ml4bio / Dense-Homolog-Retrieval

Nature Biotechnology: Ultra-fast, sensitive detection of protein remote homologs using deep dense retrieval
BSD 3-Clause "New" or "Revised" License
83 stars 1 forks source link

Error with embedding #17

Closed anuC closed 1 month ago

anuC commented 1 month ago

Hi,

I am experiencing the following error while doing the embedding,

(fastMSA) csl:~/Dense-Homolog-Retrieval$ python3 do_embedding.py trainer.ur90_path=/home/csl/D ense-Homolog-Retrieval/Uniref90_db/uniref90.tsv model.ckpt_path=/home/csl/Dense-Homolog-Retrieval/dhr2_ckpt hydra.run.dir=/home/csl/Dense-Homolog-Retrieval/OUTPUT Global seed set to 1234 /home/csl/Dense-Homolog-Retrieval/dhr2_ckpt [2024-09-06 12:18:38,598][torch.distributed.nn.jit.instantiator][INFO] - Created a temporary directory at /tmp/tmptgxvq3q2 [2024-09-06 12:18:38,599][torch.distributed.nn.jit.instantiator][INFO] - Writing /tmp/tmptgxvq3q2/_remote_module_non_sriptable.py Error executing job with overrides: ['trainer.ur90_path=/home/csl/Dense-Homolog-Retrieval/Uniref90_db/uniref90.tsv', 'model.ckpt_path=/home/csl/Dense-Homolog-Retrieval/dhr2_ckpt'] Traceback (most recent call last): File "do_embedding.py", line 56, in main trainer = pl.Trainer( File "/home/csl/miniconda3_INSTALL/envs/fastMSA/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/env_vars_connector.py", line 38, in insert_env_defaults return fn(self, **kwargs) File "/home/csl/miniconda3_INSTALL/envs/fastMSA/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 431, in init self._accelerator_connector = AcceleratorConnector( File "/home/csl/miniconda3_INSTALL/envs/fastMSA/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py", line 161, in init self.select_accelerator_type() File "/home/csl/miniconda3_INSTALL/envs/fastMSA/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py", line 228, in select_accelerator_type raise MisconfigurationException(f"You passed accelerator='gpu', but {msg}.") pytorch_lightning.utilities.exceptions.MisconfigurationException: You passed accelerator='gpu', but GPUs are not available.

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace. (fastMSA) csl:~/Dense-Homolog-Retrieval$

Any help would be highly appreciated.

Thanks in advance

heathcliff233 commented 1 month ago

Hello, it seems that your GPU is not available. Please make sure that you are on a machine with Nvidia GPU and created the environment correctly.