def regress_by_class_rbbox(self, rois, label, bbox_pred, img_meta):
"""Regress the bbox for the predicted class. Used in Cascade R-CNN.
Args:
rois (Tensor): shape (n, 5) or (n, 6)
label (Tensor): shape (n, )
bbox_pred (Tensor): shape (n, 5*(#class+1)) or (n, 5)
img_meta (dict): Image meta info.
Returns:
Tensor: Regressed bboxes, the same shape as input rois.
"""
# import pdb
# pdb.set_trace()
assert rois.size(1) == 5 or rois.size(1) == 6
if not self.reg_class_agnostic:
label = label * 5
inds = torch.stack(
(label, label + 1, label + 2, label + 3, label + 4), 1)
bbox_pred = torch.gather(bbox_pred, 1, inds)
assert bbox_pred.size(1) == 5
if rois.size(1) == 5:
if self.with_module:
# # 原先版本
# new_rois = delta2dbbox(rois, bbox_pred, self.target_means,
# self.target_stds, img_meta['img_shape'])
# 替换为第二阶段相应的解码方案
new_rois = delta2dbbox_v2(rois, bbox_pred, self.target_means,
self.target_stds,
img_meta['img_shape'])
else:
new_rois = delta2dbbox_v3(rois, bbox_pred, self.target_means,
self.target_stds,
img_meta['img_shape'])
# choose best Rroi
new_rois = choose_best_Rroi_batch(new_rois)
else:
if self.with_module:
# bboxes = delta2dbbox(rois[:, 1:], bbox_pred, self.target_means,
# self.target_stds, img_meta['img_shape'])
# 替换为第二阶段相应的解码方案
bboxes = delta2dbbox_v2(rois[:, 1:], bbox_pred,
self.target_means, self.target_stds,
img_meta['img_shape'])
else:
bboxes = delta2dbbox_v3(rois[:, 1:], bbox_pred,
self.target_means, self.target_stds,
img_meta['img_shape'])
bboxes = choose_best_Rroi_batch(bboxes)
new_rois = torch.cat((rois[:, [0]], bboxes), dim=1)
return new_rois
def forward_train(self,
img,
img_meta,
gt_bboxes,
gt_labels,
gt_bboxes_ignore=None,
gt_masks=None,
proposals=None):
x = self.extract_feat(img)
losses = dict()
# trans gt_masks to gt_obbs
# gt_obbs = gt_mask_bp_obbs_list(gt_masks)
gt_obb_masks = mask2obb_mask(gt_bboxes, gt_masks, enlarge_pixel=2)
gt_obbs = gt_mask_bp_obbs_list(gt_obb_masks)
# RPN forward and loss
if self.with_rpn:
rpn_outs = self.rpn_head(x)
rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta,
self.train_cfg.rpn)
rpn_losses = self.rpn_head.loss(
*rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
losses.update(rpn_losses)
proposal_cfg = self.train_cfg.get('rpn_proposal',
self.test_cfg.rpn)
proposal_inputs = rpn_outs + (img_meta, proposal_cfg)
proposal_list = self.rpn_head.get_bboxes(*proposal_inputs)
else:
proposal_list = proposals
# assign gts and sample proposals (hbb assign)
if self.with_bbox or self.with_mask:
bbox_assigner = build_assigner(self.train_cfg.rcnn[0].assigner)
bbox_sampler = build_sampler(
self.train_cfg.rcnn[0].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
assign_result = bbox_assigner.assign(
proposal_list[i], gt_bboxes[i], gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
proposal_list[i],
gt_bboxes[i],
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
# bbox head forward and loss
if self.with_bbox:
rois = bbox2roi([res.bboxes for res in sampling_results])
# TODO: a more flexible way to decide which feature maps to use
bbox_feats = self.bbox_roi_extractor(
x[:self.bbox_roi_extractor.num_inputs], rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred = self.bbox_head(bbox_feats)
## rbbox
# rbbox_targets = self.bbox_head.get_target(
# sampling_results, gt_masks, gt_labels, self.train_cfg.rcnn[0])
rbbox_targets = self.bbox_head.get_target(
sampling_results, gt_obb_masks, gt_labels, self.train_cfg.rcnn[0])
loss_bbox = self.bbox_head.loss(cls_score, bbox_pred,
*rbbox_targets)
# losses.update(loss_bbox)
for name, value in loss_bbox.items():
losses['s{}.{}'.format(0, name)] = (value)
pos_is_gts = [res.pos_is_gt for res in sampling_results]
roi_labels = rbbox_targets[0]
with torch.no_grad():
# import pdb
# pdb.set_trace()
rotated_proposal_list = self.bbox_head.refine_rbboxes(
roi2droi(rois), roi_labels, bbox_pred, pos_is_gts, img_meta
)
# import pdb
# pdb.set_trace()
# assign gts and sample proposals (rbb assign)
if self.with_rbbox:
bbox_assigner = build_assigner(self.train_cfg.rcnn[1].assigner)
bbox_sampler = build_sampler(
self.train_cfg.rcnn[1].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
gt_obbs_best_roi = choose_best_Rroi_batch(gt_obbs[i])
assign_result = bbox_assigner.assign(
rotated_proposal_list[i], gt_obbs_best_roi, gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
rotated_proposal_list[i],
torch.from_numpy(gt_obbs_best_roi).float().to(rotated_proposal_list[i].device),
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
if self.with_rbbox:
# (batch_ind, x_ctr, y_ctr, w, h, angle)
rrois = dbbox2roi([res.bboxes for res in sampling_results])
# feat enlarge
# rrois[:, 3] = rrois[:, 3] * 1.2
# rrois[:, 4] = rrois[:, 4] * 1.4
rrois[:, 3] = rrois[:, 3] * self.rbbox_roi_extractor.w_enlarge
rrois[:, 4] = rrois[:, 4] * self.rbbox_roi_extractor.h_enlarge
rbbox_feats = self.rbbox_roi_extractor(x[:self.rbbox_roi_extractor.num_inputs],
rrois)
if self.with_shared_head_rbbox:
rbbox_feats = self.shared_head_rbbox(rbbox_feats)
cls_score, rbbox_pred = self.rbbox_head(rbbox_feats)
rbbox_targets = self.rbbox_head.get_target_rbbox(sampling_results, gt_obbs,
gt_labels, self.train_cfg.rcnn[1])
loss_rbbox = self.rbbox_head.loss(cls_score, rbbox_pred, *rbbox_targets)
for name, value in loss_rbbox.items():
losses['s{}.{}'.format(1, name)] = (value)
pos_rrois = dbbox2roi(
[res.pos_bboxes for res in sampling_results])
mask_feats = self.mask_rroi_extractor(
x[:self.mask_rroi_extractor.num_inputs], pos_rrois)
mask_pred = self.mask_head(mask_feats)
mask_targets = self.mask_head.get_rotate_target(
sampling_results, gt_masks, self.train_cfg.rcnn[1])
pos_labels = torch.cat(
[res.pos_gt_labels for res in sampling_results])
loss_mask = self.mask_head.loss(mask_pred, mask_targets,
pos_labels)
loss_mask['loss_mask_obb'] = loss_mask.pop('loss_mask')
losses.update(loss_mask)
return losses
def forward_train(self,
img,
img_meta,
gt_bboxes,
gt_labels,
gt_bboxes_ignore=None,
gt_masks=None,
proposals=None):
x = self.extract_feat(img)
losses = dict()
# trans gt_masks to gt_obbs
gt_obbs = gt_mask_bp_obbs_list(gt_masks)
# RPN forward and loss
if self.with_rpn:
rpn_outs = self.rpn_head(x)
rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta,
self.train_cfg.rpn)
rpn_losses = self.rpn_head.loss(
*rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
losses.update(rpn_losses)
proposal_cfg = self.train_cfg.get('rpn_proposal',
self.test_cfg.rpn)
proposal_inputs = rpn_outs + (img_meta, proposal_cfg)
proposal_list = self.rpn_head.get_bboxes(*proposal_inputs)
else:
proposal_list = proposals
for i in range(self.num_stages):
self.current_stage = i
rcnn_train_cfg = self.train_cfg.rcnn[i]
lw = self.train_cfg.stage_loss_weights[i]
# assign gts and sample proposals
sampling_results = []
if self.with_bbox or self.with_mask:
bbox_assigner = build_assigner(rcnn_train_cfg.assigner)
bbox_sampler = build_sampler(
rcnn_train_cfg.sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
for j in range(num_imgs):
assign_result = bbox_assigner.assign(
proposal_list[j], gt_bboxes[j], gt_bboxes_ignore[j],
gt_labels[j])
sampling_result = bbox_sampler.sample(
assign_result,
proposal_list[j],
gt_bboxes[j],
gt_labels[j],
feats=[lvl_feat[j][None] for lvl_feat in x])
sampling_results.append(sampling_result)
# bbox head forward and loss
bbox_roi_extractor = self.bbox_roi_extractor[i]
bbox_head = self.bbox_head[i]
rois = bbox2roi([res.bboxes for res in sampling_results])
bbox_feats = bbox_roi_extractor(x[:bbox_roi_extractor.num_inputs],
rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred = bbox_head(bbox_feats)
if i < self.num_stages - 1:
bbox_targets = bbox_head.get_target(sampling_results, gt_bboxes,
gt_labels, rcnn_train_cfg)
loss_bbox = bbox_head.loss(cls_score, bbox_pred, *bbox_targets)
for name, value in loss_bbox.items():
if 'loss' in name:
losses['s{}.{}'.format(i, name)] = (value * lw if 'loss' in name else value)
else:
losses['s{}.{}'.format(i, name)] = (value)
pos_is_gts = [res.pos_is_gt for res in sampling_results]
roi_labels = bbox_targets[0] # bbox_targets is a tuple
with torch.no_grad():
proposal_list = bbox_head.refine_bboxes(
rois, roi_labels, bbox_pred, pos_is_gts, img_meta)
if i == self.num_stages - 1:
## rbbox
rbbox_targets = bbox_head.get_target(
sampling_results, gt_masks, gt_labels, rcnn_train_cfg)
loss_bbox = bbox_head.loss(cls_score, bbox_pred,
*rbbox_targets)
# losses.update(loss_bbox)
for name, value in loss_bbox.items():
if 'loss' in name:
losses['s{}.{}'.format(i, name)] = (value * lw if 'loss' in name else value)
else:
losses['s{}.{}'.format(i, name)] = (value)
pos_is_gts = [res.pos_is_gt for res in sampling_results]
roi_labels = rbbox_targets[0]
with torch.no_grad():
# import pdb
# pdb.set_trace()
rotated_proposal_list = bbox_head.refine_rbboxes(
roi2droi(rois), roi_labels, bbox_pred, pos_is_gts, img_meta
)
# import pdb
# pdb.set_trace()
# assign gts and sample proposals (rbb assign)
if self.with_rbbox:
bbox_assigner = build_assigner(self.train_cfg.rcnn[-1].assigner)
bbox_sampler = build_sampler(
self.train_cfg.rcnn[-1].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
gt_obbs_best_roi = choose_best_Rroi_batch(gt_obbs[i])
assign_result = bbox_assigner.assign(
rotated_proposal_list[i], gt_obbs_best_roi, gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
rotated_proposal_list[i],
torch.from_numpy(gt_obbs_best_roi).float().to(rotated_proposal_list[i].device),
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
if self.with_rbbox:
# (batch_ind, x_ctr, y_ctr, w, h, angle)
rrois = dbbox2roi([res.bboxes for res in sampling_results])
# feat enlarge
# rrois[:, 3] = rrois[:, 3] * 1.2
# rrois[:, 4] = rrois[:, 4] * 1.4
rrois[:, 3] = rrois[:, 3] * self.rbbox_roi_extractor.w_enlarge
rrois[:, 4] = rrois[:, 4] * self.rbbox_roi_extractor.h_enlarge
rbbox_feats = self.rbbox_roi_extractor(x[:self.rbbox_roi_extractor.num_inputs],
rrois)
if self.with_shared_head_rbbox:
rbbox_feats = self.shared_head_rbbox(rbbox_feats)
cls_score, rbbox_pred = self.rbbox_head(rbbox_feats)
rbbox_targets = self.rbbox_head.get_target_rbbox(sampling_results, gt_obbs,
gt_labels, self.train_cfg.rcnn[-1])
loss_rbbox = self.rbbox_head.loss(cls_score, rbbox_pred, *rbbox_targets)
for name, value in loss_rbbox.items():
losses['s{}.{}'.format(self.num_stages+1, name)] = (value)
return losses
def forward_train(self,
img,
img_meta,
gt_bboxes,
gt_labels,
gt_bboxes_ignore=None,
gt_masks=None,
proposals=None):
x = self.extract_feat(img)
losses = dict()
# trans gt_masks to gt_obbs
gt_obbs = gt_mask_bp_obbs_list(gt_masks)
#FCOS forward and loss
if self.with_fcos:
fcos_outs = self.fcos_head(x)
fcos_loss_inputs = fcos_outs + (gt_bboxes, gt_labels, img_meta,
self.train_cfg.fcos)
fcos_losses = self.fcos_head.loss(
*fcos_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
losses.update(fcos_losses)
bboxes_pred_inputs = fcos_outs + (img_meta, self.test_cfg.fcos)
fcos_bboxes_pred = self.fcos_head.get_bboxes(*bboxes_pred_inputs)
fcos_proposal = [0] * len(fcos_bboxes_pred)
for i in range(len(fcos_bboxes_pred)):
fcos_bboxes_pred_all = fcos_bboxes_pred[i][0]
# if len(fcos_bboxes_pred_all)>=100:
# values,topk_inds=fcos_bboxes_pred_all[:,4].topk(100)
# fcos_all_proposal_tenor=fcos_bboxes_pred_all[topk_inds, :]
# # fcos_all_proposal_tenor = torch.squeeze(fcos_bboxes_pred_all[topk_inds, :])
# else:
# fcos_all_proposal_tenor = fcos_bboxes_pred_all
fcos_all_proposal_tenor = fcos_bboxes_pred_all
fcos_proposal_tensor = fcos_all_proposal_tenor
if len(fcos_proposal_tensor.shape) >= 2:
fcos_proposal[i] = fcos_proposal_tensor
else:
fcos_proposal[i] = fcos_proposal_tensor.unsqueeze(0)
# fcos_proposal = [0]*len(fcos_bboxes_pred)
# for i in range(len(fcos_bboxes_pred)):
# fcos_bboxes_pred_p2=fcos_bboxes_pred[i][2] #output of p2
# fcos_bboxes_pred_p3 = fcos_bboxes_pred[i][4] #output of p3
# fcos_bboxes_pred_p4 = fcos_bboxes_pred[i][6] # output of p4
# fcos_bboxes_pred_p5 = fcos_bboxes_pred[i][8] # output of p5
# fcos_bboxes_pred_p6 = fcos_bboxes_pred[i][10] # output of p6
#
# fcos_p2_proposal_tensor = torch.squeeze(fcos_bboxes_pred_p2)
# fcos_p3_proposal_tensor = torch.squeeze(fcos_bboxes_pred_p3)
# fcos_p4_proposal_tensor = torch.squeeze(fcos_bboxes_pred_p4)
# fcos_p5_proposal_tensor = torch.squeeze(fcos_bboxes_pred_p5)
# fcos_p6_proposal_tensor = torch.squeeze(fcos_bboxes_pred_p6)
#
# if len(fcos_p2_proposal_tensor.shape) < 2:
# fcos_p2_proposal_tensor = fcos_p2_proposal_tensor.unsqueeze(0)
# if len(fcos_p3_proposal_tensor.shape) < 2:
# fcos_p3_proposal_tensor = fcos_p3_proposal_tensor.unsqueeze(0)
# if len(fcos_p4_proposal_tensor.shape) < 2:
# fcos_p4_proposal_tensor = fcos_p4_proposal_tensor.unsqueeze(0)
# if len(fcos_p5_proposal_tensor.shape) < 2:
# fcos_p5_proposal_tensor = fcos_p5_proposal_tensor.unsqueeze(0)
# if len(fcos_p6_proposal_tensor.shape) < 2:
# fcos_p6_proposal_tensor = fcos_p6_proposal_tensor.unsqueeze(0)
#
# fcos_proposal_tensor = torch.cat([fcos_p2_proposal_tensor, fcos_p3_proposal_tensor])
# fcos_proposal_tensor = torch.cat([fcos_proposal_tensor, fcos_p4_proposal_tensor])
# fcos_proposal_tensor = torch.cat([fcos_proposal_tensor, fcos_p5_proposal_tensor])
# fcos_proposal_tensor = torch.cat([fcos_proposal_tensor, fcos_p6_proposal_tensor])
#
# if len(fcos_proposal_tensor.shape) >= 2:
# fcos_proposal[i] = fcos_proposal_tensor
# else:
# fcos_proposal[i] = fcos_proposal_tensor.unsqueeze(0)
# RPN forward and loss
if self.with_rpn:
rpn_outs = self.rpn_head(x)
rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta,
self.train_cfg.rpn)
rpn_losses = self.rpn_head.loss(*rpn_loss_inputs,
gt_bboxes_ignore=gt_bboxes_ignore)
losses.update(rpn_losses)
proposal_cfg = self.train_cfg.get('rpn_proposal',
self.test_cfg.rpn)
proposal_inputs = rpn_outs + (img_meta, proposal_cfg)
proposal_list = self.rpn_head.get_bboxes(*proposal_inputs)
######## add fcos_proposal
proposal_list1 = [0] * len(proposal_list)
for j in range(len(proposal_list)):
try:
proposal_list1[j] = torch.cat(
[fcos_proposal[j], proposal_list[j]])
# proposal_list1[j] = proposal_list1[j][0:2000]
except:
print(fcos_proposal[0].shape, proposal_list[0].shape)
exit()
else:
proposal_list = proposals
# ###### show proposal##########
# for b in range(len(img)):
# image_0 = img[b].permute(1, 2, 0).cpu().numpy()
# _range = np.max(image_0) - np.min(image_0)
# image = ((image_0 - np.min(image_0)) / _range) * 255
# # cv.imwrite('/home/cver/data/GQX/AerialDetection/show_anchor/1.png',image)
# gt_box = gt_bboxes[b].cpu().numpy()
# fcos_anchor = fcos_proposal[b].cpu().numpy()
# RPN_anchor = proposal_list[b].cpu().numpy()
# for k in range(len(gt_box)):
# xxx1 = gt_box[k, 0]
# yyy1 = gt_box[k, 1]
# xxx2 = gt_box[k, 2]
# yyy2 = gt_box[k, 3]
# image = cv.rectangle(image, (xxx1, yyy1), (xxx2, yyy2), (0, 255, 0), 1)
# for i in range(len(fcos_anchor)):
# x1 = fcos_anchor[i, 0]
# y1 = fcos_anchor[i, 1]
# x2 = fcos_anchor[i, 2]
# y2 = fcos_anchor[i, 3]
# image = cv.rectangle(image, (x1, y1), (x2, y2), (255, 0, 0), 1)
# # # for j in range(len(RPN_anchor)):
# # for j in range(500):
# # xx1 = RPN_anchor[j, 0]
# # yy1 = RPN_anchor[j, 1]
# # xx2 = RPN_anchor[j, 2]
# # yy2 = RPN_anchor[j, 3]
# # image = cv.rectangle(image, (xx1, yy1), (xx2, yy2), (0, 0, 255), 1)
#
# random_index = str(random.random() * 10000)
# cv.imwrite(
# '/home/cver/data/GQX/AerialDetection/Proposal_show/epoch4/FCOS_all_top100_gt/' + random_index + '.png',
# image)
#########show proposal##########
# assign gts and sample proposals (hbb assign)
if self.with_bbox or self.with_mask:
bbox_assigner = build_assigner(self.train_cfg.rcnn[0].assigner)
bbox_sampler = build_sampler(self.train_cfg.rcnn[0].sampler,
context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)
] #gt_bboxes_ignore = None
sampling_results = []
for i in range(num_imgs):
assign_result = bbox_assigner.assign(proposal_list[i],
gt_bboxes[i],
gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
proposal_list[i],
gt_bboxes[i],
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
###### fcos_proposal assign gts and sample proposals
for i in range(len(fcos_proposal)):
if len(fcos_proposal[i]) > 0:
fcos_bbox_assigner = build_assigner(
self.train_cfg.rcnn[0].assigner)
fcos_bbox_sampler = build_sampler(
self.train_cfg.rcnn[0].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)
] # gt_bboxes_ignore = None
fcos_sampling_results = []
for i in range(num_imgs):
fcos_assign_result = fcos_bbox_assigner.assign(
fcos_proposal[i], gt_bboxes[i],
gt_bboxes_ignore[i], gt_labels[i])
fcos_sampling_result = fcos_bbox_sampler.sample(
fcos_assign_result,
fcos_proposal[i],
gt_bboxes[i],
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
fcos_sampling_results.append(fcos_sampling_result)
# for i in range(num_imgs):
# pos_bboxes_ = sampling_results[i].pos_bboxes
# fcos_proposal_i = fcos_proposal[i]
# if len(pos_bboxes_) + len(fcos_proposal_i) > 128:
# pos_bboxes_i = torch.cat([pos_bboxes_,fcos_proposal_i[:,:4]])[:128]
# else:
# pos_bboxes_i = torch.cat([pos_bboxes_, fcos_proposal_i[:, :4]])
# pos_inds_i = torch.tensor([x for x in range(len(pos_bboxes_i))])
# pos_is_gt_i_add = torch.tensor([0 for x in range((len(pos_bboxes_i) - len(pos_bboxes_)))])
# pos_is_gt_i = torch.cat([sampling_results[i].pos_is_gt ,pos_is_gt_i_add.cuda().type(torch.uint8)])
#
# sampling_results[i].pos_bboxes = pos_bboxes_i
# sampling_results[i].pos_inds = pos_inds_i
# sampling_results[i].pos_is_gt = pos_is_gt_i
#
# neg_bboxes_ = sampling_results[i].neg_bboxes
# sampling_results[i].neg_bboxes = neg_bboxes_[:int(len(neg_bboxes_) - (len(pos_bboxes_i) - len(pos_bboxes_)))]
# sampling_results[i].neg_inds = torch.tensor([x + len(pos_bboxes_i) for x in range(len(neg_bboxes_))])
# RoI Transformer or RoI pooling?
# bbox head forward and loss
if self.with_bbox:
rois = bbox2roi([res.bboxes for res in sampling_results])
# TODO: a more flexible way to decide which feature maps to use
bbox_feats = self.bbox_roi_extractor(
x[:self.bbox_roi_extractor.num_inputs], rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred = self.bbox_head(bbox_feats)
## rbbox
rbbox_targets = self.bbox_head.get_target(sampling_results,
gt_masks, gt_labels,
self.train_cfg.rcnn[0])
loss_bbox = self.bbox_head.loss(cls_score, bbox_pred,
*rbbox_targets)
# losses.update(loss_bbox)
for name, value in loss_bbox.items():
losses['s{}.{}'.format(0, name)] = (value)
#fcos proposal to rcnn bbox_head
for i in range(len(fcos_proposal)):
if len(fcos_proposal[i]) > 0:
fcos_rois = bbox2roi(
[res.bboxes for res in fcos_sampling_results])
fcos_bbox_feats = self.bbox_roi_extractor(
x[:self.bbox_roi_extractor.num_inputs], fcos_rois)
if self.with_shared_head:
fcos_bbox_feats = self.shared_head(fcos_bbox_feats)
fcos_cls_score, fcos_bbox_pred = self.bbox_head(
fcos_bbox_feats)
##fcos_rbbox
fcos_rbbox_targets = self.bbox_head.get_target(
fcos_sampling_results, gt_masks, gt_labels,
self.train_cfg.rcnn[0])
fcos_loss_bbox = self.bbox_head.loss(
fcos_cls_score, fcos_bbox_pred, *fcos_rbbox_targets)
# losses.update(fcos_loss_bbox)
for name, value in fcos_loss_bbox.items():
losses['s{}.{}'.format(00, name)] = (value)
pos_is_gts = [res.pos_is_gt for res in sampling_results]
roi_labels = rbbox_targets[0]
with torch.no_grad():
# import pdb
# pdb.set_trace()
### ROI Transformer
rotated_proposal_list = self.bbox_head.refine_rbboxes(
roi2droi(rois), roi_labels, bbox_pred, pos_is_gts, img_meta)
for i in range(len(fcos_proposal)):
if len(fcos_proposal[i]) > 0:
fcos_pos_is_gts = [
res.pos_is_gt for res in fcos_sampling_results
]
fcos_roi_labels = fcos_rbbox_targets[0]
with torch.no_grad():
# import pdb
# pdb.set_trace()
### ROI Transformer
fcos_rotated_proposal_list = self.bbox_head.refine_rbboxes(
roi2droi(fcos_rois), fcos_roi_labels, fcos_bbox_pred,
fcos_pos_is_gts, img_meta)
# import pdb
# pdb.set_trace()
# assign gts and sample proposals (rbb assign)
if self.with_rbbox:
bbox_assigner = build_assigner(self.train_cfg.rcnn[1].assigner)
bbox_sampler = build_sampler(self.train_cfg.rcnn[1].sampler,
context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
gt_obbs_best_roi = choose_best_Rroi_batch(gt_obbs[i])
assign_result = bbox_assigner.assign(rotated_proposal_list[i],
gt_obbs_best_roi,
gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
rotated_proposal_list[i],
torch.from_numpy(gt_obbs_best_roi).float().to(
rotated_proposal_list[i].device),
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
##fcos rbbox proposal assign and sample
for i in range(len(fcos_proposal)):
if len(fcos_proposal[i]) > 0:
fcos_bbox_assigner = build_assigner(
self.train_cfg.rcnn[1].assigner)
fcos_bbox_sampler = build_sampler(
self.train_cfg.rcnn[1].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
fcos_sampling_results = []
for i in range(num_imgs):
fcos_gt_obbs_best_roi = choose_best_Rroi_batch(
gt_obbs[i])
fcos_assign_result = fcos_bbox_assigner.assign(
fcos_rotated_proposal_list[i],
fcos_gt_obbs_best_roi, gt_bboxes_ignore[i],
gt_labels[i])
fcos_sampling_result = fcos_bbox_sampler.sample(
fcos_assign_result,
fcos_rotated_proposal_list[i],
torch.from_numpy(fcos_gt_obbs_best_roi).float().to(
fcos_rotated_proposal_list[i].device),
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
fcos_sampling_results.append(fcos_sampling_result)
if self.with_rbbox:
# (batch_ind, x_ctr, y_ctr, w, h, angle)
rrois = dbbox2roi([res.bboxes for res in sampling_results])
# feat enlarge
# rrois[:, 3] = rrois[:, 3] * 1.2
# rrois[:, 4] = rrois[:, 4] * 1.4
rrois[:, 3] = rrois[:, 3] * self.rbbox_roi_extractor.w_enlarge
rrois[:, 4] = rrois[:, 4] * self.rbbox_roi_extractor.h_enlarge
rbbox_feats = self.rbbox_roi_extractor(
x[:self.rbbox_roi_extractor.num_inputs], rrois)
if self.with_shared_head_rbbox:
rbbox_feats = self.shared_head_rbbox(rbbox_feats)
cls_score, rbbox_pred = self.rbbox_head(rbbox_feats)
rbbox_targets = self.rbbox_head.get_target_rbbox(
sampling_results, gt_obbs, gt_labels, self.train_cfg.rcnn[1])
loss_rbbox = self.rbbox_head.loss(cls_score, rbbox_pred,
*rbbox_targets)
for name, value in loss_rbbox.items():
losses['s{}.{}'.format(1, name)] = (value)
##fcos rbbox loss
for i in range(len(fcos_proposal)):
if len(fcos_proposal[i]) > 0:
fcos_rrois = dbbox2roi(
[res.bboxes for res in fcos_sampling_results])
fcos_rrois[:,
3] = fcos_rrois[:,
3] * self.rbbox_roi_extractor.w_enlarge
fcos_rrois[:,
4] = fcos_rrois[:,
4] * self.rbbox_roi_extractor.h_enlarge
fcos_rbbox_feats = self.rbbox_roi_extractor(
x[:self.rbbox_roi_extractor.num_inputs], fcos_rrois)
if self.with_shared_head_rbbox:
fcos_rbbox_feats = self.shared_head_rbbox(
fcos_rbbox_feats)
fcos_cls_score, fcos_rbbox_pred = self.rbbox_head(
fcos_rbbox_feats)
fcos_rbbox_targets = self.rbbox_head.get_target_rbbox(
fcos_sampling_results, gt_obbs, gt_labels,
self.train_cfg.rcnn[1])
fcos_loss_rbbox = self.rbbox_head.loss(
fcos_cls_score, fcos_rbbox_pred, *fcos_rbbox_targets)
for name, value in fcos_loss_rbbox.items():
losses['s{}.{}'.format(11, name)] = (value)
return losses
def forward_train(self,
img,
img_meta,
gt_bboxes,
gt_labels,
gt_bboxes_ignore=None,
gt_masks=None,
proposals=None):
x = self.extract_feat(img)
losses = dict()
# trans gt_masks to gt_obbs
gt_obbs = gt_mask_bp_obbs_list(gt_masks)
savepath = '/home/wzq/datasets/dota/dota_tmp-split-1024/show/'
if not os.path.exists(savepath):
os.mkdir(savepath)
import time
T = str(int(time.time()))
print(T)
cv.imwrite(savepath + T +'_img.png', img[0].cpu().detach().numpy().transpose(1,2,0) * 255)
x0 = torch.mean(x[0],dim=1)[0]
x0 = x0.cpu().detach().numpy()
cv.imwrite(savepath + T + '_p2.png', self.standardization(x0) * 255)
x1 = torch.mean(x[1], dim=1)[0]
x1 = x1.cpu().detach().numpy()
cv.imwrite(savepath + T + '_p3.png', self.standardization(x1) * 255)
x2 = torch.mean(x[2], dim=1)[0]
x2 = x2.cpu().detach().numpy()
cv.imwrite(savepath + T + '_p4.png', self.standardization(x2) * 255)
x3 = torch.mean(x[3], dim=1)[0]
x3 = x3.cpu().detach().numpy()
cv.imwrite(savepath + T + '_p5.png', self.standardization(x3) * 255)
x4 = torch.mean(x[4], dim=1)[0]
x4 = x4.cpu().detach().numpy()
cv.imwrite(savepath + T + '_p6.png', self.standardization(x4) * 255)
# RPN forward and loss
if self.with_rpn:
rpn_outs = self.rpn_head(x)
rpn_loss_inputs = rpn_outs + (gt_bboxes, img_meta,
self.train_cfg.rpn)
rpn_losses = self.rpn_head.loss(
*rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
losses.update(rpn_losses)
proposal_cfg = self.train_cfg.get('rpn_proposal',
self.test_cfg.rpn)
proposal_inputs = rpn_outs + (img_meta, proposal_cfg)
proposal_list = self.rpn_head.get_bboxes(*proposal_inputs)
else:
proposal_list = proposals
# assign gts and sample proposals (hbb assign)
if self.with_bbox or self.with_mask:
bbox_assigner = build_assigner(self.train_cfg.rcnn[0].assigner)
bbox_sampler = build_sampler(
self.train_cfg.rcnn[0].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
assign_result = bbox_assigner.assign(
proposal_list[i], gt_bboxes[i], gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
proposal_list[i],
gt_bboxes[i],
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
# bbox head forward and loss
if self.with_bbox:
rois = bbox2roi([res.bboxes for res in sampling_results])
# TODO: a more flexible way to decide which feature maps to use
bbox_feats = self.bbox_roi_extractor(
x[:self.bbox_roi_extractor.num_inputs], rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred = self.bbox_head(bbox_feats)
######add######
# print(cls_score)
# print('======')
# print(bbox_pred)
# rcnn_test_cfg = self.test_cfg.rcnn
# rescale = False
#
# img_shape = img_meta[0]['img_shape']
# scale_factor = img_meta[0]['scale_factor']
#
# det_bboxes, det_labels = self.bbox_head.get_det_bboxes(
# rois,
# cls_score,
# bbox_pred,
# img_shape,
# scale_factor,
# rescale=rescale,
# cfg=rcnn_test_cfg)
# print(det_bboxes)
# print('=======')
# print(det_labels)
######add#####
## rbbox
rbbox_targets = self.bbox_head.get_target(
sampling_results, gt_masks, gt_labels, self.train_cfg.rcnn[0])
loss_bbox = self.bbox_head.loss(cls_score, bbox_pred,
*rbbox_targets)
# losses.update(loss_bbox)
for name, value in loss_bbox.items():
losses['s{}.{}'.format(0, name)] = (value)
pos_is_gts = [res.pos_is_gt for res in sampling_results]
roi_labels = rbbox_targets[0]
with torch.no_grad():
# import pdb
# pdb.set_trace()
rotated_proposal_list = self.bbox_head.refine_rbboxes(
roi2droi(rois), roi_labels, bbox_pred, pos_is_gts, img_meta
)
# import pdb
# pdb.set_trace()
# assign gts and sample proposals (rbb assign)
if self.with_rbbox:
bbox_assigner = build_assigner(self.train_cfg.rcnn[1].assigner)
bbox_sampler = build_sampler(
self.train_cfg.rcnn[1].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
gt_obbs_best_roi = choose_best_Rroi_batch(gt_obbs[i])
assign_result = bbox_assigner.assign(
rotated_proposal_list[i], gt_obbs_best_roi, gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
rotated_proposal_list[i],
torch.from_numpy(gt_obbs_best_roi).float().to(rotated_proposal_list[i].device),
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
if self.with_rbbox:
# (batch_ind, x_ctr, y_ctr, w, h, angle)
rrois = dbbox2roi([res.bboxes for res in sampling_results])
# feat enlarge
# rrois[:, 3] = rrois[:, 3] * 1.2
# rrois[:, 4] = rrois[:, 4] * 1.4
rrois[:, 3] = rrois[:, 3] * self.rbbox_roi_extractor.w_enlarge
rrois[:, 4] = rrois[:, 4] * self.rbbox_roi_extractor.h_enlarge
rbbox_feats = self.rbbox_roi_extractor(x[:self.rbbox_roi_extractor.num_inputs],
rrois)
if self.with_shared_head_rbbox:
rbbox_feats = self.shared_head_rbbox(rbbox_feats)
cls_score, rbbox_pred = self.rbbox_head(rbbox_feats)
rbbox_targets = self.rbbox_head.get_target_rbbox(sampling_results, gt_obbs,
gt_labels, self.train_cfg.rcnn[1])
loss_rbbox = self.rbbox_head.loss(cls_score, rbbox_pred, *rbbox_targets)
for name, value in loss_rbbox.items():
losses['s{}.{}'.format(1, name)] = (value)
return losses
def forward_train(self,
img,
img_meta,
gt_bboxes,
gt_labels,
gt_bboxes_ignore=None,
gt_masks=None,
proposals=None):
x = self.extract_feat(img)
losses = dict()
# trans gt_masks to gt_obbs
gt_obbs = gt_mask_bp_obbs_list(gt_masks)
gt_obbs = [choose_best_Rroi_batch(gt) for gt in gt_obbs]
# RPN forward and loss
if self.with_rpn:
rpn_outs = self.rpn_head(x)
rpn_loss_inputs = rpn_outs + (gt_bboxes, gt_labels, img_meta,
self.train_cfg.rpn)
rpn_losses = self.rpn_head.loss(
*rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
losses.update(rpn_losses)
proposal_cfg = self.train_cfg.get('rpn_proposal',
self.test_cfg.rpn)
proposal_inputs = rpn_outs + (img_meta, proposal_cfg)
proposal_list = self.rpn_head.get_bboxes(*proposal_inputs)
else:
proposal_list = proposals
# assign gts and sample proposals (hbb assign)
if self.with_bbox or self.with_mask:
bbox_assigner = build_assigner(self.train_cfg.rcnn[0].assigner)
bbox_sampler = build_sampler(
self.train_cfg.rcnn[0].sampler, context=self)
num_imgs = img.size(0)
if gt_bboxes_ignore is None:
gt_bboxes_ignore = [None for _ in range(num_imgs)]
sampling_results = []
for i in range(num_imgs):
assign_result = bbox_assigner.assign(
proposal_list[i], gt_bboxes[i], gt_bboxes_ignore[i],
gt_labels[i])
sampling_result = bbox_sampler.sample(
assign_result,
proposal_list[i],
gt_bboxes[i],
gt_labels[i],
feats=[lvl_feat[i][None] for lvl_feat in x])
sampling_results.append(sampling_result)
# bbox head forward and loss
if self.with_bbox:
rois = bbox2roi([res.bboxes for res in sampling_results])
# TODO: a more flexible way to decide which feature maps to use
bbox_feats = self.bbox_roi_extractor(
x[:self.bbox_roi_extractor.num_inputs], rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred = self.bbox_head(bbox_feats)
## rbbox
gt_obbs_torch = [torch.from_numpy(gt).float().to(rois.device) for gt in gt_obbs]
rbbox_targets = self.bbox_head.get_target(
sampling_results, gt_obbs_torch, gt_labels, self.train_cfg.rcnn[0])
loss_bbox = self.bbox_head.loss(cls_score, bbox_pred, rois[:, 1:], *rbbox_targets)
# loss_bbox = self.bbox_head.loss(cls_score, bbox_pred, sampling_results,
# gt_obbs_torch, *rbbox_targets)
# loss_bbox = self.bbox_head.loss(cls_score, bbox_pred,
# *rbbox_targets)
# losses.update(loss_bbox)
for name, value in loss_bbox.items():
losses['s{}.{}'.format(0, name)] = (value)
return losses
