Torch Sparse Error when running examples
hongshuh opened this issue · comments
I was following the README instructions for Installating the enviroments, but I encountered an error message when running the code.
python simulate.py --config_yml configs/simulate/water.yml --model_dir example_model/water_1k_schnet
I got a error with following message:
Traceback (most recent call last):
File "/home/hongshuh/MDsim/simulate.py", line 28, in <module>
from mdsim.md.ase_utils import data_to_atoms, OCPCalculator, Simulator
File "/home/hongshuh/MDsim/mdsim/md/ase_utils.py", line 8, in <module>
from torch_geometric.data import Data
File "/home/hongshuh/.local/lib/python3.9/site-packages/torch_geometric/__init__.py", line 4, in <module>
import torch_geometric.data
File "/home/hongshuh/.local/lib/python3.9/site-packages/torch_geometric/data/__init__.py", line 1, in <module>
from .data import Data
File "/home/hongshuh/.local/lib/python3.9/site-packages/torch_geometric/data/data.py", line 18, in <module>
from torch_sparse import SparseTensor
File "/home/hongshuh/anaconda3/envs/mdsim/lib/python3.9/site-packages/torch_sparse/__init__.py", line 40, in <module>
from .tensor import SparseTensor # noqa
File "/home/hongshuh/anaconda3/envs/mdsim/lib/python3.9/site-packages/torch_sparse/tensor.py", line 13, in <module>
class SparseTensor(object):
File "/home/hongshuh/anaconda3/envs/mdsim/lib/python3.9/site-packages/torch/jit/_script.py", line 1302, in script
_compile_and_register_class(obj, _rcb, qualified_name)
File "/home/hongshuh/anaconda3/envs/mdsim/lib/python3.9/site-packages/torch/jit/_recursive.py", line 44, in _compile_and_register_class
script_class = torch._C._jit_script_class_compile(qualified_name, ast, defaults, rcb)
RuntimeError:
object has no attribute sparse_csc_tensor:
File "/home/hongshuh/anaconda3/envs/mdsim/lib/python3.9/site-packages/torch_sparse/tensor.py", line 520
value = torch.ones(self.nnz(), dtype=dtype, device=self.device())
return torch.sparse_csc_tensor(colptr, row, value, self.sizes())
~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
this is likely due to incorrect versions of PyG or torch_sparse. Could you make sure you installed the same versions as in README?
this is likely due to incorrect versions of PyG or torch_sparse. Could you make sure you installed the same versions as in README?
I just copied the comman from README, It should be the same version, Can you upload a enviroment.yml file?
I have the same issue. A conda environment will be more helpful.
The procedure in README was tested. Here is an export of my working environment:
name: mdsim
channels:
- https://conda.deepmodeling.com
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _openmp_mutex=5.1=1_gnu
- abseil-cpp=20210324.2=h2531618_0
- absl-py=1.0.0=pyh7a5ff2f_0
- aiohttp=3.8.1=py39h7f8727e_1
- aiosignal=1.2.0=pyhd3eb1b0_0
- argon2-cffi=21.3.0=pyhd3eb1b0_0
- argon2-cffi-bindings=21.2.0=py39h7f8727e_0
- astunparse=1.6.3=py_0
- async-timeout=4.0.2=py39h06a4308_0
- attrs=21.4.0=pyhd3eb1b0_0
- backcall=0.2.0=pyhd3eb1b0_0
- backrefs=5.0.1=pyhd8ed1ab_0
- beautifulsoup4=4.11.1=py39h06a4308_0
- blas=1.0=mkl
- bleach=4.1.0=pyhd3eb1b0_0
- blinker=1.4=py39h06a4308_0
- bracex=2.1.1=pyhd8ed1ab_0
- brotlipy=0.7.0=py39h27cfd23_1003
- c-ares=1.18.1=h7f8727e_0
- ca-certificates=2022.07.19=h06a4308_0
- cachetools=4.2.2=pyhd3eb1b0_0
- certifi=2022.9.24=py39h06a4308_0
- cffi=1.15.1=py39h74dc2b5_0
- charset-normalizer=2.0.4=pyhd3eb1b0_0
- click=8.0.4=py39h06a4308_0
- cloudpickle=2.0.0=pyhd3eb1b0_0
- cryptography=37.0.1=py39h9ce1e76_0
- cudatoolkit=11.3.1=h2bc3f7f_2
- cudnn=8.2.1=cuda11.3_0
- dargs=0.2.6=pyh7a5ff2f_0
- dataclasses=0.8=pyh6d0b6a4_7
- decorator=5.1.1=pyhd3eb1b0_0
- deepmd-kit=2.1.0=py39_0_cuda11.3_gpu
- defusedxml=0.7.1=pyhd3eb1b0_0
- entrypoints=0.4=py39h06a4308_0
- fftw=3.3.9=h27cfd23_1
- frozenlist=1.2.0=py39h7f8727e_0
- gast=0.4.0=pyhd3eb1b0_0
- giflib=5.2.1=h7b6447c_0
- google-auth=2.6.0=pyhd3eb1b0_0
- google-auth-oauthlib=0.4.1=py_2
- google-pasta=0.2.0=pyhd3eb1b0_0
- grpcio=1.42.0=py39hce63b2e_0
- gsl=2.7.1=h6e86dc7_1
- h5py=3.7.0=py39h737f45e_0
- hdf5=1.10.6=hb1b8bf9_0
- horovod=0.24.1=py39h9622761_0
- icu=68.1=h2531618_0
- idna=3.3=pyhd3eb1b0_0
- importlib-metadata=4.11.3=py39h06a4308_0
- intel-openmp=2021.4.0=h06a4308_3561
- ipython_genutils=0.2.0=pyhd3eb1b0_1
- jedi=0.18.1=py39h06a4308_1
- jpeg=9e=h7f8727e_0
- jsoncpp=1.9.4=hff7bd54_2
- jsonschema=4.16.0=py39h06a4308_0
- jupyter_client=7.3.5=py39h06a4308_0
- jupyter_core=4.11.1=py39h06a4308_0
- jupyterlab_pygments=0.1.2=py_0
- jupyterlab_widgets=1.0.0=pyhd3eb1b0_1
- keras=2.7.0=pyh7a5ff2f_0
- keras-preprocessing=1.1.2=pyhd3eb1b0_0
- krb5=1.19.2=hac12032_0
- lammps=20220623.1=h9954876_1
- ld_impl_linux-64=2.38=h1181459_1
- libcurl=7.84.0=h91b91d3_0
- libdeepmd=2.1.0=0_cuda11.3_gpu
- libedit=3.1.20210910=h7f8727e_0
- libev=4.33=h7f8727e_1
- libffi=3.3=he6710b0_2
- libgcc-ng=11.2.0=h1234567_1
- libgfortran-ng=7.5.0=ha8ba4b0_17
- libgfortran4=7.5.0=ha8ba4b0_17
- libgomp=11.2.0=h1234567_1
- libnghttp2=1.46.0=hce63b2e_0
- libopenblas=0.3.18=hf726d26_0
- libpng=1.6.37=hbc83047_0
- libprotobuf=3.14.0=h8c45485_0
- libsodium=1.0.18=h7b6447c_0
- libssh2=1.10.0=h8f2d780_0
- libstdcxx-ng=11.2.0=h1234567_1
- libtensorflow_cc=2.7.0=cuda113hbf71e95_1
- markdown=3.3.4=py39h06a4308_0
- markupsafe=2.1.1=py39h7f8727e_0
- matplotlib-inline=0.1.6=py39h06a4308_0
- mistune=0.8.4=py39h27cfd23_1000
- mkl=2021.4.0=h06a4308_640
- mkl-service=2.4.0=py39h7f8727e_0
- mkl_fft=1.3.1=py39hd3c417c_0
- mkl_random=1.2.2=py39h51133e4_0
- mpi=1.0=mpich
- mpi4py=3.1.3=py39h21fafdc_1
- mpich=3.3.2=hc856adb_0
- multidict=5.2.0=py39h5eee18b_3
- nbclient=0.5.13=py39h06a4308_0
- nbconvert=6.4.4=py39h06a4308_0
- nbformat=5.5.0=py39h06a4308_0
- nccl=2.11.4.1=h83d496c_1
- ncurses=6.3=h5eee18b_3
- notebook=6.4.12=py39h06a4308_0
- numpy=1.23.1=py39h6c91a56_0
- numpy-base=1.23.1=py39ha15fc14_0
- oauthlib=3.2.0=pyh7a5ff2f_0
- openssl=1.1.1q=h7f8727e_0
- opt_einsum=3.3.0=pyhd3eb1b0_1
- packaging=21.3=pyhd3eb1b0_0
- pandocfilters=1.5.0=pyhd3eb1b0_0
- parso=0.8.3=pyhd3eb1b0_0
- pexpect=4.8.0=pyhd3eb1b0_3
- pickleshare=0.7.5=pyhd3eb1b0_1003
- pip=22.2.2=py39h06a4308_0
- plumed=2.8.0=h5980d18_1
- prometheus_client=0.14.1=py39h06a4308_0
- protobuf=3.14.0=py39h2531618_1
- psutil=5.9.0=py39h5eee18b_0
- ptyprocess=0.7.0=pyhd3eb1b0_2
- pure_eval=0.2.2=pyhd3eb1b0_0
- pyasn1=0.4.8=pyhd3eb1b0_0
- pyasn1-modules=0.2.8=py_0
- pycparser=2.21=pyhd3eb1b0_0
- pyjwt=2.4.0=pyh7a5ff2f_0
- pylammps=20220623.1=pyh29e1a88_1
- pyopenssl=22.0.0=pyhd3eb1b0_0
- pyparsing=3.0.9=py39h06a4308_0
- pyrsistent=0.18.0=py39heee7806_0
- pysocks=1.7.1=py39h06a4308_0
- python=3.9.11=h12debd9_2
- python-dateutil=2.8.2=pyhd3eb1b0_0
- python-fastjsonschema=2.16.2=py39h06a4308_0
- python-flatbuffers=2.0=pyhd3eb1b0_0
- python-hostlist=1.21=pyh9f0ad1d_0
- pyyaml=6.0=py39h7f8727e_1
- readline=8.1.2=h7f8727e_1
- requests=2.28.1=py39h06a4308_0
- requests-oauthlib=1.3.0=py_0
- rsa=4.7.2=pyhd3eb1b0_1
- scipy=1.7.1=py39h292c36d_2
- send2trash=1.8.0=pyhd3eb1b0_1
- setuptools=63.4.1=py39h06a4308_0
- six=1.16.0=pyhd3eb1b0_1
- snappy=1.1.9=h295c915_0
- soupsieve=2.3.1=pyhd3eb1b0_0
- sqlite=3.39.3=h5082296_0
- stack_data=0.2.0=pyhd3eb1b0_0
- tensorboard=2.6.0=py_1
- tensorboard-data-server=0.6.0=py39hca6d32c_0
- tensorboard-plugin-wit=1.8.1=py39h06a4308_0
- tensorflow=2.7.0=cuda113py39h5fe7361_0
- tensorflow-estimator=2.7.0=cuda113py39h64e3112_0
- tensorflow-io-gcs-filesystem=999999=placeholder
- termcolor=1.1.0=py39h06a4308_1
- terminado=0.13.1=py39h06a4308_0
- testpath=0.6.0=py39h06a4308_0
- tk=8.6.12=h1ccaba5_0
- tornado=6.2=py39h5eee18b_0
- typing-extensions=4.3.0=py39h06a4308_0
- typing_extensions=4.3.0=py39h06a4308_0
- tzdata=2022c=h04d1e81_0
- urllib3=1.26.11=py39h06a4308_0
- wcmatch=8.2=pyhd8ed1ab_0
- wcwidth=0.2.5=pyhd3eb1b0_0
- webencodings=0.5.1=py39h06a4308_1
- werkzeug=2.0.3=pyhd3eb1b0_0
- wheel=0.37.1=pyhd3eb1b0_0
- wrapt=1.14.1=py39h5eee18b_0
- xz=5.2.6=h5eee18b_0
- yaml=0.2.5=h7b6447c_0
- yarl=1.8.1=py39h5eee18b_0
- zeromq=4.3.4=h2531618_0
- zipp=3.8.0=py39h06a4308_0
- zlib=1.2.12=h5eee18b_3
- pip:
- asttokens==2.0.8
- debugpy==1.6.3
- executing==1.1.1
- ipykernel==6.16.0
- ipython==8.5.0
- ipywidgets==8.0.2
- jinja2==3.1.2
- jupyter-client==7.4.2
- jupyterlab-widgets==3.0.3
- nest-asyncio==1.5.6
- nglview==3.0.1
- prompt-toolkit==3.0.31
- pyg-nightly==2.0.5.dev20220418
- pygments==2.13.0
- pyzmq==24.0.1
- stack-data==0.5.1
- torch==1.11.0+cu113
- torch-cluster==1.6.0
- torch-scatter==2.0.9
- torch-sparse==0.6.15
- torch-spline-conv==1.2.1
- torchaudio==0.11.0+cu113
- torchvision==0.12.0+cu113
- traitlets==5.4.0
- widgetsnbextension==4.0.3
It's most likely the version of torch-sparse. Try the torch-sparse==0.6.14.
Closing this now, feel free to reopen if problems remain.