Pointnet2.PyTorch

Pointnet2.PyTorch copied to clipboard

RuntimeError: Error compiling objects for extension

9

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...

xiaoli-ai

THC\THC.h can't find

9

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

zhou-SHU164

error happen, list out of index , while run python setup.py install,thank!

2

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...

miaozujia

For me, the other pull requests did not work. I found a solution in this question: https://stackoverflow.com/questions/72988735/replacing-thc-thc-h-module-to-aten-aten-h-module With the changes I was able to compile and run a PointNet based...

kannwism

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

JaydencoolCC

.so: undefined symbol

2

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) #...

635583042qq

Make these changes to fix the problem of verison of pytorch: ``` AT_CHECK ===> TORCH_CHECK THCState_getCurrentStream(state) ===> c10::cuda::getCurrentCUDAStream() ``` It will support higher version.

OrangeSodahub

when i use it in colab.   so what should i do?pls

zhou-SHU164

ARUN62

model.train in eval function

1

`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()`.

andraspalffy