SamsungLabs / imvoxelnet

[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
MIT License
283 stars 29 forks source link

python tools/create_data.py nuscenes error #44

Closed Bincle-Yin closed 2 years ago

Bincle-Yin commented 2 years ago

Hi,When i run creat_data.py --..... a error occurred:

Traceback (most recent call last):
python tools/create_data.py nuscenes --root-path /media/hy/DISK1/data/nuscenes/mini/v1.0-mini --out-dir ./data/nuscenes --extra-tag nuscenes

  File "tools/create_data.py", line 5, in <module>
    from tools.data_converter import kitti_converter as kitti
  File "/home/hy/hy3d/imvoxelnet/tools/data_converter/kitti_converter.py", line 5, in <module>
    from mmdet3d.core.bbox import box_np_ops
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/__init__.py", line 3, in <module>
    import mmdet
  File "/home/hy/anaconda3/envs/imvoxelnet/lib/python3.7/site-packages/mmdet/__init__.py", line 26, in <module>
    f'MMCV=={mmcv.__version__} is used but incompatible. ' \
AssertionError: MMCV==1.3.0 is used but incompatible. Please install mmcv>=1.3.17, <=1.5.0.

so, i updated mmcv version

python tools/create_data.py nuscenes --root-path /media/hy/DISK1/data/nuscenes/mini/v1.0-mini --out-dir ./data/nuscenes --extra-tag nuscenes

Traceback (most recent call last):
  File "tools/create_data.py", line 5, in <module>
    from tools.data_converter import kitti_converter as kitti
  File "/home/hy/hy3d/imvoxelnet/tools/data_converter/kitti_converter.py", line 5, in <module>
    from mmdet3d.core.bbox import box_np_ops
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/__init__.py", line 26, in <module>
    f'MMCV=={mmcv.__version__} is used but incompatible. ' \
AssertionError: MMCV==1.4.0 is used but incompatible. Please install mmcv>=1.1.5, <=1.3.0.

So what exactly is the MMCV version ==?

looking forward to y reply!

filaPro commented 2 years ago

Hi @Bincle-Yin ,

Have you tried with our Dockerfile including mmcv-full==1.2.7 and mmdet==2.10.0?

Bincle-Yin commented 2 years ago

Thank you very much for your reply,i resolve the problem .beacuse i used mmdetection latest,so

 git clone mmdetection version ==2.11.0 
 cd mmdetection/
 pip install -v -e .

but, I met new problems

(imvoxelnet) hy@hy-All-Series:~/hy3d/imvoxelnet$ python tools/create_data.py nuscenes --root-path /media/hy/DISK1/data/nuscenes/mini/v1.0-mini --out-dir ./data/nuscenes --extra-tag nuscenes
Traceback (most recent call last):
  File "tools/create_data.py", line 7, in <module>
    from tools.data_converter import nuscenes_converter as nuscenes_converter
  File "/home/hy/hy3d/imvoxelnet/tools/data_converter/nuscenes_converter.py", line 12, in <module>
    from mmdet3d.datasets import NuScenesDataset
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/datasets/__init__.py", line 3, in <module>
    from .custom_3d import Custom3DDataset
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/datasets/custom_3d.py", line 8, in <module>
    from ..core.bbox import get_box_type
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/core/__init__.py", line 2, in <module>
    from .bbox import *  # noqa: F401, F403
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/core/bbox/__init__.py", line 4, in <module>
    from .iou_calculators import (AxisAlignedBboxOverlaps3D, BboxOverlaps3D,
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/core/bbox/iou_calculators/__init__.py", line 1, in <module>
    from .iou3d_calculator import (AxisAlignedBboxOverlaps3D, BboxOverlaps3D,
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/core/bbox/iou_calculators/iou3d_calculator.py", line 5, in <module>
    from ..structures import get_box_type
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/core/bbox/structures/__init__.py", line 1, in <module>
    from .base_box3d import BaseInstance3DBoxes
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/core/bbox/structures/base_box3d.py", line 5, in <module>
    from mmdet3d.ops.iou3d import iou3d_cuda
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/ops/__init__.py", line 20, in <module>
    from .rotated_iou import IoU3DLoss, GIoU3DLoss
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/ops/rotated_iou/__init__.py", line 1, in <module>
    from .iou3d_loss import IoU3DLoss, GIoU3DLoss
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/ops/rotated_iou/iou3d_loss.py", line 7, in <module>
    from .oriented_iou_loss import cal_giou_3d, cal_iou_3d
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/ops/rotated_iou/oriented_iou_loss.py", line 2, in <module>
    from .box_intersection_2d import oriented_box_intersection_2d
  File "/home/hy/hy3d/imvoxelnet/mmdet3d/ops/rotated_iou/box_intersection_2d.py", line 8, in <module>
    from .cuda_op.cuda_ext import sort_v
ModuleNotFoundError: No module named 'mmdet3d.ops.rotated_iou.cuda_op'

now my conda env : pytorch==1.10.0 mmcv 1.3.0
mmcv-full 1.3.0
mmdet 2.11.0
mmdet3d 0.8.0
mmpycocotools 12.0.3 cuda =10.2

filaPro commented 2 years ago

Did you follow rotated_iou instruction in installation section of our readme?

Bincle-Yin commented 2 years ago

Did you follow rotated_iou instruction in installation section of our readme?

ohhh,thank y. Follow the steps you I solved the problem. this error was due to my carelessness.