You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I get this message: "No compatible CUDA device is available". As there are 2 environments, I'm not sure under which one I get it, how to solve the problem. I still get results, are they still ok? Why do we need 2 environments, they cannot be merged?
Here is how I built the environment:
To create dynamicbind env:
conda activate dynamicbind
export MKL_THREADING_LAYER=GNU #needed this as I have an AMD CPU
python run_single_protein_inference.py protein.pdb ligand.csv --savings_per_complex 40 --inference_steps 20 --header test --device 0 --paper --python /home/christian/anaconda3/envs/dynamicbind/bin/python --relax_python /home/christian/anaconda3/envs/relax/bin/python
The error I get:
...
Skipped 0 complexes
Results are in results/test
inference complete.
0%| | 0/40 [00:00<?, ?it/s]No compatible CUDA device is available
No compatible CUDA device is available
2%|█ | 1/40 [00:03<02:33, 3.94s/it]No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
5%|██▏ | 2/40 [00:04<01:12, 1.91s/it]No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
15%|██████▌ | 6/40 [00:09<00:45, 1.34s/it]No compatible CUDA device is available
100%|███████████████████████████████████████████| 40/40 [00:12<00:00, 3.28it/s]
final step structure relax complete.
The text was updated successfully, but these errors were encountered:
Hi,
I get this message: "No compatible CUDA device is available". As there are 2 environments, I'm not sure under which one I get it, how to solve the problem. I still get results, are they still ok? Why do we need 2 environments, they cannot be merged?
Here is how I built the environment:
To create dynamicbind env:
conda create -n dynamicbind python=3.10
conda activate dynamicbind
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia
conda install rdkit==2022.03.5 -c conda-forge
conda install pyg==2.3.0 pyyaml==6.0 biopython==1.78 -c pyg
pip install pyg_lib==0.2.0 torch_scatter==2.1.1 torch_sparse==0.6.17 torch_cluster==1.6.1 torch_spline_conv==1.2.2 -f https://data.pyg.org/whl/torch-2.0.1+cu117.html
pip install e3nn==0.5.1 fair-esm==2.0.0 spyrmsd==0.5.2
To create relax env:
conda create --name relax python=3.8
conda activate relax
conda install -c conda-forge openmm pdbfixer libstdcxx-ng openmmforcefields openff-toolkit ambertools=22 compilers biopython==1.78
to run:
conda activate dynamicbind
export MKL_THREADING_LAYER=GNU #needed this as I have an AMD CPU
python run_single_protein_inference.py protein.pdb ligand.csv --savings_per_complex 40 --inference_steps 20 --header test --device 0 --paper --python /home/christian/anaconda3/envs/dynamicbind/bin/python --relax_python /home/christian/anaconda3/envs/relax/bin/python
The error I get:
...
Skipped 0 complexes
Results are in results/test
inference complete.
0%| | 0/40 [00:00<?, ?it/s]No compatible CUDA device is available
No compatible CUDA device is available
2%|█ | 1/40 [00:03<02:33, 3.94s/it]No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
5%|██▏ | 2/40 [00:04<01:12, 1.91s/it]No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
15%|██████▌ | 6/40 [00:09<00:45, 1.34s/it]No compatible CUDA device is available
100%|███████████████████████████████████████████| 40/40 [00:12<00:00, 3.28it/s]
final step structure relax complete.
The text was updated successfully, but these errors were encountered: