# Could not load dynamic library 'libnvinfer.so.7' **URL:** \ **Category:** TensorRT\ **Tags:** tensorrt, cuda, python\ **Created:** [May 29, 2023, 3:14am UTC](https://forums.developer.nvidia.com/t/could-not-load-dynamic-library-libnvinfer-so-7/254736 "2023-05-29T03:14:38Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![joguiguma](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/joguiguma/32/254543_2.png) [@joguiguma](https://forums.developer.nvidia.com/u/joguiguma)\ **Post date:** [May 29, 2023, 3:14am UTC](https://forums.developer.nvidia.com/t/could-not-load-dynamic-library-libnvinfer-so-7/254736/1 "2023-05-29T03:14:38Z")
## Description I have a laptop with Ubuntu 20 Geforce RTX 3060, drivers 470, cuda 11.4, CUDNN 8.1, Python 3.8 and Tensorflow 2.10, I hace also instaled tensoRT using: pip install nvidia-pyindex pip install nvidia-tensorrt When I try to run tensorflow I have te next messages: 2023-05-28 22:08:39.240187: W tensorflow/stream\_executor/platform/default/dso\_loader.cc:64] Could not load dynamic library ‘libnvinfer.so.7’; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD\_LIBRARY\_PATH: /usr/local/cuda/lib64 2023-05-28 22:08:39.240222: W tensorflow/stream\_executor/platform/default/dso\_loader.cc:64] Could not load dynamic library ‘libnvinfer\_plugin.so.7’; dlerror: libnvinfer\_plugin.so.7: cannot open shared object file: No such file or directory; LD\_LIBRARY\_PATH: /usr/local/cuda/lib64 2023-05-28 22:08:39.240226: W tensorflow/compiler/tf2tensorrt/utils/py\_utils.cc:38] TF-TRT Warning: 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. I read a lot of blog however I could not solve this problema. ## Environment **TensorRT Version** : **GPU Type** : **Nvidia Driver Version** : **CUDA Version** : **CUDNN Version** : **Operating System + Version** : **Python Version (if applicable)**: **TensorFlow Version (if applicable)**: **PyTorch Version (if applicable)**: **Baremetal or Container (if container which image + tag)**: ## Relevant Files Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.) ## Steps To Reproduce Please include: - Exact steps/commands to build your repro - Exact steps/commands to run your repro - Full traceback of errors encountered ---
**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\ **Post date:** [May 30, 2023, 10:01am UTC](https://forums.developer.nvidia.com/t/could-not-load-dynamic-library-libnvinfer-so-7/254736/5 "2023-05-30T10:01:00Z")
Hi, It looks like some TensorRT is not correctly installed. Please refer to the installation steps from the below link if in case you are missing on anything > **[Installation Guide :: NVIDIA Deep Learning TensorRT Documentation](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html)** > > This NVIDIA TensorRT 8.6.1 Installation Guide provides the installation requirements, a list of what is included in the TensorRT package, and step-by-step instructions for installing TensorRT. Also, we suggest you use TRT NGC containers to avoid any system dependency related issues. > **[TensorRT | NVIDIA NGC](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tensorrt)** > > NVIDIA TensorRT is a C++ library that facilitates high-performance inference on NVIDIA graphics processing units (GPUs). TensorRT takes a trained network and produces a highly optimized runtime engine that performs inference for that network. Thanks! ---
**Author:** ![joguiguma](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/joguiguma/32/254543_2.png) [@joguiguma](https://forums.developer.nvidia.com/u/joguiguma)\ **Post date:** [June 7, 2023, 1:04am UTC](https://forums.developer.nvidia.com/t/could-not-load-dynamic-library-libnvinfer-so-7/254736/6 "2023-06-07T01:04:58Z")
> [@spolisetty](#): > > TRT NGC Thank you very much for your support. Before I try to install by [Installation Guide :: NVIDIA Deep Learning TensorRT Documentation](https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html), I check if I have installed tensorrt obtaining: :~$ python3 Python 3.8.10 (default, Mar 13 2023, 10:26:41) [GCC 9.4.0] on linux Type “help”, “copyright”, “credits” or “license” for more information. > > > import tensorrt > > > print(tensorrt. **version** ) > > > 8.4.3.1 > > > assert tensorrt.Builder(tensorrt.Logger()) It looks like I have installed Tensorrt. However, running Python 3 with tensorflow I obtained the following error message: 2023-06-06 19:58:53.291121: W tensorflow/stream\_executor/platform/default/dso\_loader.cc:64] Could not load dynamic library ‘libnvinfer.so.7’; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD\_LIBRARY\_PATH: /usr/local/cuda/lib64 2023-06-06 19:58:53.291192: W tensorflow/stream\_executor/platform/default/dso\_loader.cc:64] Could not load dynamic library ‘libnvinfer\_plugin.so.7’; dlerror: libnvinfer\_plugin.so.7: cannot open shared object file: No such file or directory; LD\_LIBRARY\_PATH: /usr/local/cuda/lib64 2023-06-06 19:58:53.291198: W tensorflow/compiler/tf2tensorrt/utils/py\_utils.cc:38] TF-TRT Warning: 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. What can I do? ---
**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\ **Post date:** [June 9, 2023, 10:10am UTC](https://forums.developer.nvidia.com/t/could-not-load-dynamic-library-libnvinfer-so-7/254736/7 "2023-06-09T10:10:18Z")
Hi, We recommend you to uninstall existing and reinstall TensorRT correctly, also please use the latest version of the TensorFlow. Thank you.