Ошибка Py_call_impl с Tensorflow и RMSprop - PullRequest
Новая
       6

Ошибка Py_call_impl с Tensorflow и RMSprop

0 голосов
/ 02 августа 2020

Я пытаюсь запустить пакет (через R4.0.2 - SAVERX - https://github.com/jingshuw/SAVERX), который использует sctransfer в качестве основы (https://github.com/jingshuw/sctransfer). И я столкнулся с этой ошибкой относительно rmsprop: 

[1] "Use a pretrained model: No"
[1] "Processed file saved as: 1596347497.19716/tmpdata.rds"
[1] "Data preprocessed ..."
2020-08-02 08:51:45.539119: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/R/lib:/usr/lib/x86_64-linux-gnu:/usr/lib/jvm/default-java/lib/server
2020-08-02 08:51:45.539149: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
//usr/local/lib/python3.8/dist-packages/scanpy/api/__init__.py:3: FutureWarning: 

In a future version of Scanpy, `scanpy.api` will be removed.
Simply use `import scanpy as sc` and `import scanpy.external as sce` instead.

  warnings.warn(
[1] "Python module sctransfer imported ..."
[1] "Cross-validation round: 1"
2020-08-02 08:51:48.615482: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/lib/R/lib:/usr/lib/x86_64-linux-gnu:/usr/lib/jvm/default-java/lib/server
2020-08-02 08:51:48.615506: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
2020-08-02 08:51:48.615521: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (TJC-Ubuntu): /proc/driver/nvidia/version does not exist
2020-08-02 08:51:48.615698: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-08-02 08:51:48.621149: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 1999965000 Hz
2020-08-02 08:51:48.621392: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55b0b3ac1b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-08-02 08:51:48.621406: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Error in py_call_impl(callable, dots$args, dots$keywords) : 
  KeyError: 'rmsprop'

Detailed traceback: 
  File "//usr/local/lib/python3.8/dist-packages/sctransfer/api.py", line 84, in autoencode
    loss = train(adata[adata.obs.DCA_split == 'train'],
  File "//usr/local/lib/python3.8/dist-packages/sctransfer/train.py", line 46, in train
    optimizer = opt.__dict__[optimizer](clipvalue=clip_grad)
Timing stopped at: 1.494 0.035 1.501

Есть ли какой-нибудь очевидный способ отладить это или исправить это, не дожидаясь ответа автора?

...