int(np.ceil(h / anchor_stride)),
feat_h) #计算特征图在原图上的部分
valid_feat_w = min(int(np.ceil(w / anchor_stride)), feat_w)
flags = self.approx_generators[i].valid_flags(
(feat_h, feat_w), (valid_feat_h, valid_feat_w),
device=device) #让特征和标签在特征重叠，对于超出特征图的标签进行筛选
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], 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_sampled_approxs(self,
featmap_sizes,
img_metas,
cfg,
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)
num_levels = len(featmap_sizes)
# since feature map sizes of all images are the same, we only compute
# approxes for one time
multi_level_approxs = []
for i in range(num_levels):
approxs = self.approx_generators[i].grid_anchors(
featmap_sizes[i], self.anchor_strides[i], device=device)
multi_level_approxs.append(approxs)
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]
for i in range(num_levels):
approxs = multi_level_approxs[i]
anchor_stride = self.anchor_strides[i]
feat_h, feat_w = featmap_sizes[i]
h, w = img_meta["pad_shape"][:2]
valid_feat_h = min(int(np.ceil(h / anchor_stride)), feat_h)
valid_feat_w = min(int(np.ceil(w / anchor_stride)), feat_w)
flags = self.approx_generators[i].valid_flags(
(feat_h, feat_w), (valid_feat_h, valid_feat_w),
device=device)
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],
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_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_priors(
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_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.
Most of the codes are the same with the base class
:obj: `AnchorHead`, except that it also collects and returns
the matched gt index in the image (from 0 to num_gt-1). If the
anchor bbox is not matched to any gt, the corresponding value in
pos_gt_inds is -1.
"""
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.type(torch.bool), :]
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, label_channels),
dtype=torch.float)
pos_gt_inds = anchors.new_full((num_valid_anchors, ),
-1,
dtype=torch.long)
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
# The assigned gt_index for each anchor. (0-based)
pos_gt_inds[pos_inds] = sampling_result.pos_assigned_gt_inds
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
# shadowed_labels is a tensor composed of tuples
# (anchor_inds, class_label) that indicate those anchors lying in the
# outer region of a gt or overlapped by another gt with a smaller
# area.
#
# Therefore, only the shadowed labels are ignored for loss calculation.
# the key `shadowed_labels` is defined in :obj:`CenterRegionAssigner`
shadowed_labels = assign_result.get_extra_property('shadowed_labels')
if shadowed_labels is not None and shadowed_labels.numel():
if len(shadowed_labels.shape) == 2:
idx_, label_ = shadowed_labels[:, 0], shadowed_labels[:, 1]
assert (labels[idx_] != label_).all(), \
'One label cannot be both positive and ignored'
# If background_label is 0. Then all labels increase by 1
label_ += int(self.background_label == 0)
label_weights[idx_, label_] = 0
else:
label_weights[shadowed_labels] = 0
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)
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)
pos_gt_inds = unmap(pos_gt_inds,
num_total_anchors,
inside_flags,
fill=-1)
return (labels, label_weights, bbox_targets, bbox_weights, pos_inds,
neg_inds, pos_gt_inds)
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,).
"""
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:
if hasattr(self, 'bbox_coder'):
pos_bbox_targets = self.bbox_coder.encode(
sampling_result.pos_bboxes, sampling_result.pos_gt_bboxes)
else:
# used in VFNetHead
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 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 _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)
def _get_targets_single(self,
bbox_preds,
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:
bbox_preds (Tensor): Bbox prediction of the image, which
shape is (h * w ,4)
flat_anchors (Tensor): Anchors of the image, which shape is
(h * w * num_anchors ,4)
valid_flags (Tensor): Valid flags of the image, which shape is
(h * w * num_anchors,).
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).
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 (Tensor): Labels of image, which shape is
(h * w * num_anchors, ).
label_weights (Tensor): Label weights of image, which shape is
(h * w * num_anchors, ).
pos_inds (Tensor): Pos index of image.
neg_inds (Tensor): Neg index of image.
sampling_result (obj:`SamplingResult`): Sampling result.
pos_bbox_weights (Tensor): The Weight of using to calculate
the bbox branch loss, which shape is (num, ).
pos_predicted_boxes (Tensor): boxes predicted value of
using to calculate the bbox branch loss, which shape is
(num, 4).
pos_target_boxes (Tensor): boxes target value of
using to calculate the bbox branch loss, which shape is
(num, 4).
"""
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, ) * 8
# assign gt and sample anchors
anchors = flat_anchors[inside_flags, :]
bbox_preds = bbox_preds.reshape(-1, 4)
bbox_preds = bbox_preds[inside_flags, :]
# decoded bbox
decoder_bbox_preds = self.bbox_coder.decode(anchors, bbox_preds)
assign_result = self.assigner.assign(
decoder_bbox_preds, anchors, gt_bboxes, gt_bboxes_ignore,
None if self.sampling else gt_labels)
pos_bbox_weights = assign_result.get_extra_property('pos_idx')
pos_predicted_boxes = assign_result.get_extra_property(
'pos_predicted_boxes')
pos_target_boxes = assign_result.get_extra_property('target_boxes')
sampling_result = self.sampler.sample(assign_result, anchors,
gt_bboxes)
num_valid_anchors = anchors.shape[0]
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:
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)
labels = unmap(labels,
num_total_anchors,
inside_flags,
fill=self.num_classes) # fill bg label
label_weights = unmap(label_weights, num_total_anchors,
inside_flags)
return (labels, label_weights, pos_inds, neg_inds, sampling_result,
pos_bbox_weights, pos_predicted_boxes, pos_target_boxes)
def gfl_target_single(self,
flat_anchors,
valid_flags,
num_level_anchors,
gt_bboxes,
gt_bboxes_ignore,
gt_labels,
img_meta,
cfg,
label_channels=1,
unmap_outputs=True):
inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2],
cfg.allowed_border)
if not inside_flags.any():
return (None, ) * 6
# assign gt and sample anchors
anchors = flat_anchors[inside_flags.type(torch.bool), :]
num_level_anchors_inside = self.get_num_level_anchors_inside(
num_level_anchors, inside_flags)
bbox_assigner = build_assigner(cfg.assigner)
assign_result = bbox_assigner.assign(anchors, num_level_anchors_inside,
gt_bboxes, gt_bboxes_ignore,
gt_labels)
bbox_sampler = PseudoSampler()
sampling_result = bbox_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_zeros(num_valid_anchors, 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:
labels[pos_inds] = 1
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of anchors
if unmap_outputs:
inside_flags = inside_flags.type(torch.bool)
num_total_anchors = flat_anchors.size(0)
anchors = unmap(anchors, num_total_anchors, inside_flags)
labels = unmap(labels, num_total_anchors, inside_flags)
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,
cls_scores,
bbox_preds,
flat_anchors,
valid_flags,
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:
cls_scores (list(Tensor)): Box scores for each image.
bbox_preds (list(Tensor)): Box energies / deltas for each image.
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).
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).
norm_alignment_metrics (Tensor): Normalized alignment metrics
of all priors in the image with shape (N,).
"""
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.alignment_assigner.assign(
cls_scores[inside_flags, :], bbox_preds[inside_flags, :], anchors,
gt_bboxes, gt_bboxes_ignore, gt_labels, self.alpha, self.beta)
assign_ious = assign_result.max_overlaps
assign_metrics = assign_result.assign_metrics
sampling_result = self.sampler.sample(assign_result, anchors,
gt_bboxes)
num_valid_anchors = anchors.shape[0]
bbox_targets = 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)
norm_alignment_metrics = 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:
# point-based
pos_bbox_targets = sampling_result.pos_gt_bboxes
bbox_targets[pos_inds, :] = pos_bbox_targets
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
class_assigned_gt_inds = torch.unique(
sampling_result.pos_assigned_gt_inds)
for gt_inds in class_assigned_gt_inds:
gt_class_inds = pos_inds[sampling_result.pos_assigned_gt_inds ==
gt_inds]
pos_alignment_metrics = assign_metrics[gt_class_inds]
pos_ious = assign_ious[gt_class_inds]
pos_norm_alignment_metrics = pos_alignment_metrics / (
pos_alignment_metrics.max() + 10e-8) * pos_ious.max()
norm_alignment_metrics[gt_class_inds] = pos_norm_alignment_metrics
# 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)
norm_alignment_metrics = unmap(norm_alignment_metrics,
num_total_anchors, inside_flags)
return (anchors, labels, label_weights, bbox_targets,
norm_alignment_metrics)
def assign(self,
mlvl_anchors,
mlvl_valid_flags,
gt_bboxes,
img_meta,
featmap_sizes,
anchor_scale,
anchor_strides,
gt_bboxes_ignore=None,
gt_labels=None,
allowed_border=0):
"""Assign gt to anchors.
This method assign a gt bbox to every bbox (proposal/anchor), each bbox
will be assigned with -1, 0, or a positive number. -1 means don't care,
0 means negative sample, positive number is the index (1-based) of
assigned gt.
The assignment is done in following steps, the order matters.
1. Assign every anchor to 0 (negative)
For each gt_bboxes:
2. Compute ignore flags based on ignore_region then
assign -1 to anchors w.r.t. ignore flags
3. Compute pos flags based on center_region then
assign gt_bboxes to anchors w.r.t. pos flags
4. Compute ignore flags based on adjacent anchor lvl then
assign -1 to anchors w.r.t. ignore flags
5. Assign anchor outside of image to -1
Args:
mlvl_anchors (list[Tensor]): Multi level anchors.
mlvl_valid_flags (list[Tensor]): Multi level valid flags.
gt_bboxes (Tensor): Ground truth bboxes of image
img_meta (dict): Meta info of image.
featmap_sizes (list[Tensor]): Feature mapsize each level
anchor_scale (int): Scale of the anchor.
anchor_strides (list[int]): Stride of the anchor.
gt_bboxes (Tensor): Groundtruth boxes, shape (k, 4).
gt_bboxes_ignore (Tensor, optional): Ground truth bboxes that are
labelled as `ignored`, e.g., crowd boxes in COCO.
gt_labels (Tensor, optional): Label of gt_bboxes, shape (k, ).
allowed_border (int, optional): The border to allow the valid
anchor. Defaults to 0.
Returns:
:obj:`AssignResult`: The assign result.
"""
if gt_bboxes_ignore is not None:
raise NotImplementedError
num_gts = gt_bboxes.shape[0]
num_bboxes = sum(x.shape[0] for x in mlvl_anchors)
if num_gts == 0 or num_bboxes == 0:
# No ground truth or boxes, return empty assignment
max_overlaps = gt_bboxes.new_zeros((num_bboxes, ))
assigned_gt_inds = gt_bboxes.new_zeros((num_bboxes, ),
dtype=torch.long)
if gt_labels is None:
assigned_labels = None
else:
assigned_labels = gt_bboxes.new_full((num_bboxes, ),
-1,
dtype=torch.long)
return AssignResult(num_gts,
assigned_gt_inds,
max_overlaps,
labels=assigned_labels)
num_lvls = len(mlvl_anchors)
r1 = (1 - self.center_ratio) / 2
r2 = (1 - self.ignore_ratio) / 2
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]))
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()
# 1. assign 0 (negative) by default
mlvl_assigned_gt_inds = []
mlvl_ignore_flags = []
for lvl in range(num_lvls):
h, w = featmap_sizes[lvl]
assert h * w == mlvl_anchors[lvl].shape[0]
assigned_gt_inds = gt_bboxes.new_full((h * w, ),
0,
dtype=torch.long)
ignore_flags = torch.zeros_like(assigned_gt_inds)
mlvl_assigned_gt_inds.append(assigned_gt_inds)
mlvl_ignore_flags.append(ignore_flags)
for gt_id in range(num_gts):
lvl = target_lvls[gt_id].item()
featmap_size = featmap_sizes[lvl]
stride = anchor_strides[lvl]
anchors = mlvl_anchors[lvl]
gt_bbox = gt_bboxes[gt_id, :4]
# Compute regions
ignore_region = calc_region(gt_bbox, r2, stride, featmap_size)
ctr_region = calc_region(gt_bbox, r1, stride, featmap_size)
# 2. Assign -1 to ignore flags
ignore_flags = anchor_ctr_inside_region_flags(
anchors, stride, ignore_region)
mlvl_assigned_gt_inds[lvl][ignore_flags] = -1
# 3. Assign gt_bboxes to pos flags
pos_flags = anchor_ctr_inside_region_flags(anchors, stride,
ctr_region)
mlvl_assigned_gt_inds[lvl][pos_flags] = gt_id + 1
# 4. Assign -1 to ignore adjacent lvl
if lvl > 0:
d_lvl = lvl - 1
d_anchors = mlvl_anchors[d_lvl]
d_featmap_size = featmap_sizes[d_lvl]
d_stride = anchor_strides[d_lvl]
d_ignore_region = calc_region(gt_bbox, r2, d_stride,
d_featmap_size)
ignore_flags = anchor_ctr_inside_region_flags(
d_anchors, d_stride, d_ignore_region)
mlvl_ignore_flags[d_lvl][ignore_flags] = 1
if lvl < num_lvls - 1:
u_lvl = lvl + 1
u_anchors = mlvl_anchors[u_lvl]
u_featmap_size = featmap_sizes[u_lvl]
u_stride = anchor_strides[u_lvl]
u_ignore_region = calc_region(gt_bbox, r2, u_stride,
u_featmap_size)
ignore_flags = anchor_ctr_inside_region_flags(
u_anchors, u_stride, u_ignore_region)
mlvl_ignore_flags[u_lvl][ignore_flags] = 1
# 4. (cont.) Assign -1 to ignore adjacent lvl
for lvl in range(num_lvls):
ignore_flags = mlvl_ignore_flags[lvl]
mlvl_assigned_gt_inds[lvl][ignore_flags] = -1
# 5. Assign -1 to anchor outside of image
flat_assigned_gt_inds = torch.cat(mlvl_assigned_gt_inds)
flat_anchors = torch.cat(mlvl_anchors)
flat_valid_flags = torch.cat(mlvl_valid_flags)
assert (flat_assigned_gt_inds.shape[0] == flat_anchors.shape[0] ==
flat_valid_flags.shape[0])
inside_flags = anchor_inside_flags(flat_anchors, flat_valid_flags,
img_meta['img_shape'],
allowed_border)
outside_flags = ~inside_flags
flat_assigned_gt_inds[outside_flags] = -1
if gt_labels is not None:
assigned_labels = torch.zeros_like(flat_assigned_gt_inds)
pos_flags = assigned_gt_inds > 0
assigned_labels[pos_flags] = gt_labels[
flat_assigned_gt_inds[pos_flags] - 1]
else:
assigned_labels = None
return AssignResult(num_gts,
flat_assigned_gt_inds,
None,
labels=assigned_labels)
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):
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, ) * 6
# 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.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:
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:
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)
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_targets_single(self,
flat_anchors,
valid_flags,
gt_bboxes,
gt_bboxes_ignore,
gt_masks,
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
"""
## 使用水平框的gt_bboxes来进行anchor的assign
## 使用gt_masks来生成gt_rbboxes，并进行target的计算。
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)
# EXAMPLE
# 28 pos , iou > 0.5 -> assign_result.gt_inds = 1
# 79 bad pos , 0.4< iou < 0.5 -> assign_result.gt_inds = -1
# others, iou < 0.4 -> assign_result.gt_inds = 0
########################################################
# gt_masks = [gtm for gtm in gt_masks.masks]
# if use_mod:
# gt_rbboxes = cv2_mask2rbbox_mod(gt_masks)
# else:
gt_rbboxes = cv2_mask2rbbox_mod(gt_masks)
gt_rbboxes = gt_bboxes.new_tensor(gt_rbboxes)
gt_inclines = gt_rbboxes[:, -1]
gt_rbboxes = gt_rbboxes[:, 0:-1]
sampling_result = self.sampler.sample(assign_result, anchors,
gt_rbboxes)
########################################################
num_valid_anchors = anchors.shape[0]
bbox_targets = anchors.new_zeros((anchors.shape[0], 5))
bbox_weights = anchors.new_zeros((anchors.shape[0], 5))
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
# inds是anchors的index，而非sampling_result.bboxex
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, 0:5] = pos_bbox_targets
pos_assigned_gt_inds = assign_result.gt_inds[pos_inds] - 1
bbox_targets[pos_inds, 5] = gt_inclines[pos_assigned_gt_inds]
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)
labels = unmap(labels,
num_total_anchors,
inside_flags,
fill=self.num_classes) # 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)
# if torch.sum(torch.isinf(bbox_targets).flatten()) > 0:
# print(bbox_targets)
if torch.sum(torch.isinf(bbox_targets)):
raise AssertionError
return (labels, label_weights, bbox_targets, bbox_weights, pos_inds,
neg_inds, sampling_result)
def atss_target_single(self,
flat_anchors,
valid_flags,
num_level_anchors,
gt_bboxes,
gt_masks,
gt_bboxes_ignore,
gt_labels,
img_meta,
cfg,
target_means,
target_stds,
label_channels=1,
unmap_outputs=True,
with_module=False,
hbb_trans='hbb2obb_v2'):
inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2],
cfg.allowed_border)
if not inside_flags.any():
return (None, ) * 6
# assign gt and sample anchors
anchors = flat_anchors[inside_flags.type(torch.bool), :]
num_level_anchors_inside = self.get_num_level_anchors_inside(
num_level_anchors, inside_flags)
bbox_assigner = build_assigner(cfg.assigner)
assign_result = bbox_assigner.assign(anchors, num_level_anchors_inside,
gt_bboxes, gt_bboxes_ignore,
gt_labels)
bbox_sampler = PseudoSampler()
sampling_result = bbox_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)
## 自己加的
rbbox_targets = torch.zeros(num_valid_anchors, 5).to(anchors.device)
rbbox_weights = torch.zeros(num_valid_anchors, 5).to(anchors.device)
##
labels = anchors.new_zeros(num_valid_anchors, 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
## 自己加的
pos_assigned_gt_inds = sampling_result.pos_assigned_gt_inds
gt_obbs = gt_mask_bp_obbs(gt_masks, with_module)
gt_obbs_ts = torch.from_numpy(gt_obbs).to(
sampling_result.pos_bboxes.device)
pos_gt_obbs_ts = gt_obbs_ts[pos_assigned_gt_inds]
##
if len(pos_inds) > 0:
## 自己加的
pos_ext_rbboxes = hbb2obb_v2(sampling_result.pos_bboxes)
if with_module:
pos_rbbox_targets = dbbox2delta(pos_ext_rbboxes,
pos_gt_obbs_ts, target_means,
target_stds)
else:
pos_rbbox_targets = dbbox2delta_v3(pos_ext_rbboxes,
pos_gt_obbs_ts,
target_means, target_stds)
##
pos_bbox_targets = bbox2delta(sampling_result.pos_bboxes,
sampling_result.pos_gt_bboxes,
self.target_means[:4],
self.target_stds[:4])
bbox_targets[pos_inds, :] = pos_bbox_targets
## 自己加的
rbbox_targets[pos_inds, :] = pos_rbbox_targets
rbbox_weights[pos_inds, :] = 1.0
##
bbox_weights[pos_inds, :] = 1.0
if gt_labels is None:
labels[pos_inds] = 1
else:
labels[pos_inds] = gt_labels[
sampling_result.pos_assigned_gt_inds]
if cfg.pos_weight <= 0:
label_weights[pos_inds] = 1.0
else:
label_weights[pos_inds] = cfg.pos_weight
if len(neg_inds) > 0:
label_weights[neg_inds] = 1.0
# map up to original set of anchors
if unmap_outputs:
inside_flags = inside_flags.type(torch.bool)
num_total_anchors = flat_anchors.size(0)
anchors = unmap(anchors, num_total_anchors, inside_flags)
labels = unmap(labels, num_total_anchors, inside_flags)
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)
## 自己加的
rbbox_targets = unmap(rbbox_targets, num_total_anchors,
inside_flags)
rbbox_weights = unmap(rbbox_weights, num_total_anchors,
inside_flags)
##
return (anchors, labels, label_weights, bbox_targets, bbox_weights,
pos_inds, neg_inds, rbbox_targets, rbbox_weights)
def train_detector(model,
dataset,
cfg,
distributed=False,
validate=False,
timestamp=None,
meta=None):
logger = get_root_logger(cfg.log_level)
# prepare data loaders
dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
if 'imgs_per_gpu' in cfg.data:
logger.warning('"imgs_per_gpu" is deprecated in MMDet V2.0. '
'Please use "samples_per_gpu" instead')
if 'samples_per_gpu' in cfg.data:
logger.warning(
f'Got "imgs_per_gpu"={cfg.data.imgs_per_gpu} and '
f'"samples_per_gpu"={cfg.data.samples_per_gpu}, "imgs_per_gpu"'
f'={cfg.data.imgs_per_gpu} is used in this experiments')
else:
logger.warning(
'Automatically set "samples_per_gpu"="imgs_per_gpu"='
f'{cfg.data.imgs_per_gpu} in this experiments')
cfg.data.samples_per_gpu = cfg.data.imgs_per_gpu
data_loaders = [
build_dataloader(
ds,
cfg.data.samples_per_gpu,
cfg.data.workers_per_gpu,
# cfg.gpus will be ignored if distributed
len(cfg.gpu_ids),
dist=distributed,
seed=cfg.seed) for ds in dataset
]
# put model on gpus
if distributed:
find_unused_parameters = cfg.get('find_unused_parameters', False)
# Sets the `find_unused_parameters` parameter in
# torch.nn.parallel.DistributedDataParallel
model = MMDistributedDataParallel(
model.cuda(),
device_ids=[torch.cuda.current_device()],
broadcast_buffers=False,
find_unused_parameters=find_unused_parameters)
else:
model = MMDataParallel(
model.cuda(cfg.gpu_ids[0]), device_ids=cfg.gpu_ids)
# build runner
optimizer = build_optimizer(model, cfg.optimizer)
if 'runner' not in cfg:
cfg.runner = {
'type': 'EpochBasedRunner',
'max_epochs': cfg.total_epochs
}
warnings.warn(
'config is now expected to have a `runner` section, '
'please set `runner` in your config.', UserWarning)
else:
if 'total_epochs' in cfg:
assert cfg.total_epochs == cfg.runner.max_epochs
runner = build_runner(
cfg.runner,
default_args=dict(
model=model,
optimizer=optimizer,
work_dir=cfg.work_dir,
logger=logger,
meta=meta))
# an ugly workaround to make .log and .log.json filenames the same
runner.timestamp = timestamp
# fp16 setting
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
optimizer_config = Fp16OptimizerHook(
**cfg.optimizer_config, **fp16_cfg, distributed=distributed)
elif distributed and 'type' not in cfg.optimizer_config:
optimizer_config = OptimizerHook(**cfg.optimizer_config)
else:
optimizer_config = cfg.optimizer_config
# register hooks
runner.register_training_hooks(cfg.lr_config, optimizer_config,
cfg.checkpoint_config, cfg.log_config,
cfg.get('momentum_config', None))
if distributed:
if isinstance(runner, EpochBasedRunner):
runner.register_hook(DistSamplerSeedHook())
# register eval hooks
if validate:
# Support batch_size > 1 in validation
val_samples_per_gpu = cfg.data.val.pop('samples_per_gpu', 1)
if val_samples_per_gpu > 1:
# Replace 'ImageToTensor' to 'DefaultFormatBundle'
cfg.data.val.pipeline = replace_ImageToTensor(
cfg.data.val.pipeline)
val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
val_dataloader = build_dataloader(
val_dataset,
samples_per_gpu=val_samples_per_gpu,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=distributed,
shuffle=False)
eval_cfg = cfg.get('evaluation', {})
eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
eval_hook = DistEvalHook if distributed else EvalHook
runner.register_hook(eval_hook(val_dataloader, **eval_cfg))
# user-defined hooks
if cfg.get('custom_hooks', None):
custom_hooks = cfg.custom_hooks
assert isinstance(custom_hooks, list), \
f'custom_hooks expect list type, but got {type(custom_hooks)}'
for hook_cfg in cfg.custom_hooks:
assert isinstance(hook_cfg, dict), \
'Each item in custom_hooks expects dict type, but got ' \
f'{type(hook_cfg)}'
hook_cfg = hook_cfg.copy()
priority = hook_cfg.pop('priority', 'NORMAL')
hook = build_from_cfg(hook_cfg, HOOKS)
runner.register_hook(hook, priority=priority)
if cfg.resume_from:
runner.resume(cfg.resume_from)
elif cfg.load_from:
runner.load_checkpoint(cfg.load_from)
# runner.run(data_loaders, cfg.workflow)
anchor_generator = build_anchor_generator(cfg.model.rpn_head.anchor_generator)
assigner = build_assigner(cfg.model.train_cfg.rpn.assigner)
total_num_targets = torch.tensor([0] * 5)
for iteration, data in enumerate(data_loaders):
for i in data:
# print(i.keys())
img_metas = i['img_metas']._data
# print(img_metas)
num_imgs = len(img_metas)
images = i['img']._data
gt_bboxes = i['gt_bboxes']._data
h, w = images[0].size()[-2:]
features_shape = []
for i in range(2, 7):
f_shape = [int(h/(2**i)), int(w/(2**i))]
features_shape.append(f_shape)
multi_level_anchors = anchor_generator.grid_anchors(
features_shape)
anchor_list = [multi_level_anchors for _ in range(num_imgs)]
# for each image, we compute valid flags of multi level anchors
valid_flag_list = []
for img_id, img_meta in enumerate(img_metas):
multi_level_flags = anchor_generator.valid_flags(
features_shape, img_meta[0]['pad_shape'])
valid_flag_list.append(multi_level_flags)
# print(anchor_list, valid_flag_list)
assert len(anchor_list) == len(valid_flag_list) == num_imgs
# anchor number of multi levels
num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]]
# concat all level anchors to a single tensor
concat_anchor_list = []
concat_valid_flag_list = []
for i in range(num_imgs):
assert len(anchor_list[i]) == len(valid_flag_list[i])
concat_anchor_list.append(torch.cat(anchor_list[i]))
concat_valid_flag_list.append(torch.cat(valid_flag_list[i]))
gt_bboxes_ignore_list= None
# compute targets for each image
if gt_bboxes_ignore_list is None:
gt_bboxes_ignore_list = [None for _ in range(num_imgs)]
inside_flags = anchor_inside_flags(concat_anchor_list[0], concat_valid_flag_list[0],
img_metas[0][0]['img_shape'][:2],
0)
if not inside_flags.any():
return (None, ) * 7
# assign gt and sample anchors
anchors = concat_anchor_list[0][inside_flags, :]
assign_result = assigner.assign(
anchors.cpu(), gt_bboxes[0][0], gt_bboxes_ignore_list[0],
None)
print(assign_result.pos_gt_bboxes)
pos_inds = torch.nonzero(assign_result.gt_inds > 0, as_tuple=False)
labels = anchors.new_full((anchors.shape[0], ),
-1,
dtype=torch.long)
labels[pos_inds] = 1
num_total_anchors = concat_anchor_list[0].size(0)
labels = unmap(
labels, num_total_anchors, inside_flags,
fill=-1) # fill bg label
match_results = images_to_levels([labels], num_level_anchors)
# print(match_results)
for idx, match_result in enumerate(match_results):
num = torch.where(match_result==1)[0].numel()
total_num_targets[idx] += num
# print(total_num_targets)
print(total_num_targets)
print(total_num_targets)
