def forward(self, node_preds, edge_preds, gts):
node_gts, edge_gts = [], []
for gt in gts:
node_gts.append(gt[:, 0])
edge_gts.append(gt[:, 1:].contiguous().view(-1))
node_gts = torch.cat(node_gts).long()
edge_gts = torch.cat(edge_gts).long()
node_valids = torch.nonzero(node_gts != self.ignore).view(-1)
edge_valids = torch.nonzero(edge_gts != -1).view(-1)
return dict(
loss_node=self.node_weight * self.loss_node(node_preds, node_gts),
loss_edge=self.edge_weight * self.loss_edge(edge_preds, edge_gts),
acc_node=accuracy(node_preds[node_valids], node_gts[node_valids]),
acc_edge=accuracy(edge_preds[edge_valids], edge_gts[edge_valids]))
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if cls_score is not None:
# avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
# if cls_score.numel() > 0:
# losses['loss_cls'] = self.loss_cls(
# cls_score,
# labels,
# label_weights,
# avg_factor=avg_factor,
# reduction_override=reduction_override)
# losses['acc'] = accuracy(cls_score, labels)
# Original label_weights is 1 for each roi.
new_labels, new_weights, new_avgfactors = self._remap_labels(
labels)
new_preds = self._slice_preds(cls_score)
num_bins = len(new_labels)
for i in range(num_bins):
losses['loss_cls_bin{}'.format(i)] = self.loss_bins[i](
new_preds[i],
new_labels[i].long(),
new_weights[i],
avg_factor=new_avgfactors[i],
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
return losses
def loss(self,
cls_score,
bbox_pred,
dist,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None,
img_metas=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred[pos_inds].sum()
# embedding loss for repmet
'''
if dist is not None:
mask_label = torch.eye(self.num_classes + 1)[labels.long(),:].to(labels.device)
gt_dist = torch.masked_select(dist, mask_label.bool())
neg_dist = torch.masked_select(dist, ~mask_label.bool())
neg_dist = neg_dist.reshape(labels.shape[0], self.num_classes)
neg_dist = torch.min(neg_dist, dim = 1)[0]
embedding_dist = gt_dist + self.alpha - neg_dist
embedding_dist = torch.masked_select(embedding_dist, embedding_dist.ge(0))
embedding_loss = torch.sum(embedding_dist) / embedding_dist.shape[0]
losses['loss_embedding'] = embedding_loss
'''
return losses
def loss_labels(self, outputs, targets, indices, num_boxes, log=True):
"""Classification loss (NLL)
targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]
"""
assert 'pred_logits' in outputs
src_logits = outputs['pred_logits']
idx = self._get_src_permutation_idx(indices)
target_classes_o = torch.cat(
[t["labels"][J] for t, (_, J) in zip(targets, indices)])
target_classes = torch.full(src_logits.shape[:2],
self.num_classes,
dtype=torch.int64,
device=src_logits.device)
target_classes[idx] = target_classes_o
loss_ce = F.cross_entropy(src_logits.transpose(1, 2), target_classes,
self.empty_weight)
losses = {'loss_ce': loss_ce}
if log:
# TODO this should probably be a separate loss, not hacked in this one here
losses['class_error'] = 100 - accuracy(src_logits[idx],
target_classes_o)[0]
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
if self.loss_cls_type == "CBLoss":
# fg_inds = (labels >= 0) & (labels < self.num_classes)
# fg_labels = labels[fg_inds]
unique_labels, count = torch.unique(labels,
return_counts=True)
samples_per_class = torch.zeros(self.num_classes + 1,
dtype=torch.int64).cuda()
samples_per_class[unique_labels] = count
losses['loss_cls'] = self.loss_cls(labels, cls_score,
samples_per_class,
self.num_classes + 1)
else:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
# print("pos_bbox_pred:", pos_bbox_pred)
# print("pos_bbox_targets:", bbox_targets[pos_inds.type(torch.bool)])
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
loss_cls_ = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
if isinstance(loss_cls_, dict):
losses.update(loss_cls_)
else:
losses['loss_cls'] = loss_cls_
if self.custom_activation:
acc_ = self.loss_cls.get_accuracy(cls_score, labels)
losses.update(acc_)
else:
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
# When the regression loss (e.g. `IouLoss`,
# `GIouLoss`, `DIouLoss`) is applied directly on
# the decoded bounding boxes, it decodes the
# already encoded coordinates to absolute format.
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred[pos_inds].sum()
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
gt_bboxes=None,
img_metas=None,
stage=None,
reduction_override=None):
# # rank, _ = get_dist_info()
# # if self.if_save_image and rank == 0 and self.iteration % self.save_interval == 0:
if 1:
roi_loss_save_images(img_metas, cls_score, bbox_pred, rois, labels,
gt_bboxes, self.bbox_coder, stage)
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred[pos_inds].sum()
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# print('bg ind are ')
# print(bg_class_ind)
# print('labels are')
# print(np.unique(labels.cpu()))
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bucket_cls_preds, bucket_offset_preds = bbox_pred
bucket_cls_targets, bucket_offset_targets = bbox_targets
bucket_cls_weights, bucket_offset_weights = bbox_weights
# edge cls
bucket_cls_preds = bucket_cls_preds.view(-1, self.side_num)
bucket_cls_targets = bucket_cls_targets.view(-1, self.side_num)
bucket_cls_weights = bucket_cls_weights.view(-1, self.side_num)
losses['loss_bbox_cls'] = self.loss_bbox_cls(
bucket_cls_preds,
bucket_cls_targets,
bucket_cls_weights,
avg_factor=bucket_cls_targets.size(0),
reduction_override=reduction_override)
losses['loss_bbox_reg'] = self.loss_bbox_reg(
bucket_offset_preds,
bucket_offset_targets,
bucket_offset_weights,
avg_factor=bucket_offset_targets.size(0),
reduction_override=reduction_override)
return losses
def loss(self,
cls_score,
bbox_pred,
dist,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None,
img_metas=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
#大类别分类
cls_score_all = []
for class_index in range(self.num_classes):
cls_score_all.append(
torch.max(cls_score[:, class_index *
2:(class_index + 1) * 2],
dim=1)[0].unsqueeze(1))
cls_score_all.append(cls_score[:, cls_score.shape[1] -
1].unsqueeze(1))
cls_score_all = torch.cat(cls_score_all,
dim=1).to(labels.device)
losses['loss_cls'] = self.loss_cls(
cls_score_all,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score_all, labels)
#风格分类
proposal_num_per_pic = 512
styles = torch.zeros(labels.shape[0] // proposal_num_per_pic)
for i, meta in enumerate(img_metas):
pic = meta['filename'].split('.')[0].split('/')[-1]
styles[i] = int(self.file_to_style[pic])
style_labels, cls_score_style = [], []
for proposal in range(labels.shape[0]):
if labels[proposal] != 19:
# 当前proposal所属的风格
# 每个pic512个proposal
style_index = proposal // 512
cur_style = styles[style_index]
style_labels.append(cur_style.unsqueeze(0))
cls_score_style.append(
cls_score[proposal]
[labels[proposal]:labels[proposal] +
2].unsqueeze(0))
style_labels = torch.cat(style_labels,
dim=0).to(cls_score.device).long()
cls_score_style = torch.cat(cls_score_style,
dim=0).to(cls_score.device)
label_weights = torch.ones(style_labels.shape[0]).to(
cls_score.device)
avg_factor = max(
torch.sum(label_weights > 0).float().item(), 1.)
losses['loss_cls_style'] = self.loss_cls(
cls_score_style,
style_labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred[pos_inds].sum()
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# print(pos_inds)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 5)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
5)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
# print(pos_bbox_pred,
# bbox_targets[pos_inds.type(torch.bool)],
# bbox_weights[pos_inds.type(torch.bool)])
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
# ###########################################################
from mmdet.MARK import PRINT_RBBOX_HEAD_RS_LOSS
if torch.sum(pos_inds) > 0:
# pos_inds = pos_inds[0:min(len(pos_inds), 10)]
pred_score = cls_score[pos_inds].softmax(1)
pred_score, pred_label = torch.max(pred_score, dim=1)
# 前景标签
pred_f_indices = pred_label != bg_class_ind
# from EXP_CONCONFIG.MARK import PRINT_RBBOX_HEAD
# PRINT_RBBOX_HEAD = True
pos_loss = self.loss_cls(cls_score[pos_inds], labels[pos_inds],
label_weights[pos_inds])
pos_acc = accuracy(cls_score[pos_inds], labels[pos_inds])
if torch.sum(pred_f_indices) > 0:
print('#' * 80)
print('pred_score:',
pred_score[pred_f_indices].detach().cpu().numpy())
print('pred_label:',
pred_label[pred_f_indices].detach().cpu().numpy())
print('gt_label:',
labels[pos_inds][pred_f_indices].detach().cpu().numpy())
print('pos loss: %.2f' % float(pos_loss),
' || pos acc: %.2f' % float(pos_acc))
print('total_loss:', float(losses['loss_cls']))
print('%d, %d' % (int(torch.sum(pos_inds)), len(cls_score)))
print(torch.sum(label_weights))
print('#' * 80)
# ###########################################################
return losses
def loss(self,
cls_score,
bbox_pred,
labels,
label_weights,
bbox_targets,
bbox_weights,
imgs_whwh=None,
reduction_override=None,
**kwargs):
""""Loss function of DIIHead, get loss of all images.
Args:
cls_score (Tensor): Classification prediction
results of all class, has shape
(batch_size * num_proposals_single_image, num_classes)
bbox_pred (Tensor): Regression prediction results,
has shape
(batch_size * num_proposals_single_image, 4), the last
dimension 4 represents [tl_x, tl_y, br_x, br_y].
labels (Tensor): Label of each proposals, has shape
(batch_size * num_proposals_single_image
label_weights (Tensor): Classification loss
weight of each proposals, has shape
(batch_size * num_proposals_single_image
bbox_targets (Tensor): Regression targets of each
proposals, has shape
(batch_size * num_proposals_single_image, 4),
the last dimension 4 represents
[tl_x, tl_y, br_x, br_y].
bbox_weights (Tensor): Regression loss weight of each
proposals's coordinate, has shape
(batch_size * num_proposals_single_image, 4),
imgs_whwh (Tensor): imgs_whwh (Tensor): Tensor with\
shape (batch_size, num_proposals, 4), the last
dimension means
[img_width,img_height, img_width, img_height].
reduction_override (str, optional): The reduction
method used to override the original reduction
method of the loss. Options are "none",
"mean" and "sum". Defaults to None,
Returns:
dict[str, Tensor]: Dictionary of loss components
"""
losses = dict()
bg_class_ind = self.num_classes
# note in spare rcnn num_gt == num_pos
pos_inds = (labels >= 0) & (labels < bg_class_ind)
num_pos = pos_inds.sum().float()
avg_factor = reduce_mean(num_pos)
if cls_score is not None:
if cls_score.numel() > 0:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['pos_acc'] = accuracy(cls_score[pos_inds],
labels[pos_inds])
if bbox_pred is not None:
# 0~self.num_classes-1 are FG, self.num_classes is BG
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
pos_bbox_pred = bbox_pred.reshape(bbox_pred.size(0),
4)[pos_inds.type(torch.bool)]
imgs_whwh = imgs_whwh.reshape(bbox_pred.size(0),
4)[pos_inds.type(torch.bool)]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred / imgs_whwh,
bbox_targets[pos_inds.type(torch.bool)] / imgs_whwh,
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=avg_factor)
losses['loss_iou'] = self.loss_iou(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=avg_factor)
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
losses['loss_iou'] = bbox_pred.sum() * 0
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
if bbox_pred is not None:
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred[pos_inds].sum()
if cls_score is not None:
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
argspec = inspect.getargspec(self.loss_cls.forward)
pos_ious = bbox_overlaps(pos_bbox_pred,
bbox_targets[pos_inds.type(
torch.bool)],
is_aligned=True).clamp(min=1e-7)
if 'pos_ious' not in argspec.args:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
else:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
pos_ious=pos_ious,
weight=label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
return losses
def loss(self,
similarity_logits,
track_id_targets,
track_id_weights,
reduction_override=None):
"""Calculate the loss in a batch.
Args:
similarity_logits (list[Tensor]): The predicted similarity_logits
of each pair of key image and reference image.
track_id_targets (list[Tensor]): The instance ids of Gt_labels for
all proposals in a batch, each tensor in list has shape
(num_proposals,).
track_id_weights (list[Tensor]): Labels_weights for
all proposals in a batch, each tensor in list has shape
(num_proposals,).
reduction_override (str, optional): The method used to reduce the
loss. Options are "none", "mean" and "sum".
Returns:
dict[str, Tensor]: a dictionary of loss components.
"""
assert isinstance(similarity_logits, list)
assert isinstance(track_id_targets, list)
assert isinstance(track_id_weights, list)
assert len(similarity_logits) == len(track_id_targets)
assert len(track_id_weights) == len(track_id_targets)
losses = defaultdict(list)
for similarity_logit, track_id_target, track_id_weight in zip(
similarity_logits, track_id_targets, track_id_weights):
avg_factor = max(torch.sum(track_id_target > 0).float().item(), 1.)
if similarity_logit.numel() > 0:
loss_match = self.loss_match(
similarity_logit,
track_id_target,
track_id_weight,
avg_factor=avg_factor,
reduction_override=reduction_override)
if isinstance(loss_match, dict):
for key, value in loss_match.items():
losses[key].append(value)
else:
losses['loss_match'].append(loss_match)
valid_index = track_id_weight > 0
valid_similarity_logit = similarity_logit[valid_index]
valid_track_id_target = track_id_target[valid_index]
if self.custom_activation:
match_accuracy = self.loss_match.get_accuracy(
valid_similarity_logit, valid_track_id_target)
for key, value in match_accuracy.items():
losses[key].append(value)
else:
losses['match_accuracy'].append(
accuracy(valid_similarity_logit,
valid_track_id_target))
for key, value in losses.items():
losses[key] = sum(losses[key]) / len(similarity_logits)
return losses
def loss(self,
cls_score,
bbox_pred,
fix_pred,
ratio_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
fix_targets,
fix_weights,
ratio_targets,
ratio_weights,
reduction_override=None):
losses = dict()
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
losses['loss_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['acc'] = accuracy(cls_score, labels)
bg_class_ind = self.num_classes
# 0~self.num_classes-1 are FG, self.num_classes is BG
pos_inds = (labels >= 0) & (labels < bg_class_ind)
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(bbox_pred.size(0),
4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
if pos_inds.any():
if self.reg_class_agnostic:
pos_fix_pred = fix_pred.view(fix_pred.size(0),
4)[pos_inds.type(torch.bool)]
else:
pos_fix_pred = fix_pred.view(
fix_pred.size(0), -1, 4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_fix'] = self.loss_fix(
pos_fix_pred,
fix_targets[pos_inds.type(torch.bool)],
fix_weights[pos_inds.type(torch.bool)],
avg_factor=fix_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_fix'] = fix_pred.sum() * 0
if pos_inds.any():
if self.reg_class_agnostic:
pos_ratio_pred = ratio_pred.view(ratio_pred.size(0),
1)[pos_inds.type(torch.bool)]
else:
pos_ratio_pred = ratio_pred.view(
ratio_pred.size(0), -1,
1)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_ratio'] = self.loss_ratio(
pos_ratio_pred,
ratio_targets[pos_inds.type(torch.bool)],
ratio_weights[pos_inds.type(torch.bool)],
avg_factor=ratio_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_ratio'] = ratio_pred.sum() * 0
return losses
def loss(self,
cls_score,
bbox_pred,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
# if cls_score is not None:
# avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
# if cls_score.numel() > 0:
# losses['loss_cls'] = self.loss_cls(
# cls_score,
# labels,
# label_weights,
# avg_factor=avg_factor,
# reduction_override=reduction_override)
# pos_inds = (labels >= 0) & (labels < self.num_classes)
# losses['acc'] = pos_inds.type(torch.float32).sum()
# # losses['acc'] = accuracy(cls_score, labels)
# if bbox_pred is not None:
# bg_class_ind = self.num_classes
# # 0~self.num_classes-1 are FG, self.num_classes is BG
# pos_inds = (labels >= 0) & (labels < bg_class_ind)
# # do not perform bounding box regression for BG anymore.
# if pos_inds.any():
# if self.reg_decoded_bbox:
# bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
# if self.reg_class_agnostic:
# pos_bbox_pred = bbox_pred.view(
# bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
# else:
# pos_bbox_pred = bbox_pred.view(
# bbox_pred.size(0), -1,
# 4)[pos_inds.type(torch.bool),
# labels[pos_inds.type(torch.bool)]]
# losses['loss_bbox'] = self.loss_bbox(
# pos_bbox_pred,
# bbox_targets[pos_inds.type(torch.bool)],
# bbox_weights[pos_inds.type(torch.bool)],
# avg_factor=bbox_targets.size(0),
# reduction_override=reduction_override)
# else:
# losses['loss_bbox'] = bbox_pred[pos_inds].sum()
bg_class_ind = self.num_classes
pos_inds = (labels >= 0) & (labels < bg_class_ind)
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(-1, 4)
losses['loss_bbox'] = self.loss_bbox(
pos_bbox_pred[pos_inds.type(torch.bool)],
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
pos_pred_bboxes = self.bbox_coder.decode(rois[pos_inds, 1:], bbox_pred[pos_inds])
pos_target_bboxes = self.bbox_coder.decode(rois[pos_inds, 1:], bbox_targets[pos_inds])
from mmdet.core import bbox_overlaps
score = label_weights.new_zeros(labels.shape)
score[pos_inds] = bbox_overlaps(pos_pred_bboxes,
pos_target_bboxes, is_aligned=True)
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
losses['loss_cls'] = self.loss_cls(
cls_score, (labels, score),
weight=label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['num'] = pos_inds.type(torch.float32).sum()
losses['acc'] = accuracy(cls_score, labels)
return losses
def loss(self,
okpd_outs,
rois,
labels,
label_weights,
bbox_targets,
bbox_weights,
reduction_override=None):
losses = dict()
cls_score = okpd_outs[-2]
bbox_pred = okpd_outs[-1]
bg_class_ind = self.num_classes
pos_inds = (labels >= 0) & (labels < bg_class_ind)
avg_factor = max(torch.sum(label_weights > 0).float().item(), 1.)
if cls_score.numel() > 0:
losses['loss_okpd_cls'] = self.loss_cls(
cls_score,
labels,
label_weights,
avg_factor=avg_factor,
reduction_override=reduction_override)
losses['okpd_acc'] = accuracy(cls_score, labels)
if bbox_pred is not None:
# do not perform bounding box regression for BG anymore.
if pos_inds.any():
if self.reg_decoded_bbox:
bbox_pred = self.bbox_coder.decode(rois[:, 1:], bbox_pred)
if self.reg_class_agnostic:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), 4)[pos_inds.type(torch.bool)]
else:
pos_bbox_pred = bbox_pred.view(
bbox_pred.size(0), -1,
4)[pos_inds.type(torch.bool),
labels[pos_inds.type(torch.bool)]]
losses['loss_okpd_bbox'] = self.loss_bbox(
pos_bbox_pred,
bbox_targets[pos_inds.type(torch.bool)],
bbox_weights[pos_inds.type(torch.bool)],
avg_factor=bbox_targets.size(0),
reduction_override=reduction_override)
else:
losses['loss_bbox'] = bbox_pred.sum() * 0
if self.num_kp > 0:
kp_max_target = torch.zeros_like(okpd_outs[0])
kp_max_target[pos_inds, ...] = 1.
kp_max_wts = torch.zeros_like(okpd_outs[0]) + 0.5
fn_inds = (kp_max_target > 0.) & (okpd_outs[0] < 0.5)
fp_inds = (kp_max_target < 1.) & (okpd_outs[0] > 0.5)
kp_max_wts[fp_inds | fn_inds] = 1.0
Ld_loss = smooth_l1_loss(okpd_outs[0] * kp_max_wts,
kp_max_target * kp_max_wts,
beta=0.05)
pos_mask = pos_inds.float()[:, None, None, None]
kp_ch_sum_target = torch.zeros_like(okpd_outs[1])
kp_ch_sum_target[pos_inds, ...] = 1.
Lu_loss = smooth_l1_loss(okpd_outs[1] * pos_mask,
kp_ch_sum_target * pos_mask,
beta=1.0)
losses['kp_loss'] = 0.03 * (Ld_loss + Lu_loss)
return losses
