sshaoshuai / pointnet2.pytorch Goto Github PK

Hello @sshaoshuai ,
Thanks for sharing this work.
I am getting an error called "undefined symbol: __cudaPopCallConfiguration"

My environment:
Pytorch 1.0
Cuda 10.0
GPU driver: 410.78
Python: 3.6
GCC: 5.5

I am guessing the problem might be caused by cuda version mismatch.
The full trace log is as followings:
python train_and_eval.py --batch_size 8 --epochs 100 --ckpt_save_interval 2
Traceback (most recent call last):
File "train_and_eval.py", line 186, in
MODEL = importlib.import_module(args.net) # import network module
File "/home/lin/anaconda3/envs/py36/lib/python3.6/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 994, in _gcd_import
File "", line 971, in _find_and_load
File "", line 955, in _find_and_load_unlocked
File "", line 665, in _load_unlocked
File "", line 678, in exec_module
File "", line 219, in _call_with_frames_removed
File "/media/Lindisk/git_projects/Pointnet2.PyTorch/tools/pointnet2_msg.py", line 3, in
from pointnet2.pointnet2_modules import PointnetFPModule, PointnetSAModuleMSG
File "/media/Lindisk/git_projects/Pointnet2.PyTorch/tools/../pointnet2/pointnet2_modules.py", line 5, in
from . import pointnet2_utils
File "/media/Lindisk/git_projects/Pointnet2.PyTorch/tools/../pointnet2/pointnet2_utils.py", line 7, in
import pointnet2_cuda as pointnet2
ImportError: /home/lin/anaconda3/envs/py36/lib/python3.6/site-packages/pointnet2-0.0.0-py3.6-linux-x86_64.egg/pointnet2_cuda.cpython-36m-x86_64-linux-gnu.so: undefined symbol: __cudaPopCallConfiguration

May I know your environment configurations? or any other idea about why this is happening?
Thanks in advance.

Did anyone encounter this problem and know how to fix it ?

When I build .sh file. This string occur. but no build error.
I use gcc 4.9, cuda-9.0

Thanks ahead.

您好，我的环境是：
ubuntu16.04
torch1.5
cuda10.1
我的编译一直不能正常通过，报错信息如下：
[9/9] /usr/local/cuda-10.1/bin/nvcc -I/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/include -I/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/include/TH -I/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-10.1/include -I/home/psdz/anaconda3/envs/pytorch/include/python3.8 -c -c '/home/psdz/文档/Pointnet2.PyTorch/pointnet2/src/sampling_gpu.cu' -o '/home/psdz/文档/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.8/src/sampling_gpu.o' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O2 -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=pointnet2_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1395, in _run_ninja_build
subprocess.run(
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/subprocess.py", line 512, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "setup.py", line 4, in
setup(
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/init.py", line 161, in setup
return distutils.core.setup(**attrs)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/core.py", line 148, in setup
dist.run_commands()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/dist.py", line 966, in run_commands
self.run_command(cmd)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/install.py", line 67, in run
self.do_egg_install()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/install.py", line 109, in do_egg_install
self.run_command('bdist_egg')
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/bdist_egg.py", line 173, in run
cmd = self.call_command('install_lib', warn_dir=0)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/bdist_egg.py", line 159, in call_command
self.run_command(cmdname)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/install_lib.py", line 11, in run
self.build()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/command/install_lib.py", line 107, in build
self.run_command('build_ext')
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 87, in run
_build_ext.run(self)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run
_build_ext.build_ext.run(self)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/command/build_ext.py", line 340, in run
self.build_extensions()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 580, in build_extensions
build_ext.build_extensions(self)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions
_build_ext.build_ext.build_extensions(self)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/command/build_ext.py", line 449, in build_extensions
self._build_extensions_serial()
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/command/build_ext.py", line 474, in _build_extensions_serial
self.build_extension(ext)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/setuptools/command/build_ext.py", line 208, in build_extension
_build_ext.build_extension(self, ext)
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/distutils/command/build_ext.py", line 528, in build_extension
objects = self.compiler.compile(sources,
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 414, in unix_wrap_ninja_compile
_write_ninja_file_and_compile_objects(
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1135, in _write_ninja_file_and_compile_objects
_run_ninja_build(
File "/home/psdz/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1413, in _run_ninja_build
raise RuntimeError(message)
RuntimeError: Error compiling objects for extension
请指导一下，谢谢您

Why does it happen? I can't find pointnet2_cuda

tools/train_and_eval.py, Line, function eval_one_epoch starts with setting model.train(), which is incorrect in my opinion. It should be model.eval().

Part segmentation: how to test the model with unlabeled data? I test with unmarked data and can't get the predicted point cloud output.

Hello, what I should dwonload? every link?

I can't find T-Net (spatial transformer),
which is used in PointNet and PointNet++

Hi there,

recently I upgraded the pytorch to 1.4.0 and the forward function of pointnet2 broke with errors like:
CUDA: an illegal memory access was encountered.
or
CUDA kernel failed : no kernel image is available for execution on the device
And I am pretty sure it works well with the 1.2.0 conda env.

Thanks for the code again!

May I post a question?
I noticed when using CUDA 8.0, which requires gcc 4.8, compilation warnings emerge. I wonder what your gcc version is. If using default gcc on Ubuntu 16.04 it should be gcc 6.

Hi Shaoshaui,

Regarding the network architecture in your pytorch implementation. I noticed that in the SA and FP modules, the mlp / conv2d channel input and output dimensions differ from the dimensions used in the 'official' PointNet++ code by Charles Qi. Additionally, per SA layer, there are two SharedMLP's instead of one, as in Charles' code.

What are the reasons for the differences?

Thank you!
Tam

Whenever i wish to compile the bash script to install the roi3dpool etc packages i get the error that gcc has failed with exit code 1. I checked some pointrcnn files to which they said that this is being caused due to deprecation of certain cpp packages. Is there any hack to get it to work on ubuntu 20.04, gcc-9 and cuda 11.2?

when i use it in colab.


so what should i do?pls

in the file: tool/pointnet2_msg, line 69, pc[..., 3:].transpose(1, 2).contiguous(). why need transpose(1, 2)?

Hi,

I am trying to run the script on a machine with python3.6 installed, torch==1.5 and cuda 9.1. However, I get errors similars to the attached file. It looks like it is related to the cuda version. Is there a specific version recommended? I also tried different torch versions, 1.3 and 1.6, but with no success.
error.txt

Hello, I was wondering is there any resource from which I can learn about the FPS algorithm? It's hard for me to read through your cuda code because I have no idea about how this algorithm could be implemented. Thanks!

Thanks for your great work,
G++ error occurred when I entered python setup.py install.
running install running bdist_egg running egg_info writing pointnet2.egg-info/PKG-INFO writing dependency_links to pointnet2.egg-info/dependency_links.txt writing top-level names to pointnet2.egg-info/top_level.txt listing git files failed - pretending there aren't any reading manifest file 'pointnet2.egg-info/SOURCES.txt' writing manifest file 'pointnet2.egg-info/SOURCES.txt' installing library code to build/bdist.linux-x86_64/egg running install_lib running build_ext building 'pointnet2_cuda' extension creating /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build creating /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7 creating /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src Emitting ninja build file /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) 1.10.2.git.kitware.jobserver-1 creating build/lib.linux-x86_64-3.7 g++ -pthread -shared -B /home/lq/anaconda3/envs/mvp/compiler_compat -L/home/lq/anaconda3/envs/mvp/lib -Wl,-rpath=/home/lq/anaconda3/envs/mvp/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/pointnet2_api.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/ball_query.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/ball_query_gpu.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/group_points.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/group_points_gpu.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/interpolate.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/interpolate_gpu.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/sampling.o /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/sampling_gpu.o -L/home/lq/anaconda3/envs/mvp/lib/python3.7/site-packages/torch/lib -L/usr/local/cuda-10.1/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.7/pointnet2_cuda.cpython-37m-x86_64-linux-gnu.so g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/pointnet2_api.o: No such file or directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/ball_query.o: No such file or directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/ball_query_gpu.o: No such fileor directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/group_points.o: No such file or directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/group_points_gpu.o: No such file or directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/interpolate.o: No such file ordirectory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/interpolate_gpu.o: No such file or directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/sampling.o: No such file or directory g++: error: /home/lq/New_p/VRCNet-main/utils/Pointnet2.PyTorch/pointnet2/build/temp.linux-x86_64-3.7/src/sampling_gpu.o: No such file or directory error: command 'g++' failed with exit status 1

@sshaoshuai Hi, Thanks for your open source work.

I'm very interested in your implementation of the accelerated code using CUDA.

I'd like to know the IDE in which you write CUDA and debug it. for example: pycharm? vs code? or clion.

I'd also like to learn how to implement some accelerated modules with CUDA, so I'd really appreciate if you could inform me about the CUDA compilation process and environment configuration.

Thank you!

@sshaoshuai
您好，非常感谢您提供的代码，我使用的时候出了一些问题，想向您请教一下。我成功地执行了 python setup.py install 代码，CUDA的OP也可以成功调用，但是训练过了几个epochs就会出现一个问题：CUDA: an illegal memory access was encountered. （每次训练的报错行数不一样，但是最后的报错一样）经过排查我觉得可能与CUDA和里面的线程分配有关，而且这个代码我之前几个月用着都没问题，这个问题是最近出现的。请问您是否遇到过类似的情况？下面的是一次报错的具体信息。非常感谢。

e=/pytorch/aten/src/THC/THCCachingHostAllocator.cpp line=265 error=77 : an illegal memory access was encountered THCudaCheck FAIL file=/pytorch/aten/src/THC/THCCachingHostAllocator.cpp line=265 error=77 : an illegal memory access was encountered Traceback (most recent call last): File "train_semseg.py", line 228, in <module> main(args) File "train_semseg.py", line 171, in main pred = model(points[:,:3,:],points[:,3:,:],target) File "/home/zjh/anaconda2/envs/pose/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__ result = self.forward(*input, **kwargs) File "/home/zjh/anaconda2/envs/pose/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 152, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/zjh/anaconda2/envs/pose/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 162, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/zjh/anaconda2/envs/pose/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 83, in parallel_apply raise output File "/home/zjh/anaconda2/envs/pose/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 59, in _worker output = module(*input, **kwargs) File "/home/zjh/anaconda2/envs/pose/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__ result = self.forward(*input, **kwargs) File "/home/zjh/xumingye_temp/SEMSEG_GSNet_dense_xj-xi,xi_deep_+addEdge_2loss/SemSeg_GS.py", line 617, in forward _,idx0_4, idx4 = eigen_Net(N4_points.permute(0,2,1).contiguous(), k=self.k) File "/home/zjh/xumingye_temp/SEMSEG_GSNet_dense_xj-xi,xi_deep_+addEdge_2loss/SemSeg_GS.py", line 129, in eigen_Net feature = torch.cat(( x, eigen), dim=2) RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /pytorch/aten/src/THC/THCCachingHostAllocator.cpp:265

Hi there, when I was running 'python setup.py install', there are some errors as follows:
can someone help me fix these please.
py3.7 cuda10.0 pytorch1.3.1 ubuntu18.04
thanks!

(myconda) root@9c8f0b01e9a7:/PU-Net_pytorch/pointnet2# python setup.py installrunning install
running bdist_egg
running egg_info
writing pointnet2.egg-info/PKG-INFO
writing dependency_links to pointnet2.egg-info/dependency_links.txt
writing top-level names to pointnet2.egg-info/top_level.txt
reading manifest file 'pointnet2.egg-info/SOURCES.txt'
writing manifest file 'pointnet2.egg-info/SOURCES.txt'
installing library code to build/bdist.linux-x86_64/egg
running install_lib
running build_ext
building 'pointnet2_cuda' extension
gcc -pthread -B /root/miniconda3/envs/myconda/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/TH -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/myconda/include/python3.7m -c src/pointnet2_api.cpp -o build/temp.linux-x86_64-3.7/src/pointnet2_api.o -g -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=pointnet2_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
gcc -pthread -B /root/miniconda3/envs/myconda/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/TH -I/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/root/miniconda3/envs/myconda/include/python3.7m -c src/ball_query.cpp -o build/temp.linux-x86_64-3.7/src/ball_query.o -g -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=pointnet2_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
src/ball_query.cpp: In function ‘int ball_query_wrapper_fast(int, int, int, float, int, at::Tensor, at::Tensor, at::Tensor)’:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:350:20: warning: ‘void c10::detail::deprecated_AT_CHECK()’ is deprecated [-Wdeprecated-declarations]
::c10::detail::deprecated_AT_CHECK();
^
src/ball_query.cpp:10:23: note: in expansion of macro ‘AT_CHECK’
#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
^~~~~~~~
src/ball_query.cpp:12:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
^~~~~~~~~~
src/ball_query.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(new_xyz_tensor);
^
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:325:13: note: declared here
inline void deprecated_AT_CHECK() {}
^~~~~~~~~~~~~~~~~~~
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:350:40: warning: ‘void c10::detail::deprecated_AT_CHECK()’ is deprecated [-Wdeprecated-declarations]
::c10::detail::deprecated_AT_CHECK();
^
src/ball_query.cpp:10:23: note: in expansion of macro ‘AT_CHECK’
#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
^~~~~~~~
src/ball_query.cpp:12:24: note: in expansion of macro ‘CHECK_CUDA’
#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
^~~~~~~~~~
src/ball_query.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(new_xyz_tensor);
^
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:325:13: note: declared here
inline void deprecated_AT_CHECK() {}
^~~~~~~~~~~~~~~~~~~
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:350:20: warning: ‘void c10::detail::deprecated_AT_CHECK()’ is deprecated [-Wdeprecated-declarations]
::c10::detail::deprecated_AT_CHECK();
^
src/ball_query.cpp:11:29: note: in expansion of macro ‘AT_CHECK’
#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
^~~~~~~~
src/ball_query.cpp:12:38: note: in expansion of macro ‘CHECK_CONTIGUOUS’
#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
^~~~~~~~~~~~~~~~
src/ball_query.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(new_xyz_tensor);
^
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:325:13: note: declared here
inline void deprecated_AT_CHECK() {}
^~~~~~~~~~~~~~~~~~~
In file included from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:4,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
from /root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
from src/ball_query.cpp:1:
/root/miniconda3/envs/myconda/lib/python3.7/site-packages/torch/include/c10/util/Exception.h:350:40: warning: ‘void c10::detail::deprecated_AT_CHECK()’ is deprecated [-Wdeprecated-declarations]
::c10::detail::deprecated_AT_CHECK();
^
src/ball_query.cpp:11:29: note: in expansion of macro ‘AT_CHECK’
#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
^~~~~~~~
src/ball_query.cpp:12:38: note: in expansion of macro ‘CHECK_CONTIGUOUS’
#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
^~~~~~~~~~~~~~~~
src/ball_query.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
CHECK_INPUT(new_xyz_tensor);
^

My torch version is 1.9.0, and caught errors within the following two functions/macros: AT_CHECK and THCState_getCurrentStream(state)
I changed them to TORCH_CHECK and at::cuda::getCurrentCUDAStream().stream() and it worked well, so I wonder if those changes can be published in order to support later versions.

Hello, there are three different values (0,1,-1) in the target_label in the loss function DiceLoss(nn.Module); -1 is not considered; I want to know the meaning of these three values It means background, 1 means car, so what does -1 mean?

I was wondering if this would be affected by the difference in operating systems? I'm trying to install on windows 11 but I'm getting the following error? If it's not the operating system could you also please tell me how to fix this error. Thanks again!
0.txt

Hi,
I'm using pytorch 1.5. I was installing pointnet2 in a virtualenv, using python3 setup.py install, and I got the following error:

src/ball_query.cpp:22:27: error: ‘THCState_getCurrentStream’ was not declared in this scope
   22 |     cudaStream_t stream = THCState_getCurrentStream(state);
error: command 'x86_64-linux-gnu-gcc' failed with exit status 1

Can you give me hints on how to solve this?
Thank you in advance!

Hi @sshaoshuai,
Shouldn't evaluation be performed in eval() mode?
https://github.com/sshaoshuai/Pointnet2.PyTorch/blob/master/tools/train_and_eval.py#L103

after build pointnet2, I get this error when importing:

>>> import pointnet2_cuda
Segmentation fault (core dumped)

you give the task of KITTI ourdoor foreground point cloud segmentation example, so what's the result can be referenced？

In set abstraction layer, there is a config named RADIUS
RADIUS: [[0.1, 0.5], [0.5, 1.0], [1.0, 2.0], [2.0, 4.0]]
It means Euclidean distance? or a ratio of the number of point(e.g. 0.1*4096)？

I not understand the code of pointnet2 in PCDet. How can I find an explanation for this part?

Could you please give an example of how to use your code within Python?
I have several lists of 3D points, which each represent an object.

Hi, I have a few questions about this repo.

1. How much faster is your implementation compare to the original pytorch/TensorFlow version ?
2. Can you explain more about how do you speed up the operation?
3. If I want to implement a faster TensorFlow version of pointnet++, do you have any suggestion?

Thanks.

where is pointnet2_cuda?

Hi, I can't install library. I am new to compiling C++ code using Python. Is there a way to compile using my settings?

running install
running bdist_egg
running egg_info
writing pointnet2.egg-info/PKG-INFO
writing dependency_links to pointnet2.egg-info/dependency_links.txt
writing top-level names to pointnet2.egg-info/top_level.txt
reading manifest file 'pointnet2.egg-info/SOURCES.txt'
writing manifest file 'pointnet2.egg-info/SOURCES.txt'
installing library code to build/bdist.linux-x86_64/egg
running install_lib
running build_ext
building 'pointnet2_cuda' extension
Emitting ninja build file /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/8] g++ -MMD -MF /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/ball_query.o.d -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/TH -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/THC -I/n/helmod/apps/centos7/Core/cuda/10.2.89-fasrc01/cuda/include -I/n/helmod/apps/centos7/CUDA/cuda/10.2.89-fasrc01/cudnn/7.6.5.32_cuda10.2-fasrc01/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/include/python3.6m -c -c /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp -o /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/ball_query.o -g -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=pointnet2_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
FAILED: /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/ball_query.o 
g++ -MMD -MF /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/ball_query.o.d -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/TH -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/THC -I/n/helmod/apps/centos7/Core/cuda/10.2.89-fasrc01/cuda/include -I/n/helmod/apps/centos7/CUDA/cuda/10.2.89-fasrc01/cudnn/7.6.5.32_cuda10.2-fasrc01/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/include/python3.6m -c -c /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp -o /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/ball_query.o -g -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=pointnet2_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Parallel.h:149,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/TH/THTensorApply.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/TH/THTensor.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/THC/THCTensor.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/THC/THC.h:13,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:3:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ParallelOpenMP.h:84: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
   84 | #pragma omp parallel for if ((end - begin) >= grain_size)
      | 
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp: In function ‘int ball_query_wrapper_fast(int, int, int, float, int, at::Tensor, at::Tensor, at::Tensor)’:
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:10:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   10 | #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
      |                                       ^
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:12:24: note: in expansion of macro ‘CHECK_CUDA’
   12 | #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
      |                        ^~~~~~~~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
   16 |     CHECK_INPUT(new_xyz_tensor);
      |     ^~~~~~~~~~~
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Context.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ATen.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:6,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:1:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:268:30: note: declared here
  268 |   DeprecatedTypeProperties & type() const {
      |                              ^~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:10:23: error: ‘AT_CHECK’ was not declared in this scope; did you mean ‘DCHECK’?
   10 | #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
      |                       ^~~~~~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:10:23: note: in definition of macro ‘CHECK_CUDA’
   10 | #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
      |                       ^~~~~~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
   16 |     CHECK_INPUT(new_xyz_tensor);
      |     ^~~~~~~~~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:10:39: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
   10 | #define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
      |                                       ^
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:12:24: note: in expansion of macro ‘CHECK_CUDA’
   12 | #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
      |                        ^~~~~~~~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:17:5: note: in expansion of macro ‘CHECK_INPUT’
   17 |     CHECK_INPUT(xyz_tensor);
      |     ^~~~~~~~~~~
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Context.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ATen.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:6,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:1:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:268:30: note: declared here
  268 |   DeprecatedTypeProperties & type() const {
      |                              ^~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:18:55: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
   18 |     const float *new_xyz = new_xyz_tensor.data<float>();
      |                                                       ^
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Context.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ATen.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:6,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:1:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:354:7: note: declared here
  354 |   T * data() const {
      |       ^~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:19:47: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
   19 |     const float *xyz = xyz_tensor.data<float>();
      |                                               ^
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Context.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ATen.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:6,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:1:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:354:7: note: declared here
  354 |   T * data() const {
      |       ^~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:20:37: warning: ‘T* at::Tensor::data() const [with T = int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
   20 |     int *idx = idx_tensor.data<int>();
      |                                     ^
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Tensor.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Context.h:4,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ATen.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/input-archive.h:6,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/archive.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/serialize/tensor.h:3,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:1:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/core/TensorBody.h:354:7: note: declared here
  354 |   T * data() const {
      |       ^~~~
/net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/ball_query.cpp:22:27: error: ‘THCState_getCurrentStream’ was not declared in this scope
   22 |     cudaStream_t stream = THCState_getCurrentStream(state);
      |                           ^~~~~~~~~~~~~~~~~~~~~~~~~
[2/8] g++ -MMD -MF /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/pointnet2_api.o.d -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/TH -I/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/THC -I/n/helmod/apps/centos7/Core/cuda/10.2.89-fasrc01/cuda/include -I/n/helmod/apps/centos7/CUDA/cuda/10.2.89-fasrc01/cudnn/7.6.5.32_cuda10.2-fasrc01/include -I/n/home03/theycallmefm/.conda/envs/flownet3d/include/python3.6m -c -c /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/pointnet2_api.cpp -o /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/build/temp.linux-x86_64-3.6/src/pointnet2_api.o -g -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=pointnet2_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/Parallel.h:149,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/csrc/api/include/torch/all.h:7,
                 from /n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/torch/extension.h:4,
                 from /net/coxfs01/srv/export/coxfs01/pfister_lab2/share_root/Lab/theycallmefm/flownet3d_pytorch/lib/src/pointnet2_api.cpp:2:
/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/include/ATen/ParallelOpenMP.h:84: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
   84 | #pragma omp parallel for if ((end - begin) >= grain_size)
      | 
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1515, in _run_ninja_build
    env=env)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/subprocess.py", line 438, in run
    output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "setup.py", line 22, in <module>
    cmdclass={'build_ext': BuildExtension}
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/__init__.py", line 165, in setup
    return distutils.core.setup(**attrs)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/core.py", line 148, in setup
    dist.run_commands()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/dist.py", line 955, in run_commands
    self.run_command(cmd)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/dist.py", line 974, in run_command
    cmd_obj.run()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/install.py", line 67, in run
    self.do_egg_install()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/install.py", line 109, in do_egg_install
    self.run_command('bdist_egg')
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/dist.py", line 974, in run_command
    cmd_obj.run()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/bdist_egg.py", line 174, in run
    cmd = self.call_command('install_lib', warn_dir=0)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/bdist_egg.py", line 160, in call_command
    self.run_command(cmdname)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/dist.py", line 974, in run_command
    cmd_obj.run()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/install_lib.py", line 11, in run
    self.build()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/command/install_lib.py", line 107, in build
    self.run_command('build_ext')
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/dist.py", line 974, in run_command
    cmd_obj.run()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/build_ext.py", line 87, in run
    _build_ext.run(self)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/command/build_ext.py", line 339, in run
    self.build_extensions()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 649, in build_extensions
    build_ext.build_extensions(self)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
    self._build_extensions_serial()
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
    self.build_extension(ext)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/setuptools/command/build_ext.py", line 208, in build_extension
    _build_ext.build_extension(self, ext)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension
    depends=ext.depends)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 478, in unix_wrap_ninja_compile
    with_cuda=with_cuda)
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1233, in _write_ninja_file_and_compile_objects
    error_prefix='Error compiling objects for extension')
  File "/n/home03/theycallmefm/.conda/envs/flownet3d/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1529, in _run_ninja_build
    raise RuntimeError(message)
RuntimeError: Error compiling objects for extension

My settings:
Python 3.6.10
GCC 9.3.0
CUDA 10.2
Pytorch 1.6.0

when ℹ run this command :python train_and_eval.py --batch_size 8 --epochs 100 --ckpt_save_interval 2
i get error :Traceback (most recent call last):
File "train_and_eval.py", line 183, in
MODEL = importlib.import_module(args.net) # import network module
File "/home/liyunhao/anaconda3/envs/pointnet2/lib/python3.7/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1006, in _gcd_import
File "", line 983, in _find_and_load
File "", line 967, in _find_and_load_unlocked
File "", line 677, in _load_unlocked
File "", line 728, in exec_module
File "", line 219, in _call_with_frames_removed
File "/home/liyunhao/bao/Pointnet2.PyTorch-master/tools/pointnet2_msg.py", line 3, in
from pointnet2.pointnet2_modules import PointnetFPModule, PointnetSAModuleMSG
File "/home/liyunhao/bao/Pointnet2.PyTorch-master/tools/../pointnet2/pointnet2_modules.py", line 5, in
from . import pointnet2_utils
File "/home/liyunhao/bao/Pointnet2.PyTorch-master/tools/../pointnet2/pointnet2_utils.py", line 7, in
import pointnet2_cuda as pointnet2
ImportError: /home/liyunhao/anaconda3/envs/pointnet2/lib/python3.7/site-packages/pointnet2-0.0.0-py3.7-linux-x86_64.egg/pointnet2_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: Z31gather_points_grad_wrapper_fastiiiiN2at6TensorES0_S0

I think this error has something to do with so file but i cant solve it .

Environment: ubuntu18.04 cuda11.4 pytorch 1.11.0+cu113

(base) siat@siat-Precision-3640-Tower:~/work/machine_learning/PointRCNN-master/pointnet2_lib/pointnet2$ python setup.py install
/home/siat/Downloads/ENTER/lib/python3.9/site-packages/torch/cuda/init.py:82: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:112.)
return torch._C._cuda_getDeviceCount() > 0
No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda-11.4'
running install
/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/easy_install.py:144: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
warnings.warn(
running bdist_egg
running egg_info
writing pointnet2.egg-info/PKG-INFO
writing dependency_links to pointnet2.egg-info/dependency_links.txt
writing top-level names to pointnet2.egg-info/top_level.txt
reading manifest file 'pointnet2.egg-info/SOURCES.txt'
writing manifest file 'pointnet2.egg-info/SOURCES.txt'
installing library code to build/bdist.linux-x86_64/egg
running install_lib
running build_ext
/home/siat/Downloads/ENTER/lib/python3.9/site-packages/torch/utils/cpp_extension.py:788: UserWarning: The detected CUDA version (11.4) has a minor version mismatch with the version that was used to compile PyTorch (11.3). Most likely this shouldn't be a problem.
warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda))
building 'pointnet2_cuda' extension
Traceback (most recent call last):
File "/home/siat/work/machine_learning/PointRCNN-master/pointnet2_lib/pointnet2/setup.py", line 4, in
setup(
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/init.py", line 87, in setup
return distutils.core.setup(**attrs)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/core.py", line 148, in setup
return run_commands(dist)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/core.py", line 163, in run_commands
dist.run_commands()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/dist.py", line 967, in run_commands
self.run_command(cmd)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/dist.py", line 1214, in run_command
super().run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/install.py", line 74, in run
self.do_egg_install()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/install.py", line 123, in do_egg_install
self.run_command('bdist_egg')
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/dist.py", line 1214, in run_command
super().run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/bdist_egg.py", line 165, in run
cmd = self.call_command('install_lib', warn_dir=0)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/bdist_egg.py", line 151, in call_command
self.run_command(cmdname)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/dist.py", line 1214, in run_command
super().run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/install_lib.py", line 11, in run
self.build()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/command/install_lib.py", line 107, in build
self.run_command('build_ext')
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/dist.py", line 1214, in run_command
super().run_command(command)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/dist.py", line 986, in run_command
cmd_obj.run()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/build_ext.py", line 79, in run
_build_ext.run(self)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run
_build_ext.build_ext.run(self)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 741, in build_extensions
build_ext.build_extensions(self)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions
_build_ext.build_ext.build_extensions(self)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/command/build_ext.py", line 202, in build_extension
_build_ext.build_extension(self, ext)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/setuptools/_distutils/command/build_ext.py", line 528, in build_extension
objects = self.compiler.compile(sources,
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 557, in unix_wrap_ninja_compile
cuda_post_cflags = unix_cuda_flags(cuda_post_cflags)
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 456, in unix_cuda_flags
cflags + _get_cuda_arch_flags(cflags))
File "/home/siat/Downloads/ENTER/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1626, in _get_cuda_arch_flags
arch_list[-1] += '+PTX'
IndexError: list index out of range

Hi, I tested your pointnet2 model successfully on my local Linux Ubuntu20 with torch1.0 and Python=3.6. However, when I upload the full code to the Linux based server and test my code on my own 3d LiDAR dataset (Oxford RobotCar Dataset), I got an error like this:

Besides, the configurations on the Linux server are the same as my local Ubuntu20 system. Therefore, I am so confused about this problem.