无法加载动态库“libnvinfer.so.6”

Question

我正在尝试正常导入 TensorFlow python 包，但出现以下错误：

这是上面终端图像中的文本：

2020-02-23 19:01:06.163940: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer.so.6'; dlerror: libnvinfer.so.6: cannot open shared object file: No such file or directory
2020-02-23 19:01:06.164019: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer_plugin.so.6'; dlerror: libnvinfer_plugin.so.6: cannot open shared object file: No such file or directory
2020-02-23 19:01:06.164030: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:30] Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
<module 'tensorflow_core._api.v2.version' from '/home/saman/miniconda3/envs/testconda/lib/python3.7/site-packages/tensorflow_core/_api/v2/version/__init__.py'

Answer 1

这是警告，而不是错误。您仍然可以使用 TensorFlow。共享库libnvinfer和libnvinfer_plugin是可选的，仅当您使用 nvidia 的 TensorRT 功能时才需要。

TensorFlow 的安装说明列出了 GPU 依赖项：

您的系统上必须安装以下 NVIDIA® 软件：

• NVIDIA® GPU 驱动程序 — CUDA 10.1 需要 418.x 或更高版本。
• CUDA® 工具包——TensorFlow 支持 CUDA 10.1 (TensorFlow >= 2.1.0)
• CUPTI 随 CUDA 工具包一起提供。
• cuDNN SDK (>= 7.6)
• （可选）TensorRT 6.0 可改善某些模型的推理延迟和吞吐量。

您可以使用以下命令（取自TensorFlow 文档）在 Ubuntu 18.04 上安装这些：

# Add NVIDIA package repositories
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-repo-ubuntu1804_10.1.243-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1804_10.1.243-1_amd64.deb
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
sudo apt-get update
wget http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/nvidia-machine-learning-repo-ubuntu1804_1.0.0-1_amd64.deb
sudo apt install ./nvidia-machine-learning-repo-ubuntu1804_1.0.0-1_amd64.deb
sudo apt-get update

# Install NVIDIA driver
sudo apt-get install --no-install-recommends nvidia-driver-430
# Reboot. Check that GPUs are visible using the command: nvidia-smi

# Install development and runtime libraries (~4GB)
sudo apt-get install --no-install-recommends \
    cuda-10-1 \
    libcudnn7=7.6.4.38-1+cuda10.1  \
    libcudnn7-dev=7.6.4.38-1+cuda10.1


# Install TensorRT. Requires that libcudnn7 is installed above.
sudo apt-get install -y --no-install-recommends libnvinfer6=6.0.1-1+cuda10.1 \
    libnvinfer-dev=6.0.1-1+cuda10.1 \
    libnvinfer-plugin6=6.0.1-1+cuda10.1

Answer 2

由于（意外）更新 libvnifer6 软件包，我收到此警告。它已更新为6.0.1-1+cuda10.2使用原始安装时的6.0.1-1+cuda10.1。

在我卸载引用的包cuda10.2并重新运行后

sudo apt-get install -y --no-install-recommends libnvinfer6=6.0.1-1+cuda10.1 \
    libnvinfer-dev=6.0.1-1+cuda10.1 \
    libnvinfer-plugin6=6.0.1-1+cuda10.1

这个警告消失了。