Comments (12)
yukang2017
commented on July 26, 2024
Hi Naren,
You can try to directly remove these two sentences in the pcdet/utils/spconv_utils.py
if float(spconv.__version__[2:]) >= 2.2:
spconv.constants.SPCONV_USE_DIRECT_TABLE = False
Regards,
Yukang Chen
from voxelnext.
naren2cmu
commented on July 26, 2024
Thanks Yukang. I tried that. It went past that error into another one.
root@369701605e02:/mnt/VoxelNeXt/tools# bash scripts/dist_test.sh 1 --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
+ NGPUS=1
+ PY_ARGS='--cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth'
+ python -m torch.distributed.launch --nproc_per_node=1 test.py --launcher pytorch --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
Traceback (most recent call last):
File "test.py", line 14, in <module>
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from pcdet.models import load_data_to_gpu
File "../pcdet/models/__init__.py", line 6, in <module>
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 1, in <module>
from .detector3d_template import Detector3DTemplate
File "../pcdet/models/detectors/detector3d_template.py", line 8, in <module>
from .. import backbones_2d, backbones_3d, dense_heads, roi_heads
File "../pcdet/models/backbones_3d/__init__.py", line 7, in <module>
from .spconv_backbone_voxelnext_sps import VoxelResBackBone8xVoxelNeXtSPS
File "../pcdet/models/backbones_3d/spconv_backbone_voxelnext_sps.py", line 4, in <module>
from spconv.core import ConvAlgo
ModuleNotFoundError: No module named 'spconv.core'
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/opt/conda/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 261, in <module>
main()
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/conda/bin/python', '-u', 'test.py', '--local_rank=0', '--launcher', 'pytorch', '--cfg_file', '/mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml', '--ckpt', '/mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth']' returned non-zero exit status 1.
It is missing spconv.core module. Are the dependencies not getting installed properly? I ran the python setup.py develop as well.
from voxelnext.
yukang2017
commented on July 26, 2024
Hi,
What is your version of spconv?
Regards,
Yukang Chen
from voxelnext.
naren2cmu
commented on July 26, 2024
1.2.1 according to pip show spconv
Name: spconv
Version: 1.2.1
Summary: spatial sparse convolution for pytorch
Home-page: UNKNOWN
Author: Yan Yan
Author-email: [email protected]
License: UNKNOWN
Location: /opt/conda/lib/python3.7/site-packages
Requires:
Required-by:
from voxelnext.
yukang2017
commented on July 26, 2024
Please try a new spconv version. For example, pip install spconv==2.1.25
from voxelnext.
naren2cmu
commented on July 26, 2024
Hi Yukang,
I got a different error after pip install spconv==2.1.25.
bash scripts/dist_test.sh 2 --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
+ NGPUS=2
+ PY_ARGS='--cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth'
+ python -m torch.distributed.launch --nproc_per_node=2 test.py --launcher pytorch --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
Traceback (most recent call last):
File "test.py", line 14, in <module>
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from pcdet.models import load_data_to_gpu
File "../pcdet/models/__init__.py", line 6, in <module>
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 1, in <module>
from .detector3d_template import Detector3DTemplate
File "../pcdet/models/detectors/detector3d_template.py", line 8, in <module>
from .. import backbones_2d, backbones_3d, dense_heads, roi_heads
File "../pcdet/models/backbones_3d/__init__.py", line 2, in <module>
from .spconv_backbone import VoxelBackBone8x, VoxelResBackBone8x
File "../pcdet/models/backbones_3d/spconv_backbone.py", line 30, in <module>
Traceback (most recent call last):
File "test.py", line 14, in <module>
class SparseBasicBlock(spconv.SparseModule):
AttributeError: module 'spconv' has no attribute 'SparseModule'
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from pcdet.models import load_data_to_gpu
File "../pcdet/models/__init__.py", line 6, in <module>
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 1, in <module>
from .detector3d_template import Detector3DTemplate
File "../pcdet/models/detectors/detector3d_template.py", line 8, in <module>
from .. import backbones_2d, backbones_3d, dense_heads, roi_heads
File "../pcdet/models/backbones_3d/__init__.py", line 2, in <module>
from .spconv_backbone import VoxelBackBone8x, VoxelResBackBone8x
File "../pcdet/models/backbones_3d/spconv_backbone.py", line 30, in <module>
class SparseBasicBlock(spconv.SparseModule):
AttributeError: module 'spconv' has no attribute 'SparseModule'
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/opt/conda/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 261, in <module>
main()
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/conda/bin/python', '-u', 'test.py', '--local_rank=1', '--launcher', 'pytorch', '--cfg_file', '/mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml', '--ckpt', '/mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth']' returned non-zero exit status 1.
I tried other versions of spconv (CUDA variants) available in https://github.com/traveller59/spconv
I am getting a different runtime error with them.
bash scripts/dist_test.sh 2 --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
+ NGPUS=2
+ PY_ARGS='--cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth'
+ python -m torch.distributed.launch --nproc_per_node=2 test.py --launcher pytorch --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
Traceback (most recent call last):
File "test.py", line 14, in <module>
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from pcdet.models import load_data_to_gpu
File "../pcdet/models/__init__.py", line 6, in <module>
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 12, in <module>
from .mppnet import MPPNet
File "../pcdet/models/detectors/mppnet.py", line 9, in <module>
from pcdet.datasets.augmentor import augmentor_utils, database_sampler
File "../pcdet/datasets/__init__.py", line 15, in <module>
from .argo2.argo2_dataset import Argo2Dataset
File "../pcdet/datasets/argo2/argo2_dataset.py", line 11, in <module>
from .argo2_utils.so3 import yaw_to_quat
File "../pcdet/datasets/argo2/argo2_utils/so3.py", line 10, in <module>
def quat_to_mat(quat_wxyz: Tensor) -> Tensor:
File "/opt/conda/lib/python3.7/site-packages/torch/jit/__init__.py", line 1550, in script
fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
File "/opt/conda/lib/python3.7/site-packages/torch/jit/_recursive.py", line 583, in try_compile_fn
return torch.jit.script(fn, _rcb=rcb)
File "/opt/conda/lib/python3.7/site-packages/torch/jit/__init__.py", line 1550, in script
fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
RuntimeError:
python value of type 'QuaternionCoeffOrder' cannot be used as a value:
File "/opt/conda/lib/python3.7/site-packages/kornia/geometry/conversions.py", line 492
raise ValueError(f"order must be one of {QuaternionCoeffOrder.__members__.keys()}")
if order == QuaternionCoeffOrder.XYZW:
~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
warnings.warn(
"`XYZW` quaternion coefficient order is deprecated and"
'quaternion_to_rotation_matrix' is being compiled since it was called from 'quat_to_mat'
File "../pcdet/datasets/argo2/argo2_utils/so3.py", line 19
(...,3,3) 3D rotation matrices.
"""
return C.quaternion_to_rotation_matrix(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~... <--- HERE
quat_wxyz, order=C.QuaternionCoeffOrder.WXYZ
)
Traceback (most recent call last):
File "test.py", line 14, in <module>
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from pcdet.models import load_data_to_gpu
File "../pcdet/models/__init__.py", line 6, in <module>
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 12, in <module>
from .mppnet import MPPNet
File "../pcdet/models/detectors/mppnet.py", line 9, in <module>
from pcdet.datasets.augmentor import augmentor_utils, database_sampler
File "../pcdet/datasets/__init__.py", line 15, in <module>
from .argo2.argo2_dataset import Argo2Dataset
File "../pcdet/datasets/argo2/argo2_dataset.py", line 11, in <module>
from .argo2_utils.so3 import yaw_to_quat
File "../pcdet/datasets/argo2/argo2_utils/so3.py", line 10, in <module>
def quat_to_mat(quat_wxyz: Tensor) -> Tensor:
File "/opt/conda/lib/python3.7/site-packages/torch/jit/__init__.py", line 1550, in script
fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
File "/opt/conda/lib/python3.7/site-packages/torch/jit/_recursive.py", line 583, in try_compile_fn
return torch.jit.script(fn, _rcb=rcb)
File "/opt/conda/lib/python3.7/site-packages/torch/jit/__init__.py", line 1550, in script
fn = torch._C._jit_script_compile(qualified_name, ast, _rcb, get_default_args(obj))
RuntimeError:
python value of type 'QuaternionCoeffOrder' cannot be used as a value:
File "/opt/conda/lib/python3.7/site-packages/kornia/geometry/conversions.py", line 492
raise ValueError(f"order must be one of {QuaternionCoeffOrder.__members__.keys()}")
if order == QuaternionCoeffOrder.XYZW:
~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
warnings.warn(
"`XYZW` quaternion coefficient order is deprecated and"
'quaternion_to_rotation_matrix' is being compiled since it was called from 'quat_to_mat'
File "../pcdet/datasets/argo2/argo2_utils/so3.py", line 19
(...,3,3) 3D rotation matrices.
"""
return C.quaternion_to_rotation_matrix(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~... <--- HERE
quat_wxyz, order=C.QuaternionCoeffOrder.WXYZ
)
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/opt/conda/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 261, in <module>
main()
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/conda/bin/python', '-u', 'test.py', '--local_rank=1', '--launcher', 'pytorch', '--cfg_file', '/mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml', '--ckpt', '/mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth']' returned non-zero exit status 1.
from voxelnext.
yukang2017
commented on July 26, 2024
Hi,
I think this is the problem of kornia. Would you please check its version?
Regards,
Yukang Chen
from voxelnext.
naren2cmu
commented on July 26, 2024
Hi,
It was 0.5.7.
I uninstalled it and installed the latest one (0.6.11) using pip install kornia and reran the evaluation command. I got the following error (test.py failed).
bash scripts/dist_test.sh 2 --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
+ NGPUS=2
+ PY_ARGS='--cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth'
+ python -m torch.distributed.launch --nproc_per_node=2 test.py --launcher pytorch --cfg_file /mnt/tools/cfgs/nuscenes_models/cbgs_voxel0075_voxelnext.yaml --ckpt /mnt/VoxelNeXt/voxelnext_nuscenes_kernel1.pth
/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py:188: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects `--local_rank` argument to be set, please
change it to read from `os.environ['LOCAL_RANK']` instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions
FutureWarning,
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
Traceback (most recent call last):
File "test.py", line 14, in <module>
Traceback (most recent call last):
File "test.py", line 14, in <module>
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from pcdet.models import load_data_to_gpu
File "../pcdet/models/__init__.py", line 6, in <module>
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 1, in <module>
from eval_utils import eval_utils
File "/mnt/VoxelNeXt/tools/eval_utils/eval_utils.py", line 8, in <module>
from .detector3d_template import Detector3DTemplate
File "../pcdet/models/detectors/detector3d_template.py", line 6, in <module>
from ...ops.iou3d_nms import iou3d_nms_utils
from pcdet.models import load_data_to_gpu File "../pcdet/ops/iou3d_nms/iou3d_nms_utils.py", line 9, in <module>
File "../pcdet/models/__init__.py", line 6, in <module>
from . import iou3d_nms_cuda
ImportError: ../pcdet/ops/iou3d_nms/iou3d_nms_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe28TypeMeta21_typeMetaDataInstanceIdEEPKNS_6detail12TypeMetaDataEv
from .detectors import build_detector
File "../pcdet/models/detectors/__init__.py", line 1, in <module>
from .detector3d_template import Detector3DTemplate
File "../pcdet/models/detectors/detector3d_template.py", line 6, in <module>
from ...ops.iou3d_nms import iou3d_nms_utils
File "../pcdet/ops/iou3d_nms/iou3d_nms_utils.py", line 9, in <module>
from . import iou3d_nms_cuda
ImportError: ../pcdet/ops/iou3d_nms/iou3d_nms_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe28TypeMeta21_typeMetaDataInstanceIdEEPKNS_6detail12TypeMetaDataEv
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 114) of binary: /opt/conda/bin/python
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/opt/conda/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 195, in <module>
main()
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 191, in main
launch(args)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launch.py", line 176, in launch
run(args)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/run.py", line 756, in run
)(*cmd_args)
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/opt/conda/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 248, in launch_agent
failures=result.failures,
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
test.py FAILED
------------------------------------------------------------
Failures:
[1]:
time : 2023-04-18_19:27:29
host : 97863fda069f
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 115)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2023-04-18_19:27:29
host : 97863fda069f
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 114)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
Do you, by any chance, have an alternate docker image that you may be using (with all the dependencies properly satisfied)?
Thank you
Naren
from voxelnext.
yukang2017
commented on July 26, 2024
Hi,
Have you ever installed OpenPCDet?
python3 setup.py develop
Sorry. I did not use docker.
Regards,
Yukang Chen
from voxelnext.
naren2cmu
commented on July 26, 2024
Yes, I did python3 setup.py develop
I was using the docker image you specified at https://github.com/dvlab-research/VoxelNeXt/tree/master/docker
docker pull djiajun1206/pcdet:pytorch1.6 . I guess that has problems then.
I tried to build the docker image as well. (docker build ./ -t openpcdet-docker).
That failed too with the following error.
W: GPG error: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY A4B469963BF863CC
E: The repository 'https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64 InRelease' is not signed.
from voxelnext.
yukang2017
commented on July 26, 2024
Hi, what is the output from python setup.py develop?
In addition, it seems that the problem is still in the installation of openpcdet.
from voxelnext.
AmrinKareem
commented on July 26, 2024
I have problems with installing openpcdet too. @yukang2017 I have been getting the error upon running python3 setup.py develop:
ERROR: No supported gcc/g++ host compiler found.
Use 'nvcc -ccbin ' to specify a host compiler.
I have kornia 0.7.0, spconv-117 and pytorch with cuda 11.7 installed.
from voxelnext.
Related Issues (20)
- No module named 'pcdet.version' HOT 3
- IoU related loss HOT 1
- [Question] How to run a single inference on this model? HOT 2
- Question about the settings of training
- How to use the NuScenes dataset? Please!!! HOT 6
- Can you send me the nuscene and waymo test set model?
- Question about test results
- Can't reproduce the results on waymo
- FPS
- Question about NuScenes val set
- KeyError 'model_state' while loading checkpoint HOT 1
- Could not launch VoxelNeXt due to VoxelGenerator
- Details about the code HOT 1
- The result on nuscenes test set is not good
- 3D object detection from UAV based LiDAR point clouds
- Argoverse2 trainval infos
- About the deployment
- AttributeError: 'str' object has no attribute 'DATASET'
- The CPU usage is too high.
- About gt sampling on argo2 dataset
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from voxelnext.