def regress_by_class(self, rois, label, bbox_pred, img_meta):
"""Regress the bbox for the predicted class. Used in Cascade R-CNN.
Args:
rois (Tensor): shape (n, 4) or (n, 5)
label (Tensor): shape (n, )
bbox_pred (Tensor): shape (n, 4*(#class+1)) or (n, 4)
img_meta (dict): Image meta info.
Returns:
Tensor: Regressed bboxes, the same shape as input rois.
"""
assert rois.size(1) == 4 or rois.size(1) == 5
if not self.reg_class_agnostic:
label = label * 4
inds = torch.stack((label, label + 1, label + 2, label + 3), 1)
bbox_pred = torch.gather(bbox_pred, 1, inds)
assert bbox_pred.size(1) == 4
if rois.size(1) == 4:
new_rois = delta2bbox(rois, bbox_pred, self.target_means,
self.target_stds, img_meta['img_shape'])
else:
bboxes = delta2bbox(rois[:, 1:], bbox_pred, self.target_means,
self.target_stds, img_meta['img_shape'])
new_rois = torch.cat((rois[:, [0]], bboxes), dim=1)
return new_rois
def get_det_bboxes(self,
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None):
if isinstance(cls_score, list):
cls_score = sum(cls_score) / float(len(cls_score))
scores = F.softmax(cls_score, dim=1) if cls_score is not None else None
if bbox_pred is not None:
bboxes = delta2bbox(rois[:, 1:], bbox_pred, self.target_means,
self.target_stds, img_shape)
else:
bboxes = rois[:, 1:].clone()
if img_shape is not None:
bboxes[:, [0, 2]].clamp_(min=0, max=img_shape[1] - 1)
bboxes[:, [1, 3]].clamp_(min=0, max=img_shape[0] - 1)
if rescale:
bboxes /= scale_factor
if cfg is None:
return bboxes, scores
else:
det_bboxes, det_labels = multiclass_nms(bboxes, scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
def get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False):
mlvl_proposals = []
for idx in range(len(cls_scores)):
rpn_cls_score = cls_scores[idx]
rpn_bbox_pred = bbox_preds[idx]
assert rpn_cls_score.size()[-2:] == rpn_bbox_pred.size()[-2:]
anchors = mlvl_anchors[idx]
rpn_cls_score = rpn_cls_score.permute(1, 2, 0)
if self.use_sigmoid_cls:
rpn_cls_score = rpn_cls_score.reshape(-1)
scores = rpn_cls_score.sigmoid()
else:
rpn_cls_score = rpn_cls_score.reshape(-1, 2)
scores = rpn_cls_score.softmax(dim=1)[:, 1]
rpn_bbox_pred = rpn_bbox_pred.permute(1, 2, 0).reshape(-1, 4)
if cfg.nms_pre > 0 and scores.shape[0] > cfg.nms_pre:
_, topk_inds = scores.topk(cfg.nms_pre)
rpn_bbox_pred = rpn_bbox_pred[topk_inds, :]
anchors = anchors[topk_inds, :]
scores = scores[topk_inds]
proposals = delta2bbox(anchors, rpn_bbox_pred, self.target_means,
self.target_stds, img_shape)
if cfg.min_bbox_size > 0:
w = proposals[:, 2] - proposals[:, 0] + 1
h = proposals[:, 3] - proposals[:, 1] + 1
valid_inds = torch.nonzero((w >= cfg.min_bbox_size) &
(h >= cfg.min_bbox_size)).squeeze()
proposals = proposals[valid_inds, :]
scores = scores[valid_inds]
proposals = torch.cat([proposals, scores.unsqueeze(-1)], dim=-1)
proposals, _ = nms(proposals, cfg.nms_thr)
proposals = proposals[:cfg.nms_post, :]
mlvl_proposals.append(proposals)
proposals = torch.cat(mlvl_proposals, 0)
if cfg.nms_across_levels:
proposals, _ = nms(proposals, cfg.nms_thr)
proposals = proposals[:cfg.max_num, :]
else:
scores = proposals[:, 4]
num = min(cfg.max_num, proposals.shape[0])
_, topk_inds = scores.topk(num)
proposals = proposals[topk_inds, :]
return proposals
def get_det_bboxes(self,
rois,
cls_score,
bbox_pred,
img_shape,
scale_factor,
rescale=False,
cfg=None):
if isinstance(cls_score, list):
cls_score = sum(cls_score) / float(len(cls_score))
scores = F.softmax(cls_score, dim=1) if cls_score is not None else None
if bbox_pred is not None:
bboxes = delta2bbox(rois[:, 1:], bbox_pred, self.target_means,
self.target_stds, img_shape)
else:
bboxes = rois[:, 1:].clone()
if img_shape is not None:
bboxes[:, [0, 2]].clamp_(min=0, max=img_shape[1] - 1)
bboxes[:, [1, 3]].clamp_(min=0, max=img_shape[0] - 1)
if rescale:
bboxes /= scale_factor
if cfg is None:
return bboxes, scores
else:
values, indices = torch.max(scores, dim=1)
bboxes[:, 8 +
3] = bboxes[:, 8 +
1] + (bboxes[:, 8 + 3] - bboxes[:, 8 + 1]) / 0.4
# print(bboxes[indices==3, 1])
# print(bboxes[indices==3, 3] - bboxes[indices==3, 1])
bboxes[:, 12 + 1] = bboxes[:, 12 + 3] - (bboxes[:, 12 + 3] -
bboxes[:, 12 + 1]) / 0.6
# print(bboxes[indices==3, 1])
bboxes[indices == 2, 4:8] = bboxes[indices == 2, 8:12]
bboxes[indices == 3, 4:8] = bboxes[indices == 3, 12:16]
scores[:, 1] = torch.max(scores[:, 1:], dim=1)[0]
scores[:, 2] = 0
scores[:, 3] = 0
det_bboxes, det_labels = multiclass_nms(bboxes, scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
def get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False):
assert len(cls_scores) == len(bbox_preds) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors in zip(cls_scores, bbox_preds,
mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
max_scores, _ = scores[:, 1:].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = delta2bbox(anchors, bbox_pred, self.target_means,
self.target_stds, img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([padding, mlvl_scores], dim=1)
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels
def get_bboxes_single(self,
cls_scores,
bbox_preds,
mlvl_anchors,
mlvl_masks,
img_shape,
scale_factor,
cfg,
rescale=False):
mlvl_proposals = []
for idx in range(len(cls_scores)):
rpn_cls_score = cls_scores[idx]
rpn_bbox_pred = bbox_preds[idx]
anchors = mlvl_anchors[idx]
mask = mlvl_masks[idx]
assert rpn_cls_score.size()[-2:] == rpn_bbox_pred.size()[-2:]
# if no location is kept, end.
if mask.sum() == 0:
continue
rpn_cls_score = rpn_cls_score.permute(1, 2, 0)
if self.use_sigmoid_cls:
rpn_cls_score = rpn_cls_score.reshape(-1)
scores = rpn_cls_score.sigmoid()
else:
rpn_cls_score = rpn_cls_score.reshape(-1, 2)
scores = rpn_cls_score.softmax(dim=1)[:, 1]
# filter scores, bbox_pred w.r.t. mask.
# anchors are filtered in get_anchors() beforehand.
scores = scores[mask]
rpn_bbox_pred = rpn_bbox_pred.permute(1, 2, 0).reshape(-1,
4)[mask, :]
if scores.dim() == 0:
rpn_bbox_pred = rpn_bbox_pred.unsqueeze(0)
anchors = anchors.unsqueeze(0)
scores = scores.unsqueeze(0)
# filter anchors, bbox_pred, scores w.r.t. scores
if cfg.nms_pre > 0 and scores.shape[0] > cfg.nms_pre:
_, topk_inds = scores.topk(cfg.nms_pre)
rpn_bbox_pred = rpn_bbox_pred[topk_inds, :]
anchors = anchors[topk_inds, :]
scores = scores[topk_inds]
# get proposals w.r.t. anchors and rpn_bbox_pred
proposals = delta2bbox(anchors, rpn_bbox_pred, self.target_means,
self.target_stds, img_shape)
# filter out too small bboxes
if cfg.min_bbox_size > 0:
w = proposals[:, 2] - proposals[:, 0] + 1
h = proposals[:, 3] - proposals[:, 1] + 1
valid_inds = torch.nonzero((w >= cfg.min_bbox_size) &
(h >= cfg.min_bbox_size)).squeeze()
proposals = proposals[valid_inds, :]
scores = scores[valid_inds]
proposals = torch.cat([proposals, scores.unsqueeze(-1)], dim=-1)
# NMS in current level
proposals, _ = nms(proposals, cfg.nms_thr)
proposals = proposals[:cfg.nms_post, :]
mlvl_proposals.append(proposals)
proposals = torch.cat(mlvl_proposals, 0)
if cfg.nms_across_levels:
# NMS across multi levels
proposals, _ = nms(proposals, cfg.nms_thr)
proposals = proposals[:cfg.max_num, :]
else:
scores = proposals[:, 4]
num = min(cfg.max_num, proposals.shape[0])
_, topk_inds = scores.topk(num)
proposals = proposals[topk_inds, :]
return proposals