tensorflow - Alphafold 核心转储

Question

我按照https://github.com/kuixu/alphafold的建议安装了 Alphafold 算法 但是我收到以下错误：

I0826 12:08:54.630447 139693760276288 xla_bridge.py:236] Unable to initialize backend 'tpu_driver': Not found: Unable to find driver in registry given worker: 
I0826 12:08:54.727063 139693760276288 xla_bridge.py:236] Unable to initialize backend 'tpu': Invalid argument: TpuPlatform is not available.

接着

I0826 14:47:31.789251 139693760276288 run_alphafold.py:185] Running model model_1
WARNING:tensorflow:From /home/zapata/alphafold/alphafold/model/tf/input_pipeline.py:151: calling map_fn (from tensorflow.python.ops.map_fn) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Use fn_output_signature instead
W0826 14:47:32.193996 139693760276288 deprecation.py:528] From /home/zapata/alphafold/alphafold/model/tf/input_pipeline.py:151: calling map_fn (from tensorflow.python.ops.map_fn) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Use fn_output_signature instead
I0826 14:47:37.243475 139693760276288 model.py:132] Running predict with shape(feat) = {'aatype': (4, 485), 'residue_index': (4, 485), 'seq_length': (4,), 'template_aatype': (4, 4, 485), 'template_all_atom_masks': (4, 4, 485, 37), 'template_all_atom_positions': (4, 4, 485, 37, 3), 'template_sum_probs': (4, 4, 1), 'is_distillation': (4,), 'seq_mask': (4, 485), 'msa_mask': (4, 508, 485), 'msa_row_mask': (4, 508), 'random_crop_to_size_seed': (4, 2), 'template_mask': (4, 4), 'template_pseudo_beta': (4, 4, 485, 3), 'template_pseudo_beta_mask': (4, 4, 485), 'atom14_atom_exists': (4, 485, 14), 'residx_atom14_to_atom37': (4, 485, 14), 'residx_atom37_to_atom14': (4, 485, 37), 'atom37_atom_exists': (4, 485, 37), 'extra_msa': (4, 5120, 485), 'extra_msa_mask': (4, 5120, 485), 'extra_msa_row_mask': (4, 5120), 'bert_mask': (4, 508, 485), 'true_msa': (4, 508, 485), 'extra_has_deletion': (4, 5120, 485), 'extra_deletion_value': (4, 5120, 485), 'msa_feat': (4, 508, 485, 49), 'target_feat': (4, 485, 22)}
2021-08-26 14:48:24.665668: E external/org_tensorflow/tensorflow/stream_executor/cuda/cuda_blas.cc:226] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED
2021-08-26 14:48:24.665708: F external/org_tensorflow/tensorflow/compiler/xla/service/gpu/gemm_algorithm_picker.cc:113] Check failed: stream->parent()->GetBlasGemmAlgorithms(&algorithms) 
Fatal Python error: Aborted

Current thread 0x00007f0cfcf56740 (most recent call first):
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/interpreters/xla.py", line 385 in backend_compile
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/interpreters/xla.py", line 81 in compile_or_get_cached
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/interpreters/xla.py", line 772 in _xla_callable
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/linear_util.py", line 262 in memoized_fun
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/interpreters/xla.py", line 619 in _xla_call_impl
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/core.py", line 613 in process_call
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/core.py", line 1617 in process
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/core.py", line 1605 in call_bind
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/core.py", line 1614 in bind
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/_src/api.py", line 405 in cache_miss
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/jax/_src/traceback_util.py", line 162 in reraise_with_filtered_traceback
  File "/home/zapata/alphafold/alphafold/model/model.py", line 134 in predict
  File "run_alphafold.py", line 192 in predict_structure
  File "run_alphafold.py", line 310 in main
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/absl/app.py", line 258 in _run_main
  File "/home/zapata/anaconda3/envs/af2/lib/python3.8/site-packages/absl/app.py", line 312 in run
  File "run_alphafold.py", line 338 in <module>
Aborted (core dumped)

我不明白这个错误。我有 nvidia455 和 cuda 11.1。如果有任何帮助，我将不胜感激。

标签： tensorflowpython-3.8coredump