容器环境下多体蛋白推理报错
环境及输入命令
环境：超算集群SothisAI容器
启动方式：参考光源docker pull，
实例化节点资源：单节点32核、100G、4*Z100
操作方式：
sudo su
cd /home
source env.sh
cd fastfold_pytorch
sh inference.py #此项通过
./inference_multimer.sh #此项报错蛋白质对齐报错
报错截图：
infer_multi脚本如下：
# add `--gpus [N]` to use N gpus for inference
# add `--enable_workflow` to use parallel workflow for data processing
# add `--use_precomputed_alignments [path_to_alignments]` to use precomputed msa
python3 inference.py SUGP1.fasta /public/home/jayfu/2024/data/pdb_mmcif/mmcif_files \
--output_dir ./ \
--gpus 1 \
--use_precomputed_alignments alignments/ \
--model_preset multimer \
--uniref90_database_path /public/home/jayfu/2024/data/uniref90/uniref90.fasta \
--mgnify_database_path /public/home/jayfu/2024/data/mgnify/mgy_clusters_2018_12.fa \
--pdb70_database_path /public/home/jayfu/2024/data/pdb70/pdb70 \
--uniclust30_database_path /public/home/jayfu/2024/data/uniclust30/uniclust30_2018_08/uniclust30_2018_08 \
--bfd_database_path /public/home/jayfu/2024/data/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
--uniprot_database_path /public/home/jayfu/2024/data/uniprot/uniprot_sprot.fasta \
--pdb_seqres_database_path /public/home/jayfu/2024/data/pdb_seqres/pdb_seqres.txt \
--param_path /data/params/params_model_1_multimer.npz \
--model_name model_1_multimer \
--jackhmmer_binary_path `which jackhmmer` \
--hhblits_binary_path `which hhblits` \
--hhsearch_binary_path `which hhsearch` \
--kalign_binary_path `which kalign` \
--chunk_size 4 \
--inplace \推理报错
对比光源提供的示例命令，发现没有传入对齐蛋白参数，注释该行后出现新的错误：
Colossalai should be built with cuda extension to use the FP16 optimizer
running in monomer mode...
Colossalai should be built with cuda extension to use the FP16 optimizer
WARNING: Logging before InitGoogleLogging() is written to STDERR
I1204 14:44:37.992952 2030 ProcessGroupNCCL.cpp:686] [Rank 0] ProcessGroupNCCL initialization options:NCCL_ASYNC_ERROR_HANDLING: 1, NCCL_DESYNC_DEBUG: 0, NCCL_ENABLE_TIMING: 0, NCCL_BLOCKING_WAIT: 0, TIMEOUT(ms): 1800000, USE_HIGH_PRIORITY_STREAM: 0, TORCH_DISTRIBUTED_DEBUG: OFF, NCCL_DEBUG: OFF, ID=93946160889344
I1204 14:44:37.995162 2030 ProcessGroupNCCL.cpp:686] [Rank 0] ProcessGroupNCCL initialization options:NCCL_ASYNC_ERROR_HANDLING: 1, NCCL_DESYNC_DEBUG: 0, NCCL_ENABLE_TIMING: 0, NCCL_BLOCKING_WAIT: 0, TIMEOUT(ms): 1800000, USE_HIGH_PRIORITY_STREAM: 0, TORCH_DISTRIBUTED_DEBUG: OFF, NCCL_DEBUG: OFF, ID=93946160915856
I1204 14:44:37.995922 2030 ProcessGroupNCCL.cpp:686] [Rank 0] ProcessGroupNCCL initialization options:NCCL_ASYNC_ERROR_HANDLING: 1, NCCL_DESYNC_DEBUG: 0, NCCL_ENABLE_TIMING: 0, NCCL_BLOCKING_WAIT: 0, TIMEOUT(ms): 1800000, USE_HIGH_PRIORITY_STREAM: 0, TORCH_DISTRIBUTED_DEBUG: OFF, NCCL_DEBUG: OFF, ID=93946160928768
I1204 14:44:37.996516 2030 ProcessGroupNCCL.cpp:686] [Rank 0] ProcessGroupNCCL initialization options:NCCL_ASYNC_ERROR_HANDLING: 1, NCCL_DESYNC_DEBUG: 0, NCCL_ENABLE_TIMING: 0, NCCL_BLOCKING_WAIT: 0, TIMEOUT(ms): 1800000, USE_HIGH_PRIORITY_STREAM: 0, TORCH_DISTRIBUTED_DEBUG: OFF, NCCL_DEBUG: OFF, ID=93946160941696
[12/04/24 14:44:38] INFO colossalai - colossalai - INFO: /root/miniconda3/envs/fastfold/lib/python3.10/site-packages/colossalai/context/parallel_context.py:521 set_device
INFO colossalai - colossalai - INFO: process rank 0 is bound to device 0
I1204 14:44:38.882680 2030 ProcessGroupNCCL.cpp:1340] NCCL_DEBUG: N/A
INFO colossalai - colossalai - INFO: /root/miniconda3/envs/fastfold/lib/python3.10/site-packages/colossalai/context/parallel_context.py:557 set_seed
INFO colossalai - colossalai - INFO: initialized seed on rank 0, numpy: 1024, python random: 1024, ParallelMode.DATA: 1024, ParallelMode.TENSOR: 1024,the default parallel seed is ParallelMode.DATA.
INFO colossalai - colossalai - INFO: /root/miniconda3/envs/fastfold/lib/python3.10/site-packages/colossalai/initialize.py:117 launch
INFO colossalai - colossalai - INFO: Distributed environment is initialized, data parallel size: 1, pipeline parallel size: 1, tensor parallel size: 1
Traceback (most recent call last):
File "/home/fastfold_pytorch/inference.py", line 564, in <module>
main(args)
File "/home/fastfold_pytorch/inference.py", line 167, in main
inference_monomer_model(args)
File "/home/fastfold_pytorch/inference.py", line 448, in inference_monomer_model
torch.multiprocessing.spawn(inference_model, nprocs=args.gpus, args=(args.gpus, result_q, batch, args))
File "/usr/local/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 246, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method="spawn")
File "/usr/local/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 202, in start_processes
while not context.join():
File "/usr/local/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 163, 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 "/usr/local/lib/python3.10/site-packages/torch/multiprocessing/spawn.py", line 74, in _wrap
fn(i, *args)
File "/home/fastfold_pytorch/inference.py", line 152, in inference_model
out = model(batch)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniconda3/envs/fastfold/lib/python3.10/site-packages/fastfold/model/hub/alphafold.py", line 524, in forward
outputs, m_1_prev, z_prev, x_prev = self.iteration(
File "/root/miniconda3/envs/fastfold/lib/python3.10/site-packages/fastfold/model/hub/alphafold.py", line 236, in iteration
m_1_prev, z_prev = self.recycling_embedder(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniconda3/envs/fastfold/lib/python3.10/site-packages/fastfold/model/fastnn/ops.py", line 1145, in forward
for i in range(0, para_dim, chunk_size):
UnboundLocalError: local variable 'para_dim' referenced before assignment
./inference_multimer.sh: line 9: --model_preset: command not found 请问有没有解决办法，以及我注意到代码仓库和镜像中均没有多体蛋白.npz参数，在哪里可以下载到