使用 tensorflow-gpu 后端导入 Keras 时出错（找不到 libcublas.so.10.0）
Posted
技术标签:
【中文标题】使用 tensorflow-gpu 后端导入 Keras 时出错（找不到 libcublas.so.10.0）【英文标题】：Error in importing Keras with tensorflow-gpu backend (can't find libcublas.so.10.0) 【发布时间】：2019-10-09 19:34:25 【问题描述】：我正在尝试运行 Keras 中包含的库，因为它非常耗电，我想使用 tensorflow-gpu 作为后端。 在导入期间，我收到此 ImportError
Using TensorFlow backend.
---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
~/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow.py in <module>
57
---> 58 from tensorflow.python.pywrap_tensorflow_internal import *
59 from tensorflow.python.pywrap_tensorflow_internal import __version__
~/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow_internal.py in <module>
27 return _mod
---> 28 _pywrap_tensorflow_internal = swig_import_helper()
29 del swig_import_helper
~/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow_internal.py in swig_import_helper()
23 try:
---> 24 _mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
25 finally:
~/.conda/envs/tensorflow/lib/python3.7/imp.py in load_module(name, file, filename, details)
241 else:
--> 242 return load_dynamic(name, filename, file)
243 elif type_ == PKG_DIRECTORY:
~/.conda/envs/tensorflow/lib/python3.7/imp.py in load_dynamic(name, path, file)
341 name=name, loader=loader, origin=path)
--> 342 return _load(spec)
343
ImportError: libcublas.so.10.0: cannot open shared object file: No such file or directory
During handling of the above exception, another exception occurred:
ImportError Traceback (most recent call last)
<ipython-input-11-bbde2f34164a> in <module>
2 from torch.optim import Adam
3 from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
----> 4 from keras.preprocessing.sequence import pad_sequences
5 from sklearn.model_selection import train_test_split
6 from pytorch_pretrained_bert import BertTokenizer, BertConfig
~/.conda/envs/tensorflow/lib/python3.7/site-packages/keras/__init__.py in <module>
1 from __future__ import absolute_import
2
----> 3 from . import utils
4 from . import activations
5 from . import applications
~/.conda/envs/tensorflow/lib/python3.7/site-packages/keras/utils/__init__.py in <module>
4 from . import data_utils
5 from . import io_utils
----> 6 from . import conv_utils
7
8 # Globally-importable utils.
~/.conda/envs/tensorflow/lib/python3.7/site-packages/keras/utils/conv_utils.py in <module>
7 from six.moves import range
8 import numpy as np
----> 9 from .. import backend as K
10
11
~/.conda/envs/tensorflow/lib/python3.7/site-packages/keras/backend/__init__.py in <module>
87 elif _BACKEND == 'tensorflow':
88 sys.stderr.write('Using TensorFlow backend.\n')
---> 89 from .tensorflow_backend import *
90 else:
91 # Try and load external backend.
~/.conda/envs/tensorflow/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py in <module>
3 from __future__ import print_function
4
----> 5 import tensorflow as tf
6 from tensorflow.python.framework import ops as tf_ops
7 from tensorflow.python.training import moving_averages
~/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/__init__.py in <module>
22
23 # pylint: disable=g-bad-import-order
---> 24 from tensorflow.python import pywrap_tensorflow # pylint: disable=unused-import
25
26 from tensorflow._api.v1 import app
~/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/__init__.py in <module>
47 import numpy as np
48
---> 49 from tensorflow.python import pywrap_tensorflow
50
51 # Protocol buffers
~/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow.py in <module>
72 for some common reasons and solutions. Include the entire stack trace
73 above this error message when asking for help.""" % traceback.format_exc()
---> 74 raise ImportError(msg)
75
76 # pylint: enable=wildcard-import,g-import-not-at-top,unused-import,line-too-long
ImportError: Traceback (most recent call last):
File "/home/canniz/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow.py", line 58, in <module>
from tensorflow.python.pywrap_tensorflow_internal import *
File "/home/canniz/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 28, in <module>
_pywrap_tensorflow_internal = swig_import_helper()
File "/home/canniz/.conda/envs/tensorflow/lib/python3.7/site-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 24, in swig_import_helper
_mod = imp.load_module('_pywrap_tensorflow_internal', fp, pathname, description)
File "/home/canniz/.conda/envs/tensorflow/lib/python3.7/imp.py", line 242, in load_module
return load_dynamic(name, filename, file)
File "/home/canniz/.conda/envs/tensorflow/lib/python3.7/imp.py", line 342, in load_dynamic
return _load(spec)
ImportError: libcublas.so.10.0: cannot open shared object file: No such file or directory
Failed to load the native TensorFlow runtime.
我在这里看到 --> ImportError: libcublas.so.10.0: cannot open shared object file: No such file or director 问题可能是 CUDA 版本与 tensorflow GPU 不兼容。
所以现在我的问题如下：
Tensorflow GPU 版本为 1.13
我已经安装了 CUDA 10.0（按照兼容性说明）和相关的 Cudnn 实际上是我从 nvcc --version 得到的
是
`nvcc：NVIDIA (R) Cuda 编译器驱动程序
版权所有 (c) 2005-2018 NVIDIA Corporation
建于 Sat_Aug_25_21:08:01_CDT_2018
Cuda 编译工具，10.0 版，V10.0.130
我安装了运行 sudo apt-get install nvidia-driver-430 的 Nvidia 驱动程序（这应该是我的 Nvidia-GeForce-930mX 的正确版本）
如您所见，CUDA 版本为 10.2。这怎么可能？ 是否有可能安装 Nvidia 驱动程序，它会自动将 CUDA 驱动程序设置为 10.2，然后我手动安装了 CUDA 工具包 10.0，所以现在 Tensorflow（或更具体地说是使用 tf 后端的 Keras）查看 CUDA DRIVER 版本？
我能做什么？降级Nvidia驱动程序？安全吗？是否可以仅降级 CUDA 驱动程序？
【问题讨论】：
【参考方案1】：您可以尝试卸载 tensorflow：
pip uninstall tensorflow-gpu
并安装它的旧版本：
pip install tensorflow-gpu==1.12.0
【讨论】：
不知道为什么有人给你“-1”，居然解决了问题！谢谢 啊哈，我也不知道，但很高兴能帮到你！以上是关于使用 tensorflow-gpu 后端导入 Keras 时出错（找不到 libcublas.so.10.0）的主要内容，如果未能解决你的问题，请参考以下文章
如何降级使用 tensorflow-gpu 安装的 hdf5
是否有 R 命令使 Keras Tensorflow-GPU 在 CPU 上运行？
在 ubuntu18.04 中导入错误 tensorflow-gpu