Describe the bug
Getting an error during import of dgl with sagemaker studio for the above notebook. I was getting this error with a GNN based notebook I am trying to run.
I decided to first run a notebook that's known to work but hit the same error.
To reproduce
create a jupyterstudio notebook and run the appropriate cells from link above. Since the requirements file has an year old versions I just replace the the requirements.txt to pick the latest version.
Logs
---------------------------------------------------------------------------
FileNotFoundError Traceback (most recent call last)
Cell In[1], line 7
4 import torch.nn as nn
5 import pandas as pd
----> 7 import dgl
9 from dgllife.model import load_pretrained
10 from dgllife.utils import smiles_to_bigraph, EarlyStopping, Meter, CanonicalAtomFeaturizer, CanonicalBondFeaturizer
File [/opt/conda/lib/python3.10/site-packages/dgl/__init__.py:16](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/__init__.py#line=15)
13 from .logging import enable_verbose_logging # usort: skip
14 from .backend import backend_name, load_backend # usort: skip
---> 16 from . import (
17 container,
18 cuda,
19 dataloading,
20 function,
21 ops,
22 random,
23 sampling,
24 storages,
25 )
26 from ._ffi.base import __version__, DGLError
27 from ._ffi.function import (
28 extract_ext_funcs,
29 get_global_func,
30 list_global_func_names,
31 register_func,
32 )
File [/opt/conda/lib/python3.10/site-packages/dgl/dataloading/__init__.py:13](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/dataloading/__init__.py#line=12)
11 if F.get_preferred_backend() == "pytorch":
12 from .spot_target import *
---> 13 from .dataloader import *
14 from .dist_dataloader import *
File [/opt/conda/lib/python3.10/site-packages/dgl/dataloading/dataloader.py:27](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/dataloading/dataloader.py#line=26)
25 from ..batch import batch as batch_graphs
26 from ..cuda import GPUCache
---> 27 from ..distributed import DistGraph
28 from ..frame import LazyFeature
29 from ..heterograph import DGLGraph
File [/opt/conda/lib/python3.10/site-packages/dgl/distributed/__init__.py:5](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/distributed/__init__.py#line=4)
3 from .dist_context import exit_client, initialize
4 from .dist_dataloader import DistDataLoader
----> 5 from .dist_graph import DistGraph, DistGraphServer, edge_split, node_split
6 from .dist_tensor import DistTensor
7 from .graph_partition_book import GraphPartitionBook, PartitionPolicy
File [/opt/conda/lib/python3.10/site-packages/dgl/distributed/dist_graph.py:11](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/distributed/dist_graph.py#line=10)
7 from collections.abc import MutableMapping
9 import numpy as np
---> 11 from .. import backend as F, graphbolt as gb, heterograph_index
12 from .._ffi.ndarray import empty_shared_mem
13 from ..base import ALL, DGLError, EID, ETYPE, is_all, NID
File [/opt/conda/lib/python3.10/site-packages/dgl/graphbolt/__init__.py:55](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/graphbolt/__init__.py#line=54)
51 except Exception: # pylint: disable=W0703
52 raise ImportError("Cannot load Graphbolt C++ library")
---> 55 load_graphbolt()
File [/opt/conda/lib/python3.10/site-packages/dgl/graphbolt/__init__.py:45](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/graphbolt/__init__.py#line=44), in load_graphbolt()
43 path = os.path.join(dirname, "graphbolt", basename)
44 if not os.path.exists(path):
---> 45 raise FileNotFoundError(
46 f"Cannot find DGL C++ graphbolt library at {path}"
47 )
49 try:
50 torch.classes.load_library(path)
FileNotFoundError: Cannot find DGL C++ graphbolt library at [/opt/conda/lib/python3.10/site-packages/dgl/graphbolt/libgraphbolt_pytorch_2.0.0.post101.so](https://ibsxitneoy2oj4t.studio.us-east-2.sagemaker.aws/opt/conda/lib/python3.10/site-packages/dgl/graphbolt/libgraphbolt_pytorch_2.0.0.post101.so)
Link to the notebook https://github.com/aws-samples/aws-healthcare-lifescience-ai-ml-sample-notebooks/blob/main/workshops/Molecular-property-prediction/hiv-inhibitor-prediction-dgl/molecule-hiv-inhibitor-prediction-sagemaker.ipynb
Describe the bug Getting an error during import of dgl with sagemaker studio for the above notebook. I was getting this error with a GNN based notebook I am trying to run.
I decided to first run a notebook that's known to work but hit the same error.
To reproduce create a jupyterstudio notebook and run the appropriate cells from link above. Since the requirements file has an year old versions I just replace the the requirements.txt to pick the latest version.
Logs