Uni-Mol numpy version

[favor2021]

I am facing the issue of

`No other smiles inputs
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
ImportError: numpy.core._multiarray_umath failed to import
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
RuntimeError: module compiled against API version 0x10 but this version of numpy is 0xe . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem .
2024-08-28 14:01:18 | INFO | unicore.distributed.utils | distributed init (rank 0): tcp://localhost:18393
2024-08-28 14:01:18 | INFO | unicore.distributed.utils | distributed init (rank 1): tcp://localhost:18393
2024-08-28 14:01:18 | INFO | torch.distributed.distributed_c10d | Added key: store_based_barrier_key:1 to store for rank: 1
2024-08-28 14:01:18 | INFO | torch.distributed.distributed_c10d | Added key: store_based_barrier_key:1 to store for rank: 0
2024-08-28 14:01:18 | INFO | torch.distributed.distributed_c10d | Rank 0: Completed store-based barrier for key:store_based_barrier_key:1 with 2 nodes.
2024-08-28 14:01:18 | INFO | unicore.distributed.utils | initialized host 27d257810fc0 as rank 0
2024-08-28 14:01:18 | INFO | torch.distributed.distributed_c10d | Rank 1: Completed store-based barrier for key:store_based_barrier_key:1 with 2 nodes.
2024-08-28 14:01:18 | INFO | unicore.distributed.utils | initialized host 27d257810fc0 as rank 1
Traceback (most recent call last):
File "./Uni-Mol/unimol/unimol/infer.py", line 120, in
cli_main()
File "./Uni-Mol/unimol/unimol/infer.py", line 116, in cli_main
distributed_utils.call_main(args, main)
File "/opt/conda/lib/python3.8/site-packages/unicore-0.0.1-py3.8-linux-x86_64.egg/unicore/distributed/utils.py", line 180, in call_main
torch.multiprocessing.spawn(
File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 240, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 198, in start_processes
while not context.join():
File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 160, in join
raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 0 terminated with the following error:
Traceback (most recent call last):
File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 69, in _wrap
fn(i, *args)
File "/opt/conda/lib/python3.8/site-packages/unicore-0.0.1-py3.8-linux-x86_64.egg/unicore/distributed/utils.py", line 158, in distributed_main
args.distributed_rank = distributed_init(args)
File "/opt/conda/lib/python3.8/site-packages/unicore-0.0.1-py3.8-linux-x86_64.egg/unicore/distributed/utils.py", line 138, in distributed_init
dist.all_reduce(torch.zeros(1).cuda())
RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
`

It seems to be related to a numpy version problem. I am encountering this issue while trying to run unimol_binding_pose_demo from Uni-Mol. I would appreciate any guidance on how to resolve this.

[ZhouGengmo]

You can try reinstall numpy

pip uninstall numpy
pip install numpy

And for this, you can use a smaller batch_size.

RuntimeError: CUDA error: out of memory

[favor2021]

You can try reinstall numpy

pip uninstall numpy
pip install numpy

And for this, you can use a smaller batch_size.

RuntimeError: CUDA error: out of memory

@ZhouGengmo Thank you very much for your attention and response to the problem I am having.
I've tried all of the solutions you've provided and encountered the same error about numpy version, and as for the CUDA issue, I ran the code on a higher capacity GPU and no longer get the error.

[ZhouGengmo]

Or you can choose to run it in a Docker container.
https://github.com/deepmodeling/Uni-Mol/tree/main/unimol#dependencies