You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
作者您好,在bevdet-dev2.1中,self.pts_bbox_head.get_bboxes函数里,即centerpoint_head.get_bboxes中,将bboxes的中心移到了底面中心,可以理解这是为了送入LiDARInstance3DBoxes类:
for i in range(num_samples):
for k in rets[0][i].keys():
if k == 'bboxes':
bboxes = torch.cat([ret[i][k] for ret in rets])
bboxes[:, 2] = bboxes[:, 2] - bboxes[:, 5] * 0.5 # 移至底面中心
bboxes = img_metas[i]['box_type_3d'](
bboxes, self.bbox_coder.code_size)
但是在dataset.evaluate时,_format_bbox函数中,并没有将bboxes中心点移回重心的位置就送入了NuScenesBox类,这有合理的解释吗?我看’1.0.0rc4‘的mmdetection3d官方的nuscenes_dataset.py中的_format_bbox函数是要移回重心位置的,所以感到疑惑。
The text was updated successfully, but these errors were encountered:
kingofstu
changed the title
关于_format_bbox函数中并为将bbox中心点移回中心位置的困惑
关于_format_bbox函数中并未将bbox中心点移回中心位置的困惑
Nov 28, 2024
作者您好,在bevdet-dev2.1中,self.pts_bbox_head.get_bboxes函数里,即centerpoint_head.get_bboxes中,将bboxes的中心移到了底面中心,可以理解这是为了送入LiDARInstance3DBoxes类:
for i in range(num_samples):
for k in rets[0][i].keys():
if k == 'bboxes':
bboxes = torch.cat([ret[i][k] for ret in rets])
bboxes[:, 2] = bboxes[:, 2] - bboxes[:, 5] * 0.5 # 移至底面中心
bboxes = img_metas[i]['box_type_3d'](
bboxes, self.bbox_coder.code_size)
但是在dataset.evaluate时,_format_bbox函数中,并没有将bboxes中心点移回重心的位置就送入了NuScenesBox类,这有合理的解释吗?我看’1.0.0rc4‘的mmdetection3d官方的nuscenes_dataset.py中的_format_bbox函数是要移回重心位置的,所以感到疑惑。
The text was updated successfully, but these errors were encountered: