New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A bug with torch #4
Comments
Hi @akira2025 , The bug with torch is solved! The problem was that the version of torch-sparse and torch were incompatible. |
hi humanposes1 IndexError Traceback (most recent call last) in () 12 frames /usr/local/lib/python3.7/dist-packages/torch_points3d/models/registration/ms_svconv3d.py in forward(self, *args, **kwargs) /usr/local/lib/python3.7/dist-packages/torch_points3d/models/registration/ms_svconv3d.py in apply_nn(self, input) /usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) /usr/local/lib/python3.7/dist-packages/torch_points3d/models/registration/ms_svconv3d.py in forward(self, data, **kwargs) /usr/local/lib/python3.7/dist-packages/torch_points3d/applications/sparseconv3d.py in forward(self, data, *args, **kwargs) /usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) /usr/local/lib/python3.7/dist-packages/torch_points3d/modules/SparseConv3d/modules.py in forward(self, x) /usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) /usr/local/lib/python3.7/dist-packages/torch/nn/modules/container.py in forward(self, input) /usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) /usr/local/lib/python3.7/dist-packages/torch_points3d/core/data_transform/../../../torchsparse/nn/modules/conv.py in forward(self, inputs) /usr/local/lib/python3.7/dist-packages/torch_points3d/core/data_transform/../../../torchsparse/nn/functional/conv.py in conv3d(inputs, kernel, kernel_size, bias, stride, dilation, transpose) /usr/local/lib/python3.7/dist-packages/torch_points3d/core/data_transform/../../../torchsparse/nn/functional/downsample.py in spdownsample(coords, ratio, kernel_size, tensor_stride) IndexError: too many indices for tensor of dimension 1 |
Sorry for the trouble. Now I've fixed the problem, Actually I've downgraded the version of torchsparse. |
Hi guys, I have a bug when running your code. when I run in Registration part. I have a problem below.
I also try with my machine but also have same problem. I hope you can give me some suggestion.
Thank you so much
OSError Traceback (most recent call last)
in ()
6 import requests
7 import torch
----> 8 from torch_points3d.applications.pretrained_api import PretainedRegistry
9 from torch_points3d.core.data_transform import GridSampling3D, AddFeatByKey, AddOnes, Random3AxisRotation
10 from torch_points3d.datasets.registration.pair import Pair
8 frames
/usr/local/lib/python3.7/dist-packages/torch_points3d/applications/pretrained_api.py in ()
5
6 # Import building function for model and dataset
----> 7 from torch_points3d.datasets.dataset_factory import instantiate_dataset
8 from torch_points3d.models.model_factory import instantiate_model
9
/usr/local/lib/python3.7/dist-packages/torch_points3d/datasets/dataset_factory.py in ()
4 import logging
5
----> 6 from torch_points3d.datasets.base_dataset import BaseDataset
7
8 log = logging.getLogger(name)
/usr/local/lib/python3.7/dist-packages/torch_points3d/datasets/base_dataset.py in ()
6 import numpy as np
7 import torch
----> 8 import torch_geometric
9 from torch_geometric.transforms import Compose, FixedPoints
10 import copy
/usr/local/lib/python3.7/dist-packages/torch_geometric/init.py in ()
3
4 from .debug import is_debug_enabled, debug, set_debug
----> 5 import torch_geometric.data
6 import torch_geometric.transforms
7 import torch_geometric.utils
/usr/local/lib/python3.7/dist-packages/torch_geometric/data/init.py in ()
----> 1 from .data import Data
2 from .temporal import TemporalData
3 from .batch import Batch
4 from .dataset import Dataset
5 from .in_memory_dataset import InMemoryDataset
/usr/local/lib/python3.7/dist-packages/torch_geometric/data/data.py in ()
6 import torch
7 import torch_geometric
----> 8 from torch_sparse import coalesce, SparseTensor
9 from torch_geometric.utils import (contains_isolated_nodes,
10 contains_self_loops, is_undirected)
/usr/local/lib/python3.7/dist-packages/torch_sparse/init.py in ()
13 ]:
14 torch.ops.load_library(importlib.machinery.PathFinder().find_spec(
---> 15 f'{library}_{suffix}', [osp.dirname(file)]).origin)
16
17 if torch.cuda.is_available(): # pragma: no cover
/usr/local/lib/python3.7/dist-packages/torch/_ops.py in load_library(self, path)
102 # static (global) initialization code in order to register custom
103 # operators with the JIT.
--> 104 ctypes.CDLL(path)
105 self.loaded_libraries.add(path)
106
/usr/lib/python3.7/ctypes/init.py in init(self, name, mode, handle, use_errno, use_last_error)
362
363 if handle is None:
--> 364 self._handle = _dlopen(self._name, mode)
365 else:
366 self._handle = handle
OSError: /usr/local/lib/python3.7/dist-packages/torch_sparse/_convert_cuda.so: undefined symbol: _ZNK2at6Tensor6deviceEv
The text was updated successfully, but these errors were encountered: