Error while running Chignolin tutorial.

[dondavidsb]

Hi, I am trying to run the tutorial. I don't know how to solve the following error, arises when running the train.py step:

ERROR:

/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchvision/image.so: undefined symbol: _ZN3c107WarningC1ENS_7variantIJNS0_11UserWarningENS0_18DeprecationWarningEEEERKNS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEEb'If you don't plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
warn(
Traceback (most recent call last):
File "/home/poasibrd/berlin/torchmd-net/scripts/train.py", line 12, in
from torchmdnet.module import LNNP
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchmdnet/module.py", line 10, in
from torchmdnet.models.model import create_model, load_model
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchmdnet/models/model.py", line 6, in
from torchmdnet.models import output_modules
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchmdnet/models/output_modules.py", line 5, in
from torchmdnet.models.utils import act_class_mapping, GatedEquivariantBlock, scatter
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchmdnet/models/utils.py", line 6, in
from torchmdnet.extensions import get_neighbor_pairs_kernel
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torchmdnet/extensions/init.py", line 115, in
dynamo.disallow_in_graph(get_neighbor_pairs_kernel)
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torch/_dynamo/decorators.py", line 138, in disallow_in_graph
return _disallow_in_graph_helper(throw_if_not_allowed=True)(fn)
File "/home/poasibrd/anaconda3/envs/david/lib/python3.10/site-packages/torch/_dynamo/decorators.py", line 106, in inner
raise IncorrectUsage(
torch._dynamo.exc.IncorrectUsage: disallow_in_graph is expected to be used on an already allowed callable (like torch.* ops). Allowed callables means callables that TorchDynamo puts as-is in the extracted graph.

Thank you.