-
when i train with command "python -m torch.distributed.launch --nproc_per_node=4 ./tools/train.py ./configs/nusc/voxelnet/nusc_centerpoint_voxelnet_0075voxel_dcn_flip.py " . I got this error:
......…
-
hi, i come up with a problem as below:
the coordinates first generated by:
"voxels, coordinates, num_points = self.voxel_generator.generate" with size (N,3),
but feed into the VoxelNet here:"coordi…
-
I follow your introduction in waymo.md:
I have run 3D detection: python -m tools.dist_test /home/jiawen/CenterPoint/configs/waymo/pp/waymo_centerpoint_pp_two_pfn_stride1_3x.py --work_dir /home/jiaw…
-
Hi,
since our computer does not have enough space for the entire trainval nuScenes dataset. And train the CenterPoint model is not the main purpose of our master thesis. Therefore, would you mind s…
-
I am facing this error because I am trying to evaluate on the testing set. How to view the predictions after running dist_test.py?
```
Traceback (most recent call last):
File "tools/tracking/p…
-
- 标题：定位到Dataloader有内存泄漏现象
- 版本、环境信息：
1）PaddlePaddle版本：2.1.2
2）CPU：Aistudio 32G
3）GPU：Aistudio Tesla 16G
4）系统环境：ubuntu python3.7
- 训练信息
1）单机，单卡
2）显存信息 16G
3）Opera…
-
Is [this](https://github.com/open-mmlab/mmdetection3d/blob/master/mmdet3d/datasets/nuscenes_dataset.py#L437) `if` correct?
Typical 3d detector returns `list(dict('boxes_3d':..., 'scores': ..., 'label…
-
Hi, tianweiy. I met a problem when I executed "python -m torch.distributed.launch --nproc_per_node=2 ./tools/train.py xxx/CenterPoint/configs/nusc/voxelnet/nusc_centerpoint_voxelnet_0075voxel_dcn.py".…
-
When I use analyze_logs.py
```
['work_dirs/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car/20211007_134844.log.json']
-----Analyze train time of work_dirs/hv_pointpillars_secfpn_6x8_160e_kitti-3d-car…
-
Hi,
thanks for sharing the idea for combining CenterPoint and PointPainting in https://github.com/tianweiy/CenterPoint/issues/56#issuecomment-761717909. I have attempted to run this script and the…