sunset1995 / DirectVoxGO

Direct voxel grid optimization for fast radiance field reconstruction.
https://sunset1995.github.io/dvgo
Other
1.04k stars 109 forks source link

arch_list[-1] += '+PTX' IndexError: list index out of range #55

Open derrick-xwp opened 1 year ago

derrick-xwp commented 1 year ago

export CUDA_VISIBLE_DEVICES=0 && python run.py --config configs/nerf/materials_dense_200.py --render_test

No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda-11.4' /home/comp/enter/envs/dvg/lib/python3.7/site-packages/mmcv/init.py:21: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details. 'On January 1, 2023, MMCV will release v2.0.0, in which it will remove ' Using /home/comp.cache/torch_extensions/py37_cpu as PyTorch extensions root... Detected CUDA files, patching ldflags Emitting ninja build file /home/comp/.cache/torch_extensions/py37_cpu/adam_upd_cuda/build.ninja... Traceback (most recent call last): File "run.py", line 13, in from lib import utils, dvgo, dcvgo, dmpigo File "/home/comp/DirectVoxGO/lib/utils.py", line 11, in from .masked_adam import MaskedAdam File "/home/comp/DirectVoxGO/lib/masked_adam.py", line 10, in verbose=True) File "/home/comp/enter/envs/dvg/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1219, in load keep_intermediates=keep_intermediates) File "/home/comp/enter/envs/dvg/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1440, in _jit_compile is_standalone=is_standalone) File "/home/comp/enter/envs/dvg/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1538, in _write_ninja_file_and_build_library is_standalone=is_standalone) File "/home/comp/enter/envs/dvg/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1927, in _write_ninja_file_to_build_library cuda_flags = common_cflags + COMMON_NVCC_FLAGS + _get_cuda_arch_flags() File "/home/comp/enter/envs/dvg/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1699, in _get_cuda_arch_flags arch_list[-1] += '+PTX' IndexError: list index out of range

cmy76 commented 1 year ago

I encoutered the same problem, and I found out that my torch is CPU version😂

zhouilu commented 1 year ago

try like export TORCH_CUDA_ARCH_LIST="8.6"