gcorso
unable to execute
installed as per the given instruction conda create --name diffdock python=3.9 conda activate diffdock conda install pytorch==1.11.0 pytorch-cuda=11.7 -c pytorch -c nvidia pip install torch-scatter torch-sparse torch-cluster torch-spline-conv torch-geometric==2.0.4 -f https://data.pyg.org/whl/torch-1.11.0+cu117.html python -m pip install PyYAML scipy "networkx[default]" biopython rdkit-pypi e3nn spyrmsd pandas biopandas pip install "fair-esm[esmfold]" pip install 'dllogger @ git+https://github.com/NVIDIA/dllogger.git' pip install 'openfold @ git+https://github.com/aqlaboratory/openfold.git@4b41059694619831a7db195b7e0988fc4ff3a307'
(diffdock) debanjan@debanjan:~/Downloads/DiffDock-main$ python -m inference --protein_ligand_csv data/protein_ligand_example_csv.csv --out_dir results/user_predictions_small --inference_steps 20 --samples_per_complex 40 --batch_size 10 --actual_steps 18 --no_final_step_noise /home/debanjan/Downloads/DiffDock-main/inference.py:8: DeprecationWarning: Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0), (to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries) but was not found to be installed on your system. If this would cause problems for you, please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466
import pandas as pd
Segmentation fault (core dumped)
System Info
Linux Mint OS
RTX 2070 GPU
(diffdock) debanjan@debanjan:~/Downloads/DiffDock-main$ nvidia-smi
Mon Feb 19 22:06:04 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.154.05 Driver Version: 535.154.05 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 2070 ... On | 00000000:01:00.0 On | N/A |
| 33% 37C P8 6W / 215W | 365MiB / 8192MiB | 2% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 1110 G /usr/lib/xorg/Xorg 157MiB | | 0 N/A N/A 1531 G cinnamon 52MiB | | 0 N/A N/A 8646 G /usr/lib/firefox/firefox 152MiB | +---------------------------------------------------------------------------------------+
I figured out that a lib probably missing so installed that pip install pyarrow pip install --upgrade pandas pyarrow
but still encountered by the error python -m inference --protein_ligand_csv data/protein_ligand_example_csv.csv --out_dir results/user_predictions_small --inference_steps 20 --samples_per_complex 40 --batch_size 10 --actual_steps 18 --no_final_step_noise Segmentation fault (core dumped)
Having the same issue, but for me it errors on importing torch_geometric: -> from torch_geometric.loader import DataLoader (Pdb) Segmentation fault (core dumped)
pip show torch_geometric Name: torch-geometric Version: 2.0.4
Edit: Figured out this is an issue with python compatibility with the libraries (maybe the python version in the readme was changed recently without changing the packages to install?) My fix:
Follow the readme except alter these two lines:
conda install pytorch==1.11.0 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install torch-scatter torch-sparse torch-cluster torch-spline-conv torch-geometric==2.0.4 -f https://data.pyg.org/whl/torch-1.11.0+cu117.html
Becomes:
conda install pytorch==1.13.0 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install torch-scatter==2.0.9 torch-sparse==0.6.15 torch-cluster==1.6.0 torch-spline-conv==1.2.1 torch-geometric==2.0.4 -f https://data.pyg.org/whl/torch-1.13.0+cu117.html
Having the same issue, but for me it errors on importing torch_geometric: -> from torch_geometric.loader import DataLoader (Pdb) Segmentation fault (core dumped)
pip show torch_geometric Name: torch-geometric Version: 2.0.4
Edit: Figured out this is an issue with python compatibility with the libraries (maybe the python version in the readme was changed recently without changing the packages to install?) My fix:
Follow the readme except alter these two lines:
conda install pytorch==1.11.0 pytorch-cuda=11.7 -c pytorch -c nvidia pip install torch-scatter torch-sparse torch-cluster torch-spline-conv torch-geometric==2.0.4 -f https://data.pyg.org/whl/torch-1.11.0+cu117.htmlBecomes:
conda install pytorch==1.13.0 pytorch-cuda=11.7 -c pytorch -c nvidia pip install torch-scatter==2.0.9 torch-sparse==0.6.15 torch-cluster==1.6.0 torch-spline-conv==1.2.1 torch-geometric==2.0.4 -f https://data.pyg.org/whl/torch-1.13.0+cu117.html
This worked for me. Thanks!!
I add a pull request to fix the error. https://github.com/gcorso/DiffDock/pull/214
