search

humanpose1 / MS-SVConv

Compute descriptors for 3D point cloud registration using a multi scale sparse voxel architecture
MIT License
63 stars 7 forks source link

A question about "No module named 'torchsparse'" #14

Closed QWTforGithub closed 2 years ago

QWTforGithub commented 2 years ago

Thank you for your warm reply. Now, I'd like to make some experimental comparisons with your method. When I run evalution.py, "No module named 'torchsparse'" appears :

/home/ls/anaconda3/envs/qwt_py38/bin/python /home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/evaluate.py /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/MinkowskiEngine-0.5.4-py3.6-linux-x86_64.egg/MinkowskiEngine/init.py:42: UserWarning: The environment variable OMP_NUM_THREADS not set. MinkowskiEngine will automatically set OMP_NUM_THREADS=16. If you want to set OMP_NUM_THREADS manually, please export it on the command line before running a python script. e.g. export OMP_NUM_THREADS=12; python your_program.py. It is recommended to set it below 24. "It is recommended to set it below 24.", /home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/core/utils.py:207: UserWarning: Using config_path to specify the config name is deprecated, specify the config name via config_name See https://hydra.cc/docs/next/upgrades/0.11_to_1.0/config_path_changes warnings.warn(category=UserWarning, message=msg) [2021-10-26 20:56:47,643][main][INFO] - DEVICE : cuda [2021-10-26 20:56:47,644][torch_points3d.metrics.model_checkpoint][INFO] - Loading checkpoint from /home/qwt/code/torch_points3d_master_evaluation/outputs/MS_SVCONV_B2cm_X2_3head.pt [2021-10-26 20:56:48,227][torch_points3d.datasets.registration.basetest][WARNING] - already downloaded test Processing... Done! invalid syntax (, line 1) [2021-10-26 20:56:49,356][torch_points3d.modules.SparseConv3d.nn][ERROR] - Could not import torchsparse backend for sparse convolutions Traceback (most recent call last): File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/modules/SparseConv3d/nn/init.py", line 46, in set_backend modules = importlib.import_module("." + _backend, name) # noqa: F841 File "/home/ls/anaconda3/envs/qwt_py38/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 "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/modules/SparseConv3d/nn/torchsparse.py", line 5, in import torchsparse as TS ModuleNotFoundError: No module named 'torchsparse' Traceback (most recent call last): File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/_internal/utils.py", line 198, in run_and_report return func() File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/_internal/utils.py", line 350, in overrides=args.overrides, File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/_internal/hydra.py", line 112, in run configure_logging=with_log_configuration, File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/core/utils.py", line 127, in run_job ret.return_value = task_function(task_cfg) File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/evaluate.py", line 231, in main model = checkpoint.create_model(dataset, weight_name=cfg.training.weight_name) File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/metrics/model_checkpoint.py", line 174, in create_model model = instantiate_model(OmegaConf.create(run_config), dataset) File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/models/model_factory.py", line 48, in instantiate_model model = model_cls(model_config, "dummy", dataset, modellib) File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/models/registration/ms_svconv3d.py", line 200, in init backend=option.backend, File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/models/registration/ms_svconv3d.py", line 34, in init self.unet = SparseConv3d(architecture="unet", input_nc=input_nc, config=backbone, backend=backend) File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/applications/sparseconv3d.py", line 62, in SparseConv3d sp3d.nn.set_backend(backend) File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/../../torch_points3d/modules/SparseConv3d/nn/init.py", line 52, in set_backend exec("globals()['%s'] = modules.%s" % (val, val)) File "", line 1, in NameError: name 'modules' is not defined

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/qwt/code/torch_points3d_master_evaluation/scripts/test_registration_scripts/evaluate.py", line 269, in main() File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/main.py", line 37, in decorated_main strict=strict, File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/_internal/utils.py", line 347, in _run_hydra lambda: hydra.run( File "/home/ls/anaconda3/envs/qwt_py38/lib/python3.6/site-packages/hydra/_internal/utils.py", line 237, in run_and_report assert mdl is not None AssertionError Process finished with exit code 1

Can you give me same advice?

humanpose1 commented 2 years ago

Have you installed torchsparse ?

QWTforGithub commented 2 years ago

Have you installed torchsparse ?

Oh, I confused torch_sparse with torchsparse. Thanks for your advice!